Search

• Newbie study using standard ML techniques with HAR Application and Discussions. • Activities found in Literature with the corresponding reference. • Co-occurrences between activities and sensors with the corresponding reference. • Summary and comparison among the different datasets found in Literature. • Summary of the experimentation settings with performance scores found in Literature. Human Activity Recognition (HAR) is an essential area of research related to the ability of smartphones to retrieve information through embedded sensors and recognize the activity that humans are performing. Researchers have recognized people's activities by processing the data received from the sensors with Machine Learning Models. This work is intended to be a hands-on survey with practical's tables capable of guiding the reader through the sensors used in modern smartphones and highly cited developed machine learning models that perform human activity recognition. Several papers in the literature have been studied, paying attention to the preprocessing, feature extraction, feature selection, and classification techniques of the HAR system. In addition, several summary tables illustrating HAR approaches have been provided: most popular human activities in the literature with paper references, the most popular datasets available for download (Analyzing their characteristics, such as the number of subjects involved, the activities recorded, and the sensors with online-availability), co-occurrences between activities and sensors, and a summary table showing the performance obtained by researchers. =The paper's goal is to recommend, through the discussion phase and thanks to the tables, the current state of the art on this topic. [ABSTRACT FROM AUTHOR]

• Pinch force strength is accurately predicted using sEMG. • Different pinch movements are accurately classified using sEMG. • Similarity of EMG features is evaluated. • An EMG feature-to-image method is proposed. The movement of intelligent EMG-driven prosthesis mainly relies on the synergy of different fingers to achieve function of grasping objects. The paper proposes a novel scheme for force prediction and movement classification about pinch between different fingers based on surface electromyography (sEMG) using machine learning. The pinch force and sEMG signals are recorded synchronously by a data acquisition device. Eight features are extracted, which are proven to have better performance in the estimation of sEMG-to-force. We present a novel feature selection method that uses the one-dimensional time series similarity assessment based on Manhattan distance to eliminate the repetitive information between features. Three optimal features carrying less repetitive information are retained. Seven machine learning algorithms are used to predict force strength. The results show that the Long Short Term Memory (LSTM) has the best performance of force prediction, achieving a R 2 of 0.9517 and RMSE of 3.2723. The paper proposes a novel method of converting EMG feature sequences to the normalized gray image in order to classify the finger movement. Five classifiers based on image feature extraction and the Convolutional Neural Network (CNN) are developed respectively. The experimental results indicate that the CNN performs best, achieving an accuracy of 97.66%. In this way, it not only realizes the accurate force prediction, but also realizes the movement classification between different fingers. The proposed methodology has the potential to realize simultaneous force and movement control of prosthetic hand. [ABSTRACT FROM AUTHOR]

Epilepsy is one of the most paramount neurological diseases, affecting about 1% of the world's population. Seizure detection and classification are difficult tasks and are ongoing challenges in biomedical signal processing to enhance medical diagnosis. This paper presents and highlights the unique frequency and amplitude information found within multiple seizure types, including their morphologies, to aid the development of future seizure classification algorithms. Whilst many published works in the literature have reported on seizure detection using electroencephalogram (EEG), there has yet to be an exhaustive review detailing multi-seizure type classification using EEG. Therefore, this paper also includes a detailed review of multi-seizure type classification performance based on the Temple University Hospital Seizure Corpus (TUSZ) dataset for focal and generalised classification, and multi-seizure type classification. Deep learning techniques have a higher overall average performance for focal and generalised classification compared to machine learning techniques, whereas hybrid deep learning approaches have the highest overall average performance for multi-seizure type classification. Finally, this paper also highlights the limitations of the TUSZ dataset and suggests some future work, including the curation of a standardised training and testing dataset from the TUSZ that would allow a proper comparison of classification methods and spur advancement in the field. [ABSTRACT FROM AUTHOR]

Automatic fault diagnosis in many systems is performed via the analysis of vibration data in the time or frequency domain. In the literature, many approaches for extracting featured from signals for fault diagnosis have been proposed. In this paper, we apply a variety of transform functions including Fourier, Wavelet, etc. to extract features from the vibration data, which includes the statistical features and some features automatically extracted via Convolutional Neural Networks (CNNs). For each of these feature extraction approaches, a learning algorithm is trained to diagnose the faults and their results are aggregated in an ensemble machine learning algorithm. The weights of the base learner algorithms are optimized via an evolutionary algorithm to achieve the best-weighted voting scheme. The architecture of CNNs has a significant effect on the performance of the algorithm, thus, in this paper, an evolutionary algorithm is proposed to find the best architecture for CNNs in fault diagnosis. The CNNs are trained via gradient descent algorithms which suffer from getting stuck in local optima. To manage this, we propose an evolutionary algorithm that benefits from the speed of gradient descent and the global search of evolutionary algorithms. The proposed algorithm is tested on a number of benchmark problems and the experimental results are presented. • An ensemble algorithm is proposed for fault diagnosis. • Different feature extractors are exploited. • An evolutionary training algorithm is proposed. [ABSTRACT FROM AUTHOR]

• The feature representation of the network was extracted from a randomly searched sequence of vertices. • In networks of scientific documents, representation learning needs to consider similarity and citation relationships. • This paper proposed a method to search and learn multiple paths connecting similar documents in a scientific document network. • From scientific papers and patent datasets, we found empirical evidence that our algorithm is suitable for representation learning. • This paper can contribute to preparing the basis for inducing innovation in science and technology from scientific documents. A network is a structure that can represent an organic relationship of observations. Network representation learning has the advantage of extracting latent features in a network. In recent years, various algorithms have been developed to embed network representation in a low-dimensional feature space. Conventional algorithms learn a sequence of vertices that are randomly searched from a network and convert a vertex into a vector. This study focused on the representation learning of document networks. Thus, this study proposes a scalable network representation learning algorithm that preserves the structure and content of the document network and reduces data sparsity. To do this, we used the shortest walks to extract a sequence of vertices that reflected semantic similarity from a network. The shortest walk is a method for finding several shortest paths that connect similar vertices. After this, the sequence of vertices was inputted into the language model, assuming that the sequence was a sentence. Scientific papers and patent datasets provided empirical evidence for the validity of our approach. The former, the bibliography network of scientific paper, consists of 17,716 nodes and 105,734 edges. The latter is a patent describing a technology for energy, representing a network of 24,894 nodes and 28,314 edges. The results showed that the proposed algorithm exhibited the lowest error of the tested methods in multi-class classification and link prediction tasks. The results of these tasks provided evidence that our algorithm is suitable for extracting feature representations of document networks. [ABSTRACT FROM AUTHOR]

Several biological research studies have shown that the number of individuals of certain species of anurans in a specific geographical region, and the evolution of this number over time, can be used as an indicator of climate change. To detect the presence of anurans, Wireless Sensor Networks (WSNs) are usually deployed with the aim of obtaining bio-acoustic information in a set covering numerous locations. However, the identification of the anuran species from a huge number of recordings usually involves an overwhelming task that has to be undertaken by expert and intelligent systems. Previous studies into this issue have proposed several classification techniques with a common approach: they all take into account the sequential characteristic of sounds by considering syllables or other kinds of vocal segments. In noisy sounds, as it is usually the case in recordings made in natural habitats, segmentation of the signal is no straightforward task and may cause low classification accuracy. To override this problem, a new non-sequential approach is proposed in this paper. It is based on considering very small pieces of sounds (frames) each of which is then classified without considering preceding or subsequent information. Up to nine frame-based classifiers are explored in this paper and their performances are compared to the most commonly used sequential classifier: the Hidden Markov Model (HMM). Additionally, for featuring the frames, many choices have been described, although the application of the Mel Frequency Cepstral Coefficients (MFCCs) has probably become the most common method. In this work, an alternative methodology is suggested: the use of a set of MPEG-7 parameters, which offers a normalized solution with a much greater semantic content. The experimental results have shown that the proposed method clearly outperforms the HMM, thereby showing the non-sequential classification of anuran sounds to be feasible. From among the algorithms tested, the decision-tree classifier has shown the best performance with an overall classification success rate of 87.30%, which is an especially striking result considering that the analyzed sounds were affected by a decidedly noisy background. [ABSTRACT FROM AUTHOR]

• The global and multi-scale local causal features are extracted to interpret the model and improve diagnosis accuracy. • The performance of the initial model can be improved by adopting an extensible framework to add enhancement nodes. • The sample incremental learning is developed to update incrementally based on the previous models without retraining. • Two experiments on bearing components validate the effectiveness and superiority of the proposed method. Intelligent fault diagnosis (IFD) plays a significant function in ensuring the reliable operation of mechanical equipment. However, most existing IFD methods are trained in batch learning way and the feature extraction process is unexplainable and it is challenging to satisfy the complex diagnosis requirements. Thus, this paper proposes a causal broad learning model (CBLM) guided by global and multi-scale local causal features for incremental machinery fault diagnosis. Firstly, rich global and multi-scale local causal features are extracted for training CBLM. Then, incremental learning capability is developed to update model by expanding or modifying the original weights, considerably reducing the time consumption and greatly improving the computational efficiency. When the initial model has inadequate nodes for feature learning, CBLM performs structural incremental learning by adding extra nodes to improve the diagnostic performance. As new samples with various fault degrees are entered, sample incremental learning is built to rapidly update based on previous model without retraining. Finally, two experimental results on bearings indicate that CBLM improves the testing accuracy of the initial model by 0.13% to 52.22% and 1.95% to 57.64%, respectively, and remains above 97.22% and 99.77% for the updated models. The training time consumption is reduced by 25.06 s to 133.0 s, 20.78 s and 141.9 s, respectively, and the subsequent models update time are only about 12 s and 10 s. Consequently, the proposed CBLM is an effective online IFD method because it is obviously superior to the existing IFD methods in regards to time consumption and diagnosis accuracy. [ABSTRACT FROM AUTHOR]

Predictions of the oil price are critical to support intelligent decision-making for individual investors, governments, and corporations, but a challenging task since there are complex nonlinear and random fluctuations involved in series. Additionally, most existing methods mainly focus on the data-layer fitting, and inherit uninterpretable design flowcharts and unclear layer functions. Based on the fact that living things evolve numerous advanced cognition processes after long-term interactions with environments, it is a promising problem to design bionic deep prediction networks. In this paper, an a uditory-inspired m ulti- f eature c ollaboration network (AMFC-Net) is explored to predict the oil price, and includes the feature extraction, brain memory, and comprehensive prediction blocks. Specifically, through imitating that complex sounds are captured by auditory canals and converted into electrical impulses, the first block adopts four typical activation functions to extract multi-group complementary features for detecting nonlinear changes. Through imitating that electrical impulses are transformed to the left and right hemispheres for handling and analyzing, the second block realizes gating and cooperation mechanisms to learn long short-term dependencies and highlight core information. Through imitating that information is sent to higher cerebral cortices for sensing the environment, the third block maps relationships from features to targets for producing final predictions. In summary, multi-channel convolution operations establish the imitations of both form (clear functional layer) and spirit (layer-by-layer collaboration), which not only ensure the prediction effectiveness but also improve the AMFC-Net interpretability. Three experiments (comparison with 12 machine learning methods), three experiments (comparison with 8 hybrid methods under decomposition plus ensemble framework), and seven discussions under two real-world oil price datasets all indicate that the proposed AMFC-Net is superior and suitable to predict the oil price. [ABSTRACT FROM AUTHOR]

For the purpose of managing financial risk and making investment decisions, interval stock price forecasting is essential. Currently, decomposition integration frameworks are widely used in point-valued stock price forecasting studies, mainly focusing on mining internal information. However, point forecasts are difficult to adequately capture price uncertainty and may suffer from loss of volatile information. Therefore, this paper proposes an enhanced interval-valued decomposition integration model for stock price prediction based on comprehensive feature extraction and optimized deep learning. Firstly, the interval variational modal decomposition with feedback mechanism (FIVMD) is proposed to extract internal features and can decompose interval values into interval trend and residual. FIVMD not only solves the interval decomposition challenge, but also helps to improve the internal feature extraction capability. Secondly, while considering the influencing factors more comprehensively, appropriate feature selection and compression techniques can effectively achieve external feature extraction, obtain the best influencing factors, and improve the modeling capability of high-dimensional data. Finally, the final prediction results are obtained by modeling the interval trend and residuals separately through the optimization algorithm and deep learning model to improve the prediction accuracy. The results of the empirical analysis reveal that the proposed interval decomposition integrated model has the smallest of the three evaluation metrics, where the values of interval mean average percentage errors (IMAPE) are 1.8188%, 1.1244%, 1.9001%, and 2.1542% respectively. This shows that the model is significantly more accurate and stable than the other comparative models, and it is a successful model for predicting interval-valued stock prices. [ABSTRACT FROM AUTHOR]

Joint inference is a fundamental issue in the field of artificial intelligence. The greatest advantage of the joint inference is demonstrated by its capability of avoiding errors from cascading and accumulating on a pipeline of multiple chained sub-tasks. Markov Logic Network(MLN) is the most common joint inference model that provides a flexible representation and handles uncertainty. It has been applied successfully to joint inference on many natural language processing tasks to avoid error propagation. However, due to the great expressiveness of first-order logic, the representation for it in MLN generates rather complicated graph structures, which makes the learning and inference on large scale data intractably. In this paper, we present an ensemble learning approach to deal with the challenges in MLNs. Firstly, we give a proof within the probably approximately correct (PAC) framework. The proof points out what conditions are necessary for successful applying the ensemble learning approach to MLN. Secondly, the paper explains how to combine the learners. Finally, in order to illustrate the working mechanism of the ensemble joint inference model, we present an Ensemble Markov Logic Networks (EMLNs) method and use it to extract knowledge from a large scale corpus published by Google. 1 1 code.google.com/p/relation-extraction-corpus/. Experiments suggest that significant speedup can be gained by the EMLNs. Meanwhile, it show that this approach leads to a higher precision and recall than that of those pipeline approaches. [ABSTRACT FROM AUTHOR]

Deep learning techniques for Sentiment Analysis have become very popular. They provide automatic feature extraction and both richer representation capabilities and better performance than traditional feature based techniques (i.e., surface methods). Traditional surface approaches are based on complex manually extracted features, and this extraction process is a fundamental question in feature driven methods. These long-established approaches can yield strong baselines, and their predictive capabilities can be used in conjunction with the arising deep learning methods. In this paper we seek to improve the performance of deep learning techniques integrating them with traditional surface approaches based on manually extracted features. The contributions of this paper are sixfold. First, we develop a deep learning based sentiment classifier using a word embeddings model and a linear machine learning algorithm. This classifier serves as a baseline to compare to subsequent results. Second, we propose two ensemble techniques which aggregate our baseline classifier with other surface classifiers widely used in Sentiment Analysis. Third, we also propose two models for combining both surface and deep features to merge information from several sources. Fourth, we introduce a taxonomy for classifying the different models found in the literature, as well as the ones we propose. Fifth, we conduct several experiments to compare the performance of these models with the deep learning baseline. For this, we use seven public datasets that were extracted from the microblogging and movie reviews domain. Finally, as a result, a statistical study confirms that the performance of these proposed models surpasses that of our original baseline on F1-Score. [ABSTRACT FROM AUTHOR]

As robots tend to establish their presence in every day human environments the necessity for them to attain socially acceptable behavior is a condition sine qua non. Consequently, robots need to learn and react appropriately, should they be able to share the same space with people and to reconcile their operation to man’s activity. This work proposes an integrated robot framework that allows navigation in a human populated environment. This is the first work that employs the performed actions of individuals so as to re-plan and design a collision-free and at the same time a socially acceptable trajectory. Expandability is another feature of the suggested mapping module since it is capable of incorporating an unconstrained number of actions and subsequently responses, according to the needs of the task in hand and the environment in which the robot operates. Moreover, the paper addresses the integration of the proposed mapping module with the rest of the robot framework in order to operate in a seamless fashion. The generic design of this architecture allows the replacement of modules with other similar ones, thus providing adaptability with respect to the environment and so on. The method utilizes off-line constructed 3D metric maps organized in terms of a topological graph. During its perambulation the robot is ample to detect humans while it exploits deep learning strategies to recognize their activities. The memorized actions are seamlessly associated with specific rules –deriving from the proxemics theory– and are organized in an efficient manner to be recalled during robot’s navigation. Moreover, the paper exhibits the differences of the robot navigation in inhabited and uninhabited environments and demonstrates the alteration of the robot’s trajectory with respect to the recognized actions and poses of the individuals. The system has been evaluated on a robot able to acquire RGB-D data in domestic environments. The human detection and the action recognition modules exhibited remarkable performance, the human detection one was flawless about its decision while the action recognition one confused actions regarding the number of individuals that participate in them. Last, the robot navigation component was proved capable of extracting safe trajectories in human populated environments. [ABSTRACT FROM AUTHOR]

At present, the serious challenge of human-robot collaboration is how to establish an interaction interface with multi-directional interactivity and robustness. This paper applies surface electromyography (sEMG) signals as the interface medium, and proposes a robust 3D arm strength estimation model based on hybrid deep learning networks (R3DNet) to build a stable interaction interface and achieve reliable human-robot collaboration performance in 3D operation scenarios. R3DNet adopts the modular design idea and includes a feature extraction module, a regression estimation module, and a robust enhancement module. In the feature extraction module, an autoencoder structure-based network and a new loss function are proposed to extract the fusion features of multi-channel sEMG signals. In the regression estimation module, an arm strength model based on transfer learning algorithms is proposed. This model considers the similarity of arm strength estimation in each direction and realizes the arm strength estimation from one to three dimensions through the fine-tune strategy. The robust enhancement module adopts a residual structure and aims to address the problem of poor model robustness due to non-ideal conditions such as electrode displacement, muscle fatigue, muscle time-varying characteristics and differences in muscle characteristics among subjects. Further, an improved adaptive admittance control method is proposed to help the robot to adjust collaborative behavior according to the changing arm strength of the human tutor. The results of comparison experiments and multi-point flexible assembly experiments verify the validity and engineering realizability of R3DNet for human-robot collaboration. [ABSTRACT FROM AUTHOR]

Animation drama and movies are important entertainment sources for children and young people. However, many of these entertainment videos introduce ideas such as violence, fighting, abuse, and car accidents, which are not suitable for children and young people. In order to prevent children from viewing these videos, different countries' government bodies put restrictions on age on these videos. Violence detection is mostly done using manual inspection, which is time and resource consuming and cannot achieve a very good result. Therefore, artificial technologies such as deep learning and machine learning can detect violence in a video. Bleeding is one of the distinct characteristics of violent actions presented in such videos. This paper aims to propose a system that can detect a given video's blood in real-time. Researchers have proposed different image processing-based techniques to detect violence, but their proposed systems lack precision and real-time detection. To this end, a deep learning-based approach is proposed to detect violence in a given video and images. A Faster R-CNN model is modified due to the sophisticated characteristics of the violence in the cartoon and animation images to achieve the highest performance. The backbone of the proposed violence detection model is changed to a modified RegNet model to extract the features from the frame. The standard inner lateral connection is replaced with the modulated deformable convolutional (MDC) layer to extract deformable feature maps. A novel distributed attention module (DAM) is proposed on the feature pyramid network to improve the performance of the feature extraction. The multiscale Region of interest (ROI) Align is adapted to improve the detection performance of violence in a different scenario. Moreover, the classification approach is integrated with the detection model to classify the different levels of violence in a given frame. We have explored state-of-the-art object detection methods such as Faster R-CNN, Cascade R-CNN, yolov3-spp, SSD, FCOS, and yolov5 to detect violence in a particular frame of a video. We compared the different models' performances and found out that the modified Faster R-CNN is appropriate for real-time blood detection in a given video or image with high accuracy. This study makes a significant contribution to detecting violence in animation videos which will help different platforms and government bodies to regulate entertainment content. [ABSTRACT FROM AUTHOR]

The human skin, the largest organ with multiple layered functionalities, houses melanocytes in the deeper strata of its epidermis. These cells can be adversely impacted by ultraviolet radiation, thereby instigating melanoma, the deadliest form of skin cancer. Failure to detect melanoma at an early stage can potentially lead to metastasis, forming complex tumors in other tissues. Despite substantial efforts, visual inspections can occasionally overlook melanoma cases due to inherent subjectivity. To surmount this challenge, an automated detection system is necessary. Recent attempts to establish such a system have predominantly employed "push-through" strategies involving deep (neural) networks and their ensembles, which however necessitate significant computational resources. This paper presents a novel approach, amalgamating a conventional machine learning technique, Bag of Visual Words, with a pretrained deep neural network for comprehensive deep feature extraction from enhanced input image patches. The proposed method, assessed on the ISIC Challenge 2017 dataset, surpassed all other entries on the challenge leader-board, registering an accuracy of 96.2% in the task of lesion classification. • Novel method for melanoma detection combining Bag of Visual Words with a deep network. • Patch-based feature extraction from lesion images integrated into BoVW with K-means. • Successful image enhancement technique for feature extraction from lesion images. • Efficient framework: modular architecture, easy updates, less training delay. [ABSTRACT FROM AUTHOR]

The presence of Beggiatoa Spp. indicates anoxic conditions or 'poor condition' in marine sediments beneath aquaculture pens, resulting from organic enrichment. Currently, the most efficient approach to estimate Beggiatoa Spp. coverage, and thus the extent of the issue, involves video surveys which are scored by human observers for presence of this bacteria. However, this approach is highly time-consuming and relies heavily on the expertise and experience of the individuals involved, thus affecting its accuracy. Machine learning-based computer vision techniques, such as Convolutional Neural Networks (CNNs), offer the potential for automated estimation of Beggiatoa Spp. coverage. However, most existing machine learning methods focus solely on the estimation of the coverage via presence, absence of a single type of Beggiatoa Spp.. These approaches typically rely on binary classification to distinguish the object from the background when estimating coverage. Nevertheless, the inclusion of subordinate categories within high-level classifications poses a great challenge for accurately estimating their coverage rates. In this paper, an adaptive ensemble learning approach was proposed to estimate Beggiatoa Spp. coverage. Unlike other approaches, the proposed approach is capable in adaptively extracting and fusing features from underwater images and accurately estimating the coverages of multiple types of Beggiatoa Spp. through ensemble learning. Experimental results demonstrated that our proposed approach outperforms other approaches in terms of both effectiveness and efficiency in estimating Beggiatoa Spp. coverage. • Adaptive feature extraction and fusion enhance relevant and informative features' identification. • Adaptive feature extraction and fusion enhance feature representation and reduce time cost. • Flexible ensemble learning framework improves accuracy, robustness, and efficiency. • Flexible ensemble learning framework can be extended to other models or applications. • Novel machine learning-based approach estimates subordinate categories of Beggiatoa Spp. coverage. [ABSTRACT FROM AUTHOR]

• A class incremental learning framework is proposed for open sets. • The framework is implemented based on multiple one-class classifiers (OCCs). • An improved deep SVDD is proposed as the basic OCC of the framework. • Several tricks (e.g., feature fusion, band attention) are used to improve OCC. • HSI combined with this method has broad application prospects in seed industry. Rapid and non-destructive classification of seed varieties is one of the important goals pursued by modern seed industry. Due to the large number of maize varieties in practice, collecting training samples that exhaust all varieties to train a classifier is extremely difficult. Therefore, maize seed classification in the real world faces the challenge of variety renewal and rejection of unknown varieties. This paper proposes an end-to-end trainable incremental learning (IL) framework based on hypercube data. This method achieves class-IL via learning one-class classifier (OCC) incrementally, and directly uses raw data as input without additional data preprocessing and feature extraction. The OCC is a dual deep support vector data description, which makes full use of spectral and spatial information to establish an exclusive hypersphere for a specific variety to receive the variety and reject unknown varieties. To remove the interference of redundant bands, a band attention and sparse constraint module is added to automatically assign the weights of redundant bands to zero, thereby maximally improving the performance of the model. Moreover, a new loss function is defined to alleviate the difficulty of parameter updating after sparse constraint. Experimental results on our open set indicate that the accuracy of the proposed method for receiving known varieties and rejecting unknown varieties are both above 91 %, which has significant advantages over the other two state-of-the-art IL methods. In the future, the corresponding OCCs can also be deleted from the whole framework according to the varieties eliminated by the government to reduce computational overhead and inter-class interference. Overall, the proposed method can perform both IL and open set recognition. [ABSTRACT FROM AUTHOR]

The continuous malicious software (malware) attacks on smartphones pose a serious threat to the security of users, especially the dominant platform Android. Data-driven methods based on machine learning algorithms are a promising way to defend against that. In this paper, we explore the limitations of this kind of methods in improving the performance of malware detection, e.g., considering each feature in isolation and relying on balanced class data, and propose a multi-model ensemble framework MEFDroid by combining individual predictors, where hybrid deep learning based feature extraction methods are adopted to learn meaningful features from raw data. Besides, a novel fusion scheme is exploited to fuse multi-level representations and mine their correlations to maximize the utilization of original information. To evaluate the effectiveness of the MEFDroid framework, we conduct a step-by-step model justification experiment to investigate how the proposed algorithms (i.e., ESAES, EDAES and EDAFS) enhance the malware detection performance gradually. We also compare the proposed algorithms with classical machine learning methods, conventional sampling solutions for the imbalance problem. Besides, we investigate the reliability of our proposed methods using another public dataset. Our extensive experimental results demonstrate that the target model EDAFS in MEFDroid outperforms others in terms of most metrics, which means that it is an effective alternative solution to detect Android malware. [ABSTRACT FROM AUTHOR]

Due to the presence of redundant and irrelevant features in large-dimensional biomedical datasets, the prediction accuracy of disease diagnosis can often be decreased. Therefore, it is important to adopt feature extraction methodologies that can deal with problem structures and identify underlying data patterns. In this paper, we propose a novel approach called the Anti Coronavirus Optimized Kernel-based Softplus Extreme Learning Machine (ACO-KSELM) to accurately predict different types of skin cancer by analyzing high-dimensional datasets. To evaluate the proposed ACO-KSELM method, we used four different skin cancer image datasets: ISIC 2016, ACS, HAM10000, and PAD-UFES-20. These dermoscopic image datasets were preprocessed using Gaussian filters to remove noise and artifacts, and relevant features based on color, texture, and shape were extracted using color histogram, Haralick texture, and Hu moment extraction approaches, respectively. Finally, the proposed ACO-KSELM method accurately predicted and classified the extracted features into Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC), Actinic Keratosis (ACK), Seborrheic Keratosis (SEK), Bowen's disease (BOD), Melanoma (MEL), and Nevus (NEV) categories. The analytical results showed that the proposed method achieved a higher rate of prediction accuracy of about 98.9%, 98.7%, 98.6%, and 97.9% for the ISIC 2016, ACS, HAM10000, and PAD-UFES-20 datasets, respectively. [ABSTRACT FROM AUTHOR]

In semiconductor manufacturing, wafer map defect pattern provides critical information for facility maintenance and yield management, so the classification of defect patterns is one of the most important tasks in the manufacturing process. In this paper, we propose a novel way to represent the shape of the defect pattern as a finite-dimensional vector, which will be used as an input for a neural network algorithm for classification. The main idea is to extract the topological features of each pattern by using the theory of persistent homology from topological data analysis (TDA). Through some experiments with a simulated dataset, we show that the proposed method is faster and much more efficient in training with higher accuracy, compared with the method using convolutional neural networks (CNN) which is the most common approach for wafer map defect pattern classification. Moreover, it was shown that our method outperforms the CNN-based method when the number of training data is not enough and is imbalanced. • A novel approach for wafer map defect pattern classification is proposed. • This new method is based on the theory from topological data analysis. • The proposed method is accurate and computationally efficient. • This algorithm is fast enough to provide a real-ti me prediction. • This method is robust against a small and imbalanced dataset. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is an irreversible disease that damages blood vessels and results in permanent visual impairment. Timely detection and proper diagnosis can mitigate severe eye impacts and slow DR progression. Color fundus images are commonly used by eye specialists to diagnose DR. However, manual operations are tedious, laborious, time-consuming, and error-prone. As a result, automated techniques are gaining increased attention in the medical domain due to their ability to precisely analyze unstructured clinical notes. In this paper, a novel Gannet-optimized deep belief network-based wavelet kernel extreme learning machine (GO-DBN-WKELM) technique is proposed for detecting DR occurrences and assessing its progressive stages. The GO-DBN-WKELM approach detects and classifies DR severities into six distinct classes: no DR (i.e., normal), early DR, mild non-proliferative DR, moderate non-proliferative DR, severe non-proliferative DR, and proliferative DR. Initially, detailed information from the original datasets is extracted by reducing feature dimensions using the Deep Belief Network (DBN) model. Subsequently, the extracted images are analyzed by the proposed GO-DBN-WKELM classification model, which effectively detects and accurately classifies fundus images based on their severities into distinct classes. The enhanced detection performance is primarily due to the application of the GO algorithm with a wavelet kernel extreme learning machine (WKELM). The GO algorithm not only optimizes the kernel parameters of the WKELM but also increases the convergence speed of the classifier. The proposed classifier is analyzed using three different types of datasets, namely MESSIDOR, DIARETDB1, and IDRiD datasets. The effectiveness of the proposed classification model is determined by evaluating its ability to detect DR in terms of diverse performance metrics, such as accuracy, precision, recall, and F-measure. Simulation results reveal that the proposed GO-DBN-WKELM classifier achieved a high accuracy rate of approximately 98% for the MESSIDOR dataset and 97.8% for the DIARETDB1 dataset. These outcomes demonstrate the potential of the GO-DBN-WKELM approach in detecting and classifying diabetic retinopathy severities, offering an efficient, automated alternative to manual methods that can aid eye specialists in providing timely diagnoses and interventions for patients with this condition. [ABSTRACT FROM AUTHOR]

Highlights • To study the effects of handwriting on predicting personality traits. • Graphology features and their psychological characteristics are studied. • Applications in several domains for handwriting-based personality have been explored. • Links between handwriting and personality psychology are provided. • Challenges to detect personality based on handwriting have been discussed. Abstract Personality is a combination of various characteristics and qualities of an individual. It may be affected by the growth and evolution of one's values, attributes, relationships with the community, personal memories of life events, habits, and skills. Behaviours and decisions of an individual are largely directed by his/her personality. Identification of such a personality trait can be performed based on an individual's handwriting features. Handwriting may be unique for each person and a person's nature, behaviour, and certain psychological aspects can be inferred based on it. It is introduced as the field of graphology, also called graphoanalysis, to analyze personality based on handwriting. We perceived that many researchers have worked on personality and/or behaviour identification based on handwriting, however, most of them were limited to a few numbers of features. According to graphology, there is a vast range of features of handwriting strokes which carry psychological characteristics of the writer. In this survey, we present links between handwriting and personality psychology and examine different mechanisms for features extraction to predict a writer's personality. Psychologically supported handwriting features help to understand personality traits. The paper relates these features and encourages the use of computer-based graphology for personality prediction. It also discusses applications of graphology in various fields. [ABSTRACT FROM AUTHOR]

Highlights • Novel use of neural networks and multitask learning for yield curve forecasting. • Multilayer perceptron using the most relevant features achieved the best results. • The most relevant features depend on target yield and forecasting horizon. • Synthetic data from linear regression model tends to improve forecasting accuracy. • Encouraging results for the development of robust forecasting systems for bond market. Abstract The yield curve is the centrepiece in bond markets, a massive asset class with an overall size of USD 100 trillion that remains relatively under-investigated using machine learning. This paper is the first comprehensive study using artificial neural networks in the context of yield curve forecasting. Specifically, two models were used for forecasting the European yield curve: multivariate linear regression and multilayer perceptron (MLP), at five forecasting horizons, from next day to 20 days ahead. Five variants of the MLP were analysed with different sets of features: target to predict (univariate); the most relevant features; all generated features; and the former two incorporating synthetic data generated by the linear regression model. Additionally, two different techniques of multitask learning were employed: simultaneous modelling and transformation into multiple single task learning. The results show that considering all forecasting horizons, the MLP using the most relevant features achieved the best results and the addition of synthetic data tends to improve accuracy. Furthermore, different targets and forecasting horizons resulted in different relevant features, reinforcing the importance of custom-built models. In the two multitask learning methodologies no clear differentiation could be demonstrated, and several explaining factors are identified. Overall, the outcome is very encouraging for the development of better forecasting systems for fixed income markets. [ABSTRACT FROM AUTHOR]

This paper presents an intelligent human trajectory destination detection system from video. The system assumes a passive collection of video from a wide scene used by humans in their daily motion activities such as walking towards a door. The proposed system includes three main modules, namely human blob detection, star skeleton detection and destination area prediction, and it works directly with raw video, producing motion features for destination prediction system, such as position, velocity and acceleration from detected human skeletons, resulting in several input features that are used to train a machine learning classifier. We adopted a university campus exterior scene for the experimental study, which includes 348 pedestrian trajectories from 171 videos and five destination areas: A, B, C, D and E. A total of six data processing combinations and four machine learning classifiers were compared, under a realistic growing window evaluation. Overall, high quality results were achieved by the best model, which uses 37 skeleton motion inputs, undersampling on training data and a random forest. The global discrimination, in terms of area of the receiver operating characteristic curve is around 87%. Furthermore, the best model can predict in advance the five destination classes, obtaining a very good ahead discrimination for classes A, B, C and D, and a reasonable ahead discrimination for class E. [ABSTRACT FROM AUTHOR]

Nowadays, insider attacks are emerging as one of the top cybersecurity threats. However, the detection of insider threats is a more arduous task for many reasons. A significant cause is the availability of various data types related to insider activities and their possible behavioral drift. Another major reason is that threat activities rarely happen within any organizational environment and usually remain submerged within a massive amount of normal activities thereby creating data imbalance issues. Any insider threat event requires three major components to get materialized: proper motivation, suitable opportunity and a minimum skill set. The simultaneous occurrence of all these elements is rarely found in organizational environment compared to regular activity traits, and the data imbalance thus caused makes accurate detection of threat activities quite challenging. Existing insider threat detection techniques are mainly divided into statistical rule-based, machine learning-based, and deep learning-based methods. Although recent deep learning methods have been found to extract intrinsic behavioral properties from users' activity patterns more effectively than traditional rule-based and machine-learning methods by utilizing their multilayer architecture. But sporadic approaches prioritize critical sections of activity patterns in their detection scheme. Also, rare methods focused on taking advantage of multiple deep learning-based feature extraction models together in their detection process. Finally, rare methods have adequately focused on data imbalance issues, especially over the unequal proportion of different categories of threat instances. In this paper, we proposed an insider threat detection approach using an ensemble of stacked-LSTM and stacked-GRU-based attention models. Our models are first trained on the user's single-day sequential activity logs. Then a stacked ensemble of trained attention models is used to extract the user's single-day activity information in the form of the feature vector, which is finally used for classification. To address the data imbalance issues, we propose a new equally-weighted random sampling approach for balancing the population of the different categories of threat patterns. We randomly undersample the nonmalicious instances followed by random oversampling of the different categories of threat instances in an equally-weighted manner so that the training models can learn the behavioral characteristics of the different types of insider activity patterns without getting biased towards any particular type, which is a major limitation of random oversampling and random undersampling-based techniques. Experiments have been performed on the different versions of the CMU CERT insider threat datasets. For robust evaluation, stratified division-based train-test sets have been used based on different categories of insider activities. An average AUC of 0.99 on CMU CERT v4.2 and v5.2 datasets and 0.97 on its v6.2 dataset shows the robustness of the proposed approach in detecting insider threats. • Stacked ensemble of attention models-based insider threat detection approach. • Broad categorization of user activity improves insider threat detection process. • Equally weighted random sampling (EWRS) technique used for handling data imbalance. • Stratified division of insider threat dataset is used for evaluation purpose. • AUC score of 0.99 achieved on CMU CERT v4.2, v5.2 and 0.97 on v6.2 datasets. [ABSTRACT FROM AUTHOR]

Web traffic refers to the amount of data that is sent and received by people visiting online websites. Web traffic anomalies represent abnormal changes in time series traffic, and it is important to perform detection quickly and accurately for the efficient operation of complex computer networks systems. In this paper, we propose a C-LSTM neural network for effectively modeling the spatial and temporal information contained in traffic data, which is a one-dimensional time series signal. We also provide a method for automatically extracting robust features of spatial-temporal information from raw data. Experiments demonstrate that our C-LSTM method can extract more complex features by combining a convolutional neural network (CNN), long short-term memory (LSTM), and deep neural network (DNN). The CNN layer is used to reduce the frequency variation in spatial information; the LSTM layer is suitable for modeling time information; and the DNN layer is used to map data into a more separable space. Our C-LSTM method also achieves nearly perfect anomaly detection performance for web traffic data, even for very similar signals that were previously considered to be very difficult to classify. Finally, the C-LSTM method outperforms other state-of-the-art machine learning techniques on Yahoo's well-known Webscope S5 dataset, achieving an overall accuracy of 98.6% and recall of 89.7% on the test dataset. [ABSTRACT FROM AUTHOR]

Usage of depth data in various computer vision applications gains popularity with cheap depth sensors available on the market. In this study, a method that utilizes Deep Learning is proposed for single human actions and dyadic actions. Depth data of the actions are used to construct a three-dimensional (3D) template. These templates are rotated in different directions and two-dimensional (2D) views from different angles are stored. Acquired 2D images are used in deep feature extraction. AlexNet (Krizhevsky, Sutskever, & Hinton, 2012) pre-trained convolutional neural network is used for deep feature extraction. For all viewpoints, deep features are extracted and concatenated. After that random forest classifier is used for action recognition. The contributions of this paper are as follows. First, a 3D isosurface models is constructed to figure actions sequence. Second, we project 3D shapes into a 2D feature space by taking its snapshots from different views and giving them to a pre-trained CNN as input for feature extraction. We explore more information about the actions by extracting features from different layers of the deep neural network. We compare the results of the deep features extracted from different layers of the pre-trained CNN. Various classifiers are trained with extracted deep features. Because of the complex structure of the 3D shapes, there are a limited number of feature extraction methods. Our method obtains close to state-of-the-art performance on various single and two-person action datasets. [ABSTRACT FROM AUTHOR]

In practice, pattern recognition applications often suffer from imbalanced data distributions between classes, which may vary during operations w.r.t. the design data. For instance, in many video surveillance applications, e.g., face re-identification, the face individuals must be recognized over a distributed network of video cameras. An important challenge in such applications is class imbalance since the number of faces captured from an individual of interest is greatly outnumbered by those of others. Two-class classification systems designed using imbalanced data tend to recognize the majority (negative) class better, while the class of interest (positive class) often has the smaller number of samples. Several data-level techniques have been proposed to alleviate this issue, where classifier ensembles are designed with balanced data subsets by up-sampling positive samples or under-sampling negative samples. However, some informative samples may be neglected by random under-sampling and adding synthetic positive samples through up-sampling adds to training complexity. In this paper, a new ensemble learning algorithm called Progressive Boosting (PBoost) is proposed that progressively inserts uncorrelated groups of samples into a Boosting procedure to avoid loosing information while generating a diverse pool of classifiers. In many real-world recognition problems, the samples may be regrouped using some application-based contextual information. For example, in face re-identification applications, facial regions of a same person appearing in a camera field of view may be regrouped based on their trajectories found by face tracker. From one iteration to the next, the PBoost algorithm accumulates these uncorrelated groups of samples into a set that grows gradually in size and imbalance. Base classifiers are trained on samples selected from this set and validated on the whole set. Consequently, PBoost is more robust when the operational data may have unknown and variable levels of skew. In addition, the computation complexity of PBoost is lower than Boosting ensembles in literature that use under-sampling for learning from imbalanced data because not all of the base classifiers are validated on all negative samples. The new loss factor used in PBoost avoids biasing performance towards the negative class. Using this loss factor, the weight update of samples and classifier contribution in final predictions are set according to the ability of classifiers to recognize both classes. The proposed approach was validated and compared using synthetic data and videos from the Faces In Action, and COX dataset that emulate face re-identification applications. Results show that PBoost outperforms state of the art techniques in terms of both accuracy and complexity over different levels of imbalance and overlap between classes. [ABSTRACT FROM AUTHOR]

Project-based learning is based on the idea of iteratively learning for future projects from the successes and failures of past projects. This paper proposes a semi-automated implementation approach for double-loop learning in project environments. A combined application of two complementary methods is suggested for this purpose: Latent Semantic Analysis (LSA) and Analytic Network Process (ANP). By this means, the approach addresses two problems of the project management practice. First, the information overload in project environments, whereby the LSA is used for the semi-automated extraction of lessons learned from large collections of textual project documentation. Second, the lack of procedures and methods for the practical implementation of available project knowledge, whereby the ANP is used for the systematic modeling of extracted lessons learned and their integration into the evaluation of project concepts and current project management routines. Thus, the proposed implementation approach improves the ability of project-based organizations to consequently learn from past failures or successes. From a practical perspective, evident shortcomings of existing computerized double-loop learning approaches are addressed. The proposed approach contributes to the project management practice not only by demonstrating a solution for the exploration of representative and potentially new lessons from multiple combined experience reports, but also by presenting a solution for the systematic assessment of such project-governing variables and their mutual relationships as part of the decision-making in new projects. From a theoretical perspective, specific research avenues for further development of the double-loop learning concept by means of expert and intelligent systems are provided. [ABSTRACT FROM AUTHOR]

Feature engineering is fundamental in applied machine learning. It plays a major role in writer identification of handwritten documents, which has been an active area of research in the literature. In this paper, we propose a conceptually simple, yet high-quality and computationally efficient descriptor referred to as block wise local binary count (BW-LBC) for offline text independent writer identification of handwritten documents. The proposed BW-LBC operator characterizes the writing style of each writer by a set of histograms calculated from all the connected components in the writing. Each histogram is constructed by calculating the occurrence distribution of pixels corresponding to the writing within small blocks in each connected component extracted and cropped from the input handwriting sample (document or set of words/text lines). Specifically, for a given connected component divided into N × N non-overlapping blocks, the appearance probability of writing pixels in the block number i corresponds to the histogram bin number i in the produced corresponding histogram of N × N bins. The samples are classified according to their normalized histogram feature vectors through the nearest-neighbor rule (1-NN) using the Hamming distance. Extensive experiments performed on four challenging handwritten databases (IFN/ENIT, AHTID/MW, CVL and IAM) containing handwritten texts in Arabic and English languages, show that the proposed system using the BW-LBC operator demonstrates superior performance on the Arabic databases (i.e., AHTID/MW and IFN/ENIT) and competitive performance on the English scripts compared to the old and recent state-of-the-art writer identification approaches. [ABSTRACT FROM AUTHOR]

A number of industries use human inspection to visually classify the quality of their products and the raw materials used in the production process, this process could be done automatically through digital image processing. The industries are not always interested in the most accurate technique for a given problem, but most appropriate for the expected results, there must be a balance between accuracy and computational cost. This paper investigates the classification of the quality of wood boards based on their images. For such, it compares the use of deep learning, particularly Convolutional Neural Networks, with the combination of texture-based feature extraction techniques and traditional techniques: Decision tree induction algorithms, Neural Networks, Nearest neighbors and Support vector machines. Reported studies show that Deep Learning techniques applied to image processing tasks have achieved predictive performance superior to traditional classification techniques, mainly in high complex scenarios. One of the reasons pointed out is their embedded feature extraction mechanism. Deep Learning techniques directly identify and extract features, considered by them to be relevant, in a given image dataset. However, empirical results for the image data set have shown that the texture descriptor method proposed, regardless of the strategy employed is very competitive when compared with Convolutional Neural Network for all the performed experiments. The best performance of the texture descriptor method could be caused by the nature of the image dataset. Finally are pointed out some perspectives of futures developments with the application of Active learning and Semi supervised methods. [ABSTRACT FROM AUTHOR]

We are living in an era in which daily interaction between individuals and businesses involves sending, uploading, and sharing videos as a means of communication and advertising. However, many users are unaware of the risks associated with opening a malicious video file, it is thus no surprise that cyber-criminals have taken advantage of this situation and adopted this attack vector in recent years. MP4 is one of the most commonly used video formats, and its properties make it well-suited for software vulnerability exploitation across multiple platforms, which can ultimately lead to a cyberattack. Due to their deterministic, signature-based technique, antivirus software solutions are limited in their ability to detect unknown malware, let alone zero-day attacks. Machine learning (ML) algorithms have been effective in detecting known and unknown malware across various file formats, domains, and platforms. ML algorithms' performance relies heavily on the feature extraction methodology. However, to the best of our knowledge, there is no designated and specialized feature extraction methodology for MP4 files which generates a set of features for the task of unknown MP4 file malware detection. In this paper, we present three innovative and efficient feature extraction methodologies for unknown MP4 file malware detection. Two of them are file structure-based and one is knowledge-based. The methodologies are evaluated in a series of five experiments using six ML algorithms and 177 different datasets which represent different configurations of feature extraction, representation, and selection. The datasets are based on a representative collection of 6,229 files − 5,066 benign (∼81.3 %) files and 1,163 malicious files (∼18.7 %). The first three experiments demonstrate the methodologies' discrimination and generalization capabilities across multiple configurations, in terms of known and unknown MP4 file malware detection. The fourth experiment shows that applying principal component analysis (PCA) on the features suggested by the methodologies can improve time and space complexity and feature resilience while maintaining strong detection and generalization capabilities. In the fifth experiment, the methodologies' best performing configuration is compared to state-of-the-art, generic feature extraction methodologies, such as n -grams, MinHash, and representation and transfer learning (using a CNN), in the task of unknown MP4 file malware detection. The results show that our best performing configuration outperforms all other state-of-the-art feature extraction methodologies with an AUC, TPR, and FPR of 0.9951, 0.976, and 0.0 respectively. [ABSTRACT FROM AUTHOR]

• Diabetic retinopathy (DR) detection from Fundus Images has been proposed. • Parallel CNN with fewer parameters and layers for distinctive feature extraction. • Extreme Learning Machine (ELM) technique was utilized for the DR classification. • The model demonstrated robustness for different types of datasets. • Accuracy upto 97.27 % was achieved and outscored state-of-the-art models. Diabetic retinopathy (DR) is an incurable retinal condition caused by excessive blood sugar that, if left untreated, can result in even blindness. A novel automated technique for DR detection has been proposed in this paper. To accentuate the lesions, the fundus images (FIs) were preprocessed using Contrast Limited Adaptive Histogram Equalization (CLAHE). A parallel convolutional neural network (PCNN) was employed for feature extraction and then the extreme learning machine (ELM) technique was utilized for the DR classification. In comparison to the similar CNN structure, the PCNN design uses fewer parameters and layers, which minimizes the time required to extract distinctive features. The effectiveness of the technique was evaluated on two datasets (Kaggle DR 2015 competition (Dataset 1; 34,984 FIs) and APTOS 2019 (3,662 FIs)), and the results are promising. For the two datasets mentioned, the proposed technique attained accuracies of 91.78 % and 97.27 % respectively. However, one of the study's subsidiary discoveries was that the proposed framework demonstrated stability for both larger and smaller datasets, as well as for balanced and imbalanced datasets. Furthermore, in terms of classifier performance metrics, model parameters and layers, and prediction time, the suggested approach outscored existing state-of-the-art models, which would add significant benefit for the medical practitioners in accurately identifying the DR. [ABSTRACT FROM AUTHOR]

In this paper, we provide an experimental study for two unsupervised processes, namely, the random initialization and the Hebbian learning, which can be used to determine the input weights in Single-hidden Layer Feedforward Neural Networks (SLFNs). In addition, a fusion technique that combines the two feature spaces is proposed. Experiments are conducted on six publicly available facial image datasets. Experimental results show that the proposed fusion technique can improve the performance of Hebbian and random feature spaces when they achieve similar performance. In the cases where the difference in performance of the two feature spaces is high, the proposed fusion scheme preserves the power of the most discriminating one and outperforms the average fused feature space. The experimental results show that there is a trade-off between the generalization of the Hebbian feature space and the low computational cost of the random one. [ABSTRACT FROM AUTHOR]

The aim of this paper is, first, to recall fuzzy relational compositions (products) and, to introduce an idea, how excluding features could be incorporated into the theoretical background. Apart from definitions, we provide readers with a theoretical investigation. This investigation addresses two natural questions. Firstly, under which conditions (in which underlying algebraic structures) the given three natural approaches to the incorporation of excluding symptoms coincide. And secondly, under which conditions, the proposed incorporation of excluding features preserves the same natural and desirable properties similar to those preserved by fuzzy relational compositions. The positive impact of the incorporation on reducing the suspicions provided by the basic “circlet” composition without losing the possibly correct suspicion is demonstrated on a real taxonomic identification (classification) of Odonata. Here, we demonstrate how the proposed concept may eliminate the weaknesses provided by the classical fuzzy relational compositions and, at the same time, compete with powerful machine learning methods. The aim of the demonstration is not to show that proposed concept outperforms classical approaches, but to show, that its potential is strong enough in order to complete them or in order to be combined with them and to use its different nature. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization has been widely used in co-clustering tasks which group data points and features simultaneously. In recent years, several proposed co-clustering algorithms have shown their superiorities over traditional one-side clustering, especially in text clustering and gene expression. Due to the NP-completeness of the co-clustering problems, most existing methods relaxed the orthogonality constraint as nonnegativity, which often deteriorates performance and robustness as a result. In this paper, penalized nonnegative matrix tri-factorization is proposed for co-clustering problems, where three penalty terms are introduced to guarantee the near orthogonality of the clustering indicator matrices. An iterative updating algorithm is proposed and its convergence is proved. Furthermore, the high-order nonnegative matrix tri-factorization technique is provided for symmetric co-clustering tasks and a corresponding algorithm with proved convergence is also developed. Finally, extensive experiments in six real-world datasets demonstrate that the proposed algorithms outperform the compared state-of-the-art co-clustering methods. [ABSTRACT FROM AUTHOR]

• Extraction of image features for some classifiers. Selection of the five most successful classifiers for Phase-1 and Phase-2. Designing a system using majority voting and creating a theoretical framework. Designing the graphical user interface application. The COVID-19 pandemic has been affecting the world since December 2019, and nowadays, the number of infected is increasing rapidly. Chest X-ray images are clinical adjuncts that can be used in the diagnosis of COVID-19 disease. Because of the rapid spread of COVID-19 disease worldwide and the limited number of expert radiologists, the proposed method uses the automatic diagnosis method rather than a manual diagnosis method. In the paper, COVID-19 Positive/Negative (2275 Positive, 4626 Negative) and Normal/Pneumonia (2313 Normal, 2313 Pneumonia) are diagnosed using chest X-ray images. Herein, 80 % and 20 % of the images are used in the training and validation set, respectively. In the proposed method, six different classifiers are trained using chest X-ray images, and the five most successful classifiers are used in both phases. In Phase-1 and Phase-2, image features are extracted using the Bag of Features method for Cosine K-Nearest Neighbor (KNN), Linear Discriminant, Logistic Regression, Bagged Trees Ensemble, Medium Gaussian Support Vector Machine (SVM), excluding SqueezeNet Deep Learning (K = 2000 and K = 1500 for Phase-1 and Phase-2, respectively). In both phases, the five most successful classifiers are determined, and images classify with the help of the Majority Voting (Mathematical Evaluation) method. The application of the proposed method is designed for users to diagnose COVID-19 Positive, Normal, and Pneumonia. The results show that accuracy values obtained by Majority Voting (Mathematical Evaluation) method for Phase-1 and Phase-2 are equal to 99.86 % and 99.28 %, respectively. Thus, it indicates that the accuracy of the whole system is 99.63 %. When we analyze the classification performance metrics for Phase-1 and Phase-2, Specificity (%), Precision (%), Recall (%), F 1 Score (%), Area Under Curve (AUC), and Matthews Correlation Coefficient (MCC) are equal to 99.98–99.83–99.07–99.51–0.9974–0.9855 and 99.73–99.69–98.63–99.23–0.9928–0.9518, respectively. Moreover, if the classification performance metrics of the whole system are examined, it is seen that Specificity (%), Precision (%), Recall (%), F 1 Score (%), AUC, and MCC are 99.88, 99.78, 98.90, 99.40, 0.9956, and 0.9720 , respectively. When the studies in the literature are examined, the results show that the proposed model is better than its counterparts. Because the best performance metrics for the dataset used were obtained in this study. In addition, since the biphasic majority voting technique is used in the study, it is seen that the proposed model is more reliable. On the other hand, although there are tens of thousands of studies on this subject, the usability of these models is debatable since most of them do not have graphical user interface applications. Already, in artificial intelligence technologies, besides the performance of the developed models, their usability is also important. Because the developed models can generally be used by people who are less knowledgeable about artificial intelligence. [ABSTRACT FROM AUTHOR]

The curse of dimensionality is a common problem in classification tasks. However, feature selection is an exciting approach to deal with this type of problem by searching for a suboptimal feature set, either by eliminating irrelevant attributes, those with redundant information, or even both. Furthermore, although the use of machine learning techniques for the classification of drum cymbals is found in the literature, little attention has been paid to approaches that focus on classifying these instruments according to their bronze alloys. This paper aims to explore and evaluate the temporal information retrieved from audios, using TSFEL (Time Series Feature Extraction Library) as a tool to extract 18 temporal attributes, three feature selection approaches to assess these features, and logistic regression as a classifier. To this end, 276 audios referring to four drum cymbals of three different bronze alloys were captured in the studio through a sound acquisition procedure that took into account environment and microphone variations. Hence, one expects to find an optimal subset of features that contains enough information from the audios to achieve the best classification performance in the proposed problem. The experimental results show that a feature selection approach sequentially based on L 1 Regularization and Correlation Analysis was able to find a subset consisting of 5 attributes that achieved an average accuracy of 97.08%. • The computational model can identify the cymbals' bronze alloys through their sound. • A standardized impact procedure is developed for the audio signals acquisition. • Feature selection could reduce the dimensionality up to 70%, improving accuracy. • Logistic Regression with feature selection achieved high material classification rate. • High accuracy is attained even considering different sound capture perspectives. [ABSTRACT FROM AUTHOR]

The goal of few-shot learning is to use limited labeled samples to complete independent classification tasks. The feature extractor of few-shot learning needs to have a stronger feature expression ability to generalize in unseen novel classes. To further enhance the expressive ability, in this paper, we propose an inherited feature extraction method, named Base and Meta Feature Extraction (BMFE). Base feature represents the task-irrelevant classification information of each sample. Meta feature obtained by the proposed Triplet Meta-train Mechanism (TMM) inherits the classification information and also contains the task-related meta information of each sample. We concatenate both the base and meta features to complementarily express the rich information of each sample. Besides, instead of relying on limited support samples to obtain the prototype, we propose a novel unsupervised prototype correction module, named Prototype Self-updating (PSU). All unlabeled query samples in a few-shot test task participate in the iterative updating of each prototype in the task without training. Extensive experiments prove that our overall method can obtain richer features by BMFE and more accurate prototypes by PSU. Our overall method outperforms state-of-the-art methods on miniImageNet and tiredImageNet datasets, and especially under the 1-shot case we obtains 78.45% and 81.21% classification accuracy respectively. • BMFE can obtain the complementary features representation of FSL. • TMM mechanism can better perform meta-training of BMFE. • PSU can correct prototypes without training process. • The proposed CFPSU gets outstanding results on two standard datasets. [ABSTRACT FROM AUTHOR]

Disease diagnosis and prediction methods in biotechnology and medicine have significantly advanced over time. Consequently, analyzing raw gene expression is crucial for identifying diseases such as cancer. Interestingly, microarrays are a tool that records gene expression from deoxyribonucleic acid (DNA) or ribonucleic acid. This technique exhibits intriguing characteristics, such as generating high-dimensional data with a small sample size. However, in the case of such dataset, the classification model is prone to overfitting. This limitation can be overcome by reducing the dimensions of the microarray datasets to a reasonable number. Machine learning (ML)-based data reduction has recently achieved considerable attention in genomic research. Therefore, this review examines recent studies that present state-of-the-art data reduction and classification algorithms for microarray gene expression data to diagnose tumors and analyzes their performance. To the best of our knowledge, this is the first review that provides a comprehensive view of data preprocessing, dimensionality reduction, including feature (i.e., gene) selection, feature extraction, and their hybrid, and ML algorithms. The paper is structured as follows. First, this review summarizes several data preprocessing methods applied to gene expression datasets. Then, a detailed review of various ML-based feature selection algorithms, including filter, wrapper, embedded, ensemble, and hybrid algorithms, is discussed. These algorithms are examined under three main classes—supervised, unsupervised, and semisupervised ML. Next, the feature extraction and hybrid of feature extraction and selection algorithms are thoroughly reviewed. Furthermore, a detailed review of broadly applied ML algorithms to simplify tumor and nontumor classification using microarray datasets is presented. Finally, the challenges and open questions related to gene expression datasets for accurate cancer classification and detection are highlighted. [Display omitted] • A comprehensive review on microarray gene expression reduction is proposed. • A novel taxonomy of up-to-date gene reduction algorithms is presented. • The strength and limitations of each type of gene reduction algorithms are provided. • Provide an outline of the accurately used type of machine learning algorithms. • Analyze the performance of the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Multimodal biometrics provides rich information in biometric recognition systems, thus a valid multimodal feature fusion framework and an efficient recognition algorithm are desirable for multimodal biometrics systems. In this paper, we design a multimodal fusion framework for face and fingerprint images using block based feature-image matrix, and extract a type of middle-layer semantic feature from local features—a local fusion visual feature, which has better characterization capabilities with lower dimension for multimodal biometrics. Furthermore, we create recognition utilizing the Variational Bayesian Extreme Learning Machine (VBELM), which has an obvious speed advantage by random input weights, and also has superior stability and generalization by adding a non-informative full Gaussian prior. This research enables multimodal biometrics recognition system to have a concentrated fusion feature description and great recognition performance. Experimental results show that the proposed multimodal biometrics recognition system has a higher testing accuracy in comparison to the traditional methods with higher efficiency and better stability. [ABSTRACT FROM AUTHOR]

Office documents are used extensively by individuals and organizations. Most users consider these documents safe for use. Unfortunately, Office documents can contain malicious components and perform harmful operations. Attackers increasingly take advantage of naive users and leverage Office documents in order to launch sophisticated advanced persistent threat (APT) and ransomware attacks. Recently, targeted cyber-attacks against organizations have been initiated with emails containing malicious attachments. Since most email servers do not allow the attachment of executable files to emails, attackers prefer to use of non-executable files (e.g., documents) for malicious purposes. Existing anti-virus engines primarily use signature-based detection methods, and therefore fail to detect new unknown malicious code which has been embedded in an Office document. Machine learning methods have been shown to be effective at detecting known and unknown malware in various domains, however, to the best of our knowledge, machine learning methods have not been used for the detection of malicious XML-based Office documents ( * .docx, * .xlsx, * .pptx, * .odt, * .ods, etc.). In this paper we present a novel structural feature extraction methodology ( SFEM ) for XML-based Office documents. SFEM extracts discriminative features from documents, based on their structure. We leveraged SFEM ’s features with machine learning algorithms for effective detection of malicious * .docx documents. We extensively evaluated SFEM with machine learning classifiers using a representative collection (16,938 * .docx documents collected "from the wild") which contains ∼4.9% malicious and ∼95.1% benign documents. We examined 1,600 unique configurations based on different combinations of feature extraction, feature selection, feature representation, top-feature selection methods, and machine learning classifiers. The results show that machine learning algorithms trained on features provided by SFEM successfully detect new unknown malicious * .docx documents. The Random Forest classifier achieves the highest detection rates, with an AUC of 99.12% and true positive rate (TPR) of 97% that is accompanied by a false positive rate (FPR) of 4.9%. In comparison, the best anti-virus engine achieves a TPR which is ∼25% lower. [ABSTRACT FROM AUTHOR]

Zero-shot learning enables the recognition of classes not seen during training through the use of semantic information comprising a visual description of the class either in textual or attribute form. Despite the advances in the performance of zero-shot learning methods, most of the works do not explicitly exploit the correlation between the visual attributes of the image and their corresponding semantic attributes for learning discriminative visual features. In this paper, we introduce an attention-based strategy for deriving features from the image regions regarding the most prominent attributes of the image class. In particular, we train a Convolutional Neural Network (CNN) for image attribute prediction and use a gradient-weighted method for deriving the attention activation maps of the most salient image attributes. These maps are then incorporated into the feature extraction process of Zero-Shot Learning (ZSL) approaches for improving the discriminability of the features produced through the implicit inclusion of semantic information. For experimental validation, the performance of state-of-the-art ZSL methods was determined using features with and without the proposed attention model. Surprisingly, we discover that the proposed strategy degrades the performance of ZSL methods in classical ZSL datasets (AWA2), but it can significantly improve performance when using face datasets. Our experiments show that these results are a consequence of the interpretability of the dataset attributes, suggesting that existing ZSL datasets attributes are, in most cases, difficult to be identifiable in the image. Source code is available at https://github.com/CristianoPatricio/SGAM. • An attention-based method for improving the performance of zero-shot face recognition. • Derivation of Attribute Attention Maps (AAM) for the most salient image attributes. • Extensive visual analysis of the AAM obtained from both CelebA and ZSL datasets. [ABSTRACT FROM AUTHOR]

The growing rate of malware and its complexity demands a new approach to detecting evolving malware instead of relying only on high-level features such as opcodes, API calls, control flow graphs, etc. Moreover, extracting these features is an expensive and time-consuming because it requires disassembling or code execution. This paper presents a new malware detection architecture using image analysis & machine learning, requiring significantly fewer resources and does not depend upon code disassembling or execution. The collected binary samples are systematically labeled using the AVClass tool and clustering method based on similar characteristics of them. The labeled malicious program is visualized into grayscale images to extract the local and global textural features. The local textural features are extracted using SIFT, KAZE, and ORB descriptors, and global features are extracted using GIST, Hu Moments, and HOG. A bag of visual words (BoVW) algorithm is designed to select low-dimensional features and construct a local feature map of malware grayscale images. The feature maps from different image descriptors are stacked and used to train five machine learning algorithms, namely, k-Nearest Neighbor (k-NN), Support Vector Machine(SVM), Random Forest (RF), Naive Bayes(NB), and ExtraTree classifier. Two datasets are used for evaluations — the public MalImg dataset of 9339 samples of 25 different families and 690 real-world malware of 22 families collected on honeypots in the wild. Intensive experiments are performed for image descriptors, image ratios, vocabulary size, and computational time as a mean time to detection(MTTD) to devise the best detector. The proposed method obtained test accuracy of 98.34% with stacked global features and 98.23% with stacked local features. Test accuracy of 92.75% with low false-positive rates is obtained for real-world recent malware datasets. Experiment results reveal the efficacy of the proposed method in detecting polymorphic obfuscated malware. Finally, a comparison with other similar malware detection systems is presented. • A new architecture of malware detection and classification using machine learning. • Novel use of hybrid textural features and bag of visual words. • A single image descriptor has difficulty capturing complex patterns of malware. [ABSTRACT FROM AUTHOR]

Machine learning has become an appealing signature-less approach to detect and classify malware because of its ability to generalize to never-before-seen samples and to handle large volumes of data. While traditional feature-based approaches rely on the manual design of hand-crafted features based on experts' knowledge of the domain, deep learning approaches replace the manual feature engineering process by an underlying system, typically consisting of a neural network with multiple layers, that perform both feature learning and classification altogether. However, the combination of both approaches could substantially enhance detection systems. In this paper we present an hybrid approach to address the task of malware classification by fusing multiple types of features defined by experts and features learned through deep learning from raw data. In particular, our approach relies on deep learning to extract N-gram like features from the assembly language instructions and the bytes of malware, and texture patterns and shapelet-based features from malware's grayscale image representation and structural entropy, respectively. These deep features are later passed as input to a gradient boosting model that combines the deep features and the hand-crafted features using an early-fusion mechanism. The suitability of our approach has been evaluated on the Microsoft Malware Classification Challenge benchmark and results show that the proposed solution achieves state-of-the-art performance and outperforms gradient boosting and deep learning methods in the literature. • It presents an hybrid system for malware classification. • It provides a detailed description of hand-crafted and deep features. • It presents an effective mechanism to fuse hand-crafted and deep features. • It successfully combines the benefits of feature engineering and deep learning. • It performs an exhaustive evaluation of the features on the Microsoft benchmark. [ABSTRACT FROM AUTHOR]

Every year billions of Euros are lost worldwide due to credit card fraud. Thus, forcing financial institutions to continuously improve their fraud detection systems. In recent years, several studies have proposed the use of machine learning and data mining techniques to address this problem. However, most studies used some sort of misclassification measure to evaluate the different solutions, and do not take into account the actual financial costs associated with the fraud detection process. Moreover, when constructing a credit card fraud detection model, it is very important how to extract the right features from the transactional data. This is usually done by aggregating the transactions in order to observe the spending behavioral patterns of the customers. In this paper we expand the transaction aggregation strategy, and propose to create a new set of features based on analyzing the periodic behavior of the time of a transaction using the von Mises distribution. Then, using a real credit card fraud dataset provided by a large European card processing company, we compare state-of-the-art credit card fraud detection models, and evaluate how the different sets of features have an impact on the results. By including the proposed periodic features into the methods, the results show an average increase in savings of 13%. [ABSTRACT FROM AUTHOR]

Over the last few decades, classification applied to numerous applications in science, engineering, business and industries have rapidly been increased, especially for big data. However, classifiers dealing with complicated high dimension problems with non-conforming patterns with high accuracy are rare, especially for bit-level features. It is a challenging research problem. This paper proposed a novel efficient classifier based on cellular automata model, called Cellular Automata-based Classifier (CAC). CAC possesses the promising capability to deal with non-conforming patterns in the bit-level features. It was developed on a new kind of the proposed elementary cellular automata, called Decision Support Elementary Cellular Automata (DS-ECA). The classification capability of DS-ECA is promising since it can describe very complicated decision rule in high dimension problems with less complexity. CAC comprises double rule vectors and a decision function, the structure of which has two layers; the first layer is employed to evolve an input pattern into feature space and the other interprets the patterns in feature space as binary answer through the decision function. It has a time complexity of learning at O( n 2 ), while the classification for one instance is O(1), where n is a number of bit patterns. For classification performance, 12 datasets consisting of binary and non-binary features are empirically implemented in comparison with Support Vector Machines (SVM) using k -fold cross validation. In this respect, CAC outperforms SVM with the best kernel for binary features, and provides the promising results equivalent to SVM on average for non-binary features. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel and efficient system for large-scale action recognition from realistic video clips. Our approach combines several recent advances in this area. We use improved dense trajectory features in combination with Fisher vector encoding, and perform learning and classification with extreme learning machine classifiers. The resulting system is a fast and accurate alternative to more traditional action classification approaches like bag of words and support vector machines. Additionally, we use mid-level features that encode information about presence of humans in the videos, as well as color distributions. We extensively evaluate each step of our pipeline in a comparative manner, and report results on the recently published THUMOS 2014 benchmark, which was introduced as a challenge dataset with temporally untrimmed videos and 101 action classes. We achieve 63.37% mean average precision using the challenge protocol (i.e. sequestered test labels and limited system submissions), and got the third rank among eleven participants. The results show that it is possible to obtain a high accuracy with extreme learning machines in an efficient way, without using the extensively trained and computationally heavy deep neural networks that the top performing systems of the challenge incorporated. [ABSTRACT FROM AUTHOR]

Dysphagia is a widespread swallowing disorder. One of the most widely used clinical assessments is the bedside swallowing disorder screening, including the water swallow test. This method can only diagnose the disease according to the choking situation of the liquid, and the aspiration may appear during the drinking water test. In this paper, an automatic diagnostic system is designed according to the patient's performance in pronunciation. To diagnose dysphagia, we treat it as a binary classification task. We use a throat vibrator to collect the vibration signals of the subjects during pronunciation for clear speech signals. Feature engineering techniques, including feature extraction, data balancing and dimensionality reduction are implemented to extract the features for classification. Three popular classifiers are integrated to make the final predictions. Experimental results show that the integrated classifier performs better with accuracy = 72.09%, sensitivity = 63.64% and specificity = 80.95% respectively. Different from the traditional clinical ways, a new machine learning based swallowing disorders detection system is proposed with vibration signals of throat acquired for high-quality speech analysis. It may help to realize a portal and low-cost telemedicine device for dysphagia diagnosis at home. • We achieve an early screening of dysphagia based on speech analysis. • We use a new data acquisition system to collect clear throat vibration. • We design a new integrated classifier that performs well. • A new group of speech features is tested and performs better than previous methods. [ABSTRACT FROM AUTHOR]

• 3 layer neural networks outperform other ML algorithms in automated assessments. • In subjective assignments, deep neural networks can improve score prediction. • Word embeddings and linguistic feature results in more precise text mining models. • Extraction and selection of appropriate features can improve results. Machine learning (ML) has recently gained popularity in a variety of domains for automating tasks. This has also been used in the evaluation of student responses/ assignments. This paper presents a qualitatively enhanced methodology for automated score prediction of subjective assignments. To consider all the major aspects of a human grader, 21 linguistic features related to syntactical, grammatical, sentimental, and readability are analyzed from the assignments. This study makes use of the ASAP competition dataset from Kaggle. The evaluation metric used is Quadratic Weighted Kappa (QWK), which measures the agreement between the human graded score and the predicted score. The effect of appropriate feature selection has been observed using Mutual Information Regression. Four ML algorithms are investigated on identified linguistic features. 3 Layer Neural Network with feature selection performed well among all chosen ML algorithms with average QWK of 0.678. To include the benefits of deep learning, a new hybrid model (LF-BiLSTM-att-FS) is proposed that combines a higher level deep neural network (DNN) with the selected features. Pre-trained Glove embedding is used to include contextual information of the text. The proposed model results demonstrated an improvement in overall accuracy, with an average QWK value of 0.768. [ABSTRACT FROM AUTHOR]