Search

Around a third of the total population of Europe suffers from mental disorders. The use of electroencephalography (EEG) together with Machine Learning (ML) algorithms to diagnose mental disorders has recently been shown to be a prominent research area, as exposed by several reviews focused on the field. Nevertheless, previous to the application of ML algorithms, EEG data should be correctly preprocessed and prepared via Feature Engineering (FE). In fact, the choice of FE techniques can make the difference between an unusable ML model and a simple, effective model. In other words, it can be said that FE is crucial, especially when using complex, non-stationary data such as EEG. To this aim, in this paper we present a Systematic Mapping Study (SMS) focused on FE from EEG data used to identify mental disorders. Our SMS covers more than 900 papers, making it one of the most comprehensive to date, to the best of our knowledge. We gathered the mental disorder addressed, all the FE techniques used, and the Artificial Intelligence (AI) algorithm applied for classification from each paper. Our main contributions are: (i) we offer a starting point for new researchers on these topics, (ii) we extract the most used FE techniques to classify mental disorders, (iii) we show several graphical distributions of all used techniques, and (iv) we provide critical conclusions for detecting mental disorders. To provide a better overview of existing techniques, the FE process is divided into three parts: (i) signal transformation, (ii) feature extraction, and (iii) feature selection. Moreover, we classify and analyze the distribution of existing papers according to the mental disorder they treat, the FE processes used, and the ML techniques applied. As a result, we provide a valuable reference for the scientific community to identify which techniques have been proven and tested and where the gaps are located in the current state of the art. [ABSTRACT FROM AUTHOR]

Automatic Speech Emotion Recognition (ASER) has recently garnered attention across various fields including artificial intelligence, pattern recognition, and human–computer interaction. However, ASER encounters numerous challenges such as a shortage of diverse datasets, appropriate feature selection, and suitable intelligent recognition techniques. To address these challenges, a systematic literature review (SLR) was conducted following established guidelines. A total of 60 primary research papers spanning from 2011 to 2023 were reviewed to investigate, interpret, and analyze the related literature by addressing five key research questions. Despite being an emerging area with applications in real-life scenarios, ASER still grapples with limitations in existing techniques. This SLR provides a comprehensive overview of existing techniques, datasets, and feature extraction tools in the ASER domain, shedding light on the weaknesses of current research studies. Additionally, it outlines a list of limitations for consideration in future work. [ABSTRACT FROM AUTHOR]

The image object recognition and detection technology are widely used in many scenarios. In recent years, big data has become increasingly abundant, and big data-driven artificial intelligence models have attracted more and more attention. Evolutionary computation has also provided a powerful driving force for the optimization and improvement of deep learning models. In this paper, we propose an image object detection method based on self-supervised and data-driven learning. Differ from other methods, our approach stands out due to its innovative use of multispectral data fusion and evolutionary computation for model optimization. Specifically, our method uniquely combines visible light images and infrared images to detect and identify image targets. Firstly, we utilize a self-supervised learning method and the AutoEncoder model to perform high-dimensional feature extraction on the two types of images. Secondly, we fuse the extracted features from the visible light and infrared images to detect and identify objects. Thirdly, we introduce a model parameter optimization method using evolutionary learning algorithms to enhance model performance. Validation on public datasets shows that our method achieves comparable or superior performance to existing methods. [ABSTRACT FROM AUTHOR]

The retinal impulse signal is the basic carrier of visual information. It records the distribution of light on the retina. However, its direct conversion to a scene image is difficult due to the nonlinear characteristics of its distribution. Therefore, the use of artificial neural network to reconstruct the scene from retinal spikes has become an important research area. This paper proposes the architecture of a neural network based on vector quantization, where the feature vectors of spike trains are extracted, compressed, and stored using a feature extraction and compression network. During the decoding process, the nearest neighbour search method is used to find the nearest feature vector corresponding to each feature vector in the feature map. Finally, a reconstruction network is used to decode a new feature map composed of matching feature vectors to obtain a visual scene. This paper also verifies the impact of vector quantization on the characteristics of pulse signals by comparing experiments and visualizing the characteristics before and after vector quantization. The network delivers promising performance when evaluated on different datasets, demonstrating that this research is of great significance for improving relevant applications in the fields of retinal image processing and artificial intelligence. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) system performance and reliability can be improved through the detection of defects in PV modules and the evaluation of their effects on system operation. In this paper, a novel system is proposed to detect and classify defects based on electroluminescence (EL) images. This system is called Fault Detection and Classification (FDC) and splits into four modules, which are (1) Image Preprocessing Module (IPM), (2) Feature Extraction Module (FEM), (3) Feature Selection Module (FSM), and (4) Classification Module (CM). In the first module (i.e., IPM), the EL images are preprocessed to enhance the quality of the images. Next, the two types of features in these images are extracted and fused together through FEM. Then, during FSM, the most important and informative features are extracted from these features using a new feature selection methodology, namely, Feature Selection-based Chaotic Map (FS-CM). FS-CM consists of two stages: filter stage using chi-square to initially select the most effective features and a modified selection stage using an enhanced version of Butterfly Optimization Algorithm (BOA). In fact, BOA is a popular swarm-based metaheuristic optimization algorithm that has only recently found success. While BOA has many benefits, it also has some drawbacks, including a smaller population and an increased likelihood of getting stuck in a local optimum. In this paper, a new methodology is proposed to improve the performance of BOA, called chaotic-based butterfly optimization algorithm. Finally, these selected features are used to feed the proposed classification model through CM. During CM, Hybrid Classification Model (HCM) is proposed. HCM consists of two stages, which are binary classification stage using Naïve Bayes (NB) and multi-class classification stage using enhanced multi-layer perceptron. According to the experimental results, the proposed system FDC outperforms the most recent methods. FDC introduced 98.2%, 89.23%, 87.2%, 87.9%, 87.55%, and 88.20% in terms of accuracy, precision, sensitivity, specificity, g-mean, and f-measure in the same order. [ABSTRACT FROM AUTHOR]

To address the problem that the traditional detection method for litchi sugar content is time-consuming and laborious and will destroy the tested sample, this paper proposed a non-destructive detection method for litchi sugar content based on near-infrared spectroscopy (NIR) and artificial intelligence algorithm. Firstly, to remove noise and other interference, the preprocessing methods for spectral data are studied. Nine preprocessing methods, such as moving average smoothing (MA), standard normal variate transform (SNV), and multiplicative scatter correction (MSC), are adopted to preprocess the spectral data. Then, to reduce the input dimension of the model and overcome the interference of redundant bands, the feature extraction methods for spectral data are examined. Two feature extraction methods, including Monte-Carlo uninformative variable elimination (MCUVE) and competitive adaptive reweighted sampling (CARS), are utilized to extract the features of spectral data. Finally, partial least squares regression (PLSR) and stochastic configuration network (SCN) are adopted to establish the prediction model of litchi sugar content. The experimental results show that the SNV-CARS-SCN prediction model has the highest accuracy. The coefficient of determination ( R 2 ), RMSE, and MAE of the training dataset are 0.9996, 0.1145, and 0.1154, respectively. R 2 , RMSE, and MAE of the test dataset are 0.9740, 0.4962, and 0.3818, respectively. The NIR detection system and SCN prediction model designed in this paper are of great significance for the design of litchi automatic sorting system. [ABSTRACT FROM AUTHOR]

In this paper, we have proposed a hybrid bio-inspired algorithm which takes the merits of whale optimization algorithm (WOA) and adaptive particle swarm optimization (APSO). The proposed algorithm is referred as the hybrid WOA_APSO algorithm. We utilize a convolutional neural network (CNN) for classification purposes. Extensive experiments are performed to evaluate the performance of the proposed model. Here, pre-processing and segmentation are performed on 120 lung CT images for obtaining the segmented tumored and non-tumored region nodule. The statistical, texture, geometrical and structural features are extracted from the processed image using different techniques. The optimized feature selection plays a crucial role in determining the accuracy of the classification algorithm. The novel variant of whale optimization algorithm and adaptive particle swarm optimization, hybrid bio-inspired WOA_APSO, is proposed for selecting optimized features. The feature selection grouping is applied by embedding linear discriminant analysis which helps in determining the reduced dimensions of subsets. Twofold performance comparisons are done. First, we compare the performance against the different classification techniques such as support vector machine, artificial neural network (ANN) and CNN. Second, the computational cost of the hybrid WOA_APSO is compared with the standard WOA and APSO algorithms. The experimental result reveals that the proposed algorithm is capable of automatic lung tumor detection and it outperforms the other state-of-the-art methods on standard quality measures such as accuracy (97.18%), sensitivity (97%) and specificity (98.66%). The results reported in this paper are encouraging; hence, these results will motivate other researchers to explore more in this direction. [ABSTRACT FROM AUTHOR]

Machine learning techniques aim to mimic the human ability to automatically learn how to perform tasks through training examples. They have proven capable of tasks such as prediction, learning and adaptation based on experience and can be used in virtually any scientific application, ranging from biomedical, robotic, to business decision applications, and others. However, the lack of domain knowledge for a particular application can make feature extraction ineffective or even unattainable. Furthermore, even in the presence of pre-processed datasets, the iterative process of optimizing Machine Learning parameters, which do not translate from one domain to another, maybe difficult for inexperienced practitioners. To address these issues, we present in this paper a Vectorized Automated ML Pre-processIng and post-pRocEssing framework, approximately named (VAMPIRE), which implements feature extraction algorithms capable of converting large time-series recordings into datasets. Also, it introduces a new concept, the Activation Engine, which is attached to the output of a Multi Layer Perceptron and extracts the optimal threshold to apply binary classification. Moreover, a tree-based algorithm is used to achieve multi-class classification using the Activation Engine. Furthermore, the internet of things gives rise to new applications such as remote sensing and communications, so consequently applying Machine Learning to improve operation accuracy, latency, and reliability is beneficial in such systems. Therefore, all classifications in this paper were performed on the edge in order to reach high accuracy with limited resources. Moreover, forecasts were applied on three unrelated biomedical datasets, and on two other pre-processed urban and activity detection datasets. Features were extracted when required, and training and testing were performed on the Raspberry Pi remotely, where high accuracy and inference speed were achieved in every experiment. Additionally, the board remained competitive in terms of power consumption when compared with a laptop which was optimized using a Graphical Processing Unit. [ABSTRACT FROM AUTHOR]

This paper presents survey on various techniques used to classify plants and its disease. Classification is concerned with classifying each sample into different classes. Classification is a method of separating a healthy and diseased leaf on its morphological features such as texture, color, shape, pattern and so on. Due to resemblance in the visual properties among plants, sorting and classification are complicated to carry out especially in large area. There are various methods based on image processing techniques and computer vision. Choosing the suitable classification technique is quite difficult as the result varies on different input data. Classification of leaf diseases in plants has wide applications in different fields such as agriculture and biological research. This paper provides a general idea of few existing methods, its pros and cons, state of art of different techniques used by several authors in leaf disease identification and classification such as preprocessing techniques, feature extraction and selection techniques, datasets used, classifiers and performance metrics. Apart from these some challenges and research gaps are identified and their probable solutions are pointed out. [ABSTRACT FROM AUTHOR]

This paper proposes a novel data preprocessing method that converts numeric data into representative graphs (polygons) expressing all of the relationships between data variables in a systematic way based on Hamiltonian cycles. The advantage of the proposed method is that it has an embedded feature extraction capability in which each generated polygon depicts a class-specific representation in the data, thereby supporting accurate "end-to-end learning" in industrial fault classification applications. Moreover, the generated polygons can play a significant role in the interpretation of trained deep learning fault classifiers. The performance of the proposed method was demonstrated using a benchmark dataset in the process industry. It was also tested successfully to classify challenging faults in major equipment in a thermomechanical pulp mill located in Canada. The results of the proposed method show better performance than other comparable fault classifiers. [ABSTRACT FROM AUTHOR]

The rapid development of artificial intelligence gave motivations to researchers to apply it in information security, biometrics, and medical image encryption. This paper presents an encryption approach for CT images that are used in diagnosing COVID-19 disease. To add more privacy, the proposed encryption mechanism links the CT image and the facial image of a person. Firstly, a simple Convolutional Neural Network (CNN) is utilized to extract features from facial images. The architecture of the CNN model includes three convolutional groups, and each group consists of a convolutional layer, a batch normalization layer, a Rectified Linear Unit (ReLU), and a maximum pooling layer. Moreover, the extracted feature vector is utilized to adjust the initial states of a two-dimensional Sine Logistic Modulation Map (2D-SLMM), so as to generate chaotic matrices SLM1 and SLM2, and to adjust the initial states of a Tent Logistic Map (TLM) in order to get two other chaotic matrices, TLM1 and TLM2. Finally, the Chaotic Magic Transform (CMT) confusion operation and the bitwise XOR diffusion operation are used to randomly scramble the pixel locations and change the pixel values, respectively. Only after two rounds of CMT and two bitwise XOR operations with chaotic matrices SLM1, SLM2, TLM1 and TLM2, we get an unrecognizable encrypted CT image with a high security level. In adittion, we study and analyze the performance of the proposed approach in the presence of differential, entropy and key sensitivity attacks. In the experiments, when performing decryption, two cases are discussed; utilization of the correct key and utilization of the correct key with small variation. The robustness of the proposed encryption approach is measured using different metrics like Correlation Coefficient (CC), entropy, histogram analysis, and elapsed time. The maximum elapsed time is about 0.4361 seconds. [ABSTRACT FROM AUTHOR]

Purpose: To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies. Methods: We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated. Result: In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community. Conclusion: In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers. Critical relevance statement: A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning. Key points: • A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score (https://metricsscore.github.io/metrics/METRICS.html) and a repository created to collect feedback from the radiomics community (https://github.com/metricsscore/metrics). [ABSTRACT FROM AUTHOR]

The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection. [ABSTRACT FROM AUTHOR]

The most basic and important attributes of virtual reality (VR) are immersion, interactivity and creativity. For this young media, the continuous development and change and the exploration of content are the current situation of VR art. The arrival of 5G communication technology provides an important foundation for the popularization of VR technology. The rapid development of technology and hardware rewrites and expands the possibility of VR art design expression at any time. As the latest technology of natural human–computer interaction, somatosensory interaction technology enables users to interact with computers directly through body movements, gestures, etc., and control the environment at will. Its core value lies in that it not only enables the computer to have more accurate and effective "eyes" to observe the world, not only to understand human body language, but also to complete various instructions according to the body language, to achieve real-time interaction with people. Gesture, as a common communication mode with the ability of information expression, has the advantages of intuitionistic, natural and easy to understand. Therefore, the somatosensory interaction technology based on gesture recognition has become an effective means of natural human–computer interaction. With the rapid development of key technologies of VR, VR has been widely used in games, fitness, real estate, education, film and television and other industries. In recent years, VR systems are everywhere, including virtual home decoration system, virtual panoramic VR live broadcasting system, virtual fitness system, etc. The design and implementation of this VR system mainly includes four parts: scene modeling, rendering and rendering, performance and interaction, and network application. Based on this, this paper uses the comprehensive data analysis technology to build the human–computer interaction design model in the virtual environment. The AI and speech information are combined to perform the optimal analysis. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) using inertial motion data has gained a lot of momentum in recent years both in research and industrial applications. From the abstract perspective, this has been driven by the rapid dynamics for building intelligent, smart environments, and ubiquitous systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc., which necessitate and subsume activity recognition aiming at recognizing the actions, characteristics, and goals of one or more agent(s) from a temporal series of observations streamed from one or more sensors. From a more concrete and seemingly orthogonal perspective, such momentum has been driven by the ubiquity of inertial motion sensors on-board mobile and wearable devices including smartphones, smartwatches, etc. In this paper we give an introductory and a comprehensive survey to the subject from a given perspective. We focus on a subset of topics, that we think are major, that will have significant and influential impacts on the future research and industrial-scale deployment of HAR systems. These include: (1) a comprehensive and detailed description of the inertial motion benchmark datasets that are publicly available and/or accessible, (2) feature selection and extraction techniques and the corresponding learning methods used to build workable HAR systems; we survey classical handcrafted datasets as well as data-oriented automatic representation learning approach to the subject, (3) transfer learning as a way to overcome many hurdles in actual deployments of HAR systems on a large scale, (4) embedded implementations of HAR systems on mobile and/or wearable devices, and finally (5) we touch on adversarial attacks, a topic that is essentially related to the security and privacy of HAR systems. As the field is very huge and diverse, this article is by no means comprehensive; it is though meant to provide a logically and conceptually rather complete picture to advanced practitioners, as well as to present a readable guided introduction to newcomers. Our logical and conceptual perspectives mimic the typical data science pipeline for state-of-the-art AI-based systems. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cardiac-related disorders are rapidly growing throughout the world. Accurate classification of cardiovascular diseases is an important research topic in healthcare. During COVID-19, auscultating heart sounds was challenging as health workers and doctors wear protective clothing, and direct contact with patients can spread the outbreak. Thus, contactless auscultation of heart sound is necessary. In this paper, a low-cost ear contactless stethoscope is designed where auscultation is done with the help of a bluetooth-enabled micro speaker instead of an earpiece. The PCG recordings are further compared with other standard electronic stethoscopes like Littman 3 M. This work is made to improve the performance of deep learning-based classifiers like recurrent neural networks (RNN) and convolutional neural networks (CNN) for different valvular heart problems using tuning of hyperparameters like learning rate of optimizers, dropout rate, and hidden layer. Hyper-parameter tuning is used to optimize the performances of various deep learning models and their learning curves for real-time analysis. The acoustic, time, and frequency domain features are used in this research. The investigation is made on the heart sounds of normal and diseased patients available from the standard data repository to train the software models. The proposed CNN-based inception network model achieved an accuracy of 99.65 ± 0.06% on the test dataset with a sensitivity of 98.8 ± 0.05% and specificity of 98.2 ± 0.19%. The proposed hybrid CNN-RNN architecture attained 91.17 ± 0.03% accuracy on test data after hyperparameter optimization, whereas the LSTM-based RNN model achieved 82.32 ± 0.11% accuracy. Finally, the evaluated results were compared with machine learning algorithms, and the improved CNN-based Inception Net model is the most effective among others. [ABSTRACT FROM AUTHOR]

Heart disease is a common condition worldwide and has become one of the leading causes of death worldwide. The electrocardiogram (PCG) is a safe, painless, and non-invasive test that captures bioacoustic information reflecting the function of the heart by capturing the acoustic signal of the patient's heart. Nowadays, based on biosignal processing and artificial intelligence technologies, automated heart sound classification is playing an increasingly important role in clinical applications. In this paper, we propose a new parallel CNNs-transformer network with multi-scale feature context aggregation (PCTMF-Net). It combines the advantages of CNNs and transformer to achieve efficient heart sound classification. In PCTMF-Net, firstly, the heart tone signal features are extracted using the second-order spectral analysis, and a transformer-based MHTE-4 (multi-head transformer encoder with four attention heads) is designed to encode and aggregate the contextual information, and then, two CNNs feature extractors are designed in parallel with MHTE-4 to capture the hierarchical features. Finally, the feature vectors obtained from CNNs and MHTE-4 through feature fusion in PCTMF-Net will be fed into the fully connected layer for predicting the classification results of heart sounds. In addition, we perform validation based on two publicly available mutually exclusive heart sound datasets and conduct extensive experiments and comparisons of existing algorithms under different metrics. The experimental results show that our proposed method achieves 99.36% accuracy on the Yaseen dataset and 93% accuracy on the PhysioNet dataset. It surpasses current algorithms in terms of accuracy, recall and F1-score metrics. The aim of this study is to apply these new techniques and methods to improve the diagnostic accuracy and validity of heart disease for clinical use. [ABSTRACT FROM AUTHOR]

Coronavirus Disease 2019 (COVID-19) is an evolving communicable disease caused due to Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) which has led to a global pandemic since December 2019. The virus has its origin from bat and is suspected to have transmitted to humans through zoonotic links. The disease shows dynamic symptoms, nature and reaction to the human body thereby challenging the world of medicine. Moreover, it has tremendous resemblance to viral pneumonia or Community Acquired Pneumonia (CAP). Reverse Transcription Polymerase Chain Reaction (RT-PCR) is performed for detection of COVID-19. Nevertheless, RT-PCR is not completely reliable and sometimes unavailable. Therefore, scientists and researchers have suggested analysis and examination of Computing Tomography (CT) scans and Chest X-Ray (CXR) images to identify the features of COVID-19 in patients having clinical manifestation of the disease, using expert systems deploying learning algorithms such as Machine Learning (ML) and Deep Learning (DL). The paper identifies and reviews various chest image features using the aforementioned imaging modalities for reliable and faster detection of COVID-19 than laboratory processes. The paper also reviews and compares the different aspects of ML and DL using chest images, for detection of COVID-19. [ABSTRACT FROM AUTHOR]

Lung cancer is an uncontrolled growth of tissue causing a lump in the human lung. If lung cancer can be detected early, it can increase the survival rate. Therefore, a multi-classification approach of lung nodule detection with high computational effectiveness is required. In this paper, a multi-classification approach of lung nodule detection and classification is proposed using artificial intelligence on computed tomography (CT) scan images. Different preprocessing steps are applied for resizing, smoothing, and enhancement of the CT images. Then, two different approaches for feature extraction using VGG16 transfer learning and morphological segmentation are proposed. Morphological segmentation and feature extraction are applied for the segmentation of the region of interest and to extract the distinct features. Finally, the proposed deep learning architecture and seven different machine learning algorithms are applied on the preprocessed data and the extracted features for the classification of lung nodules into three classes: malignant, benign, and normal. It is observed that the stacked ensemble model of deep learning convolutional neural network (CNN) and VGG16 transfer learning models (CNN+VGG16) can achieve 99.55% accuracy using preprocessed data. It is also observed that all the ML algorithms perform with reasonably high accuracy using the low-dimensional morphological features. It is observed from the fivefold cross-validation results that logistic regression performs with 99.36% accuracy in 23.71 s time using the preprocessed data. Whereas, using the morphological features, k-nearest neighbor, and the support vector machine perform with the highest accuracy of 99.76% with very reduced computational time of 0.017 and 0.008 s, respectively. [ABSTRACT FROM AUTHOR]

In current era, the intelligent development of traditional Chinese medicine (TCM) has attracted more and more attention. As the main carrier of clinical medication, formulas use synergies of active substances to enhance efficacy and reduce side effects. Related studies show that there is a nonlinear relationship between the efficacy of formulas and herbs. Deep learning is an effective technique for fitting nonlinear relationships. However, it is not good for using deep learning model directly due to ignoring the characteristics of formulas. In this paper, we propose a detached feature extraction approach (TCM2Vec) based on deep learning for better feature extraction and efficacy prediction. We build two detached encoders, one of it uses cross-feature-based unsupervised pre-training model (FMh2v) to extract the relationship features of herbal medicines for initializing, while the other one simulates multi-dimensional characteristics of medicines by normal distribution. Then we integrate relationships and medicinal characteristics for deep feature extraction. We processed 31,114 unlabeled formulas for pre-training and two classification tasks in-domain for predicting and fine-tuning. One of tasks is multi-classed with 1036 formulas, other one is multi-labelled with 1,723 formulas. For labelled formulas, different feature extraction models based on detached encoder are trained to predict efficacy. Compared with the no pre-training, CBOW and BERT baseline models, FMh2v leads to performance gains. Moreover, the detached encoder offers large positive effects in different models which for efficacy prediction, where ACC increased by 5.80% on average and F1 increased by 12.06% on average. Overall, the proposed feature extraction is an effective method for obtaining characteristic representation of TCM formulas, and provides reference for the adaptability of artificial intelligence technology in the domain of TCM. [ABSTRACT FROM AUTHOR]

Recently, artificial intelligence-based applications are universally acknowledged. Digit recognition, particularly Persian/Arabic handwritten digits, has many applications in today's commercial contexts for example office automation and document processing. However, researcher are struggling in hand-crafted digit scripts due to the presence of different digit writing patterns, cursive nature and lack of large public databases that make the feature extraction process more complex. Therefore, critical investigation is needed to reduce these challenges. In this study, a modified Deep Convolutional Neural Network (DCNN) architecture using three convolutional layers blocks based on convolution, batch normalization, pooling, fully connected and dropout regularization parameters are employed to hinder overfitting and increase generalization performance is proposed to recognize handwritten digits. Initially, digits taken from the HODA database are pre-processed using various steps including smoothing, black and white images to grayscale intensity images conversion and resizing it to a fixed dimension. Then optimal features extraction and recognition of handwritten images are done by the DCNN algorithm. In deep learning domain, optimization algorithms are considered core solution and their performances highly depends on optimization algorithm selection. In this paper, various optimization algorithms such as stochastic gradient descent (SGD), Adam, Adadelta, Adagrad, Adamax, Momentum, RMSprop and Nag are employed for the optimization of proposed DCNN. Moreover, current research also analyzes the role of different epochs to ameliorate optical character recognition (OCR) performance of Persian/Arabic handwritten digits. At the end, we also worked on finding a suitable composition of learning parameters to establish high performance DCNN architecture that conquer the loopholes of traditional methods. Results reveal that the proposed DCNN model achieves state-of-the-art performance and outperform other studies in the literature. [ABSTRACT FROM AUTHOR]

In recent years, the exponential growth of malware has posed a significant security threat to intelligent systems. Earlier static and dynamic analysis methods fail to achieve effective recognition rate and incurs high computational complexity. The recently developed machine learning (ML) and deep learning (DL) models can be employed to detect and classify cyberattacks and Malware efficiently. This paper presents a fusion of deep learning based cyberattack detection and classification model for intelligent systems named FDL-CADIS technique. The proposed FDL-CADIS technique transforms the Malware binary files into two-dimensional images, which are then classified by the fusion model. The FDL-CADIS technique employs the binary input images into the MobileNetv2 model for the extraction of features and the hyper parameter tuning process takes place utilizing the black widow optimization technique. The MobileNetv2 model derives all features from the Malware dataset and trains the model using the derived features. Finally, an ensemble of voting based classifiers, including gated recurrent unit and long short-term memory techniques, for Malware cyberattack detection and classification was developed. A comprehensive range of experimental analysis is performed against the benchmark dataset to demonstrate the FDL-CADIS technique's promising performance. According to the comparative analysis of the results, the FDL-CADIS technique outperformed current approaches. [ABSTRACT FROM AUTHOR]

Recent advances in visionary technologies impacted multi-object recognition and scene understanding. Such scene-understanding tasks are a demanding part of several technologies such as augmented reality based scene integration, robotic navigation, autonomous driving and tourist guide applications. Incorporating visual information in contextually unified segments, super-pixel-based approaches significantly mitigate the clutter, which is normal in pixel wise frameworks during scene understanding. Super-pixels allow customized shapes and variable size patches of connected components to be obtained. Furthermore, the computational time for these segmentation approaches can significantly decreased due to the reduced number of super-pixel target clusters. Hence, the super pixel-based approaches are more commonly used in robotics, computer vision and other intelligent systems. In this paper, we propose a Maximum Entropy scaled Super-Pixels (MEsSP) Segmentation method that encapsulates super-pixel segmentation based on an Entropy Model and utilizes local energy terms to label the pixels. Initially, after acquisition and pre-processing, image is segmented by two different methods: Fuzzy C-Means (FCM) and MEsSP. Then, to extract the features from these segmented objects, the dynamic geometrical features, fast Fourier transform (FFT), blob extraction, Maximally Stable Extremal Regions (MSER) and KAZE features are extracted using the bag of features approach. Then, to categorize the objects, multiple kernel learning is applied. Finally, a deep belief network (DBN) assigns the relevant labels to the scenes based on the categorized objects, intersection over union scores and dice similarity coefficient. The experimental results regarding multiple objects recognition accuracy, precision, recall and F1 scores over PASCAL VOC, Caltech 101 and UIUC Sports datasets show a remarkable performance. In addition, the evaluation of proposed scene recognition method over these benchmark datasets outperforms the state of the art (SOTA) methods. [ABSTRACT FROM AUTHOR]

The recent evolution of machine learning (ML) algorithms and the high level of expertise required to use them have fuelled the demand for non-experts solutions. The selection of an appropriate algorithm and the configuration of its hyperparameters is among the most complicated tasks while applying ML to new problems. It necessitates well awareness and knowledge of ML algorithms. The algorithm selection problem (ASP) is defined as the process of identifying the algorithm (s) that can deliver top performance for a particular problem, task, and evaluation measure. In this context, meta-learning is one of the approaches to achieve this objective by using prior learning experiences to assist the learning process on unseen problems and tasks. As a data-driven approach, appropriate data characterization is of vital importance for the meta-learning. Nonetheless, the recent literature witness a variety of data characterization techniques including simple, statistical and information theory based measures. However, their quality still needs to be improved. In this paper, a new Autoencoder-kNN (AeKNN) based meta-model with built-in latent features extraction is proposed. The approach is aimed to extract new characterizations of the data, with lower dimensionality but more significant and meaningful features. AeKNN internally uses a deep autoencoder as a latent features extractor from a set of existing meta-features induced from the dataset. From this new features vectors the computed distances are more significant, thus providing a way to accurately recommending top-performing pipelines for previously unseen datasets. In an application on a large-scale hyperparameters optimization task for 400 real world datasets with varying schemas as a meta-learning task, we show that AeKNN offers considerable improvements of the classical kNN as well as traditional meta-models in terms of performance. [ABSTRACT FROM AUTHOR]

Almost all malwares running on web-server are php codes. Then, the present paper creates a next generation antivirus (NGAV) expert in auditing threats web-based, specifically from php files, in real time. In our methodology, the malicious behaviors, of the personal computer, serve as input attributes of the statistical learning machines. In all, our dynamic feature extraction monitors 11,777 behaviors that the web fileless attack can do when launched directly from a malicious web-server to a listening service in a personal computer. Our NGAV achieves an average 99.95% accuracy in the distinction between benign and malware web scripts. Distinct initial conditions and kernels of neural networks classifiers are investigated in order to maximize the accuracy of our NGAV. Our NGAV can supply the limitations of the commercial antiviruses as for the detection of Web fileless attack. In opposition of analysis of individual events, our engine employs authorial Web-server Sandbox, machine learning, and artificial intelligence in order to identify malicious Web-sites. [ABSTRACT FROM AUTHOR]

With the rapid development of artificial intelligence and Internet of Things (IoT) technology, increasingly edge devices have entered people's daily lives. However, due to the limited performance of edge devices, complex models can affect the response speed and efficiency of the whole system. Existing research still cannot simultaneously satisfy the demand for accuracy and response speed of edge devices. This paper proposes a lightweight and highly accurate object detection model that uses the Transformer to address edge devices' limited computational capacity and storage space. Specifically, the proposed model adopts the Swin Transformer for multi-scale feature extraction to achieve better global modeling capability. In addition, we propose the Neck module with path aggregation network (PAN), which is designed with a two-feature pyramid structure capable of combining semantic and localization information in order to improve the operational performance by exploiting the underlying location features. A lightweight detection head is then developed using group convolution, fusing the two localization branches and removes the additional decoupling operation. Finally, we conduct comparative experiments on three datasets: the Retail-cabinet dataset, the Roadsign dataset, and the Pascal VOC dataset. Experimental results show that compared with the baseline model, our model achieves an 11.8% improvement in mAP on the Retail-cabinet dataset while reducing Params and FLOPs by 23.19% and 71.50%, respectively. The proposed model effectively reduces the model's computational complexity and improves detection performance, thereby possessing high practical value. This code is released on https://github.com/ydlam/ST-YOLOX. [ABSTRACT FROM AUTHOR]

This review paper presents the practical development of imaging biomarkers in the scope of the PRIMAGE (PRedictive In silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis, Empowered by imaging biomarkers) project, as a noninvasive and reliable way to improve the diagnosis and prognosis in pediatric oncology. The PRIMAGE project is a European multi-center research initiative that focuses on developing medical imaging-derived artificial intelligence (AI) solutions designed to enhance overall management and decision-making for two types of pediatric cancer: neuroblastoma and diffuse intrinsic pontine glioma. To allow this, the PRIMAGE project has created an open-cloud platform that combines imaging, clinical, and molecular data together with AI models developed from this data, creating a comprehensive decision support environment for clinicians managing patients with these two cancers. In order to achieve this, a standardized data processing and analysis workflow was implemented to generate robust and reliable predictions for different clinical endpoints. Magnetic resonance (MR) image harmonization and registration was performed as part of the workflow. Subsequently, an automated tool for the detection and segmentation of tumors was trained and internally validated. The Dice similarity coefficient obtained for the independent validation dataset was 0.997, indicating compatibility with the manual segmentation variability. Following this, radiomics and deep features were extracted and correlated with clinical endpoints. Finally, reproducible and relevant imaging quantitative features were integrated with clinical and molecular data to enrich both the predictive models and a set of visual analytics tools, making the PRIMAGE platform a complete clinical decision aid system. In order to ensure the advancement of research in this field and to foster engagement with the wider research community, the PRIMAGE data repository and platform are currently being integrated into the European Federation for Cancer Images (EUCAIM), which is the largest European cancer imaging research infrastructure created to date. [ABSTRACT FROM AUTHOR]

Microelectronics production failure analysis is an important step in improving product quality and development. In fact, the understanding of the failure mechanisms and therefore the implementation of corrective actions on the cause of the failure depend on the results of this analysis. These analyses are saved under textual features format. Then such data need first to be preprocessed and vectorized (converted to numeric). Second, to overcome the curse of dimensionality caused by the vectorisation process, a dimension reduction is applied. A two-stage variable selection and feature extraction is used to reduce the high dimensionality of a feature space. We are first interested in studying the potential of using an unsupervised variable selection technique, the genetic algorithm, to identify the variables that best demonstrate discrimination in the separation and compactness of groups of textual data. The genetic algorithm uses a combination of the K-means or Gaussian Mixture Model clustering and validity indices as a fitness function for optimization. Such a function improves both compactness and class separation. The second work looks into the feasibility of applying a feature extraction technique. The adopted methodology is a Deep learning algorithm based on variational autoencoder (VAE) for latent space disentanglement and Gaussian Mixture Model for clustering of the latent space for cluster identification. The last objective of this paper is to propose a new methodology based on the combination between variational autoencoder (VAE) for the latent space disentanglement, and genetic algorithm (GA) to find, in an unsupervised way, the latent variables allowing the best discrimination of clusters of failure analysis data. This methodology is called VAE-GA. Experiments on textual datasets of failure analysis demonstrate the effectiveness of the VAE-GA proposed method which allows better discrimination of textual classes compared to the use of GA or VAE separately or the combination of PCA with GA (PCA-GA) or a simple Auto-encoders with GA (AE-GA). [ABSTRACT FROM AUTHOR]

Facial expression recognition is a process of identifying the different facial expressions of the individuals to categorize the mental health of the individual. This system is used in most of the fields but is vastly used in the medical field to identify the mental health issues. In this paper, a novel approach has been proposed to identify the facial expressions of the individuals and categorizing it into seven different emotions. Initially, the images collected from the dataset are subjected to pre-processing for de-noising. Then, the major geometric and appearance-based features are extracted from the images. The most relevant features are selected from the extracted feature set. Finally, based on the selected features, the classification is performed where the input images get labelled into seven different emotions. The classification is carried out with the use of the hybrid strategy called the Deep Belief Rain Optimization (DBRO) technique. The efficiency of the proposed model is proved through the simulations and it is identified to outperform the other existing approaches. [ABSTRACT FROM AUTHOR]

Human emotion recognition is an active research area in artificial intelligence and has made substantial progress over the past few years. Many recent works mainly focus on facial regions to infer human affection, while the surrounding context information is not effectively utilized. In this paper, we proposed a new deep network to effectively recognize human emotions using a novel global-local attention mechanism. Our network is designed to extract features from both facial and context regions independently, then learn them together using the attention module. In this way, both the facial and contextual information is used to infer human emotions, therefore enhancing the discrimination of the classifier. The intensive experiments show that our method surpasses the current state-of-the-art methods on recent emotion datasets by a fair margin. Qualitatively, our global-local attention module can extract more meaningful attention maps than previous methods. The source code and trained model of our network are available at https://github.com/minhnhatvt/glamor-net. [ABSTRACT FROM AUTHOR]

In the recent years, with the rapid development of China's national economy, people's living standards have been greatly improved. People's consumption demand is constantly increasing, and the consumption structure is constantly upgrading. In the automotive industry, which is increasingly related to residents' travel, consumers' demand for cars also presents a rising trend. The production and sales of domestic automobile market in China have increased greatly, and it has become the largest automobile consumer market in the world for eight consecutive years. In the information age, the speed of information interaction is faster and faster. Today, 5G technology has entered the commercial era, and the era of interconnection of everything has come. According to the work report of the Chinese government, the future city should be a smart city. In the background of Internet of things, smart city will greatly facilitate people's life in the way of ecosystem. As part of the future smart city ecosystem, intelligent cars must be self driving vehicles that meet the needs of smart city ecosystems. Therefore, the marketing strategy of smart cars is very important. Voice has always been one of the most concerned research contents in the field of human–computer communication and interaction. The main purpose of automatic speech recognition is to enable the computer to "understand" human speech and convert speech waveform signal into text. Speech recognition technology is one of the key technologies to realize intelligent human–computer interaction. The application of voice, the most natural way of interaction between human and machine, can effectively improve the input efficiency, error prone and other shortcomings of traditional interaction methods. This paper studies the intelligent vehicle marketing strategy based on speech recognition and artificial intelligence driven feature extraction technology. Through the modelling and the comparison simulations, the performance of the designed model is verified. [ABSTRACT FROM AUTHOR]

Cross-drainage hydraulic structures such as culverts and bridges in urban landscapes are prone to get blocked by the transported debris (e.g., urban, vegetated), which often reduces their hydraulic capacity and triggers flash floods. Unavailability of relevant data from blockage-originated flooding events and complex nature of debris accumulation are highlighted factors hindering the research within the blockage management domain. Wollongong City Council (WCC) blockage conduit policy is the leading formal guidelines to incorporate blockage into design guidelines; however, are criticized by the hydraulic engineers for its dependence on the post-flood visual inspections (i.e., visual blockage) instead of peak floods hydraulic investigations (i.e., hydraulic blockage). Apparently, no quantifiable relationship is reported between the visual blockage and hydraulic blockage; therefore, many consider WCC blockage guidelines invalid. This paper exploits the power of Artificial Intelligence (AI), motivated by its recent success, and attempts to relate visual blockage with hydraulic blockage by proposing a deep learning pipeline to predict hydraulic blockage from an image of the culvert. Two experiments are performed where the conventional pipeline and end-to-end learning approaches are implemented and compared in the context of predicting hydraulic blockage from a single image. In experiment one, the conventional deep learning pipeline approach (i.e., feature extraction using CNN and regression using ANN) is adopted. In contrast, in experiment two, end-to-end deep learning models (i.e., E2E_ MobileNet, E2E_ BlockageNet) are trained and compared with the conventional pipeline approach. Dataset (i.e., Hydraulics-Lab Blockage Dataset (HBD), Visual Hydraulics-Lab Dataset (VHD)) used in this research were collected from laboratory experiments performed using scaled physical models of culverts. E2E_ BlockageNet model was reported best in predicting hydraulic blockage with R 2 score of 0.91 and indicated that hydraulic blockage could be interrelated with the visual features at the culvert. [ABSTRACT FROM AUTHOR]

The advancements of the Internet of Things (IoT) and voice-based multimedia applications have resulted in the generation of big data consisting of patterns, trends and associations capturing and representing many features of human behaviour. The latent representations of many aspects and the basis of human behaviour is naturally embedded within the expression of emotions found in human speech. This signifies the importance of mining audio data collected from human conversations for extracting human emotion. Ability to capture and represent human emotions will be an important feature in next-generation artificial intelligence, with the expectation of closer interaction with humans. Although the textual representations of human conversations have shown promising results for the extraction of emotions, the acoustic feature-based emotion detection from audio still lags behind in terms of accuracy. This paper proposes a novel approach for feature extraction consisting of Bag-of-Audio-Words (BoAW) based feature embeddings for conversational audio data. A Recurrent Neural Network (RNN) based state-of-the-art emotion detection model is proposed that captures the conversation-context and individual party states when making real-time categorical emotion predictions. The performance of the proposed approach and the model is evaluated using two benchmark datasets along with an empirical evaluation on real-time prediction capability. The proposed approach reported 60.87% weighted accuracy and 60.97% unweighted accuracy for six basic emotions for IEMOCAP dataset, significantly outperforming current state-of-the-art models. [ABSTRACT FROM AUTHOR]

In the past decade, social media networks have received much attention among ordinary people, agencies, and research scholars. Twitter is one of the fastest-growing social media tools. By means of the Twitter application on smartphones, users are able to immediately report events happening around them on a real-time basis. The information disseminated by millions of active users every day generates a new version of a dynamic database that contains information about various topics. Twitter data can be utilized as a major traffic data source along with conventional sensors. In this aspect, this paper presents a novel firefly algorithm-based feature selection with a deep learning model for traffic flow analysis (FFAFS-DLTFA) using Twitter data. The goal of FFAFS-DLTFA is to determine the class labels for tweets as relevant to traffic events. The proposed FFAFS-DLTFA encompasses several processes, such as preprocessing, feature extraction, feature selection, and classification. Primarily, tweets are preprocessed in several ways, such as tokenization, removal of stop words, and stemming. At the same time, three types of embedding vectors, unigram, bigram, and POS features, are used. In addition, the firefly algorithm (FFA) is applied for the optimal selection of feature subsets. Finally, a deep neural network (DNN) model is applied for the identification of tweets into three classes, namely, positive, neutral, and negative. The performance validation of FFAFS-DLTFA takes place using the benchmark Kaggle repository, and the results are inspected under different aspects. The experimental values demonstrate the better performance of FFAFS-DLTFA on the other techniques with the maximum accuracy of 98.83%. [ABSTRACT FROM AUTHOR]

Customer Relationship Management (CRM) has gained more attention due to customer satisfaction based on management decisions. However, customer review maintenance is challenging in the management field because of the structured and unstructured data. This paper proposes a novel Generalized Savitzky-Golay Filter (GS-GF) and Hybrid Self Constructing Neural Fuzzy based African Buffalo Optimization (HSCFN-ABO) techniques for maintaining customer reviews; the customer's reaction may be positive, negative, or neutral. This novel technique provides a solution for classifying customer comments based on the specified problem, including food quality, food delivery, and payment issues. Initially, pre-processing and feature extraction is performed using the novel GS-GF approach. Once the features are extracted from the dataset, they enter the classification layer to value customer reviews using the novel HSCFN-ABO replica. The execution of this research is done using the MATLAB R2018b platform. The proposed HSCFN-ABO classifier method in CRM is tested using the real dataset from swiggy. CRM performance for customer review data using the proposed technique is validated with different case studies. Furthermore, the projected HSCFN-ABO method is compared with various other traditional methods in terms of accuracy, precision, and F measure, proving the significance of the HSCFN-ABO classifier in CRM applications. [ABSTRACT FROM AUTHOR]

Nowadays, the issue of fluctuations in the price of digital Bitcoin currency has a striking impact on the profit or loss of people, international relations, and trade. Accordingly, designing a model that can take into account the various significant factors for predicting the Bitcoin price with the highest accuracy is essential. Hence, the current paper uses market sentiment and multiple feature extraction to present several Bitcoin price prediction models based on convolutional neural network and long short-term memory. In the proposed models, several parameters, including Twitter data, news headlines, news content, Google Trends, Bitcoin-based stock, and finance, are employed based on deep learning to make a more accurate prediction. Such parameters are the input data used to predict the Bitcoin price. Besides, the proposed model analyzes the Valence Aware Dictionary and Sentiment Reasoner sentiments to examine the market's latest news and cryptocurrencies. According to this study's various inputs and analyses, several effective feature selection methods, including mutual information regression, linear regression, correlation-based, and a combination of the feature selection models, are exploited to predict the price of Bitcoin. Finally, a careful comparison is made between the proposed models in terms of some performance criteria like mean square error (MSE), root-mean-square error, mean absolute error, median absolute error, and coefficient of determination (R2). The obtained results indicate that the proposed hybrid model based on sentiments analysis and combined feature selection with MSE value of 0.001 and R2 value of 0.98 provides better estimations with more minor errors regarding Bitcoin price. This proposed model can also be employed as an individual assistant for more informed trading decisions associated with Bitcoin. [ABSTRACT FROM AUTHOR]

Nowadays, the economy of countries highly depends on the agriculture productivity which has a great effect on the development of human civilization. Sometimes, plant diseases cause a major reduction in agricultural products. This paper proposes a new approach for the automatic detection and classification of plant leaf diseases based on using the ELM deep learning algorithm on a real dataset of plant leaf images. The proposed approach uses the k-means clustering algorithm for image segmentation and applies the GLCM for feature extraction. The BDA optimization algorithm is employed for feature selection, and lastly the ELM algorithm is used for plant leaf diseases classification. The presented approach optimizes the input weights and hidden biases for ELM. The dataset used in this study includes 73 plant leaf images, such that we tested our approach on four diseases that usually affect plants, including: Alternaria alternata, Anthracnose, Bacterial blight, and Cercospora leaf spot. The experimental results show that the proposed approach has achieved encouraging results in terms of these classification measures: accuracy, error rate, recall, F score, and AUC which are 94%, 6%, 92%, 95%, and 96% respectively. Babu [ABSTRACT FROM AUTHOR]

The recognition of stomatological disorders and the classification of dental caries are important areas of biomedicine that can hugely benefit from machine learning tools for the construction of relevant mathematical models. This paper explores the possibility of using reflectivity data to distinguish between healthy tissues and caries by deep learning and multilayer convolutional neural networks. The experimental data set includes more than 700 observations recorded in the stomatology laboratory. For rigor, the results obtained from the deep learning systems are compared with those evaluated for selected sets of features estimated for each observation and classified by a decision tree, support vector machine (SVM), k-nearest neighbor, Bayesian methods, and two-layer neural networks. The classification accuracy obtained for the deep learning systems was 98.1% and 94.4% for data in the signal and spectral domains, respectively, in comparison with an accuracy of 97.2% and 87.2% evaluated by the SVM method. The proposed method conclusively demonstrates how the artificial intelligence and deep learning methodology can contribute to improved diagnosis of dental problem in stomatology. [ABSTRACT FROM AUTHOR]

Machine health monitoring systems are vital components of modern manufacturing industries. As advanced sensors collecting machine health-related data become commonplace, such systems have started adopting data-driven approaches to harness the collected data. However, dealing with noisy data and gleaning the spatial and temporal correlation within the data is a challenge. Extant literature focuses on the use of feature extraction to judge the state of normal and worn tools. However, the process of detecting the features of worn tools can often damage the workpiece material and result in machine downtime, which increases costs. Using recent developments in artificial intelligence, data features can be used to gauge the condition of tools in real-time. This paper proposes Holistic–Local Long Short-Term Memory (HLLSTM), a deep learning approach that adopts Long Short-Term Memory to predict tool wear based on holistic and local features. The data is divided into segments to learn short-term data features and further divided into holistic training and local training data to extract more implicit feature information to improve the accuracy of tool wear prediction. Experimental results indicate that HLLSTM can reduce the mean absolute error of real tool wear value two-fold and accurately predict tool wear. [ABSTRACT FROM AUTHOR]

The algorithm is based on the machine vision processing model of R-CNN and integrates a disease discrimination algorithm on the basis of R-CNN. Tang et al. [[16]] analyzes the feature algorithm based on the feature extraction requirements of pituitary tumor pictures and compares a variety of commonly used algorithms to select a classification algorithm suitable for the model of this paper through comparison methods. Web intelligence strives to develop innovative solutions and frameworks that deepen the understanding of computational, logical, cognitive, physical, and social foundations of the future web. [Extracted from the article]

Traffic forecasting using deep learning represents a crucial aspect of intelligent transportation systems, carrying substantial implications for congestion reduction and efficient route planning. Despite its significance, accurately predicting traffic states remains a challenge. Existing methodologies focus on capturing the temporal trends of traffic states and the spatial dependencies between roads to enhance prediction accuracy. However, two noteworthy limitations persist in these approaches: (1) Many models neglect the interaction between spatiotemporal features across varying time spans, hindering their ability to utilize traffic state information effectively for predicting future conditions. (2) Genuine correlations between roads are time-varying, making it inadequate to rely on static graphs or static pre-trained node embeddings to model dynamic correlations between roads. To address these challenges, we propose the Multiple Time-Scale Graph Attention Network (MTS-GATN), which comprises two key modules: the Multiple Time-Scale Spatiotemporal Features Extraction Module and the Feature Augmentation Module. The first module involves stacking multiple spatiotemporal extraction layers to discern traffic state information at different time scales. In the second module, we employ dynamic spatial semantic embedding for feature augmentation, providing nodes with dynamic representations over time. Subsequently, we leverage a multi-head spatiotemporal attention mechanism to comprehensively consider location information and real-time semantic data, facilitating the interaction of traffic state information across multiple time scales. Experimental results on two distinct traffic datasets validate the superior performance of MTS-GATN in medium-term and long-term forecasting scenarios. [ABSTRACT FROM AUTHOR]

Accurate resource utilization estimation is crucial for efficient resource allocation, capacity planning, and cost optimization in cloud systems. In the past, several artificial intelligence, machine learning, and deep learning-based techniques have been evolved to forecast cloud cluster workload. Despite the abundance of available techniques, most existing techniques fail to achieve the desired prediction efficiency and generalization capability. They are computationally inefficient in accurately determining resource utilization at a machine-level granularity. The current research proposes a computationally less-expensive hybrid approach combining cluster analysis and deep neural learning with transfer learning to estimate the machine-level workload. The method implements clustering to identify the similarity patterns among the non-linear usage profiles of machines present in the input dataset. Subsequently, the generalized deep neural learning models are developed considering only a sample dataset belonging to each identified cluster. Lastly, the concept of transfer learning is deployed using pre-trained generalized models to estimate the workload for all remaining machines relating to the clusters. The performance validation of the proposed approach is carried out on the real-world traces dataset of the google cluster. The comparative evaluation of the proposed approach with benchmark approaches verifies the achieved performance benefits and accuracy. [ABSTRACT FROM AUTHOR]

Humans' ability to manage their emotions has a big impact on their ability to plan and make decisions. In order to better understand people and improve human–machine interaction, researchers in affective computing and artificial intelligence are investigating the detection and recognition of emotions. However, different cultures have distinct ways of expressing emotions, and the existing emotion recognition datasets and models may not effectively capture the nuances of the Indian population. To address this gap, this study proposes custom-built lightweight Convolutional Neural Network (CNN) models that are optimized for accuracy and computational efficiency. These models are trained and evaluated on two Indian emotion datasets: The Indian Spontaneous Expression Dataset (ISED) and the Indian Semi Acted Facial Expression Database (iSAFE). The proposed CNN model with manual feature extraction provides remarkable accuracy improvement of 11.14% for ISED and 4.72% for iSAFE datasets as compared to baseline, while reducing the training time. The proposed model also surpasses the accuracy produced by pre-trained ResNet-50 model by 0.27% ISED and by 0.24% for the iSAFE dataset with significant improvement in training time of approximately 320 s for ISED and 60 s for iSAFE dataset. The suggested lightweight CNN model with manual feature extraction offers the advantage of being computationally efficient and more accurate compared to pre-trained model making it a more practical and efficient solution for emotion recognition among Indians. [ABSTRACT FROM AUTHOR]

Due to the complexity of the Wire-arc Additive Manufacturing (WAAM) process, it is prone to the occurrence of defects in the product. One of the most common defects is porosity, which is detrimental to the mechanical and fatigue properties of the product. To guarantee the product quality, it is important to detect its occurrence. In this research, a strategy was developed to detect the occurrence of porosity and to identify its root cause. To develop a porosity detection strategy, a monitoring set-up was designed in which the WAAM process is monitored by a current sensor, condenser microphone, structural Acoustic Emission sensor, spectrometer and flow meter. Seventeen experiment samples were produced and the sensor data were stored using a data acquisition system. A sensor data analysis showed that current and acoustic signals could be correlated with the occurrence of porosity. From these sensor signals, 74 features were extracted. A validation of the samples, based on milling, grinding and image processing, was developed to obtain the pore density values for the corresponding feature set. A long short-term memory neural network was trained through supervised learning to classify feature data into acceptable or non-acceptable pore densities. A test accuracy of 82.52% was achieved. Apart from the porosity detection, a strategy for porosity root cause detection was developed in order to distinguish between process related porosity and contaminant related porosity. An accuracy of 90.67% was achieved, whereby the remaining inaccuracy is interpreted as a physical phenomenon and the results from the model are interpreted actually as more accurate than the prior assumption of the training labels. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the prognostic value of radiomics features based on late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) images in patients with cardiac amyloidosis (CA). Methods: This retrospective study included 120 CA patients undergoing CMR at three institutions. Radiomics features were extracted from global and three different segments (base, mid-ventricular, and apex) of left ventricular (LV) on short-axis LGE images. Primary endpoint was all-cause mortality. The predictive performance of the radiomics features and semi-quantitative and quantitative LGE parameters were compared by ROC. The AUC was used to observe whether Rad-score had an incremental value for clinical stage. The Kaplan–Meier curve was used to further stratify the risk of CA patients. Results: During a median follow-up of 12.9 months, 30% (40/120) patients died. There was no significant difference in the predictive performance of the radiomics model in different LV sections in the validation set (AUCs of the global, basal, middle, and apical radiomics model were 0.75, 0.77, 0.76, and 0.77, respectively; all p > 0.05). The predictive performance of the Rad-score of the base-LV was better than that of the LGE total enhancement mass (AUC:0.77 vs. 0.54, p < 0.001) and LGE extent (AUC: 0.77 vs. 0.53, p = 0.004). Rad-score combined with Mayo stage had better predictive performance than Mayo stage alone (AUC: 0.86 vs. 0.81, p = 0.03). Rad-score (≥ 0.66) contributed to the risk stratification of all-cause mortality in CA. Conclusions: Compared to quantitative LGE parameters, radiomics can better predict all-cause mortality in CA, while the combination of radiomics and Mayo stage could provide higher predictive accuracy. Clinical relevance statement: Radiomics analysis provides incremental value and improved risk stratification for all-cause mortality in patients with cardiac amyloidosis. Key Points: • Radiomics in LV-base was superior to LGE semi-quantitative and quantitative parameters for predicting all-cause mortality in CA. • Rad-score combined with Mayo stage had better predictive performance than Mayo stage alone or radiomics alone. • Rad-score ≥ 0.66 was associated with a significantly increased risk of all-cause mortality in CA patients. [ABSTRACT FROM AUTHOR]

Objectives: To investigate the value of magnetic resonance imaging (MRI) radiomics for distinguishing solitary fibrous tumor (SFT) from schwannoma in the orbit. Materials and methods: A total of 140 patients from two institutions were retrospectively included. All patients from institution 1 were randomized into a training cohort (n = 69) and a validation cohort (n = 35), and patients from institution 2 were used as an external testing cohort (n = 36). One hundred and six features were extracted from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CET1WI). A radiomics model was built for each sequence using least absolute shrinkage and selection operator logistic regression, and radiomics scores were calculated. A combined model was constructed and displayed as a radiomics nomogram. Two radiologists jointly assessed tumor category based on MRI findings. The performances of the radiomics models and visual assessment were compared via area under the curve (AUC). Results: The performances of the radiomics nomogram combining T2WI and CET1WI radiomics scores were superior to those of the pooled readers in the training (AUC 0.986 vs. 0.807, p < 0.001), validation (AUC 0.989 vs. 0.788, p = 0.009), and the testing (AUC 0.903 vs. 0.792, p = 0.093), although significant difference was not found in the testing cohort. Decision curve analysis demonstrated that the radiomics nomogram had better clinical utility than visual assessment. Conclusion: MRI radiomics nomogram can be used for distinguishing between orbital SFT and schwannoma, which may help tumor management by clinicians. Clinical relevance statement: It is of great importance and challenging for distinguishing solitary fibrous tumor from schwannoma in the orbit. In the present study, an MRI-based radiomics nomogram were developed and independently validated, which could help the discrimination of the two entities. Key Points: • It is challenging to differentiate solitary fibrous tumor from schwannoma in the orbit due to similar clinical and image features. • A radiomics nomogram based on T2-weighted imaging and contrast-enhanced T1-weighted imaging has advantages over radiologists. • Radiomics can provide a non-invasive diagnostic tool for differentiating between the two entities. [ABSTRACT FROM AUTHOR]

Yoga pose recognition and correction are artificial intelligent techniques to provide standardized and appropriate yoga poses. Incorrect yoga poses can cause serious injuries and long-term complications. Analyzing human posture can identify and rectify abnormal positions, improving well-being at home. A posture estimator extracts yoga asana attributes from properly represented images. These extracted features are then utilized directly as inputs for various neural networks and machine learning models. These models serve the purpose of evaluating and predicting the accuracy of specific yoga poses. The objective of this research is to explore multiple methods for classifying yoga poses. The LGDeep model is introduced, which combines a novel residual convolutional neural network with three deep learning approaches: Xception, VGGNet, and SqueezeNet. Additionally, the LGDeep model incorporates feature extraction methods such as LDA and GDA. Experimental results demonstrate that the LGDeep classifier outperforms other approaches and achieves the highest classification accuracy ratio.Article highlights: New Four ensemble-based Yoga pose estimation models have been introduced that boost the performance of the individual three DL techniques: Xception, VGGNet, and SqueezeNet. A core new residual convolutional neural network combines the DL techniques to make three models. The core model is integrated with LDA and GDA features together or separately. LGDeep, GDeep, LDeep, and Deep are the proposed novel models that have been examined on a publicly accessible dataset, exceeding earlier state-of-the-art approaches. The LGDeep surpassed other previous approaches designed for the same purpose since the ensembling technique aided in the acquisition of complementary information, allowing individual models to outperform. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorder (ASD) is characterized as a neurodevelopmental disorder with a heterogeneous nature, influenced by genetics and exhibiting diverse clinical presentations. In this study, we dissect Autism Spectrum Disorder (ASD) into its behavioral components, mirroring the diagnostic process used in clinical settings. Morphological features are extracted from magnetic resonance imaging (MRI) scans, found in the publicly available dataset ABIDE II, identifying the most discriminative features that differentiate ASD within various behavioral domains. Then, each subject is categorized as having severe, moderate, or mild ASD, or typical neurodevelopment (TD), based on the behavioral domains of the Social Responsiveness Scale (SRS). Through this study, multiple artificial intelligence (AI) models are utilized for feature selection and classifying each ASD severity and behavioural group. A multivariate feature selection algorithm, investigating four different classifiers with linear and non-linear hypotheses, is applied iteratively while shuffling the training-validation subjects to find the set of cortical regions with statistically significant association with ASD. A set of six classifiers are optimized and trained on the selected set of features using 5-fold cross-validation for the purpose of severity classification for each behavioural group. Our AI-based model achieved an average accuracy of 96%, computed as the mean accuracy across the top-performing AI models for feature selection and severity classification across the different behavioral groups. The proposed AI model has the ability to accurately differentiate between the functionalities of specific brain regions, such as the left and right caudal middle frontal regions. We propose an AI-based model that dissects ASD into behavioral components. For each behavioral component, the AI-based model is capable of identifying the brain regions which are associated with ASD as well as utilizing those regions for diagnosis. The proposed system can increase the speed and accuracy of the diagnostic process and result in improved outcomes for individuals with ASD, highlighting the potential of AI in this area. [ABSTRACT FROM AUTHOR]

Recognizing faces from the video employs artificial intelligence-based computer technology. This includes applications such as law enforcement, biometrics, security, personal safety, etc., for tracking and enabling surveillance in real-time. However, detection and recognition of the face from the video are influenced by the change in variation of pose, brightness, occlusion, expression, and resolutions. While facial images are simple to detect, others may necessitate the use of specialized software. To address those challenges we propose an efficient face detection and recognition system with optimal features. Initially, the keyframes are extracted by the Key Frame Extraction method which utilizes Wavelet Information. Subsequently, the characteristics such as holo-entropy, appearance features, SURF feature, and multi-angle movement feature are extracted. The Oppositional Grass Hopper Optimization Algorithm is used to identify optimal features from this large feature set. The extracted features are classified using the fuzzy classifier that was designed. The proposed method's performance is validated using several benchmark video datasets and its efficiency is measured in terms of keyframe extraction time, sensitivity, accuracy, and specificity by comparing it to other state-of-the-art approaches. The proposed method outperforms previous state-of-the-art methods in terms of recognition accuracy. [ABSTRACT FROM AUTHOR]