Search

With the fast-moving deployment of IoT (Internet of Things) applications, a large amount of data is generated and the data is in need for processing to be able contribute to the user's requirements. All of the IoT applications require low latency and certain bandwidth to provide us with new features which are Time-Dependent. Thus, it would be advantageous to redesign the current IoT architecture by understanding the unique properties of communications and computational power to support intelligent processing of IoT data and its analysis. The paper is focused on topics such as characteristics of IoT data, trends in IoT network architecture, problems in IoT data analysis and their solutions. Thus, in particular, the paper is a discussion that Edge software-defined computing and CEP (Complex Event Processing) based fog computing as a architecture that promises to support the different requirements of IoT data analytics. And also, the paper is a discussion about how machine learning, deep learning are useful in removing data processing anomalies. The leader node election for data processing at cloud is also a time consuming task, the proposed genetic based Genetic based Leader Election Algorithm (GLEA) algorithm in the paper show promising results for the solution. [ABSTRACT FROM AUTHOR]

The development of stereo matching algorithm is still one of the challenging problems, especially in ill-posed regions. Hence, this article presents a survey on the algorithm frameworks related to the stereo matching algorithm. Based on the early survey that had been conducted, two major frameworks available in current stereo matching algorithm development, they are traditional and artificial intelligence (AI) frameworks. Most of the traditional methods are very low accuracy compared to the AI-based approach. This can be observed in the standard benchmarking dataset, such as from the KITTI and the Middlebury, where AI methods rank at the top of the accuracy list. Additionally, the trend for solving computer vision problems uses AI or machine learning tools that become more apparent in recent years. Thus, this paper is focusing on the survey between the deep learning frameworks, which is one of the machine learning tools related to the convolutional neural network (CNN). Several mixed approaches between CNN based method and traditional handcraft method, as well as the end to end CNN method also discussed in this paper. [ABSTRACT FROM AUTHOR]

This comprehensive review focuses on the Autonomous Driving System (ADS), which aims to reduce human errors that are the reason for about 95% of car accidents. The ADS consists of six stages: sensors, perception, localization, assessment, path planning, and control. We explain the main state-of-the-art techniques used in each stage, analyzing 275 papers, with 162 specifically on path planning due to its complexity, NP-hard optimization nature, and pivotal role in ADS. This paper categorizes path planning techniques into three primary groups: traditional (graph-based, sampling-based, gradient-based, optimization-based, interpolation curve algorithms), machine and deep learning, and meta-heuristic optimization, detailing their advantages and drawbacks. Findings show that meta-heuristic optimization methods, representing 23% of our study, are preferred for being general problem solvers capable of handling complex problems. In addition, they have faster convergence and reduced risk of local minima. Machine and deep learning techniques, accounting for 25%, are favored for their learning capabilities and fast responses to known scenarios. The trend towards hybrid algorithms (27%) combines various methods, merging each algorithm's benefits and overcoming the other's drawbacks. Moreover, adaptive parameter tuning is crucial to enhance efficiency, applicability, and balancing the search capability. This review sheds light on the future of path planning in autonomous driving systems, helping to tackle current challenges and unlock the full capabilities of autonomous vehicles. [ABSTRACT FROM AUTHOR]

Intelligent Fault-Tolerant Control (IFTC) refers to the applications of machine learning algorithms for fault diagnosis and design of Fault-Tolerant Control (FTC). The overall goal of the FTC is to accommodate defects in the system components while they are in use and maintain stability with little to no performance reduction. These systems are crucial for mission-critical and safety-related applications where the safety of people is at stake and service continuity is crucial. In this review paper, a systematic study has been done for the development of FTC with machine learning, deep learning, and transfer learning algorithms. The challenges and limitations faced with their possible solutions through machine learning theories for the IFTC model are lined up. This paper guides researchers on the different possible types of machine learning algorithms and their advanced forms like deep learning and transfer learning. The differences among these are highlighted by the challenges and limitations of each. The paper is significant such that most of the important literature references from the Scopus database particularly related to important electrical and mechanical industrial problems have been discussed to guide the researchers who want to apply IFTC for specific industrial problems, being the research gap. Finally, future research directions for the development of IFTC are highlighted. [ABSTRACT FROM AUTHOR]

Intelligent machines are an important carrier of artificial intelligence, which are widely used not only in the industrial field, but also in various fields of daily life and work. Path planning is an important research direction for studying machine intelligence. The main purpose is to search for a feasible path so that the robot can walk along the searched path in a complex environment. This paper aims to study the evolutionary algorithm of intelligent machines based on artificial intelligence. On the basis of introducing the characteristics of artificial potential field algorithm, the concept and characteristics of genetic algorithm, using genetic algorithm as the framework, the artificial potential field algorithm is combined with the crossover of genetic algorithm. In the operator, the optimization performance of the crossover operator is improved. The research results show that the length of the path obtained by the improved algorithm is shorter and better than that of the genetic algorithm of the single-point crossover operator. [ABSTRACT FROM AUTHOR]

This paper presents a Text similarity detection method based on artificial intelligence and natural language processing. The method combines statistical machine learning and deep learning techniques and designs six models from three perspectives: character-level, word-level, and semantic-level. These models include the diff model based on machine learning, cosine similarity model, Jaccard model, TF-IDF model, as well as the SimCSE and SBERT models based on deep learning methods. To fully leverage the characteristics of these models, three scenarios are designed to calculate the similarity scores based on experience and multiple experimental results. The results show that calculating the similarity scores using these three scenarios not only achieves high accuracy but also requires fewer computational resources. As deep learning and natural language processing technologies continue to advance, Text similarity detection methods based on artificial intelligence and natural language processing will continue to be improved and play a more significant role in practice. Future research can explore more models and algorithms to enhance the accuracy and robustness of plagiarism detection. [ABSTRACT FROM AUTHOR]

Deep learning technologies have been rapidly developing recently. They have shown excellent performances in many fields. However, deep learning networks have weak adaptability to small sample sizes.Usually, deep learning networks require tens of thousands of samples to avoid overfitting. In contrast, the kernel method can deal with small sample sizes. In this paper, we use only dozens of samples to train a successful classifier. Deep multiple kernel learning (DMKL) has emerged in recent years. It combines the ideas of deep learning and multiple kernel learning. Unfortunately, the DMKL network with a fixed structure cannot adapt to data of different dimensions and sizes. Therefore, in this paper, we propose a novel depth-width-scaling multiple kernel learning (DWS-MKL) algorithm. It has the ability to adjust the architecture according to the input data. We optimize the estimation of leave-one-out error by using the span bound instead of the dual objective function. Finally, we choose a large number of data sets from the UCI benchmark data sets for classification tasks. We also evaluate DWS-MKL on the MNIST data set. The experimental results show that different frameworks have different performances on the same dataset. Our DWS-MKL algorithm obtains better classification results than the state-of-the-art kernel learning algorithms, as determined by a thorough comparison. The encouraging results demonstrate that our method has the potential to improve generalization performance of the model. [ABSTRACT FROM AUTHOR]

The amount of network traffic generated from the Internet of Things (IoT) devices is massive which leads to Big data. In present scenario, IoT devices has taken a leap ahead in terms of growing technology and insecure network traffic flow. The sensitivity of the data in the IoT network is becoming very high, which concern the security in legal and privacy issues. Traditional Intrusion Detection System (IDS) is used as a primary line security to differentiate between the attack and benign network traffic flow. As the size of the network traffic capture increases, it becomes more important to handle such big data. Similarly, when the number of classes and instances increases, the complexity of the data also increases. In this paper, we propose a big data platform based intrusion detection system which can differentiate between the types of network traffic flow generated from the IoT devices. We compared the performance of deep learning algorithms with machine learning algorithms on Apache Spark platform and found that machine learning algorithms outperform deep learning algorithms with greater accuracy and less training time for the model. We evaluated our research based on real world network traffic dataset BoT-IoT [1] for an improved intrusion detection system in IoT network traffic. [ABSTRACT FROM AUTHOR]

In this paper, a comparative study on the state of charge (SOC) estimation of the lithium-rich manganese-based battery (LRMB) has been conducted by systematically considering the equivalent circuit model (ECM), aging state and algorithms. The results show that the first-order RC model combined with the Extended Kalman filter (EKF) is more suitable for the SOC estimation of the LRMB when the battery decays less severely. The maximum value of root mean square error of SOC estimation error no exceeds 1.6 % under various dynamic operating conditions, which can well meet the practical application. Besides, the first-order model based EKF algorithm occupies least computing resource and simultaneously possesses the best convergence velocity against the initial SOC value deviation. When the LRMB suffers a severe aging, the SOC estimation performance decreases significantly with the max error exceeding 6 %, to overcome this, a new algorithm combined deep learning and Extend Kalman filter (EKF) is proposed, which exhibit high SOC estimation accuracy with the RMSE less than 0.16 %. In summary, a systematic study about the SOC estimation of LRMB has been carried out, which can provide great guidance for the future engineering application of LRMB. • Various Bayesian filtering algorithms and neural networks are systematically compared. • The aging states of LRMB are taken into account. • The different types of ECMs are adopted in the SOC estimation of LRMB. [ABSTRACT FROM AUTHOR]

The removal of shadows from images is a classic problem in computer vision, aiming to restore the lighting in shadowed areas, thereby reducing the information interference and loss caused by the presence of shadows. In recent years, numerous excellent shadow removal algorithms have emerged, particularly with the rapid development of deep learning technology, which has disrupted traditional physics-based approaches and significantly improved the effectiveness of shadow removal. In this paper, we conduct a comprehensive survey of shadow removal methods published from 2017 to the present. We first introduce background knowledge about image shadow removal, providing detailed explanations of both physics-based and learning-based shadow removal methods. We analyze and compare these algorithms from both quantitative and qualitative perspectives, reassessing all models that provided open-source result sets according to uniform criteria. Additionally, we introduce commonly used datasets and evaluation metrics in the field. Finally, we discuss applications of shadow removal in specific scenarios, along with research challenges and opportunities in this domain. • Surveys taxonomy of recently image shadow removal techniques, datasets and performance metrics. • Systematic quantitative evaluations are summarized. • The impacts, applications and importance of shadow removal are explored. • Challenges and future direction are explored and analyzed. [ABSTRACT FROM AUTHOR]

Detecting anomalies in telemetry data captured on-board a spacecraft is critical to ensure its safe operation. Although there exist various techniques for automatically detecting point, contextual, and collective anomalies from time-series data, quantifying their performance remains under-researched. In this paper, we thoroughly validate our approach for the task of anomalous event detection that is built upon a two-stage technique, in which the telemetry signal is predicted using a long short-term memory network based on the historical data, and then the prediction is compared with the actual (captured) data. If the difference between those two is sufficiently large, we can infer that an anomalous event has happened. To evaluate the capabilities of such detection techniques over the simulated and benchmark time-series data, we investigate a set of commonly used metrics obtained for a range of anomaly detection approaches, and present their shortcomings, especially related to their inability of capturing the temporal aspects of the detectors. We tackle this issue by introducing new quality metrics which enable us to objectively verify if the detectors can timely spot the anomalies in sequential data. The experimental study showed that inferring the conclusions based on a subset of metrics can lead to biased observations, as the best algorithms determined based on the overlap metrics, including the Dice coefficient, do not necessarily correspond to the algorithms that offer the fastest detection. Finally, we discuss the Antelope Toolbox—our software tool for simulating nominal telemetry data of given characteristics, alongside well-defined anomalous events, and to perform the quantitative and qualitative analysis of anomaly detection algorithms over such simulated events. • We investigate the quality metrics to verify anomaly detection in telemetry data. • We introduce new measures that capture temporal aspects of anomaly detectors. • We present an end-to-end machine learning pipeline for anomaly detection. • We objectively assess 15 anomaly detection algorithms using all metrics. • Exploiting only a subset of all metrics can easily lead to biased conclusions. [ABSTRACT FROM AUTHOR]

Large neural networks usually perform well for executing machine learning tasks. However, models that achieve state-of-the-art performance involve arbitrarily large number of parameters and therefore their training is very expensive. It is thus desired to implement methods with small per-iteration costs, fast convergence rates, and reduced tuning. This paper proposes a multivariate adaptive gradient descent method that meets the above attributes. The proposed method updates every element of the model parameters separately in a computationally efficient manner using an adaptive vector-form learning rate, resulting in low per-iteration cost. The adaptive learning rate computes the absolute difference of current and previous model parameters over the difference in subgradients of current and previous state estimates. In the deterministic setting, we show that the cost function value converges at a linear rate for smooth and strongly convex cost functions. Whereas in both the deterministic and stochastic setting, we show that the gradient converges in expectation at the order of O (1 / k) for a non-convex cost function with Lipschitz continuous gradient. In addition, we show that after T iterates, the cost function of the last iterate scales as O (log (T) / T) for non-smooth strongly convex cost functions. Effectiveness of the proposed method is validated on convex functions, smooth non-convex function, non-smooth convex function, and four image classification data sets, whilst showing that its execution requires hardly any tuning unlike existing popular optimizers that entail relatively large tuning efforts. Our empirical results show that our proposed algorithm provides the best overall performance when comparing it to tuned state-of-the-art optimizers. [ABSTRACT FROM AUTHOR]

• Basic factors affecting deep learning models for streamflow forecasting. • Hybrid deep learning models for streamflow forecasting. • Input and hyperparameter optimization of deep learning models. • Limitation and prospects in streamflow forecasting. Deep learning has emerged as a powerful tool for streamflow forecasting and its applications have garnered significant interest in the hydrological community. Despite the publication of several review articles on machine learning applications in streamflow forecasting, no review paper has yet focused explicitly on deep learning and its hybrid forms. This paper starts with some characteristics of deep learning models to provide a quick view of deep learning. Next, the configurations and characteristics of hybrid deep learning models, which is a hybridization of modeling techniques with deep learning, are discussed. Another vital role while implementing deep learning modeling is the methods applied for input and hyperparameter optimization. Finally, the limitations encountered in streamflow forecasting using deep learning models and recommendations for further research are outlined. This review covers related studies from 2017 to 2023 to provide the most recent snapshot of deep learning modeling applications in streamflow forecasting. These efforts are expected to contribute to the advancement of streamflow forecasting, potentially enabling more informed decision-making in water resource management. [ABSTRACT FROM AUTHOR]

The primary purpose of this paper is to realize robust place recognition algorithms towards simultaneous viewpoint and condition changes, and provide satisfactory computational efficiency. In this paper, we significantly improve the viewpoint invariance of the SeqSLAM algorithm by using state-of-the-art deep learning techniques to generate robust feature representations of images and develop the SeqCNNSLAM . Experimental results show that SeqCNNSLAM outperforms state-of-the-art place recognition systems in most cases, such as, when precision is maintained at 100%, the maximum recall obtained by SeqCNNSLAM is 50% higher than SeqSLAM on the Norland dataset with simultaneous condition change and 12.5% viewpoint change. Besides, we develop an acceleration method called A-SeqCNNSLAM , which exploits the location relationship between the matching images of adjacent images to reduce the matching range of the current image. Experimental results demonstrate that an acceleration of  ∼  5 times is achieved with minimal accuracy degradation of  ∼  5%. Finally, to enable A-SeqCNNSLAM adaptability in new environments, O-SeqCNNSLAM is devised for the online parameter adjustment in A-SeqCNNSLAM. [ABSTRACT FROM AUTHOR]

This paper introduces a deep learning method for image classification that leverages knowledge formalized as a graph created from information represented by pairs attribute/value. The proposed method investigates a loss function that adaptively combines the classical cross-entropy commonly used in deep learning with a novel penalty function. The novel loss function is derived from the representation of nodes after embedding the knowledge graph and incorporates the proximity between class and image nodes. Its formulation enables the model to focus on identifying the boundary between the most challenging classes to distinguish. Experimental results on several image databases demonstrate improved performance compared to state-of-the-art methods, including classical deep learning algorithms and recent algorithms that incorporate knowledge represented by a graph. [ABSTRACT FROM AUTHOR]

Recently, the Extreme Learning Machine (ELM) algorithm has been applied to various fields due to its rapidity and significant generalization performance. Traditionally, deep learning (DL) and wavelet neural networks (WNN) methods reach a high classification accuracy in machine learning applications. As a result, a new structure based on WNN, deep architecture and ELM is proposed in this paper. The proposed method is based on Extreme Learning Machine Auto-Encoder with DL structure and a composite wavelet activation function used in the hidden nodes. To evaluate the performance of our approach, we used standard benchmark data-sets, namely COIL-20, Pima Indian Diabetes (PID), MNIST and EMNIST. Experimental results show that our method offers satisfactory results and performance compared to other approaches. [ABSTRACT FROM AUTHOR]

Hybrid quantum machine learning (QML) algorithms have potentials for current quantum computing technologies since only part of the model is computed by a quantum device. This paper proposes a novel hybrid quantum-classical deep learning model for cybersecurity application: domain generation algorithms (DGA)-based botnet detection. We analyzed our hybrid model's performance compared with the classical model counterpart to investigate the quantum circuit's effectivity as a layer in a deep learning model. We used four features of the Botnet DGA dataset: MinREBotnets, CharLength, TreeNewFeature, and nGramReputation_Alexa. The hybrid model's quantum circuit is a combination of Pennylane's embedding (Angle Embedding and IQP Embedding) and layers circuit (Basic Entangler Layers, Random Layers, and Strongly Entangling Layers). Also, we implemented noise models for assessing the applicability of the model for current Noisy Intermediate Scale Quantum (NISQ) technology. We found that in some cases, the hybrid model reached high performance (maximum accuracy up to 94,7% using n= 100; 93,9% using n= 1,000). We discovered that the combination of Angle Embedding and Strongly Entangled delivers high accuracy, superior to the classical deep learning model in n= 100 experiments). However, the overall performance is still inferior for the rest cases compared to the classical deep learning model counterpart. [ABSTRACT FROM AUTHOR]

An approach is presented that generalize OCR task including polish letters using deep learning technique. The paper extends EMNIST dataset so that two new classes of polish diacritics "Ą" and "Ć" are attached. Using this new dataset and deep learning technique one can analyze sensitives of standard as well as presented extended approach with different parameters of convolutional neural network. The analysis of the results shows that the shadows and noises that Polish characters, leave with their hooks leads, can be properly recognized and two similar letters "A" and "Ą" can be distinguished by convolutional neural network. On the other hand a neural network trained on dataset without Polish characters do not treat letters "Ą" and "Ć" properly. [ABSTRACT FROM AUTHOR]

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the Q -values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstable behaviour while improving agent's training performance. However, agents are often highly sensitive to the selection of the multi-step update horizon (n), and our empirical experiments show that a poorly chosen static value for n can in many cases lead to worse performance than single-step DQN. Inspired by the success of n -step DQN and the effects that multi-step updates have on overestimation bias, this paper proposes a new algorithm that we call 'Elastic Step DQN' (ES-DQN) to alleviate overestimation bias in DQNs. ES-DQN dynamically varies the step size horizon in multi-step updates based on the similarity between states visited. Our empirical evaluation shows that ES-DQN out-performs n -step with fixed n updates, Double DQN and Average DQN in several OpenAI Gym environments while at the same time alleviating the overestimation bias. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Medical Imaging & Radiation Sciences is the property of Elsevier B.V. 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.)

Deep learning is a branch of neural network which has been intensively developed in the last decade. Due to the high-accuracy classification ability, the deep learning algorithms have been widely used in many fields, such as speech recognition, image recognition, and natural speech processing. However, they also show some shortcomings especially on the selection of some parameters in the network, including hyper-parameters, which is still treated as a time consuming task. In this paper, a modified ABC (ABC-ISB) optimization algorithm is proposed to automatically train the parameters of Feed-Forward Artificial Neural Networks, which is a typical a neural network. In the proposed ABC algorithm, we utilize the information of neighbors with better performance to accelerate the convergence of employed and onlooker bees respectively. In addition, a new selection strategy and a gbest-guided strategy are introduced to enhance the global search capability and balance the exploration and exploitation of the algorithm separately. The experimental results show our ABC-ISB is generally leading and competitive. [ABSTRACT FROM AUTHOR]

Background: The application of artificial intelligence to interpret the electrocardiogram (ECG) has predominantly included the use of knowledge engineered rule-based algorithms which have become widely used today in clinical practice. However, over recent decades, there has been a steady increase in the number of research studies that are using machine learning (ML) to read or interrogate ECG data.Objective: The aim of this study is to review the use of ML with ECG data using a time series approach.Methods: Papers that address the subject of ML and the ECG were identified by systematically searching databases that archive papers from January 1995 to October 2019. Time series analysis was used to study the changing popularity of the different types of ML algorithms that have been used with ECG data over the past two decades. Finally, a meta-analysis of how various ML techniques performed for various diagnostic classifications was also undertaken.Results: A total of 757 papers was identified. Based on results, the use of ML with ECG data started to increase sharply (p < 0.001) from 2012. Healthcare applications, especially in heart abnormality classification, were the most common application of ML when using ECG data (p < 0.001). However, many new emerging applications include using ML and the ECG for biometrics and driver drowsiness. The support vector machine was the technique of choice for a decade. However, since 2018, deep learning has been trending upwards and is likely to be the leading technique in the coming few years. Despite the accuracy paradox, accuracy was the most frequently used metric in the studies reviewed, followed by sensitivity, specificity, F1 score and then AUC.Conclusion: Applying ML using ECG data has shown promise. Data scientists and physicians should collaborate to ensure that clinical knowledge is being applied appropriately and is informing the design of ML algorithms. Data scientists also need to consider knowledge guided feature engineering and the explicability of the ML algorithm as well as being transparent in the algorithm's performance to appropriately calibrate human-AI trust. Future work is required to enhance ML performance in ECG classification. [ABSTRACT FROM AUTHOR]

We explored the problem about function approximation error and complex mission adaptability in multi-agent deep reinforcement learning. This paper proposes a new multi-agent deep reinforcement learning algorithm framework named multi-agent time delayed deep deterministic policy gradient. Our work reduces the overestimation error of neural network approximation and variance of estimation result using dual-centered critic, group target network smoothing and delayed policy updating. According to experiment results, it improves the ability to adapt complex missions eventually. Then, we discuss that there is an inevitable overestimation issue about existing multi-agent algorithms about approximating real action-value equations with neural network. We also explain the approximate error of equations in the multi-agent deep deterministic policy gradient algorithm mathematically and experimentally. Finally, the application of our algorithm in the mixed cooperative competition experimental environment further demonstrates the effectiveness and generalization of our algorithm, especially improving the group's ability of adapting complex missions and completing more difficult missions. [ABSTRACT FROM AUTHOR]

This paper proposes a novel domain adaptation algorithm to handle the challenges posed by the satellite and aerial imagery, and demonstrates its effectiveness on the built-up region segmentation problem. Built-up area estimation is an important component in understanding the human impact on the environment, effect of public policy and in general urban population analysis. The diverse nature of aerial and satellite imagery (capturing different geographical locations, terrains and weather conditions) and lack of labeled data covering this diversity makes machine learning algorithms difficult to generalize for such tasks, especially across multiple domains. Re-training for new domain is both computationally and labor expansive mainly due to the cost of collecting pixel level labels required for the segmentation task. Domain adaptation algorithms have been proposed to enable algorithms trained on images of one domain (source) to work on images from other dataset (target). Unsupervised domain adaptation is a popular choice since it allows the trained model to adapt without requiring any ground-truth information of the target domain. On the other hand, due to the lack of strong spatial context and structure, in comparison to the ground imagery, application of existing unsupervised domain adaptation methods results in the sub-optimal adaptation. We thoroughly study limitations of existing domain adaptation methods and propose a weakly-supervised adaptation strategy where we assume image level labels are available for the target domain. More specifically, we design a built-up area segmentation network (as encoder-decoder), with image classification head added to guide the adaptation. The devised system is able to address the problem of visual differences in multiple satellite and aerial imagery datasets, ranging from high resolution (HR) to very high resolution (VHR), by investigating the latent space as well as the structured output space. A realistic and challenging HR dataset is created by hand-tagging the 73.4 sq-km of Rwanda, capturing a variety of build-up structures over different terrain. The developed dataset is spatially rich compared to existing datasets and covers diverse built-up scenarios including built-up areas in forests and deserts, mud houses, tin and colored rooftops. Extensive experiments are performed by adapting from the single-source domain datasets, such as Massachusetts Buildings Dataset, to segment out the target domain. We achieve high gains ranging 11.6–52% in IoU over the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

One-shot learning has recently attracted growing attention to produce models which can classify significant events from a few or even no labeled examples. In this paper, we introduce a deep Q-network strategy into one-shot learning (OL-DQN) to design a more intelligent learner to infer whether to label a sample automatically or request the true label for the active-learning set-up. Then we conducted experiments in the ALOI dataset for the classification of objects recorded under various imaging circumstances and a dataset for handwriting recognition composed of both characters and digits to have a performance evaluation and application analysis of the proposed model respectively, and the obtained results demonstrate that our model can achieve a better trade-off between prediction accuracy and the need of label requests compared with a purely supervised task, a prior work AOL, and a conventional active learning algorithm QBC. [ABSTRACT FROM AUTHOR]

Computer-generated holography (CGH) is a technique that aims to produce specific illumination patterns using coherent light. However, traditional CGH algorithms often struggle to balance computational speed with the accuracy of the generated hologram. To address this issue, a non-iterative algorithm named "DL-GSA" is proposed in this paper. DL-GSA combines unsupervised learning in machine learning with convolutional neural networks (CNN) to generate holograms with high accuracy and fixed computational complexity. Simulation experiments reveal that DL-GSA generates hologram patterns faster than the Modified Gerchberg-Saxton algorithm (MGSA) and double-phase retrieval algorithm (DPRA). Furthermore, the average accuracy of the generated holograms is higher than 95 %. These findings suggest that DL-GSA has the potential to significantly enhance the real-time hologram generation capabilities, making it a promising technique for future applications. [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]

Highlights • Optimization is an important issue in machine learning because many machine learning models are reformulated as optimization problems. Different kinds of machine learning algorithms mainly focus on minimizing their emiprical loss like deep learning, logisitic regression, and support vector machine. Because data is explosively growing, it is challenging to deal with a large-scale optimization problem. We propose a fast and most condition number free algorithm for train machine learning algorithms. This algorithm has several advantages. • Contrast to previous work which approximates Hessian matrix by sketched or subsampled Hessian directly, we use the sketched or subsampled Hessian matrix as preconditioner and get the direction vector by preconditioned conjugate gradient method. Accordingly, we propose a novel stochastic second-order algorithm called Preconditioned Newton Conjugate Gradient with Sketched Hessian (PNCG). This strategy makes our algorithm almost independent on the condition number. • We numerically demonstrate the effectiveness and robustness of our algorithms in widely used machine learning algorithm Ridge Logistic Regression on several real datasets with different condition number. Our algorithms show good performance compared with existing second order methods in all cases, especially when condition number is large. Abstract Optimization is an important issue in machine learning because many machine learning models are reformulated as optimization problems. Different kinds of machine learning algorithms mainly focus on minimizing their empirical loss like deep learning, logistic regression, and support vector machine. Because data is explosively growing, it is challenging to deal with a large-scale optimization problem. Recently, stochastic second-order methods have emerged to attract much attention due to their efficiency in each iteration. These methods show good performance on training machine learning algorithms like logistic regression and support vector machine. However, the computational complexity of existing stochastic second-order methods heavily depends on the condition number of the Hessian. In this paper, we propose a new Newton-like method called Preconditioned Newton Conjugate Gradient with Sketched Hessian (PNCG). The runtime complexity of PNCG is at most logarithmic in the condition number of the Hessian. PNCG exhibits advantages over existing subsampled Newton methods especially when the Hessian matrix in question is ill-conditioned. We also show that our method has good performance on training machine learning algorithm empirically. The results show consistent improvements in computational efficiency. [ABSTRACT FROM AUTHOR]

Highlights • A deep learning method for steel seismic fuse damage inspection is investigated. • Micromechanical fracture index is defined to quantify the fuse damage condition. • A saliency-based method is adopted for damage feature pattern visualization. • The effectiveness of the proposed method is demonstrated in two case studies. Abstract This paper presents a deep learning based structural steel damage condition assessment method that uses images for post-hazard inspection of ultra-low cycle fatigue induced damage in structural steel fuse members. The deep learning model – Convolutional Neural Network (CNN) model, can be trained to represent the high dimensional features in huge amount of raw data which traditional mathematical models are unable to describe. A saliency-based visualization method is employed to visualize the feature-related pattern recognized by the deep learning model. To quantify the damage condition of the inspected structure fuse members, a micromechanical fracture index is defined as the damage index and used for labeling the images in the training data set. To provide large training dataset, cumulative plastic strain contour plot images generated through finite element (FE) simulation are adopted for the training data. Parametric studies were performed to validate and optimize the deep learning based damage condition assessment method. The method and findings are further examined using real experimental images collected from cyclic testing of a steel notched plate specimen. The results suggest that the proposed method provides a promising automation tool for rapid inspection of structural steel fuse member damage condition. [ABSTRACT FROM AUTHOR]

Many of the existing machine learning algorithms, both supervised and unsupervised, depend on the quality of the input characteristics to generate a good model. The amount of these variables is also important, since performance tends to decline as the input dimensionality increases, hence the interest in using feature fusion techniques, able to produce feature sets that are more compact and higher level. A plethora of procedures to fuse original variables for producing new ones has been developed in the past decades. The most basic ones use linear combinations of the original variables, such as PCA ( Principal Component Analysis ) and LDA ( Linear Discriminant Analysis ), while others find manifold embeddings of lower dimensionality based on non-linear combinations, such as Isomap or LLE ( Linear Locally Embedding ) techniques. More recently, autoencoders (AEs) have emerged as an alternative to manifold learning for conducting nonlinear feature fusion. Dozens of AE models have been proposed lately, each with its own specific traits. Although many of them can be used to generate reduced feature sets through the fusion of the original ones, there also AEs designed with other applications in mind. The goal of this paper is to provide the reader with a broad view of what an AE is, how they are used for feature fusion, a taxonomy gathering a broad range of models, and how they relate to other classical techniques. In addition, a set of didactic guidelines on how to choose the proper AE for a given task is supplied, together with a discussion of the software tools available. Finally, two case studies illustrate the usage of AEs with datasets of handwritten digits and breast cancer. [ABSTRACT FROM AUTHOR]

• This paper proposes an unsupervised deep learning model. • This paper proposes an optimized sparse representation method. • This paper proposes a new image fusion algorithm based on unsupervised deep learning-optimized sparse representation. The image fusion method based on deep learning has problems such as the supervised learning of the model, the edge and noise of the fused image, and the setting of the image fusion weight map. To solve these problems, this paper proposes an end-to-end unsupervised deep learning model that performs one-to-many focus image fusion. It solves the training problem encountered by supervised deep learning models while avoiding the unreasonable image fusion weight maps. In addition, this paper proposes an optimized sparse representation method that divides an image into a target area and a background area. Then, it uses super complete dictionary learning to obtain a sparse representation of the image background area. This approach makes the proposed unsupervised deep learning image fusion method robust to noise. Finally, using this method to carry out image fusion experiments, the results show that the quality evaluation indicators of the fused image obtained by this method substantially outperform those of both mainstream machine learning and deep learning image fusion methods. [ABSTRACT FROM AUTHOR]

• Convolutional Neural Networks can be improved in terms of the classification performance and robustness by using variable weight structures. • Analysis of different data processing methods, models' robustness and statistical properties. • Comparative analysis of variable weight convolutional neural networks and other widely used machine learning techniques. • Medical applications to the classification of seizure phases and types. Deep learning techniques have recently achieved impressive results and raised expectations in the domains of medical diagnosis and physiological signal processing. The widely adopted methods include convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the existing models possess static connection weights between layers, which might limit the generalization capability and the classification performance of the models as the weights of different layers are fixed after training. Furthermore, to deal with a large amount of data, a neural network with a sufficiently large size is required. This paper proposes the variable weight convolutional neural networks (VWCNNs), which are a type of network structure employing dynamic weights instead of static weights in their convolutional layers and fully-connected layers. VWCNNs are able to adapt to different characteristics of input data and can be viewed as an infinite number of traditional, fixed-weight CNNs. We will show that the proposed VWCNN structure outperforms the conventional CNN in terms of the classification accuracy, generalization capability, and robustness when the inputs are contaminated by noise. In this paper, VWCNNs are applied to the classification of three seizure phases (seizure-free, pre-seizure and seizure) based on measured electroencephalography (EEG) data. VWCNNs achieve 100% test accuracy and show strong robustness in the classification of the three seizure phases, and thus show the potential to be a useful classification tool for medical diagnosis. Furthermore, the classification of seven types of seizures is investigated in this paper using the world's largest open source database of seizure recordings, TUH EEG seizure corpus. Comparisons with conventional CNNs, RNN, MobileNet, ResNet, DenseNet and traditional machine learning methods including random forest, decision tree, support vector machine, K-nearest neighbours, standard neural networks, and Naïve Bayes are being conducted using realistic test data sets. The results demonstrate that VWCNNs have advantages over other classifiers in terms of classification accuracy and robustness. [ABSTRACT FROM AUTHOR]

Deep Reinforcement Learning systems are now a hot topic in Machine Learning for their effectiveness in many complex tasks, but their application in safety-critical domains (e.g., robot control or self-autonomous driving) remains dangerous without mechanism to detect and prevent risk situations. In Deep RL, such risk is mostly in the form of adversarial attacks, which introduce small perturbations to sensor inputs with the aim of changing the network-based decisions and thus cause catastrophic situations. In the light of these dangers, a promising line of research is that of providing these Deep RL algorithms with suitable defenses, especially when deploying in real environments. This paper suggests that this line of research could be greatly improved by the concepts from the existing research field of Safe Reinforcement Learning, which has been postulated as a family of RL algorithms capable of providing defenses against many forms of risks. However, the connections between Safe RL and the design of defenses against adversarial attacks in Deep RL remain largely unexplored. This paper seeks to explore precisely some of these connections. In particular, this paper proposes to reuse some of the concepts from existing Safe RL algorithms to create a novel and effective instance-based defense for the deployment stage of Deep RL policies. The proposed algorithm uses a risk function based on how far a state is from the state space known by the agent, that allows identifying and preventing adversarial situations. The success of the proposed defense has been evaluated in 4 Atari games. [ABSTRACT FROM AUTHOR]

High Efficiency Video Coding (HEVC) surpasses its predecessors in encoding efficiency by introducing new coding tools at the cost of an increased encoding time-complexity. The Coding Tree Unit (CTU) is the main building block used in HEVC. In the HEVC standard, frames are divided into CTUs with the predetermined size of up to 64 × 64 pixels. Each CTU is then divided recursively into a number of equally sized square areas, known as Coding Units (CUs). Although this diversity of frame partitioning increases encoding efficiency, it also causes an increase in the time complexity due to the increased number of ways to find the optimal partitioning. To address this complexity, numerous algorithms have been proposed to eliminate unnecessary searches during partitioning CTUs by exploiting the correlation in the video. In this paper, existing CTU depth decision algorithms for HEVC are surveyed. These algorithms are categorized into two groups, namely statistics and machine learning approaches. Statistics approaches are further subdivided into neighboring and inherent approaches. Neighboring approaches exploit the similarity between adjacent CTUs to limit the depth range of the current CTU, while inherent approaches use only the available information within the current CTU. Machine learning approaches try to extract and exploit similarities implicitly. Traditional methods like support vector machines or random forests use manually selected features, while recently proposed deep learning methods extract features during training. Finally, this paper discusses extending these methods to more recent video coding formats such as Versatile Video Coding (VVC) and AOMedia Video 1 (AV1). [ABSTRACT FROM AUTHOR]

In this paper we propose and discuss different Deep Learning-based ensemble algorithms for a problem of low-visibility events prediction due to fog. Specifically, seven different Deep Learning (DL) architectures have been considered, from which multiple individual learners are generated. Hyperparameters of the models, including parameters concerning data preprocessing, models architecture and training procedure, are randomly selected for each model within a pre-defined discrete range. Also, every model is trained with slightly different data sampled randomly, assuring that every models introduce variety in the ensemble. Then, three different information fusion techniques are employed to build the ensemble models. The influence of the filtering process and the elitism level (the percentage of the individual models entering the ensemble) is also assessed. The performance of the proposed methodology have been tested in two real problems of low-visibility events prediction due to orographical and radiation fog, at the north of Spain. Comparison with different Machine Learning, alternative DL algorithms and meteorological-based methods show the good performance of the proposed deep learning ensembles in this problem. [ABSTRACT FROM AUTHOR]

The colored paintings on the surfaces of ancient Chinese buildings have suffered from the wind and the sun and produced many defects such as paint loss, blurring, and color distortion. Previous methods have not been able to virtually repair them well. Therefore, this paper proposed a virtual restoration method for the weathered beams in the Forbidden City using multiple deep learning algorithms. Instead of using only one technology to restore paintings, this paper divided the painting into 3 parts, i.e., the background, the golden edges, and the dragon patterns, and restored them in different technology. For the background, this paper transformed the problem of unrecognizable color restoration into a semantic segmentation problem using U-Net MobileNet. For the golden edges, this paper used traditional image processing technology to obtain them from the color maps generated by the semantic segmentation algorithm. For the dragon patterns, after sketching the skeletons according to the dragon patterns, the image translation algorithm Pix2pix was applied to generate a realistic dragon pattern. Finally, the three repair results are superimposed to complete the repair. The virtually restored paintings can provide reference and guidance for traditional manual restoration and help the restorers to imagine what they looked like before oxidation, thus alleviating some repetitive work and reducing the complexity of restoration. Besides, each step of the method could form a layer, so that the restorers could overlay or modify them as they wish. [ABSTRACT FROM AUTHOR]

Abstract The emergence of machine learning algorithms enhanced the effectiveness of satellite image applications. On account of the high variability in-born in satellite data, a large portion of the present classification proposals are not sensible for handling satellite datasets. In this paper, we assessed profound learning systems in view of Convolutional Neural Networks for the precise order of multispectral remote sensing information. The Normalized Difference Vegetation Index (NDVI) is a solitary parameter for detecting landcover by utilizing the red and near-infrared band (NIR) information of the electromagnetic spectrum. NDVI is used to break down remote detecting images and survey the presence or absence of live green vegetation. The experiment is conducted on new publicaly available SAT-4 dataset, where the classes involved are types of vegetation. As NDVI computation require just two band data, it takes the benefit of both RED and NIR band information to classify diverse land covers. In the present work, the AlexNet architecture with two band information along with the reduced number of filters were trained and high-level features obtained from tested model managed to classify different land cover classes in the dataset. The proposed architecture is compared against the benchmark and results are estimated in terms of accuracy, precision and total number of trainable parameters. The proposed design brings about the aggregate diminishment of trainable parameters, while retaining high accuracy and precision, when compared against the existing architecture, which utilizes four bands. [ABSTRACT FROM AUTHOR]

Abstract Different semantic interpretation tasks such as text entailment and question answering require the classification of semantic relations between terms or entities within text. However, in most cases, it is not possible to assign a direct semantic relation between entities/terms. This paper proposes an approach for composite semantic relation classification using one or more relations between entities/term mentions, extending the traditional semantic relation classification task. The proposed model is different from existing approaches which typically use machine learning models built over lexical and distributional word vector features in that is uses a combination of a large commonsense knowledge base of binary relations, a distributional navigational algorithm and sequence classification to provide a solution for the composite semantic relation classification problem. The proposed approach outperformed existing baselines with regard to F1-score, Accuracy, Precision and Recall. [ABSTRACT FROM AUTHOR]

There are two categories of partial shape matching problem: whole-to-part matching and part-to-part matching. The first establishes the best match between an open curve and a part of a closed curve, while the second is to find a part of the first input closed curve that can be well aligned with a part of the second input closed curve. In this paper, we present a novel approach to solve these two categories of the partial shape matching problem. First, we propose a novel shape descriptor, triangular centroid distances (TCDs), for shape representation; the TCDs shape descriptor is invariant to translation, rotation, scaling, and considerable shape deformations. Then, using the TCDs shape descriptor, we present a method to deal with the whole-to-part partial shape matching problem. Finally, we extend our work to part-to-part partial shape matching. Here, we propose a new approach, again using the TCDs shape descriptor, to solve the part-to-part partial shape matching problem. Experimental results demonstrate that our method outperforms existing methods in 2D nonrigid partial shape matching. [ABSTRACT FROM AUTHOR]

Word embeddings and CNN (convolutional neural networks) architecture are crucial ingredients of sentiment analysis. However, sentiment and lexicon embeddings are rarely used and CNN is incompetent to capture global features of sentence. To this end, semantic embeddings, sentiment embeddings and lexicon embeddings are applied for texts encoding, and three different attentions including attention vector, LSTM (long short term memory) attention and attentive pooling are integrated with CNN model in this paper. Additionally, a word and its context are explored to disambiguate the meaning of the word for rich input representation. To improve the performance of three different attention CNN models, CCR (cross-modality consistent regression) and transfer learning are presented. It is worth noticing that CCR and transfer learning are used in textual sentiment analysis for the first time. Finally, some experiments on two different datasets demonstrate that the proposed attention CNN models achieve the best or the next-best results against the existing state-of-the-art models. [ABSTRACT FROM AUTHOR]

This paper proposes a novel echo state network (ESN) architecture in a deep learning framework for time series prediction. The architecture is a uniform and consistent system with functional parts of the pre-training input network that effectively captures information with different degrees of abstraction in the observed data, and the minimum complexity ESN that possesses the powerful nonlinear approximation capability and highly efficient training. To our best knowledge, this is the first systematic model attempting to introduce the deep learning methodology to the ESN modeling, which provides a more robust alternative to the conventional shallow ESNs. Extensive experiments on various widely used benchmarks of different origins and features show that our model achieves a great enhancement in the prediction accuracy and short-term memory capacity, without significant tradeoff in the model’s computational efficiency. [ABSTRACT FROM AUTHOR]

In massive multiple-input multiple-output (MIMO), it is much challenging to obtain accurate channel state information (CSI) after radio frequency (RF) chain reduction due to the high dimensions. With the fast development of machine learning(ML), it is widely acknowledged that ML is an effective method to deal with channel models which are typically unknown and hard to approximate. In this paper, we use the low complexity vector approximate messaging passing (VAMP) algorithm for channel estimation, combined with a deep learning framework for soft threshold shrinkage function training. Furthermore, in order to improve the estimation accuracy of the algorithm for massive MIMO channels, an optimized threshold function is proposed. This function is based on Gaussian mixture (GM) distribution modeling, and the expectation maximum Algorithm (EM Algorithm) is used to recover the channel information in beamspace. This contraction function and deep neural network are improved on the vector approximate messaging algorithm to form a high-precision channel estimation algorithm. Simulation results validate the effectiveness of the proposed network. [ABSTRACT FROM AUTHOR]

The Successor Feature framework for Reinforcement Learning algorithms improves task transfer by decomposing the learned state–action value function. The decomposition involves two components, one that captures future-expected state features and the other that models the task-related reward structure. However, successful transfer between tasks depends heavily on how the reward function changes, possibly leading to failure of the original Successor Feature formulation. This paper proposes the Dynamic Successor Feature framework, DynSF, by extending the mathematical formulation of the original Successor Feature framework to center around a learned state-transition model. Under this formulation, the state-transition model dynamically induces the acting policy. The flexibility of DynSF also extends to the architecture, requiring only a state-transition model and a small vector of parameters. This architecture provides immense flexibility in the choice of the model used to learn the state-transition model. The DynSF framework is evaluated and compared to other baseline algorithms through several experiments in a continuous grid world environment, a robotic Reacher, and pixels in the Doom environment. • DynSF enables a state-transition model to be used in Reinforcement Learning. • Policy and discount factors can be parameterized dynamically. • Different supervised ML algorithms can be used to learn the state transition model. • DynSF can be used for guided exploration and transfer learning. • DynSF performs better during task transfer than the Successor Feature framework. [ABSTRACT FROM AUTHOR]

• We proposed a deep learning model for electrocardiogram signals delineation. • An end-to-end model using CNN and LSTM were designed to extract high level features. • The model was trained and validated on two different publicly available databases. • DENS-ECG model shows a high performance in electrocardiogram signals delineation. With the technological advancements in the field of tele-health monitoring, it is now possible to gather huge amount of electro-physiological signals such as the electrocardiogram (ECG). It is therefore necessary to develop models/algorithms that are capable of analysing these massive amount of data in real-time. This paper proposes a deep learning model for real-time segmentation of heartbeats. The proposed DENS-ECG algorithm, combines convolutional neural network (CNN) and long short-term memory (LSTM) model to detect onset, peak, and offset of different heartbeat waveforms such as the P-waves, QRS complexes, T-waves, and No waves (NW). Using ECG as the inputs, the model learns to extract high level features through the training process, which, unlike other classical machine learning based methods, eliminates the feature engineering step. The proposed DENS-ECG model was trained and validated on a dataset with 105 ECG records of length 15 min each and achieved an average sensitivity and precision of 97.95% and 95.68%, respectively, using a stratified 5-fold cross validation. Additionally, the model was evaluated on an unseen dataset to examine its robustness in QRS detection, which resulted in a sensitivity of 99.61% and precision of 99.52%. The empirical results show the flexibility and accuracy of the combined CNN-LSTM model for ECG signal delineation. This paper proposes an efficient and easy to use approach using deep learning for heartbeat segmentation, which could potentially be used in real-time tele-health monitoring systems. [ABSTRACT FROM AUTHOR]

As a hotspot of machine learning research, deep learning is applied in many fields. Embedded systems are becoming more and more complex and networked, so the real-time performance of embedded systems and the security of network embedded devices face severe challenges. Based on this, this paper studies the real-time task scheduling problem for complex embedded systems and the security of embedded network devices. For real-time, this paper proposes a comprehensive task scheduling algorithm. Based on the task classification in the embedded system, different scheduling methods are adopted for different tasks, and the scheduling mode is flexibly changed as the system load changes. A dynamic integrity measurement model is established based on the star trust chain structure, and the hardware implementation mechanism of constructing dynamic trust chain in embedded system is studied. The dynamic reconfigurable hardware design method based on FPGA is applied to the construction of dynamic trust chain, and a verification system is designed to verify the dynamic measurement mechanism. This can solve the security problem of deep network embedded devices to a certain extent. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is a field of computer science that aims to mimic human thought processes, learning capacity, and knowledge storage. AI techniques have been applied in cardiovascular medicine to explore novel genotypes and phenotypes in existing diseases, improve the quality of patient care, enable cost-effectiveness, and reduce readmission and mortality rates. Over the past decade, several machine-learning techniques have been used for cardiovascular disease diagnosis and prediction. Each problem requires some degree of understanding of the problem, in terms of cardiovascular medicine and statistics, to apply the optimal machine-learning algorithm. In the near future, AI will result in a paradigm shift toward precision cardiovascular medicine. The potential of AI in cardiovascular medicine is tremendous; however, ignorance of the challenges may overshadow its potential clinical impact. This paper gives a glimpse of AI's application in cardiovascular clinical care and discusses its potential role in facilitating precision cardiovascular medicine. [ABSTRACT FROM AUTHOR]

SMS spams are one of the concerns and many people do not like to receive them since they are annoying. Many SMS spam detection methods already exist and different classifiers were used, such classifiers depended on Support Vector machine, Naïve Bays and many other machine learning algorithms. In this paper, new classifier is proposed which depends mainly on using H2O as platform to make comparisons between different machine learning algorithms. Moreover, Machine learning algorithms that are used for comparisons are random forest, deep learning and naïve bays. In addition to using deep learning and random forest as classifiers, they are also used to determine the most important features that can be used as input to random forest, deep learning and naïve bays classifiers. Experimental results show that the most significant features that can affect the detection of SMS spam are the number of digits and existing of URL in SMS text. The dataset that is used in experiment is the one proposed by UCI Machine Learning Repositories. Therefore, experiments show that the faster algorithm that achieves high performance is naïve bays with runtime 0.6 seconds, however after comparing it with deep learning and random forest it has the lowest precision, recall, f-measure and accuracy. On the other hand, random forest is the best in term of accuracy with 50 trees and 20 maximum depths, where precision, recall, f-measure and accuracy are 96%, 86%, 91% and 0.977% respectively; nevertheless the runtime is high 30.28 seconds. [ABSTRACT FROM AUTHOR]

Self-attention mechanism-based algorithms are attractive in digital pathology due to their interpretability, but suffer from computation complexity. This paper presents a novel, lightweight Attention-based Multiple Instance Mutation Learning (AMIML) model to allow small-scale attention operations for predicting gene mutations. Compared to the standard self-attention model, AMIML reduces the number of model parameters by approximately 70%. Using data for 24 clinically relevant genes from four cancer cohorts in TCGA studies (UCEC, BRCA, GBM, and KIRC), we compare AMIML with a standard self-attention model, five other deep learning models, and four traditional machine learning models. The results show that AMIML has excellent robustness and outperforms all the baseline algorithms in the vast majority of the tested genes. Conversely, the performance of the reference deep learning and machine learning models vary across different genes, and produce suboptimal prediction for certain genes. Furthermore, with the flexible and interpretable attention-based pooling mechanism, AMIML can further zero in and detect predictive image patches. • The lightweight AMIML model allows small-scale self-attention and quicker turnaround compared to standard self-attention models. • AMIML shows excellent robustness and outperforms other existing deep learning and machine learning models. • AMIML improves the prediction of a wide range of genes over the current literature reports. • The interpretability of AMIML workflow can help pathologists to zero in on important ROIs [ABSTRACT FROM AUTHOR]