Search

Detecting defects in welds used in critical or non-critical industrial applications is of intense interest. Several non-destructive inspection methods are available, each allowing the preservation of the integrity of the sample under analysis. However, visual-based inspection methods are the most well-assessed, which usually require human experts to inspect each sample, looking for shallow defects. This process often requires time and effort by the human operator, therefore not allowing to perform real-time defect identification, which may result in unexpected (and undesired) production costs. In recent years, several methods have been proposed to automatically deal with visual-based inspection, mainly through convolutional neural networks. However, while effective, these models require a lot of data and computational power to be trained, which is also time-consuming. This paper proposes a high-throughput data gathering and processing method using laser profilometry, along with an automatic defect detection method based on lightweight machine learning algorithms. Six different machine and deep learning approaches are compared, including SVMs, decision forests, and neural networks, achieving a top-1 accuracy of 99.79 % for defect identification and 99.71 % for defect categorization. Thanks to its effectiveness and the high data throughput achievable by data gathering, the whole method can be implemented in real production lines to minimize costs and perform real-time monitoring and defects assessment. [ABSTRACT FROM AUTHOR]

Deep reinforcement learning has always been used to solve high-dimensional complex sequential decision problems. However, one of the biggest challenges for reinforcement learning is sample efficiency, especially for high-dimensional complex problems. Model-based reinforcement learning can solve the problem with a learned world model, but the performance is limited by the imperfect world model, so it usually has worse approximate performance than model-free reinforcement learning. In this paper, we propose a novel model-based reinforcement learning algorithm called World Model with Trajectory Discrimination (WMTD). We learn the representation of temporal dynamics information by adding a trajectory discriminator to the world model, and then compute the weight of state value estimation based on the trajectory discriminator to optimize the policy. Specifically, we augment the trajectories to generate negative samples and train a trajectory discriminator that shares the feature extractor with the world model. Experimental results demonstrate that our method improves the sample efficiency and achieves state-of-the-art performance on DeepMind control tasks. [ABSTRACT FROM AUTHOR]

With the rapid advancements of sensor technologies and mobile computing, Mobile Crowd Sensing (MCS) has emerged as a new paradigm to collect massive-scale rich trajectory data. Nomadic sensors empower people and objects with the capability of reporting and sharing observations on their state, their behavior and/or their surrounding environments. Processing and mining multi-source sensor data in MCS raise several challenges due to their multi-dimensional nature where the measured parameters (i.e., dimensions) may differ in terms of quality, variability, and time scale. We consider the context of air quality MCS and focus on the task of mining the micro-environment from the MCS data. Relating the measures to their micro-environment is crucial to interpret them and analyse the participant's exposure properly. In this paper, we focus on the problem of investigating the feasibility of recognizing the human's micro-environment in an environmental MCS scenario. We propose a novel approach for learning and predicting the micro-environment of users from their trajectories enriched with environmental data represented as multidimensional time series plus GPS tracks. We put forward a multi-view learning approach that we adapt to our context, and implement it along with other time series classification approaches. We extend the proposed approach to a hybrid method that employs trajectory segmentation to bring the best of both methods. We optimise the proposed approaches either by analysing the exact geolocation (which is privacy invasive), or simply applying some a priori rules (which is privacy friendly). The experimental results, applied to real MCS data, not only confirm the power of MCS and air quality (AQ) data in characterizing the micro-environment, but also show a moderate impact of the integration of mobility data in this recognition. Furthermore, and during the training phase, multi-view learning shows similar performance as the reference deep learning algorithm, without requiring specific hardware. However, during the application of models on new data, the deep learning algorithm fails to outperform our proposed models. [ABSTRACT FROM AUTHOR]

Sensors, wearables, mobile devices, and other Internet of Things (IoT) devices are becoming increasingly integrated into all aspects of our lives. They are capable of gathering enormous amounts of data, such as image data, which can then be sent to the cloud for processing. However, this results in an increase in network traffic and latency. To overcome these difficulties, edge computing has been proposed as a paradigm for computing that brings processing closer to the location where data is produced. This paper explores the merging of cloud and edge computing for IoT and investigates approaches using machine learning for dimensionality reduction of images on the edge, employing the autoencoder deep learning-based approach and principal component analysis (PCA). The encoded data is then sent to the cloud server, where it is used directly for any machine learning task without significantly impacting the accuracy of the data processed in the cloud. The proposed approach has been evaluated on an object detection task using a set of 4000 images randomly chosen from three datasets: COCO, human detection, and HDA datasets. Results show that a 77% reduction in data did not have a significant impact on the object detection task's accuracy. [ABSTRACT FROM AUTHOR]

Colorectal cancer (CRC) exhibits a significant death rate that consistently impacts human lives worldwide. Histopathological examination is the standard method for CRC diagnosis. However, it is complicated, time-consuming, and subjective. Computer-aided diagnostic (CAD) systems using digital pathology can help pathologists diagnose CRC faster and more accurately than manual histopathology examinations. Deep learning algorithms especially convolutional neural networks (CNNs) are advocated for diagnosis of CRC. Nevertheless, most previous CAD systems obtained features from one CNN, these features are of huge dimension. Also, they relied on spatial information only to achieve classification. In this paper, a CAD system is proposed called "Color-CADx" for CRC recognition. Different CNNs namely ResNet50, DenseNet201, and AlexNet are used for end-to-end classification at different training–testing ratios. Moreover, features are extracted from these CNNs and reduced using discrete cosine transform (DCT). DCT is also utilized to acquire spectral representation. Afterward, it is used to further select a reduced set of deep features. Furthermore, DCT coefficients obtained in the previous step are concatenated and the analysis of variance (ANOVA) feature selection approach is applied to choose significant features. Finally, machine learning classifiers are employed for CRC classification. Two publicly available datasets were investigated which are the NCT-CRC-HE-100 K dataset and the Kather_texture_2016_image_tiles dataset. The highest achieved accuracy reached 99.3% for the NCT-CRC-HE-100 K dataset and 96.8% for the Kather_texture_2016_image_tiles dataset. DCT and ANOVA have successfully lowered feature dimensionality thus reducing complexity. Color-CADx has demonstrated efficacy in terms of accuracy, as its performance surpasses that of the most recent advancements. [ABSTRACT FROM AUTHOR]

An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians' decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between "shallow" learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and "deep" learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence. Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics). • Deep classifiers implement automatic feature extraction and classification. • The classifier selection is based on data and computational resources availability, task, and explanation needs. [ABSTRACT FROM AUTHOR]

Context: With the union of machine learning (ML) and quantum chemistry, amid the debate between machine-learned functionals and human-designed functionals in density functional theory (DFT), this paper aims to demonstrate the generation of potential energy surfaces using computations with machine-learned density functional approximation (ML-DFA). A recent research trend is the application of ML in quantum sciences in the design of density functionals such as DeepMind's Deep Learning model (DeepMind21, DM21). Though science reported the state-of-the-art performance of DM21, the opportunity to utilize DeepMind's pretrained DM21 neural networks in computations in quantum chemistry has not yet been tapped. So far in the literature, the Deep Learning density functionals (DM21) have not been applied to generate potential energy surfaces. While the superior accuracy of DM21 has been reported, there is still a scarcity of publications that apply DM21 in calculations in the field. In this context, for the first time in literature, neural density functionals inferring 2D potential energy surfaces (ML-DFA-PES) based on machine-learned DFA-based computational method is contributed in this paper. This paper reports the ML-DFA-generated PES for C4H8, H2O, H2, and H2+ by employing a pretrained DM21m TensorFlow model with cc-pVDZ basis set. In addition, we also analyze the long-range behavior of DM21 based PES to investigate the ability to describe a system at long ranges. Furthermore, we compare PES diagrams from DM21 with popular DFT functionals (b3lyp/ PW6B95) and CCSD(T). Methods: In this method, 2D potential energy surfaces are obtained using a method that relies upon the neural network's ability to accurately learn the mapping between 3D electron density and exchange–correlation potential. By inserting Deep Learning inference in DFT with a pretrained neural network, self-consistent field (SCF) energy at different geometries along the coordinates of interest is computed, and then, potential energy surfaces are plotted. In this method, first, the electron density is computed mathematically, and this computed 3D electron density is used as a ML feature vector to predict the exchange correlation potential as a ML inference computed by a forward pass of pre-trained DM21 TensorFlow computational graph, followed by the computation of self-consistent field energy at multiple geometries, and then, SCF energies at different bond lengths/angles are plotted as 2D PES. We implement this in a python source code using frameworks such as PySCF and DM21. This paper contributes this implementation in open source. The source code and DM21-DFA-based PES are contributed at https://sites.google.com/view/MLfunctionals-DeepMind-PES. [ABSTRACT FROM AUTHOR]

Evidences are important proofs to support judicial trials. Automatically extracting evidences from judgement documents can be used to assess the trial quality and support "Intelligent Court". Current evidence extraction is primarily depended on sequence labelling models. Despite their success, they can only assign a label to a token, which is difficult to recognize nested evidence entities in judgment documents, where a token may belong to several evidences at the same time. In this paper, we present a novel evidence extraction architecture called ATT-MRC, in which extracting evidence entities is formalized as a question answer problem, where all evidence spans are screened out as possible correct answers. Furthermore, to address the data imbalance problem in the judgement documents, we revised the loss function and combined it with a data enhancement technique. Experimental results demonstrate that our model has better performance than related works in evidence extraction. [ABSTRACT FROM AUTHOR]

This review aims to explore the growing impact of machine learning and deep learning algorithms in the medical field, with a specific focus on the critical issues of explainability and interpretability associated with black-box algorithms. While machine learning algorithms are increasingly employed for medical analysis and diagnosis, their complexity underscores the importance of understanding how these algorithms explain and interpret data to take informed decisions. This review comprehensively analyzes challenges and solutions presented in the literature, offering an overview of the most recent techniques utilized in this field. It also provides precise definitions of interpretability and explainability, aiming to clarify the distinctions between these concepts and their implications for the decision-making process. Our analysis, based on 448 articles and addressing seven research questions, reveals an exponential growth in this field over the last decade. The psychological dimensions of public perception underscore the necessity for effective communication regarding the capabilities and limitations of artificial intelligence. Researchers are actively developing techniques to enhance interpretability, employing visualization methods and reducing model complexity. However, the persistent challenge lies in finding the delicate balance between achieving high performance and maintaining interpretability. Acknowledging the growing significance of artificial intelligence in aiding medical diagnosis and therapy, and the creation of interpretable artificial intelligence models is considered essential. In this dynamic context, an unwavering commitment to transparency, ethical considerations, and interdisciplinary collaboration is imperative to ensure the responsible use of artificial intelligence. This collective commitment is vital for establishing enduring trust between clinicians and patients, addressing emerging challenges, and facilitating the informed adoption of these advanced technologies in medicine. [ABSTRACT FROM AUTHOR]

The growing energy demand and population raising require alternative, clean, and sustainable energy systems. During the last few years, hydrogen energy has proven to be a crucial factor under the current conditions. Although the energy conversion process in polymer electrolyte fuel cells (PEFCs) is clean and noiseless since the only by-products are heat and water, the inside phenomena are not simple. As a result, correct monitoring of the health situation of the device is required to perform efficiently. This paper aims to explore and evaluate the machine learning (ML) and deep learning (DL) models for predicting classification fault detection in PEFCs. It represents a support for decision-making by the fuel cell operator or user. Seven ML and DL model classifiers are considered. A database comprising 182,156 records and 20 variables arising from the fuel cell's energy conversion process and operating conditions is considered. This dataset is unbalanced; therefore, techniques to balance are applied and analyzed in the training and testing of several models. The results showed that the logistic regression (LR), k-nearest neighbor (KNN), decision tree (DT), random forest (RF), and Naive Bayes (NB) models present similar and optimal trends in terms of performance indicators and computational cost; unlike support vector machine (SMV) and multi-layer perceptron (MLP) whose performance is affected when the data is balanced and even presents a higher computational cost. Therefore, it is a novel approach for fault detection analysis in PEFC that combines the interpretability of different ML and DL algorithms while addressing data imbalance, so common in the real world, using resampling techniques. This methodology provides clear information for the model decision-making process, improving confidence and facilitating further optimization; in contrast to traditional physics-based models, paving the way for data-driven control strategies. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) has gained an increased interest during the last decades as part of enriched affective computing. As a consequence, a variety of engineering approaches have been developed addressing the challenge of the SER problem, exploiting different features, learning algorithms, and datasets. In this paper, we propose the application of the graph theory for classifying emotionally-colored speech signals. Graph theory provides tools for extracting statistical as well as structural information from any time series. We propose to use the mentioned information as a novel feature set. Furthermore, we suggest setting a unique feature-based identity for each emotion belonging to each speaker. The emotion classification is performed by a Random Forest classifier in a Leave-One-Speaker-Out Cross Validation (LOSO-CV) scheme. The proposed method is compared with two state-of-the-art approaches involving well known hand-crafted features as well as deep learning architectures operating on mel-spectrograms. Experimental results on three datasets, EMODB (German, acted) and AESDD (Greek, acted), and DEMoS (Italian, in-the-wild), reveal that our proposed method outperforms the comparative methods in these datasets. Specifically, we observe an average UAR increase of almost 18 % , 8 % and 13 % , respectively. [ABSTRACT FROM AUTHOR]

Modern data mining techniques using machine learning (ML) and deep learning (DL) algorithms have been shown to excel in the regression-based task of materials property prediction using various materials representations. In an attempt to improve the predictive performance of the deep neural network model, researchers have tried to add more layers as well as develop new architectural components to create sophisticated and deep neural network models that can aid in the training process and improve the predictive ability of the final model. However, usually, these modifications require a lot of computational resources, thereby further increasing the already large model training time, which is often not feasible, thereby limiting usage for most researchers. In this paper, we study and propose a deep neural network framework for regression-based problems comprising of fully connected layers that can work with any numerical vector-based materials representations as model input. We present a novel deep regression neural network, iBRNet, with branched skip connections and multiple schedulers, which can reduce the number of parameters used to construct the model, improve the accuracy, and decrease the training time of the predictive model. We perform the model training using composition-based numerical vectors representing the elemental fractions of the respective materials and compare their performance against other traditional ML and several known DL architectures. Using multiple datasets with varying data sizes for training and testing, We show that the proposed iBRNet models outperform the state-of-the-art ML and DL models for all data sizes. We also show that the branched structure and usage of multiple schedulers lead to fewer parameters and faster model training time with better convergence than other neural networks. Scientific contribution: The combination of multiple callback functions in deep neural networks minimizes training time and maximizes accuracy in a controlled computational environment with parametric constraints for the task of materials property prediction. [ABSTRACT FROM AUTHOR]

The security of machine learning attracts increasing attention in both academia and industry due to its vulnerability to adversarial examples. However, the research on adversarial examples in intrusion detection is currently in its infancy. In this paper, two novel adversarial attack amplification methods based on a unified framework are proposed to promote the attack performance of the classic white-box attack methods. The proposed methods shield the underlying implementation details of the target attack methods and can effectively boost different target attack methods through a unified interface. The proposed methods extract the original adversarial perturbations from the adversarial examples produced by the target attack methods and amplify the original adversarial perturbations to generate the amplified adversarial examples. The preliminary experimental results show that the proposed methods can effectively improve the attack performance of the classic white-box attack methods. Besides, the amplified adversarial examples crafted by the proposed methods show excellent transferability across different machine learning classifiers, which ensures that the application of the proposed methods is not limited to the white-box setting. Consequently, the proposed methods can be utilized to better assess the robustness of the machine learning-based intrusion detection systems against adversarial examples in various contexts. [ABSTRACT FROM AUTHOR]

Wire Arc Additive Manufacturing is a Direct Energy Deposition additive technology that uses the principle of wire welding to deposit layers of material to create a finished component. This technology is finding an increasing interest in the manufacturing industry, especially thanks the low cost and the possibility to build large-scale components. Nowadays, the boosting to transition into smart manufacturing systems and the increasingly computational resources allowed the development of intelligent applications for smart production systems for both in situ inspection and process parameter control. This paper aims to provide an review of applications developed using artificial intelligence techniques for Wire Arc Additive Manufacturing, with particular focus on defect detection software modules, feedback generation for control system and innovative control strategies as reinforcement learning to overcome problems related to model non-linearity and uncertainties. [ABSTRACT FROM AUTHOR]

Features of data are much critical to the classification. However, when only small data are available, suitable features can not be easily obtained, easily leading to the bad classification performance. This paper propose a novel approach to automatically learns features from the irrelevant domain with much discriminative features for the given classification task. It first computes as the learning objectives the central vectors of each class in the irrelevant domain, and then uses machine learning method to automatically learn features for each sample in the target domain from these objectives. The merits of our method lie in that unlike the transfer learning, our method does not require the similarity between two domains. It can learn features from much discriminative domains. Its learned features are not limited to its original ones, unlike feature selection and feature extraction methods, so that the classification performance with the learned features can be better. Finally, our method is much general, simple, and efficient. Lots of experimental results validated the proposed method. [ABSTRACT FROM AUTHOR]

Target tracking provides important location-based services in many applications. The main challenge of target tracking is to combat the severe degradation problem in Non-Line-of-Sight (NLOS) scenario. Most Deep Learning algorithms available in literature to address this issue belong to batch learning with high complexity. This paper proposes a novel online sequential learning algorithm, Improved Recurrent Extreme Learning Machine (IRELM), to solve the NLOS target tracking problem as a position series prediction task. IRELM is able to train Recurrent Neural Network (RNN) inputs one-by-one and adaptively update the input weight, hidden weight, feedback weight and output weight. Extensive simulations and experiments prove the superior tracking performance and feasible complexity of IRELM over the state-of-the-art Deep Learning methods. [ABSTRACT FROM AUTHOR]

Time series forecasting models are gaining traction in many real-world domains as valuable decision support tools. Stock market analysis is a challenging domain, characterized by a complex multi-variate and time-evolving nature, with high volatility, and multiple correlations with exogenous factors. Autoregressive, machine learning, and deep learning models for temporal data have been adopted thus far to solve this task. However, they are usually limited to the analysis of a single data source or modality, and do not collectively deal with all the inherent challenges and complexities presented by stock market data. In this paper, inspired by the promising learning capabilities of hybrid ensemble methods, we propose a novel stacking ensemble approach for stock market prediction that jointly considers news headlines, multi-variate time series data, and multiple base models as predictors. By taking multiple factors into consideration, our model is able to learn historical patterns leveraging multiple data sources and models. Our experiments showcase the ability of our model to outperform popular baselines on next-day stock market trend prediction. A portfolio analysis reveals that our method is also able to yield potential gains or capital preservation capabilities when its predictions are exploited for trading decisions. [ABSTRACT FROM AUTHOR]

Routability estimation identifies potentially congested areas in advance to achieve high-quality routing solutions. To improve the routing quality, this paper presents a deep learning-based congestion estimation algorithm, which serves to guide the initial pattern routing of a global router to reduce unexpected overflows. Unlike existing methods based on traditional compressed 2D features for model training and prediction, our algorithm extracts appropriate 3D features from the placed netlists. Furthermore, an improved RUDY (Rectangular Uniform wire DensitY) method is developed to estimate 3D routing demands. For the model selection, we employ the U-net model with good image prediction ability as a routability estimator, and the prediction results are used for guiding the initial routing process. Since our training set is formed by cropping training designs, the structural information between two adjacent cropped designs may be missed. Hence, we divide experiments into two parts, experiments based on normal designs and experiments based on big designs. Compared with the state-of-the-art method, experimental results show that our routability estimator can significantly improve the Pearson Correlation Coefficient (PCC) index and reduce the Mean Absolute Normalized Error (MANE) and the Standard Deviation in the Normalized Error (SDNE). Furthermore, our congestion-guided global routing can reduce the routing overflows, wirelength, and via count both on normal designs and big designs, compared to CUGR. [ABSTRACT FROM AUTHOR]

Dangerous driving, e.g., using mobile phone while driving, can result in serious traffic problem and threaten to safety. To efficiently alleviate such problem, in this paper, we design an intelligent monitoring system to detect the dangerous behavior while driving. The monitoring system is combined by a designed target detection algorithm, camera, terminal server and voice reminder. An efficiently deep learning model, namely Mobilenet combined with single shot multi-box detector (Mobilenet-SSD), was applied to identify the behavior of driver. To evaluate the performance of proposed system, a dangerous driving dataset,consisting of 6796 images, was constructed. The experimental results show that the proposed system can achieve the accuracy of 99%, and could be used for real-time monitoring of the drivers' status. [ABSTRACT FROM AUTHOR]

False information, such as rumours, has seriously affected our daily lives and threatened the political, economic, cultural and other fields. Therefore, rumour detection on social media has become a hot research topic in recent years. The development of deep learning algorithms provides new technology for rumour detection. It has been shown that capsule networks have several advantages, while their validity in the domain of text has been less explored. An effective method named the BiGRU_capsule network model has been recently proposed. This method can fully consider the contextual relationship without the loss of text spatial structure information. The proposed model introduces features of user personas and uses a two-way GRU (BiGRU) network to improve the capsule network, which can improve rumour detection accuracy. Experimental results show that compared with benchmark rumour detection models on the Twitter dataset, the accuracy of the proposed model can be improved by 6.7% under dynamic routing and by 6.1% under static routing. This reflects the effectiveness of the proposed method on rumour detection in social media. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification has continued to be a hot research topic in recent years, and the broad learning system (BLS) has been considered by scholars for the classification of HSIs due to its superior internal structure. Different from the traditional HSI classification mechanism, this paper proposes an active broad learning system approach for HSI classification. The spectral and spatial features of the image are extracted using principal component analysis and local binary patterns, respectively. Then, the vector fusion of the above two features is utilized as the input of the BLS and trained to obtain pre-labels of the samples. The next training samples are selected among the pre-labels by active learning. Unlike other classification algorithms, the method proposed in this paper utilizes active learning (AL) to select high-quality samples for training, thereby reducing the number of samples used and the cost of sample labeling. In addition, the use of incremental learning in broad learning significantly reduces the training time and improves the classification accuracy. The algorithm proposed in this paper is more effective compared to other state-of-the-art algorithms on three HSI datasets. [ABSTRACT FROM AUTHOR]

With the advent of the Internet, the activities of individuals and businesses have expanded into the online realm. As a result, vulnerabilities that result in actual breaches can lead to data loss and program failure. The number of breaches is increasing every year, as is the number of vulnerabilities. To address this problem, current research focuses on the detection of vulnerabilities using static analysis techniques. To prevent the propagation of vulnerabilities, a new paradigm is needed to quickly detect vulnerabilities, analyze them, and take actions such as blocking or removing them. Recently, artificial intelligence algorithms such as deep learning have been introduced for vulnerability detection. In this paper, we propose a vulnerability detection model, V-CNN, which aims to detect CWE/CVE (Common Weakness Enumeration/Common Vulnerabilities and Exposures) using CNN (convolutional neural network). We trained CWE for deep learning and redefined vulnerabilities based on CWE. We propose an experimental algorithm to improve vulnerability detection. The accuracy of the proposed V-CNN model is 98%, which exceeds the 95% of the random forest model. Therefore, our V-CNN has excellent correctness detection performance in the field of vulnerability detection. The V-CNN vulnerability detection algorithm can be used instead of static analysis to detect various security vulnerabilities. [ABSTRACT FROM AUTHOR]

Topics covered in this issue are categorized into the following five themes: (1) network and security, (2) machine learning and artificial intelligence, (3) communication and routing strategies, (4) optimization and algorithms, and (5) data analysis. In recent years, various machine learning methods such as supervised methods (e.g. I k i nearest neighbors (kNN), Bayes' classifier, decision tree (DT), support vector machine (SVM), random forest (RF), neural network (NN), convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM) network, gated recurrent unit (GRU) network) [[1]-[3]], unsupervised methods (e.g. association rules, I k i -means, density-based spatial clustering of applications with noise (DBSCAN), hierarchical clustering, deep belief networks (DBN), deep Boltzmann machine (DBM), auto-encoder (AE), de-noising auto-encoder, etc.) [[4]], reinforcement learning methods (e.g. generative adversarial network (GAN), deep Q-network (DQN), trust region policy optimization, etc.) [[6]], and federated learning methods have been applied to trust, security, and privacy in computing and communications. 2022; 2022: 22. 10.1186/s13638-022-02105-7 13 Liu T, Yu Z. The analysis of financial market risk based on machine learning and particle swarm optimization algorithm. For instance, improving machine learning methods for detecting malicious activity, attack detection, mobile endpoint analysis, repetitive security task automation, and zero-day vulnerability prevention are critical issues in the field. [Extracted from the article]

The aim of this paper is to develop a system for drug–target interaction prediction using artificial intelligence which involves development of both machine learning and deep learning-based systems. In this paper, we use a convolutional neural network (CNN) model, to classify drug–target interactions between drug pairs. Applied to the DDI-Corpus dataset, the single CNN model achieve performance with an F1-score of 0.82 ± 0.012 for the single model and 0.81 ± 0.015 for the ensemble model using deep learning-based CNN with an approved accuracy of 96.72% which is an extra-ordinary achievement. This work has also been performed using the machine learning-based classifiers support vector machine (SVM). For machine learning-based implementation, drug-bank dataset was used for the training and testing. The main challenge when using machine learning for this purpose is the availability of negative DTI to train on. Training machine learning model, the SVM achieved an area under the ROC curve (AUC) of 0.753 ± 0.006, which taking the difference in computational resources into consideration compares well to the AUC of 0.886 ± 0.010 network-based state-of-the-art approach. We achieved and best accuracy of 93.76% using SVM after testing several times. [ABSTRACT FROM AUTHOR]

Penetration recognition is the critical technology to improve manufacturing quality and automation level in arc welding. In this paper, recent research advances concerning penetration recognition based on machine learning are comprehensively reviewed, focused on signals feature extraction and application of machine learning in this field. Three types of signals originating from arc welding, namely, weld pool image, arc sound, and arc voltage, are used to analyze the correlation with the penetration state and extract effective features. Next, the following contents briefly introduce some machine learning methods including conventional machine learning and deep learning, and emphatically summarize their application and performance in penetration recognition. Notably, the deep learning method possesses higher classification accuracy and better generalization ability in penetration recognition due to its deeper architecture and effective learning capacity. In the end, some challenges and tendencies, involving multi-sensor information fusion, data-driven recognition, model development incorporating attention mechanism, lightweight model deployment, and real-time control, are presented for further research. This paper is an attempt to provide a reference source and some guidance for researchers who use machine learning methods for penetration monitoring. [ABSTRACT FROM AUTHOR]

Scholarly work points to 5S + 1, a simple yet powerful method of initiating quality in manufacturing, as one of the foundations of Lean manufacturing and the Toyota Production Systems. The 6th S, safety, is often used to prevent future occupational hazards, therefore, reducing the loss of time, money, and human resources. This paper aims to show how Industry 4.0 technologies such as computer-based vision and object detection algorithms can help implement the 6th S in 5S + 1 through monitoring and detecting workers who fail to adhere to standard safety practices such as wearing personal protective equipment (PPE). The paper evaluated and analyzed three different detection approaches and compared their performance metrics. In total, seven models were proposed to perform such a task. All the proposed models utilized You-Only-Look-Once (YOLO v7) architecture to verify workers' PPE compliance. In approach I, three models were used to detect workers, safety helmets and safety vests. Then, a machine learning algorithm was used to verify if each detected worker is in PPE compliance. In approach II, the model simultaneously detects individual workers and verifies PPE compliance. In approach III, three different models were used to detect workers in the input feed. Then, a deep learning algorithm was used to verify the safety. All models were trained on Pictor-v3 dataset. It is found that the third approach, when utilizing VGG-16 algorithm, achieves the best performance, i.e., 80% F1 score, and can process 11.79 frames per second (FPS), making it suitable for real-time detection. [ABSTRACT FROM AUTHOR]

Surface defect detection is an important part of the process of product quality control in the industry. Automatic detection of surface defects based on machine learning is an up-and-coming research field, and there have been many successful cases. Deep learning has become the most suitable detection method for this task. Most algorithms require a large number of defect samples to achieve good results. However, defect samples in actual production are very limited. Although some unsupervised or semi-supervised methods can reduce training costs, their accuracy is difficult to guarantee, so they are difficult to be applied in industrial inspection. In this paper, we propose a detail-semantic guide network (DSGNet), which can achieve better result with fewer training samples. It is a two-stage neural network framework. In the first stage, we design a new semantic branch based on the modified residual shrinkage network and the proposed joined atrous spatial pyramid pooling (JASPP) module. This is the first time that residual shrinkage network is applied to defect detection and achieves good results. Also, we design a clear and efficient detail branch based on dense connection network. Specially, we propose a new detail-semantic guide module (DSGM), which can better integrate the feature information of the two branches. In the training phase, we propose a weight mask based on defect area to improve the ability of extracting small defects. We did experiments on four datasets and our method achieved excellent detection results even with only a small number of training samples. [ABSTRACT FROM AUTHOR]

Malware attacks on the Android platform are rapidly increasing due to the high consumer adoption of Android smartphones. Advanced technologies have motivated cyber-criminals to actively create and disseminate a wide range of malware on Android smartphones. The researchers have conducted numerous studies on the detection of Android malware, but the majority of the works are based on the detection of generic Android malware. The detection based on malware categories will provide more insights about the malicious patterns of the malware. Therefore, this paper presents a detection solution for different Android malware categories, including adware, banking, SMS malware, and riskware. In this paper, a novel Huffman encoding-based feature vector generation technique is proposed. The experiments have proved that this novel approach significantly improves the efficiency of the detection model. This method makes use of system call frequencies as features to extract malware's dynamic behavior patterns. The proposed model was evaluated using machine learning and deep learning methods. The results show that the proposed model with the Random Forest classifier outperforms some existing methodologies with a detection accuracy of 98.70%. [ABSTRACT FROM AUTHOR]

Adding hooked industrial steel fibers (ISF) to concrete boosts its tensile and flexural strength. However, the understanding of ISF's influence on the compressive strength (CS) behavior of concrete is still questioned by the scientific society. The presented paper aims to use machine learning (ML) and deep learning (DL) algorithms to predict the CS of steel fiber reinforced concrete (SFRC) incorporating hooked ISF based on the data collected from the open literature. Accordingly, 176 sets of data are collected from different journals and conference papers. Based upon the initial sensitivity analysis, the most influential parameters like water-to-cement (W/C) ratio and content of fine aggregates (FA) tend to decrease the CS of SFRC. Meanwhile, the CS of SFRC could be enhanced by increasing the amount of superplasticizer (SP), fly ash, and cement (C). The least contributing factors include the maximum size of aggregates (Dmax) and the length-to-diameter ratio of hooked ISFs (L/DISF). Several statistical parameters are also used as metrics to evaluate the performance of implemented models, such as coefficient of determination (R2), mean absolute error (MAE), and mean of squared error (MSE). Among different ML algorithms, convolutional neural network (CNN) with R2 = 0.928, RMSE = 5.043, and MAE = 3.833 shows higher accuracy. On the other hand, K-nearest neighbor (KNN) algorithm with R2 = 0.881, RMSE = 6.477, and MAE = 4.648 results in the weakest performance. [ABSTRACT FROM AUTHOR]

Insufficient data is always a challenge for developing an accurate machine learning or deep learning model in manufacturing processes, especially in tool wear monitoring under varied cutting conditions. This paper presents a Random Forest model for predicting tool wear under varied cutting conditions as well as studies extracted signal features. The Random Forest algorithm was chosen as the machine learning model, rather than the novel deep learning model. This was due to the feature importance investigation, which was embedded in the Random Forest algorithm, thereby making it easier to study the physical meanings of signal features. The frequency domain signals were rearranged as features related to spindle speeds and machine tool structure based on domain knowledge. This is the first paper to rearrange the frequency domain signals for observing the physical meanings of selected features. When data normalization was adopted, frequency domain signals related to spindle speeds were excluded from important features. Only spectrum energy related to structure vibration and time domain signals were important features. Data normalization enhanced the weighting of structure vibration features in a machine learning model. This study showed that feature normalization made the machine learning model more adaptable to different cutting conditions. Furthermore, prediction accuracy for cutting condition of spindle speed = 42,000 rpm and feed = 1.5 μm/rev (lowest prediction accuracy among cutting tests in this study) showed an increase from 68.0 to 84.1%. In addition, spindle speed had a more significant effect than feed on classification accuracy in tool wear monitoring based on experimental results. As a result, at least two data sets of the same spindle speed as in tool wear prediction were recommended to be used for model training. When there were at least two data sets in training data with the same spindle speed as in testing data, the study showed prediction accuracies were greater than 75% without data normalization and 81% with data normalization. [ABSTRACT FROM AUTHOR]

Determining which variables affect price realized volatility has always been challenging. This paper proposes to explain how financial assets influence realized volatility by developing an optimal day-to-day forecast. The methodological proposal is based on using the best econometric and machine learning models to forecast realized volatility. In particular, the best forecasting from heterogeneous autoregressive and long short-term memory models are used to determine the influence of the Standard and Poor's 500 index, euro–US dollar exchange rate, price of gold, and price of Brent crude oil on the realized volatility of natural gas. These financial assets influenced the realized volatility of natural gas in 87.4% of the days analyzed; the euro–US dollar exchange rate was the primary financial asset and explained 40.1% of the influence. The results of the proposed daily analysis differed from those of the methodology used to study the entire period. The traditional model, which studies the entire period, cannot determine temporal effects, whereas the proposed methodology can. The proposed methodology allows us to distinguish the effects for each day, week, or month rather than averages for entire periods, with the flexibility to analyze different frequencies and periods. This methodological capability is key to analyzing influences and making decisions about realized volatility. [ABSTRACT FROM AUTHOR]

Modern web application development involves handling enormous amounts of sensitive and consequential data. Security is, therefore, a crucial component of developing web applications. A web application's security is concerned with safeguarding the data it processes. The web application framework must have safeguards to stop and find application vulnerabilities. Among all web application attacks, SQL injection and XSS attacks are common, which may lead to severe damage to Web application data or web functionalities. Currently, there are many solutions provided by various study for SQLi and XSS attack detection, but most of the work shown have used either SQL/XSS payload-based detection or HTTP request-based detection. Few solutions available can detect SQLi and XSS attacks, but these methods provide very high false positive rates, and the accuracy of these models can further be improved. We proposed a novel approach for securing web applications from both cross-site scripting attacks and SQL injection attacks using decoding and standardization of SQL and XSS payloads and HTTP requests and trained our model using hybrid deep learning networks in this paper. The proposed hybrid DL model combines the strengths of CNNs in extracting features from input data and LSTMs in capturing temporal dependencies in sequential data. The soundness of our approach lies in the use of deep learning techniques that can identify subtle patterns in the data that traditional machine learning-based methods might miss. We have created a testbed dataset of Normal and SQLi/XSS HTTP requests and evaluated the performance of our model on this dataset. We have also trained and evaluated the proposed model on the Benchmark dataset HTTP CSIC 2010 and another SQL/XSS payload dataset. The experimental findings show that our proposed approach effectively identifies these attacks with high accuracy and a low percentage of false positives. Additionally, our model performed better than traditional machine learning-based methods. This soundness approach can be applied to various network security applications such as intrusion detection systems and web application firewalls. Using our model, we achieved an accuracy of 99.84%, 99.23% and 99.77% on the SQL-XSS Payload dataset, Testbed dataset and HTTP CSIC 2010 dataset, respectively. [ABSTRACT FROM AUTHOR]

For efficient operation, solar power operators often require generation forecasts for multiple sites with varying data availability. Many proposed methods for forecasting solar irradiance / solar power production formulate the problem as a time-series, using current observations to generate forecasts. This necessitates a real-time data stream and enough historical observations at every location for these methods to be deployed. In this paper, we propose the use of Global methods to train generalised models. Using data from 20 locations distributed throughout the UK, we show that it is possible to learn models without access to data for all locations, enabling them to generate forecasts for unseen locations. We show a single Global model trained on multiple locations can produce more consistent and accurate results across locations. Furthermore, by leveraging weather observations and measurements from other locations we show it is possible to create models capable of accurately forecasting irradiance at locations without any real-time data. We apply our approaches to both classical and state-of-the-art Machine Learning methods, including a Transformer architecture. We compare models using satellite imagery or point observations (temperature, pressure, etc.) as weather data. These methods could facilitate planning and optimisation for both newly deployed solar farms and domestic installations from the moment they come online. [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]

This paper proposes an intelligent hybrid model that leverages machine learning and artificial intelligence to enhance the security of Wireless Sensor Networks (WSNs) by identifying and preventing cyberattacks. The study employs feature reduction techniques, including Singular Value Decomposition (SVD) and Principal Component Analysis (PCA), along with the K-means clustering model enhanced information gain (KMC-IG) for feature extraction. The Synthetic Minority Excessively Technique is introduced for data balancing, followed by intrusion detection systems and network traffic categorization. The research evaluates a deep learning-based feed-forward neural network algorithm's accuracy, precision, recall, and F-measure across three vital datasets: NSL-KDD, UNSW-NB 15, and CICIDS 2017, considering both full and reduced feature sets. Comparative analysis against benchmark machine learning approaches is also conducted. The proposed algorithm demonstrates exceptional performance, achieving high accuracy and reliability in intrusion detection for WSNs. The study outlines the system configuration and parameter settings, contributing to the advancement of WSN security. [ABSTRACT FROM AUTHOR]

Monitoring water resources requires accurate predictions of rainfall data. Our study introduces a novel deep learning model named the deep residual shrinkage network (DRSN)—temporal convolutional network (TCN) to remove redundant features and extract temporal features from rainfall data. The TCN model extracts temporal features, and the DRSN enhances the quality of the extracted features. Then, the DRSN–TCN is coupled with a random forest (RF) model to model rainfall data. Since the RF model may be unable to classify and predict complex patterns and data, our study develops the RF model to model outputs with high accuracy. Since the DRSN–TCN model uses advanced operators to extract temporal features and remove irrelevant features, it can improve the performance of the RF model for predicting rainfall. We use a new optimizer named the Gaussian mutation (GM)–orca predation algorithm (OPA) to set the DRSN–TCN–RF (DTR) parameters and determine the best input scenario. This paper introduces a new machine learning model for rainfall prediction, improves the accuracy of the original TCN, and develops a new optimization method for input selection. The models used the lagged rainfall data to predict monthly data. GM–OPA improved the accuracy of the orca predation algorithm (OPA) for feature selection. The GM–OPA reduced the root mean square error (RMSE) values of OPA and particle swarm optimization (PSO) by 1.4%–3.4% and 6.14–9.54%, respectively. The GM–OPA can simplify the modeling process because it can determine the most important input parameters. Moreover, the GM–OPA can automatically determine the optimal input scenario. The DTR reduced the testing mean absolute error values of the TCN–RAF, DRSN–TCN, TCN, and RAF models by 5.3%, 21%, 40%, and 46%, respectively. Our study indicates that the proposed model is a reliable model for rainfall prediction. [ABSTRACT FROM AUTHOR]

Sound is one of the primary forms of sensory information that we use to perceive our surroundings. Usually, a sound event is a sequence of an audio clip obtained from an action. The action can be rhythm patterns, music genre, people speaking for a few seconds, etc. The sound event classification address distinguishes what kind of audio clip it is from the given audio sequence. Nowadays, it is a common issue to solve in the following pipeline: audio pre-processing→perceptual feature extraction→classification algorithm. In this paper, we improve the traditional sound event classification algorithm to identify unknown sound events by using the deep learning method. The compact cluster structure in the feature space for known classes helps recognize unknown classes by allowing large room to locate unknown samples in the embedded feature space. Based on this concept, we applied center loss and supervised contrastive loss to optimize the model. The center loss tries to minimize the intra- class distance by pulling the embedded feature into the cluster center, while the contrastive loss disperses the inter-class features from one another. In addition, we explored the performance of self-supervised learning in detecting unknown sound events. The experimental results demonstrate that our proposed open-set sound event classification algorithm and self-supervised learning approach achieve sustained performance improvements in various datasets. [ABSTRACT FROM AUTHOR]

Flight delay prediction is one of the most significant components of intelligent aviation systems that may spread throughout the whole aviation network and cause multi-billion-dollar losses faced by airlines and airports, it is quickly becoming an important research issue to improve airport and airline performance. Thus this paper proposed an effective algorithm called Flight Delay Path Previous-based Machine Learning (FDPP-ML) capable of improved prediction of individual flight delay minutes using regression models to an up level of accuracy. As aviation system connectivity presents complex spatial–temporal correlations, machine learning approaches have addressed flight delay prediction by using complex flight or weather features, or private information for specific airports and airlines that are hard to obtain, In contrast, the proposed FDPP-ML improved prediction based only on basic flight schedule features even with wide flight networks. The FDPP-ML consists of a novel algorithm with a supervised learning model, which works on reshaping datasets and creates two new features the main feature is previous flight delay (PFD) for flight paths, there is a strong relationship between departure and arrival delay, and vice versa for the same flight path, which increases the strength of the training model based on historical data. For target future flights, the algorithm works on inheriting the predicted flight delay to the next flight on the same flight path and repeats this process to end the prediction forecast horizon. The proving of approach effectiveness by using a wide network of US flight arrival and departure flights containing 366 airports and 10 airlines with various metrics accuracies of regression, and explanatory the impacts on various forecast horizons 2, 6, and 12 h for future flights. The FDPP-ML outperforms traditional training models by using machine and deep learning models and improving model accuracy in 10 models with an average of up to 39% in MAE, and 42% in MSE in a forecast horizon of 2 h. Finally, providing airport and airline analysis further reveals that can improve prediction than traditional training models for the individual busiest airports "Core 30" with an average of 35% in MAE and 42% in MSE respectively, and for the busiest 10 airlines with an average of 36% in MAE and 47% in MSE respectively. The findings of this study may offer informative recommendations to airport regulators and aviation authorities for developing successful air traffic control systems for enhanced flight delay prediction to flight operational effectiveness, not only over the US flight network but with wide worldwide flight networks if a dataset of flights existed. [ABSTRACT FROM AUTHOR]

The combination of flexible sensors and deep learning has attracted much attention as an efficient method for the recognition of human postures. In this paper, an in situ polymerized MXene/polypyrrole (PPy) composite is dip-coated on a polydimethylsiloxane (PDMS) sponge to fabricate an MXene/PPy@PDMS (MPP) piezoresistive sensor. The sponge sensor achieves ultrahigh sensitivity (6.8925 kPa−1) at 0–15 kPa, a short response/recovery time (100/110 ms), excellent stability (5000 cycles) and wash resistance. The synergistic effect of PPy and MXene improves the performance of the composite materials and facilitates the transfer of electrons, making the MPP sponge at least five times more sensitive than sponges based on each of the individual single materials. The large-area conductive network allows the MPP sensor to maintain excellent electrical performance over a large-scale pressure range. The MPP sensor can detect a variety of human body activity signals, such as radial artery pulse and different joint movements. The detection and analysis of human motion data, which is assisted by convolutional neural network (CNN) deep learning algorithms, enable the recognition and judgment of 16 types of human postures. The MXene/PPy flexible pressure sensor based on a PDMS sponge has broad application prospects in human motion detection, intelligent sensing and wearable devices. [ABSTRACT FROM AUTHOR]

As it is widely known, big data can comprehensively describe the inherent laws governing various phenomena. However, the effective and efficient analysis of available data has become a major challenge in the fields of artificial intelligence, machine learning, data mining, and others. Deep learning, with its powerful learning ability and effective data-processing methods, has been extensively researched and applied in numerous academic domains. Nevertheless, the data obtained during the deep learning process often exhibits feature homogenization, resulting in highly redundant features in the hidden layers, which, in turn, affects the learning process. Therefore, this paper proposes an algorithm based on graph clustering to optimize the features of hidden layer units, with the aim of eliminating redundancy and improving learner generation. [ABSTRACT FROM AUTHOR]

In recent decades, fault diagnosis methods based on machine learning and deep learning have achieved excellent results in fault diagnosis and are characterized by powerful automatic feature extraction and accurate identification capabilities. In many real-world scenarios, gathering enough samples of each fault type can be time-consuming and difficult. The scarcity of samples may significantly degrade the performance of these learning-based methods, making it extremely challenging to train a robust fault diagnosis classifier. In this paper, a few-shot fault diagnosis method based on the improved meta-relation network (IMRN) model is proposed to overcome the challenge of implementing fault diagnosis with limited data samples. First, a multiscale feature encoder module that utilizes two one-dimensional convolutional neural networks with different kernel sizes is used to automatically extract signal features from the original support dataset and query dataset. Then, a metric meta-learner module is designed to obtain relation scores between support samples and query samples. Finally, the feature vector output by the feature encoder module is input to the metric meta-learner module to determine the category of query samples by comparing the relation scores between the query dataset and support dataset, thus implementing the classification of fault categories. Experiments are conducted on three public datasets (TE, PU and CWRU), and the experimental results show that the proposed method outperforms other benchmark few-shot learning methods in terms of accuracy and exhibits remarkable robustness and adaptability in fault diagnosis. [ABSTRACT FROM AUTHOR]

Deep learning models have demonstrated substantial progress in medical image segmentation. However, these models require large datasets for training, which can prove to be clinically difficult. Medical imaging datasets exhibit domain shift problems due to different imaging techniques, scanners, and data privacy issues and, conventional deep neural networks lack generalization capabilities, as their effectiveness decreases with different data distributions. This paper presents a deep learning-based attention-adaptive instance normalization style transfer technique to address the challenges encountered when segmenting blood vessels. The proposed methodology combines adaptive instance normalization style transfer with a dense extreme inception network and convolution block attention module to achieve the best observed vessel segmentation performance. A simple yet effective method is proposed, and it improves the generalization performance of deep neural networks in vascular segmentation. The network is trained on natural images and tested on medical images, thereby overcoming the need for a large dataset or labelled ground truth to train for vessel segmentation. The proposed technique uses experimental results from five distinct medical datasets to demonstrate higher cross-domain generalization capabilities than the state-of-the-art baselines available in the current literature, and the segmentation performance is compared qualitatively and quantitatively with other models. The results demonstrate the feasibility of generalizing our approach to various datasets. This approach overcomes the constraints of traditional deep learning algorithms, which require enormous volumes of medical data along with manually-labelled ground truth. The predictions by the proposed approach are based on natural image training and can be reliably used to detect and identify cardiac and retinal abnormalities without prior medical imaging information. [ABSTRACT FROM AUTHOR]

Endoscopic ultrasound (EUS) has emerged as a pivotal tool for the screening and diagnosis of submucosal tumors (SMTs). However, the inherently low-quality and highly variable image content presents substantial obstacles to the automation of SMT diagnosis. Deep learning, with its adaptive feature extraction capabilities, offers a potential solution, yet its implementation often requires a vast quantity of high-quality data - a challenging prerequisite in clinical settings. To address this conundrum, this paper proposes a novel data-efficient visual analytics method that integrates human feedback into the model lifecycle, thereby augmenting the practical utility of data. The methodology leverages a two-stage deep learning algorithm, which encompasses self-supervised pre-training and an attention-based network. Comprehensive experimental validation reveals that the proposed approach facilitates the model in deciphering the hierarchical structure information within high-noise EUS images. Moreover, when allied with human-machine interaction, it enhances data utilization, thereby elevating the accuracy and reliability of diagnostic outcomes. The code is available at https://github.com/Zehebi29/LA-RANet.git. [ABSTRACT FROM AUTHOR]

Enhancing IoT security is a corner stone for building trust in its technology and driving its growth. Limited resources and diversified nature of IoT devices make them vulnerable to attacks. Botnet attacks compromise the IoT systems and can pose significant security challenges. Numerous investigations have utilized machine learning and deep learning techniques to identify botnet attacks in IoT. However, achieving high detection accuracy with reasonable computational requirements is still a challenging research considering the particularity of IoT. This paper aims to analytically study the performance of the tree based machine learning in detecting botnet attacks for IoT ecosystems. Through an empirical study performed on a public botnet dataset of IoT environment, basic decision tree algorithm in addition to ensemble learning of different bagging and boosting algorithms are compared. The comparison covers two perspectives: IoT botnet detection capability and computational performance. Results demonstrated that the significant potential for the tree based ML algorithms in detecting network intrusions in IoT environments. The RF algorithm achieved the best performance for multi-class classification with accuracy rate of 0.999991. It achieved also the highest results in all other measures. [ABSTRACT FROM AUTHOR]

Broad Learning System (BLS) is proposed as an alternative to deep learning. It has a fast adaptive model selection and online incremental learning capability, which has been successfully applied in many fields. In this paper, the BLS model is introduced into intrusion detection, and considering the weakness of the BLS model in mining the internal structural information of samples, this paper proposes a Manifold Regularized Broad Learning System based on LU decomposition (LU-MRBLS) intrusion detection. Based on the manifold hypothesis, the LU-MRBLS model firstly constructs the graph Laplacian operator in the data input space to mine the potential information of the data. Then, under the manifold regularized framework, the feature nodes, enhancement nodes, and Laplacian matrix are combined to construct the objective function to regularize and optimize the BLS model to avoid the model falling into local optimization. Finally, the LU decomposition method is used to solve the output weight matrix of the MRBLS model, shorten the training time of the MRBLS model, avoid singular value problems of the solution process, and improve the intrusion detection performance of the model. In this paper, we use the KDD Cup99 dataset for parameter selection and apply it to other network models. Through rigorous experiments, the LU-MRBLS model is applied to KDD Cup99, NSL-KDD, UNSW-NB15, and CIDDS-001 datasets with better detection results than the classical machine learning models and the latest intrusion detection models. [ABSTRACT FROM AUTHOR]

Since 2007, methods that utilize side-channel data to detect hardware Trojan (HT) problems have been widely studied. Machine learning methods are widely used for hardware Trojan detection, but with the development of integrated circuits (ICs), better results are usually obtained using deep learning methods. In this paper, we propose an architecture inspired by Residual-Block and Dense-Block and combine it with SE Attention Mechanism, which we named the Res-Dense-SE-Net network. By combining residual connectivity, dense connectivity, and attention mechanism, the Res-Dense-SE-Net network can enjoy the advantages of these three network architectures at the same time, which can improve the expressiveness and performance of the model. The Res-Dense-SE-Net network can capture the key features in the image better, and it can solve the problems of gradient vanishing and feature transfer efficiently, which can in turn improve the classification accuracy and the generalization ability of the model. Based on the publicly available AES series of hardware Trojans from TrustHub and the publicly available hardware Trojan-side channel data by Faezi et al., we evaluate the effectiveness of the method proposed in this paper. The experimental results show that when a single Trojan exists, the method proposed in this paper has a high accuracy rate; and when multiple types of hardware Trojans exist at the same time and need to be categorized, the categories of hardware Trojans can also be effectively identified, and the categorization accuracy is high compared with the existing deep learning methods. [ABSTRACT FROM AUTHOR]

Work-related musculoskeletal disorders are a very impactful problem, both socially and economically, in the manufacturing sector. To control their effect, standardised methods and technologies for ergonomic assessment have been developed. The main technologies used are inertial sensors and vision-based systems. The former are accurate and reliable, but invasive and not affordable for many companies. The latter use machine learning algorithms to detect human pose and assess ergonomic risks. In this paper, using data collecting by reproducing the working environment in LUBE, the major Italian kitchen manufacturer, we propose SPECTRE (Sensor-independent Parallel dEep ConvoluTional leaRning nEtwork): a fully sensor-independent learning model based on convolutional networks to classify postures in the workplace. This system assesses ergonomic risks in major body segments through Deep Learning with a minimal impact. SPECTRE's performance is evaluated using established metrics for imbalanced data (precision, recall, F1-score and area under the precision-recall curve). Overall, SPECTRE shows good performance and, thanks to an agnostic explainable machine learning method, is able to extrapolate which patterns are significant in the input. [ABSTRACT FROM AUTHOR]

The problem that I present in this paper concerns the issue of ethical evaluation of algorithms, especially those used in social media and which create profiles of users of these media and new technologies that have recently emerged and are intended to change the functioning of technologies used in data management. Systems such as Overton, SambaNova or Snorkel were created to help engineers create data management models, but they are based on different assumptions than the previous approach in machine learning and deep learning. There is a need to analyze both deep learning algorithms and new technologies in database management in terms of their actions towards a person who leaves their digital footprints, on which these technologies work. Then, the possibilities of applying the existing deep learning technology and new Big Data systems in the economy will be shown. The opportunities offered by the systems mentioned above seem to be promising for many companies and—if implemented on a larger scale—they will affect the functioning of the free market. [ABSTRACT FROM AUTHOR]

Existing research shows that cooperative multi-agent deep reinforcement learning (c-MADRL) is vulnerable to adversarial attacks, and c-MADRL is increasingly being applied to safety-critical domains. However, the robustness of c-MADRL against adversarial attacks has not been fully studied. In the setting of c-MADRL, unlike the single-agent scenario, an adversary can attack multiple agents or all agents at each time step, but the attacker needs more computation to generate adversarial examples and will be more easily detected. Therefore, how the attacker chooses one or several agents instead of all agents to attack is a significant issue in the setting of c-MADRL. Aiming to address this issue, this paper proposes a novel adversarial attack approach, which dynamically groups the agents according to relevant features and selects a group to attack based on the group's contribution to the overall reward, thus effectively reducing the cost and number of attacks, as well as improving attack efficiency and decreasing the chance of attackers being detected. Moreover, we exploit the transferability of adversarial examples to greatly reduce the computational cost of generating adversarial examples. Our method is tested in multi-agent particle environments (MPE) and in StarCraft II. Experimental results demonstrate that our proposed method can effectively degrade the performance of multi-agent deep reinforcement learning algorithms with fewer attacks and lower computational costs. [ABSTRACT FROM AUTHOR]

Policymaking and administration of national tactics of action for food security rely heavily on advances in models for accurate estimation of food output. In several fields, including food science and engineering, machine learning (ML) has been established to be an effective tool for data investigation and modelling. There has been a rise in recent years in the application of ML models to the tracking and forecasting of food safety. In our analysis, we focused on two sources of food production: livestock production and agricultural production. Livestock production was measured in terms of yield, number of animals, and sum of animals slaughtered; crop output was measured in terms of yields and losses. An innovative hybrid deep learning model is proposed in this paper by fusing a Dense Convolutional Network (DenseNet) with a Long Short-Term Memory (LSTM) to do production analysis. The hybridised algorithm, or A-ROA for short, combines the Arithmetic Optimisation Algorithm (AOA) and the Rider Optimisation Algorithm (ROA) to determine the ideal weight of the LSTM. The current investigation focuses on Iran as a case study. Therefore, we have collected FAOSTAT time series data on livestock and farming outputs in Iran from 1961 to 2017. Findings from this study can help policymakers plan for future generations' food safety and supply by providing a model to anticipate the upcoming food construction. [ABSTRACT FROM AUTHOR]