Search

The fault management process is facilitated by equipping power distribution systems with automated devices, especially remote-controlled switches (RCSs). Although RCS plays a key role in improving the system's reliability, it imposes significant investment, installation, and maintenance costs. Hence, RCSs should be optimally located in distribution feeders for the highest profit. In previous works, reliability-oriented mathematical optimization models have been formulated to reach this goal. However, the number of test solutions exponentially grows with the problem size to find the globally optimal solution. This paper uses machine learning to propose a scalable and easy-to-implement model for optimal switch placement in real power distribution systems. At first, the features of candidate points for installing RCSs are introduced. Then, a learning model is applied to deeply explore the relationship between these features and optimal locations for installing RCSs. After training, the learning-based surrogate model directly determines the optimal RCS placement strategy in real power distribution systems by leveraging knowledge gained from past experiences. Simulation results demonstrate that the proposed surrogate model is approximately 29 times faster than the integer programming-based mathematical model, without a significant loss of accuracy, when implemented on a modified 11 kV network connected to Bus 4 of the Roy Billiton test system. This paper also employs explainable artificial intelligence (XAI) tools to select the most important features, where the Hamming loss is decreased by approximately 5%. [ABSTRACT FROM AUTHOR]

The aging of transformer oil–paper insulation (OPI) contributes significantly to transformer failure and reduced service life. Therefore, reliable and precise evaluation of the aging status of transformer insulation condition is crucial in averting transformer failure. This article proposes a novel deep learning-based aging condition assessment technique of transformers by combining FDS (Frequency domain spectroscopy) and squeeze-and-excitation-enabled convolutional neural network (SE-CNN). An intrinsic product-based transformation using a Gramian angular field is employed to dimensionally expand the 1-D FDS signals acquired from OPI samples into 2D images. Each feature extraction channel in the SE-CNN-based aging diagnosis framework is assigned a specific weight, enabling the model to concentrate on the most relevant features while discarding the rest. Furthermore, the effect of moisture variation on the model is also considered under three different conditions to ensure the consequence of compensation for the effect of moisture on FDS. A comparison with traditional machine learning models has also been made to ensure the viability of the proposed methodology. Additionally, the model is interpreted by creating explanation weight plots of the feature coefficients using a local interpretable model-agnostic explanations (LIME) method in Python. The findings demonstrate that the novel aging diagnosis framework visually assesses the transformer's OPI system with the highest accuracy of 99.12% in the test set. Furthermore, it facilitates the automatic extraction of deep aging features, thus providing better generalization and convergence capability. [ABSTRACT FROM AUTHOR]

Audio classification and source separation are two important components in the music industry and for audio engineering as well. The Indian classical music industry is filled with a lot of similar-sounding instruments. The application of these in the field of music composition, audio signal processing and voice recognition can be a huge boon for the music industry. This research paper proposes an improvised method for audio source separation followed by a novel method for classification of the separated sources using a unique as well as novel dataset consisting of classical Indian musical instruments. The method entails decoupling the conglomerate of audio signals and categorising the resulting sources according to their unique traits using Indian Musical Instrument Classification models, CNN (Convolutional Neural Networks) and SVM (Support Vector Machine) models. The proposed novel dataset Indian Musical Instrument Dataset(IMID) is an important contribution to the area because there are not any unique organised datasets for classical Indian instruments. The IMIDataset includes ten Indian instruments — Flute, Veena, Sitar, Sarod, Tabla, Violin, Guitar, Piano, Bass and Drums. To evaluate and compare the efficacy of the proposed model, comparison was made with the different datasets based on their accuracy and loss metrics. Link to the dataset. [ABSTRACT FROM AUTHOR]

Longitudinal impulse, as a common dynamic problem of heavy haul trains, could induce the lateral instability of the coupler and the separation of the locomotive and wagon connection and thus seriously hinder the train running safety. The coupler force undergoes complex changes during longitudinal impulse transmission and exhibits strong nonlinear characteristics, which poses significant challenges to the identification of the coupler force. To address these issues, this paper reports a novel quantitative method for the coupler force identification of heavy haul locomotives. Firstly, the moving average filtering method is used to preprocess the signal of longitudinal relative displacement between the coupler and carbody (LRDCC), and the approximate relative velocity (ARV) feature is also extracted from the preprocessed signal. Then, a Convolutional Neural Network (CNN) model is constructed to extract high-level features from LRDCC and ARV. The model with randomly initialized weight parameters does not require additional training and thus reduces the computational cost. Finally, an Extreme Learning Machine (ELM) is used as the regression layer to process the extracted high-level features and further improve the identification performance. Additionally, the dung beetle algorithm is used to obtain the optimal model parameters to improve the coupler force identification performance. Not only a dynamics simulation but a field test is carried out to show that the proposed method could accurately detect the coupler force of heavy haul locomotives. Furthermore, the proposed method shows promising prospects in replacing the traditional monitoring method under the actual long-term working conditions of trains. • An indirect measurement scheme is proposed for coupler force dynamic identification. • The proposed network model presents high identification Accuracy and efficiency. • Method showcases strong generalization under complex, long-term train operations. [ABSTRACT FROM AUTHOR]

In the face of uncontrolled offensive content on social media, automated detection emerges as a critical need. This paper tackles this challenge by proposing a novel approach for identifying offensive language in multilingual, code-mixed, and script-mixed settings. The study presents a novel multilingual hybrid dataset constructed by merging diverse monolingual and bilingual resources. Further, we systematically evaluate the impact of input representations (Word2Vec, Global Vectors for Word Representation (or GloVe), Bidirectional Encoder Representations from Transformers (or BERT), and uniform initialization) and deep learning models (Convolutional Neural Network (or CNN), Bidirectional Long Short Term Memory (or Bi-LSTM), Bi-LSTM-Attention, and fine-tuned BERT) on detection accuracy. Our comprehensive experiments on a dataset of 42,560 social media comments from five languages (English, Hindi, German, Tamil, and Malayalam) reveal the superiority of fine-tuned BERT. Notably, it achieves a macro average F 1 -score of 0.79 for monolingual tasks and an impressive 0.86 for code-mixed and script-mixed tasks. These findings significantly advance offensive language detection methodologies and shed light on the complex dynamics of multilingual social media, paving the way for more inclusive and safer online communities. [ABSTRACT FROM AUTHOR]

In the face of uncontrolled offensive content on social media, automated detection emerges as a critical need. This paper tackles this challenge by proposing a novel approach for identifying offensive language in multilingual, code-mixed, and script-mixed settings. The study presents a novel multilingual hybrid dataset constructed by merging diverse monolingual and bilingual resources. Further, we systematically evaluate the impact of input representations (Word2Vec, Global Vectors for Word Representation (or GloVe), Bidirectional Encoder Representations from Transformers (or BERT), and uniform initialization) and deep learning models (Convolutional Neural Network (or CNN), Bidirectional Long Short Term Memory (or Bi-LSTM), Bi-LSTM-Attention, and fine-tuned BERT) on detection accuracy. Our comprehensive experiments on a dataset of 42,560 social media comments from five languages (English, Hindi, German, Tamil, and Malayalam) reveal the superiority of fine-tuned BERT. Notably, it achieves a macro average F 1 -score of 0.79 for monolingual tasks and an impressive 0.86 for code-mixed and script-mixed tasks. These findings significantly advance offensive language detection methodologies and shed light on the complex dynamics of multilingual social media, paving the way for more inclusive and safer online communities. [ABSTRACT FROM AUTHOR]

This paper for the first time treats the interpretation of electrochemical noise time-frequency spectra as an image classification problem. It investigates the application of a convolutional neural network (CNN) for deep learning image classification of electrochemical noise time-frequency transient information. Representative slices of these spectra were selected by our transient analysis technique and served as input images for the CNN. Corrosion data from two types of pitting corrosion processes serve as test cases: AISI304 and AA2024-T3 immersed in a 0.01M HCl and 0.1M NaCl solution between 0 and 1ks after immersion, respectively. Continuous wavelet transform (CWT) spectra and modulus maxima (MM) are used to train the CNN, either individually or in a combined form. The classification accuracy of the CNN trained with the combined dataset is 0.97 and with the two individual datasets 0.72 (only CWT spectrum) and 0.84 (only MM). The ability to additionally classify a more progressed form of pitting corrosion of AA2024-T3 between 9 and 10ks after immersion indicates that the proposed method is sufficiently robust using combined datasets with CWT spectra and MM. The pitting processes can effectively be detected and classified by the proposed method. The most important contribution of the present work is to introduce a novel procedure that decreases the classical need for large amounts of raw data for training and validation purposes, while still achieving a satisfactory classification robustness. A relatively small number of individual signals thereby generates a multitude of input images that still contain all relevant kinetic information about the underlying chemo-physical process. [Display omitted] • Electrochemical noise interpretation is treated as an image classification problem. • Continuous wavelet transform spectra are divided into single transient spectra. • A small number of individual signals generates a multitude of input images. • Amount of raw data needed for training the convolutional neural network is reduced. • Modulus maxima increase the classification accuracy of pitting corrosion. [ABSTRACT FROM AUTHOR]

The high-power direct current (DC) charging method for electric vehicles (EVs) can easily lead to overheating during the charging process, potentially resulting in thermal runaway accidents. Addressing this safety issue, accurately and reliably predicting and providing multi-level warnings for thermal accidents during the charging of EVs becomes an urgent problem to be solved. Therefore, this paper proposes the construction of a composite prediction model called QCNB (Q learning- CNN- BiNLSTM- BiGRU) by incorporating Convolutional Neural Networks (CNN), Bidirectional Nested Long Short-Term Memory Networks (BiNLSTM), Bidirectional Gated Recurrent Units (BiGRU), and Q learning algorithm. First, taking into account the influence of ambient temperature, three sets of charging historical data from spring/autumn, summer, and winter are selected for model training. Second, the sliding window analysis method is employed to establish the multi-level warning thresholds and rules using the historical charging data, enabling safety multi-level warnings. Lastly, the effectiveness of the QCNB model is validated using actual operating data from EVs. The experimental results demonstrate that the QCNB's prediction accuracy outperforms other models, and the abnormal characteristics of temperature and voltage can be used to identify the charging thermal runaway accident in advance and adopt the multi-level warning for effective protection. This achievement emphasizes the importance of employing a combination of predictive models to address the complex characteristics of charging data and implementing multi-level warnings for protection. It effectively mitigates the occurrence of thermal accidents, offering promising possibilities for practical applications. [ABSTRACT FROM AUTHOR]

Implementing key engineering solutions to optimise the operation of energy industries requires daily electricity demand forecasting and including uncertainty, to promote markets insight analysis as part of their strategic planning, regulating and supplying electricity to consumers. This paper proposes hybrid artificial intelligence models combining convolutional neural networks (CNN) as a feature extraction algorithm with extreme learning machines (ELM) as a framework to predict electricity demand with confidence intervals generated by Kernel Density Estimation (KDE) approaches. In order to develop CELM-KDE model, time-lagged series of daily electricity demand with local climate variables based on the air temperature, atmospheric vapour pressure, evaporation, solar radiation, humidity and sea level pressures are used to train the proposed CELM-KDE hybrid model. In order to fully evaluate the newly developed model from a point-based, as well as a probabilistic prediction strategy, the observed and predicted electricity demand as well as the probability distribution of errors are analysed using KDE method that operates without prior data distribution assumptions. Based on observed and predicted electricity demand and the relevant probabilistic confidence intervals generated by the CELM-KDE model, the final results show that the proposed method attains significantly better probability interval predictions than traditionally-used point-based models. The proposed CELM-KDE model is demonstrated to be highly effective in providing a comprehensive coverage of predicted errors, as well as providing greater insights into the average bandwidth and detailed predicted electricity demand in the testing stage. The results also indicate that the proposed hybrid model is a reliable decision support tool to develop engineering solutions in area of energy modelling, monitoring and forecasting, which could potentially be useful to the industry policymakers. We show that the point-and probabilistic-based electricity demand predictive models can be employed as an effective tool to improve accuracy of forecasting and provision of insights for national electricity markets and key energy industry stakeholder application tools. [Display omitted] • A hybrid deep learning model for daily electricity demand prediction is proposed. • A Kernel Density Estimation is applied to derive probabilistic prediction intervals. • The algorithm quantifies uncertainties in point-based electricity demand predictions. • The proposed model outperforms deep learning models using statistical uncertainty indicators. [ABSTRACT FROM AUTHOR]

Understanding thermal dynamics and obtaining the computational model of residential buildings enable its scaled application in energy retrofits, control optimization and decarbonization. In this paper, we present a deep learning approach to model building thermal dynamics with smart thermostat data collected from residential buildings, with the goal to investigate model generalizability. In the first stage, we developed and compared different Deep Learning architectures including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) models and CNN-LSTM to predict indoor air temperature in a multi-step time horizon. In the second stage, we implemented a Transfer Learning (TL) process, which aims to improve the prediction performance on a new set of buildings (targets), exploiting the knowledge of related or similar buildings (sources). Different TL strategies and source model identification methods were investigated. The study showed that the CNN-LSTM performed the best among the architectures compared, with an average Mean Absolute Error (MAE) of 0.26 °C for one-hour-ahead (twelve 5-min future steps) predictions. Furthermore, the results showed that freezing the LSTM layer and fine-tuning the other layers of the CNN-LSTM achieved the best performance among four TL strategies, which further improved the performance with respect to a machine learning approach by 10%, and proving the effectiveness and generalizability of the proposed approach. A comparison of three different source model identification methods showed that randomly selecting source models constrained by similar building characteristics can provide good TL performance while retaining simplicity comparing with other quantitative source identification methods. • Investigated deep transfer learning techniques for residential thermal dynamics using smart thermostat data. • Compared diverse neural network architectures for indoor temperature prediction. • Explored transfer learning to enhance model accuracy. • Evaluated four transfer learning methods and three source model identification approaches. • Achieved high accuracy and generalizability with the proposed deep transfer learning approach. [ABSTRACT FROM AUTHOR]

Traditional machine learning methods require the assumption that training and test data are drawn from the same distribution, which proves challenging in real-world applications. Moreover, deep learning models require a substantial amount of labeled data for training in classification tasks and limited samples may lead to overfitting. In many real-world scenarios, there is an insufficient supply of labeled samples within the target domain for learning. Transfer learning offers an effective solution, allowing knowledge from a source domain to be transferred to a target domain. Additionally, data augmentation enhances model generalization by increasing data samples, particularly beneficial when dealing with limited target domain data. In this paper, we synergistically enhance the model's performance on classification tasks by integrating transfer learning techniques with a data augmentation strategy. By conducting numerous experiments across various datasets, we verified the effectiveness of our proposed approach. [ABSTRACT FROM AUTHOR]

Sensors of an aircraft engine have the problems of multiple kinds of faults and difficulty to diagnose. Moreover, the diagnosis performance cannot meet practical demands. Therefore, this paper proposes a novel approach for sensor fault diagnosis integrating the advantages of selective ensemble learning, siamese convolutional neural network (SCNN), and Bayesian interval estimation (BIE). The Bayesian interval estimation with hypothesis testing is developed with real-time data update to reduce the confidence interval. The attention mechanism is introduced to enhance fault diagnosis performance. Moreover, ensemble selection learning with Akaike information criteria is proposed to obtain optimal SCNNs. The theorems of convergence and optimal confidence data in ensemble learning are proven. Furthermore, this paper develops a novel improved learning algorithm based on AdaMod (Adaptive and momental bound method) and SGD (stochastic gradient descent), and achieves a new fault diagnosis algorithm to improve the diagnosis performance. The sensor data of aircraft engines from China Eastern Airlines is adopted for validation and experimental results show that proposed approach reaches an excellent tradeoff between sensor diagnosis performance, confidence interval, and runtime. The ablation studies are performed to analyze the role of leaner's components. The proposed method improves training accuracy by 6.2%, fault diagnosis performance by 5.1%, fault prediction mean result by 4.6%, and fault prediction variance is reduced by 38.1% than the state-of-the-art methods. • A novel diagnosis approach combining selective ensemble SCNN and Bayesian interval estimation (BIE) is proposed. • The Bayesian interval estimation method with hypothesis testing is developed to support better fault diagnosis with data update. • The theorems of convergence and optimal confidence are proved. • The improved learning algorithm based on AdaMod and SGD is developed. • A novel algorithm is adopted for diagnosing sensor faults of aircraft engine to improve the diagnosis performance. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has experienced phenomenal expansion over the past few years and has emerged as one of the most dynamic sectors of the international market. Android has become the driving force behind the rapid development of the IoT, and malware is one of the most severe concerns. Android is an open-source platform with a significant number of users. The identification of Android malware has become more critical in cybersecurity due to the meteoric rise of Android malware over the past few years and the severity of the damage it inflicts on smartphone users. Existing traditional Android malware detection methods based on machine learning have achieved encouraging performance. Still, the solution requires a massive workforce of feature engineering to build dynamic or static features and continuous learning through pre-extracted features to maintain high performance in identifying malware. Therefore, technologies for end-to-end malware detection without human interaction are necessary. In response to the rapid evolution of Android malware, a convolutional neural network that can acquire knowledge without requiring feature extraction is ideally suited. This paper offers a unique classification approach for malware based on a convolutional neural network, with feature extraction selected from the current pre-trained models DenseNet169, Xception, InceptionV3, ResNet50, and VGG16. The proposed methods have an advantage over existing detection methods due to their end-to-end learning process. Our suggested approaches convert Android APK files to binary codes and RGB images for usage as inputs to deep learning models. These models are trained and evaluated using the CICInvesAndMal2019 dataset, which consists of 333 benign and 428 malicious applications. Experiments demonstrate that the proposed approaches achieve a classification accuracy of 95.24%, 95.24%, and 95.83% for DenseNet169, InceptionV3, and VGG16, respectively, on a 761-sample dataset of malware, which is superior to other compared algorithms. Compared to previous methods, our suggested methods are more applicable to Android IoT devices since they do not require manual feature engineering and consume fewer resources. [ABSTRACT FROM AUTHOR]

Ship classification based on machine learning (ML) has proven to be a significant underwater acoustic research direction. One of the critical challenges rests with how to embed domain signal knowledge into ML models to obtain suitable features that highly correlate with the classification and create better predictors. In this paper, a novel ML-based ship classification model, Hierarchical Underwater Acoustic Transformer (HUAT), is proposed to improve the classification performance. Firstly, the Detection of Envelope Modulation on Noise (DEMON) spectra of ship-radiated noise signals are estimated by cyclostationary analysis. The motivation for using a DEMON-based preprocessing scheme is that valuable propeller information can be revealed by exploiting the second-order cyclostationarity of ship-radiated noise signals. Secondly, the useful features of DEMON spectra are enhanced using a multi-head self-attention module, and the potential features of the Mel spectrograms are extracted employing a Convolutional Neural Network (CNN) module. The two kinds of features are fused to provide ship classification patterns. The challenge of feature learning in the deep classification model is reduced by leveraging domain-related classification knowledge. Finally, the Swin Transformer, based on shifted window self-attention mechanism, is used to learn high-level feature representations and conduct ship classification. Experimental results show that the HUAT model achieves excellent classification performance on ship-radiated noise datasets, ShipsEar and DeepShip. And its classification efficiency is better than the model based on traditional Transformer architecture. In addition, the proposed method provides technical support for the underwater intelligent system capable of automatically sensing sailing vessels and recognizing vessel types. • The Detection of Envelope Modulation on Noise (DEMON) spectra of ship-radiated noise signals are estimated by cyclostationary analysis. • A novel feature fusion strategy is proposed for embedding domain signal knowledge into ML models to obtain suitable features highly correlated with the classification. • The valuable features of DEMON spectra and the Mel spectrogram of ship signals are extracted using two different feature extractors. • The Swin Transformer is used to learn high-level feature representations and conduct ship classification. [ABSTRACT FROM AUTHOR]

One of the most important features of a reliable power system is its capability to supply the demand continuously. This continuous supply has been maintained by the transient stability of the system against large disturbances. The study of this type of stability is examined through different indicators. One of the common indicators to evaluate the transient stability of the power system is the well-known Critical Clearing Time (CCT) index. Conventional methods for calculating CCT have presented good accuracy, however, their computational cost is very high which makes them not suitable for real-time applications and real large-scale networks. Considering their ability to feature extraction of big data, deep neural networks can be utilized as reliable tools to cover these deficiencies. In this regard, to cover the shortcomings of the conventional methods, this paper proposes a method based on deep Convolutional Neural Networks (CNN) to estimate the CCT index in real-time power system applications. Moreover, to analyze a realistic case, nonlinear limiters of the excitation systems which have a considerable effect on transient stability index are considered in this study. Thanks to the using of several deep layers and the comprehensive established database, the accuracy of proposed method is appropriately high. Numerical studies on IEEE standard networks as well as a real case in Iran Power Grid (IPG) represents the advantages of the proposed method. • A deep-learning-based convolutional neural network is designed to estimate CCT index of power system. • Nonlinear limiters of the excitation system are taken into account. • A real case study in Iran grid is considered for simulation. • As a result, the transient stability of system is accurately determined in on-line manner. [ABSTRACT FROM AUTHOR]

Parkinson's disease consists in the degeneration of the mesencephalic black substance, affecting the dopaminergic vias. Its causes are varied, including exposure to pesticides, genetic factors and, one of the most influential ones, age. Given the decrease in dopamine levels, the most common symptoms are the appearance of tremors and muscle rigidity. Due to the rigidity of the muscles, the patient has voice alterations which have great potential for non-invasive and early diagnosis of the disease. In addition, considering the low cost of the sound recorder respect to the clinical studies, this approach allows the diagnosis of Parkinson's disease in a large number of people. Recent works, which present the analysis of voice recordings through Convolutional Neural Networks, show high level of accuracy in the diagnosis of Parkinson's disease. Convolutional Neural Networks use a Multilayer Neural Network to classify convolutional feature vectors. In order to improve the training time of the classifier, in this paper the use Extreme Learning Machines are proposed. Experiments considering 4 types of spectrograms with AlexNet, VGG-16, SqueezeNet, Inception V3 and ResNet-50 Convolutional Neural Networks models. In the experiments, hit rate, training and testing time, sensitivity and the specificity indicators of all the neural architectures involved in the work are objectively compared. It is shown that the Extreme Learning Machine have a high level of accuracy in the diagnosis of Parkinson's disease but with reduced training time. [ABSTRACT FROM AUTHOR]

Finding the best toolpath planning strategy for Computer Numerical Control (CNC) machining requires a trial-and-error approach. One needs to follow a number of steps: generating the toolpath, performing simulations/machining, measuring various parameters to quantify the quality of the toolpath, and then selecting the best toolpath. This conventional iterative approach is time-consuming and often error-prone, which is a bottleneck in the current CNC machining industry. This paper presents a novel framework to create a machine learning based system for choosing the best toolpath planning strategy for CNC machining (finishing) of complex freeform surfaces directly from the CAD model. Three tool path planning strategies are considered: Adaptive planar, Iso-scallop, and Hybrid. At first, a novel toolpath analysis module is presented to evaluate the quality of the toolpath considering three performance parameters: surface finish, toolpath length, and smoothness. This quality measurement technique is extensively tested for robustness and accuracy. It is then used to analyze and label a large number of CAD models to create a dataset for supervised learning. Finally, a Convolutional Neural Network (CNN) is designed and trained using this dataset to predict the best toolpath planning strategy. Compared to the conventional approaches, the developed system uses multiple performance parameters and chooses the best strategy directly from the CAD model. Results show that the proposed data-driven model achieved 96.8% test accuracy. [ABSTRACT FROM AUTHOR]

Attention mechanism, one of the most extensively utilized components in computer vision, can assist neural networks in emphasizing significant elements and suppressing irrelevant ones. However, the vast majority of channel attention mechanisms only contain channel feature information and ignore spatial feature information, resulting in poor model representation effect or object detection performance, and the spatial attention modules were often complex and expensive. In order to strike a balance between performance and complexity, this paper proposes a lightweight Mixed Local Channel Attention (MLCA) module to improve the performance of the object detection network, and it can simultaneously incorporate both channel information and spatial information, as well as local information and global information to improve the expression effect of the network. On this basis, the MobileNet-Attention-YOLO(MAY) algorithm for comparing the performance of various attention modules is presented. On the Pascal VOC and SMID datasets, MLCA achieves a better balance between model representation efficacy, performance, and complexity than alternative attention techniques. Against the Squeeze-and-Excitation(SE) attention mechanism on the PASCAL VOC dataset and the Coordinate Attention(CA) method on the SIMD dataset, the mAP is enhanced by 1.0 % and 1.5 %, respectively. [Display omitted] • Proposed a lightweight Mixed Local Channel Attention (MLCA) method. • Proposed a new object detection network called MobileNet-Attention-YOLO (MAY). • Verified the feasibility and effectiveness of MLCA and MAY. [ABSTRACT FROM AUTHOR]

Pulse repetition interval modulation (PRIM) recognition is a critical task in electronic intelligence (ELINT) and electronic support measure (ESM) systems for detecting radar threats accurately. However, PRI recognition is a complex issue due to missing and spurious pulses, resulting in noisy PRI pattern changes in real environments. To address this problem, this paper proposes a novel approach that recognizes the five common types of PRIM through a four-phase process. In the first phase, a deep convolutional neural network (DCNN) is used as a feature extractor. Then, extreme learning machines (ELMs) are used for real-time recognition of the PRIM patterns in the second phase. In the third phase, we employ the biogeography-based optimizer (BBO) to enhance the network's robustness by optimizing the connection weights and biases. To address the increasing complexity of the model, we introduce an optimized variable-length internet protocol-based BBO (VBBO) in the fourth phase. In this approach (i.e., DCNN-VBBO-ELM), each layer of DCNN is encoded by an IP address into a habitat of VBBO in the same sequence as the DCNN layers. To evaluate the proposed method, we develop a real experimental dataset consisting of five common PRI patterns. Our approach achieves a final accuracy of 97.05%, which is better than other ELM-based benchmark models. Moreover, the proposed model requires only 27 s of training time to process 50,000 training images, confirming its real-time capabilities. In conclusion, our proposed approach improves PRI recognition by leveraging DCNN, ELM, and VBBO, resulting in a more accurate and robust real-time radar PRI classifier. [ABSTRACT FROM AUTHOR]

Automatic seismic phase detection and phase arrival time picking are always fundamental tasks in seismology. With the emergence of machine learning, and deep learning in particular, a number of neural network architectures are being used to explore the correlations between seismic waveforms and hidden information of interest. In this paper, we present a sequential attention (SEA) module that can learn both local and long-distance corrections to effectively extract sequential features. This module is lightweight and plug-in-play. Based on the SEA module, a fully convolutional neural network with sequential attention mechanism was constructed to detect seismic events and determine the arrival time of phases. Further experiments on STEAD dataset, in comparison with existing methods, show that our proposed model outperforms other algorithms with a higher F1-score (100% for seismic detection, 98.8% for P arrival picking, and 89.0% for S arrival picking) and fewer residual errors. Comparatively, our model has a quarter of the model parameters and computational complexity as well as a 36.7% reduction in processing time compared to the current state-of-the-art method. This demonstrates that the proposed architecture is effective for seismic sequential learning tasks and, as a result, can serve as an improved alternative backbone. [ABSTRACT FROM AUTHOR]

Anomaly detection of train wheels helps railway operators to find wheel defects and save cost by enabling condition-based maintenance. Existing approaches focus on applications on freight trains and use supervised data-driven methods which need substantial volume of fault data. This is often unavailable in passenger railways that normally provide reliable services. In this regard, this paper reports an unsupervised data-driven approach for anomaly detection of passenger train wheels. Particularly, short-time Fourier transform (STFT) is used to extract time–frequency features from the vibration signal collected with a pair of fiber Bragg grating (FBG) sensors during normal operating hours. Then, four common unsupervised learning algorithms, namely, non-negative matrix factorization (NMF), one-class support vector machine (OC-SVM), multilayer perceptron autoencoder (MLP-AE), and convolutional neural network autoencoder (CNN-AE), are used to derive five health indexes for monitoring the health condition of the train wheels. The proposed workflow is tested against a dataset complied with respect to the wheel turning record. Our results show that the health indexes obtained from the proposed workflow lead to improved correlation with the condition of train wheels compared with existing health metric. In addition, comparison of the four learning algorithms indicates that NMF and MLP-AE outperformed OC-SVM and CNN-AE. [Display omitted] [ABSTRACT FROM AUTHOR]

Malware detection approaches can be classified into two classes, including static analysis and dynamic analysis. Conventional approaches of the two classes have their respective advantages and disadvantages. For example, static analysis is faster but cannot detect the malware variants generated through code obfuscation, whereas dynamic analysis can effectively detect variants generated through code obfuscation but is slower and requires intensive resources. This paper proposes a novel deep learning-based approach for malware detection. It delivers better performance than conventional approaches by combining static and dynamic analysis advantages. First, it visualises a portable executable (PE) file as a coloured image. Second, it extracts deep features from the colour image using fine-tuned deep learning model. Third, it detects malware based on the deep features using support vector machines (SVM). The proposed method combines deep learning with machine learning and eliminates the need for intensive feature engineering tasks and domain knowledge. The proposed approach is scalable, cost-effective, and efficient. The detection effectiveness of the proposed method is validated through 12 machine learning models and 15 deep learning models. The generalisability of the proposed framework is validated on various benchmark datasets. The proposed approach outperformed with an accuracy of 99.06% on the Malimg dataset. The Wilcoxon signed-rank test is used to show the statistical significance of the proposed framework. The detailed experimental results demonstrate the superiority of the proposed method over the other state-of-the-art approaches, with an average increase in accuracy of 16.56%. Finally, to tackle the problems of imbalanced data and the shortage of publicly available datasets for malware detection, various data augmentation techniques are proposed, which lead to improved performance. It is evident from the results that the proposed framework can be useful to the defence industry, which will be helpful in devising more efficient malware detection solutions. [Display omitted] • A novel hybrid framework combines deep transfer learning and machine learning for malware detection. • An image-based PE dataset is generated by transforming malicious and benign Windows executables into RGB-coloured images. • The second step involves a novel combination of deep learning and machine learning models for malware detection. • An in-depth analysis using 15 deep learning and 12 machine learning models is presented for malware detection. • The framework is scalable, cost-effective, and efficient. It eliminates the need for domain experts for reverse engineering tasks. [ABSTRACT FROM AUTHOR]

A huge and rapidly growing quantity of medical documents is available in an electronic versions. These informing documents mostly have textual content in natural language. These facts can make the documents difficult to read, ambiguous, or even contain mistakes. Consequently, when a doctor decides on treatment, many medical critical errors can happen. The information extraction in unstructured documents can handle this problem. In our paper, we introduce an automatic section detection method in the medical field SDM (S ection D etection in M edical field) to improve information extraction tasks by providing more context. Accordingly, we have constructed some rules to prepare automatically the training set. Then, we benefit from numerous features such as formatting style, syntactic, and semantic features to train a machine learning model to find titles. Then, a section tree is generated that can be useful for other tasks. As anticipated, our experiments show that merging these features using a Convolutional Neural Network (CNN) can lead to a better result in real medical documents according to the F1-score measure. Thus, we benefit from the layout information and our method can provide the document sections in a tree form. It is worth noting that our method can be easily applied in other fields since it is not strongly dependent on the document type or language. [ABSTRACT FROM AUTHOR]

Building occupancy information could aid energy preservation while simultaneously maintaining the end-user comfort level. Energy conservation becomes essential since energy resources are scarce and human dependency on appliances is only exponentially increasing. While intrusive sensors (i.e., cameras and microphones) can raise privacy concerns, this paper presents an innovative non-intrusive occupancy detection approach using environmental sensor data (e.g., temperature, humidity, carbon dioxide (CO 2), and light sensors). The proposed scheme transforms multivariate time-series data into images for better encoding and extracting relevant features. The utilized image transformation method is based on data normalization and matrix conversion. Precisely, by representing time-series in 2D space, an encoding kernel can move in two directions while it can move only in one direction when applied to a 1D signal. Moreover, machine learning (ML) and deep learning (DL) techniques are utilized to classify occupancy patterns. Several simulations are used to evaluate the approach; mainly, we investigated pre-trained and custom convolutional neural network (CNN) models. The latter attained an accuracy of 99.00%. Additionally, pixel data are extracted from the generated images and subjected to traditional ML methods. Throughout the numerous comparison settings, it was observed that the latter strategy provided the optimal balance of 99.42% accuracy performance and minimal training time across the occupancy datasets. • Exhaustive literature review on occupancy detection schemes based on sensor data. • Image transformation technique based on data normalization and matrix conversion. • Assessing a variety of pre-trained and custom CNN models to predict occupancy status. • Pixel extraction to gather values and integrate them with conventional ML algorithms. [ABSTRACT FROM AUTHOR]

Stroke, categorized under cardiovascular and circulatory diseases, is considered the second foremost cause of death worldwide, causing approximately 11% of deaths annually. Stroke diagnosis using a Computed Tomography (CT) scan is considered ideal for identifying whether the stroke is hemorrhagic or ischemic. However, most methods for stroke classification are based on a single slice-level prediction mechanism, meaning that the most imperative CT slice has to be manually selected by the radiologist from the original CT volume. This paper proposes an integration of Convolutional Neural Network (CNN), Vision Transformers (ViT), and AutoML to obtain slice-level predictions as well as patient-wise prediction results. While the CNN with inductive bias captures local features, the transformer captures long-range dependencies between sequences. This collaborative local-global feature extractor improves upon the slice-wise predictions of the CT volume. We propose stroke-specific feature extraction from each slice-wise prediction to obtain the patient-wise prediction using AutoML. While the slice-wise predictions helps the radiologist to verify close and corner cases, the patient-wise predictions makes the outcome clinically relevant and closer to real-world scenario. The proposed architecture has achieved an accuracy of 87% for single slice-level prediction and an accuracy of 92% for patient-wise prediction. For comparative analysis of slice-level predictions, standalone architectures of VGG-16, VGG-19, ResNet50, and ViT were considered. The proposed architecture has outperformed the standalone architectures by 9% in terms of accuracy. For patient-wise predictions, AutoML considers 13 different ML algorithms, of which 3 achieve an accuracy of more than 90%. The proposed architecture helps in reducing the manual effort by the radiologist to manually select the most imperative CT from the original CT volume and shows improvement over other standalone architectures for classification tasks. The proposed architecture can be generalized for volumetric scans aiding in the patient diagnosis of head and neck, lungs, diseases of hepatobiliary tract, genitourinary diseases, women's imaging including breast cancer and various musculoskeletal diseases. Code for proposed stroke-specific feature extraction with the pre-trained weights of the trained model is available at: https://github.com/rishiraj-cs/StrokeViT_With_AutoML. [Display omitted] • Most methods for stroke classification are based on slice-level prediction mechanism. • An integration of CNN and ViT is proposed for slice-level prediction. • For patient-wise predictions, stroke-specific feature extraction is proposed. • AutoML is trained on the proposed domain-specific features extracted. [ABSTRACT FROM AUTHOR]

Identification of exfoliated graphene flakes and classification of the thickness are important in the nanomanufacturing of advanced materials and devices. This paper presents a deep learning method to automatically identify and classify exfoliated graphene flakes on Si/SiO 2 substrates from optical microscope images. The presented framework uses a hierarchical deep convolutional neural network that is capable of learning new images while preserving the knowledge from previous images. The deep learning model was trained and used to classify exfoliated graphene flakes into monolayer, bi-layer, tri-layer, four-to-six-layer, seven-to-ten-layer, and bulk categories. Compared with existing machine learning methods, the presented method showed high accuracy and efficiency as well as robustness to the background and resolution of images. The results indicated that the pixel-wise accuracy of the trained deep learning model was 99% in identifying and classifying exfoliated graphene flakes. This research will facilitate scaled-up manufacturing and characterization of graphene for advanced materials and devices. • A machine intelligence approach is developed to classify exfoliated graphene flakes. • A hierarchical deep convolutional neural network is applied for the classification task. • The neural network can learn from new images while preserving the learned knowledge. • The approach is robust to the background and resolution of microscopy images. • Advanced vision techniques are incorporated to handle highly imbalanced datasets. [ABSTRACT FROM AUTHOR]

Accurate indoor location information in multi-building/floor environments is essential for establishing many indoor location-based services (LBS). Wi-Fi fingerprinting with received signal strength indicators (RSSI) has become one of the most practical techniques to localize users indoors. However, the fluctuation of wireless signals caused by fading, the multipath effect, and device heterogeneity leads to considerable variations in RSSIs, which poses a challenge to accurate localization. This paper proposes an indoor positioning method, which is constructed based on a convolutional neural network (CNN) framework. Specifically, a novel model by combining an extreme learning machine autoencoder (ELM-AE) with a two-dimensional CNN is proposed. The ELM-AE extracts critical features by reducing input dimensions, while the CNN is trained to effectively achieve significant performance in the positioning phase. To increase positioning accuracy and deal with data shortages, a data augmentation strategy by frequently adding noisy data to the original fingerprint map is devised. The statistical properties namely, the RSS values of each MAC address, are utilized to adjust input noise. The performance of the proposed system is evaluated on two Tampere and UJIIndoorLoc datasets. The experimental results show that EA-CNN achieves better performance than CNN by decreasing average positioning error up to 40.95% and 43.74% in Tampere and UJIIndoorLoc datasets, respectively. Compared to state-of-the-art deep learning-based methods, the positioning performance improves up to 68.36% in Tampere and 67.56% in the UJIIndoorLoc dataset by exploiting only 25% of the training samples. Compared to several state-of-the-art deep learning models, EA-CNN achieves higher accuracy in both positioning and floor estimation. • EA-CNN outperform the state-of-the-art CNN-based procedures. • ELM-AE decrease input dimension, and increase positioning performance of CNN. • Augmentation strategy dealing with data shortages, improve the training efficiency. • Large scale environments and crowdsourced data are utilized for evaluation. [ABSTRACT FROM AUTHOR]

Freezing of gait (FOG) is one of the most incapacitating symptoms in Parkinson's disease, affecting more than 50% of patients in advanced stages of the disease. The presence of FOG may lead to falls and a loss of independence with a consequent reduction in the quality of life. Wearable technology and artificial intelligence have been used for automatic FOG detection to optimize monitoring. However, differences between laboratory and daily-life conditions present challenges for the implementation of reliable detection systems. Consequently, improvement of FOG detection methods remains important to provide accurate monitoring mechanisms intended for free-living and real-time use. This paper presents advances in automatic FOG detection using a single body-worn triaxial accelerometer and a novel classification algorithm based on Transformers and convolutional networks. This study was performed with data from 21 patients who manifested FOG episodes while performing activities of daily living in a home setting. Results indicate that the proposed FOG-Transformer can bring a significant improvement in FOG detection over the reproduction of related approaches based on machine and deep learning (i.e., from 0.916 to 0.957 in the AUC metric compared with the baseline, with a corresponding sensitivity, specificity, and precision of 0.842, 0.939 and 0.617, respectively) using a leave-one-subject-out cross-validation (LOSO CV). These results present opportunities for the implementation of accurate monitoring systems for use in ambulatory or home settings. [ABSTRACT FROM AUTHOR]

Rapid fire progression, such as flashover, has been one of the leading causes for firefighter deaths and injuries in residential building environments. Due to long computational time of and the required prior knowledge about the fire scene, existing models cannot be used to predict the potential occurrence of flashover in practical firefighting applications. In this paper, a scene-agnostic model (FlashNet) is proposed to predict flashover based on limited heat detector temperature information up to 150 °C. FlashNet utilizes spatial temporal graph convolutional neural networks to effectively learn features from the limited temperature information and to tackle building structure variations. The proposed model is benchmarked against five different state-of-the-art flashover prediction models. Results show that FlashNet outperforms the existing flashover prediction models and it can reliably predict flashover 30 s preceding its occurrence with an overall accuracy of about 92.1%. Ablation study is carried out to examine the effectiveness of different key model components and geometric average adjacency matrix. The research outcomes from this study are expected to enhance firefighters' situational awareness in the fire scene, protecting them from hazardous fire environments and to pave the way for the development of data-driven prediction systems. [ABSTRACT FROM AUTHOR]

Froth Flotation is one of the fundamental processes used in iron ore attainment. It involves various physical–chemical reactions, and its multivariate control is not trivial. Traditionally, plant operators get quality measurements from laboratory analysis of sampled material, which can take hours to be published. In this paper, we present alternatives that eliminate both the necessity to periodically sample material as well as the delay associated with laboratory analysis: a predictive machine learning model working as a soft sensor. Two different classes of models were developed, exploring both deep and shallow approaches of machine learning, with a deep neural network architecture constructed for the particular task at hand. All models yielded accurate predictions, with results favoring the deep neural network when a larger volume of data is available. [ABSTRACT FROM AUTHOR]

Recent work has highlighted the vulnerability of many deep machine learning models to adversarial examples. It attracts increasing attention to adversarial attacks, which can be used to evaluate the security and robustness of models before they are deployed. However, to our best knowledge, there is no specific research on the adversarial robustness and attacks for multi-view deep models. Based on the fact that adversarial examples generalize well among different models, this paper takes the adversarial attack on the multi-view convolutional neural network as an example to investigate the adversarial robustness of multi-view deep models, and further proposes effective multi-view adversarial attacks. This paper proposes two strategies, two-stage attack (TSA) and end-to-end attack (ETEA), to attack against well-trained multi-view models. With the mild assumption that the single-view model on which the target multi-view model is based is known, we first propose the TSA strategy. The main idea of TSA is to attack the multi-view model with adversarial examples generated by attacking the associated single-view model, by which state-of-the-art single-view attack methods are directly extended to the multi-view scenario. Then we further propose the ETEA strategy where the multi-view model is provided publicly. The ETEA is applied to accomplish direct attacks on the target multi-view model, where we develop three effective multi-view attack methods. Extensive experimental results show that multi-view models are more robust than single-view models and demonstrate the effectiveness of the proposed multi-view adversarial attacks. [ABSTRACT FROM AUTHOR]

In this paper a multi-modal unsupervised Deep Learning based algorithm for fault detection is proposed. Such method is applied to real data from a testing procedure implemented on an industrial production line. Both thermal images and current and power measurements coming from industrial refrigerators are collected. The considered dataset is highly unbalanced with the vast majority of samples being healthy. Thermal images are processed via a Deep Convolutional neural network. The features extracted from the thermal images are thus merged to structured data of power, current and temperature. Therefore, a Deep Auto-Encoder is trained on the dataset to signal anomalies corresponding to faults in the refrigerators. Three different methods are trained and compared: (1) an automatic method in which an expert extracts relevant features from thermal images without using the image recognition module; (2) a semi-automatic method where the convolutional neural network is applied to regions of interest within the thermal images selected by an expert operator; (3) a fully automatic method in which the Deep convolutional network processes the whole thermal image without any human intervention. The three methods show comparable results with nevertheless slight differences. [ABSTRACT FROM AUTHOR]

The purpose of feeder-level energy disaggregation is to decouple the net load measured at the feeder-head into various components. This technology is vital for power system utilities since increased visibility of controllable loads enables the realization of demand-side management strategies. However, energy disaggregation at the feeder level is difficult to realize since the high penetration of embedded generation masks the actual demand and different loads are highly aggregated. In this paper, the solar energy at the grid supply point is separated from the net load at first via either an unsupervised upscaling method or the supervised gradient boosting regression tree (GBRT) method. To deal with the uncertainty of the load components, the probabilistic energy disaggregation models based on multi-quantile recurrent neural network model (multi-quantile long short-term memory (MQ-LSTM) model and multi-quantile gated recurrent unit (MQ-GRU) model) are proposed to disaggregate the demand load into thermostatically controlled loads (TCLs), non-thermostatically controlled loads (non-TCLs), and non-controllable loads. A variety of relevant information, including feeder measurements, meteorological measurements, calendar information, is adopted as the input features of the model. Instead of providing point prediction, the probabilistic model estimates the conditional quantiles and provides prediction intervals. A comprehensive case study is implemented to compare the proposed model with other state-of-the-art models (multi-quantile convolutional neural network (MQ-CNN), quantile gradient boosting regression tree (Q-GBRT), Quantile Light gradient boosting machine (Q-LGB)) from training time, reliability, sharpness, and overall performance aspects. The result shows that the MQ-LSTM can estimate reliable and sharp Prediction Intervals for target load components. And it shows the best performance among all algorithms with the shortest training time. Finally, a transfer learning algorithm is proposed to overcome the difficulty to obtain enough training data, and the model is pre-trained via synthetic data generated from a public database and then tested on the local dataset. The result confirms that the proposed energy disaggregation model is transferable and can be applied to other feeders easily. • Feeder level energy disaggregation system to separate demand into sub-components. • A multi-quantile LSTM model that estimates the conditional quantiles. • A solar energy separation model to detect the behind-the-meter PV generation. • A transfer learning model to apply a pre-trained model to other location. [ABSTRACT FROM AUTHOR]

Hyperparameter optimization is critical for the performance of machine learning algorithms. Significant efforts have been dedicated to improve the final accuracy of algorithm by hyperparameter tuning. However, some indicators (such as latency, cpu utilization) are also very important in the actual environment. In this paper, we propose a novel method EMORL (E ffective M ulti- O bjective R einforcement L earning) based on multi-objective reinforcement learning for hyperparameter optimization to solve the above limitations. Specifically, we extend hyperparameter optimization problem to the reinforcement learning framework and employ an agent to select hyperparameters sequentially, and design a scalarization function that combines accuracy and latency as a multi-objective reward to guide the policy update. To improve the efficiency of hyperparameter optimization, previously successful configuration is reused for reshaping the advantage function. In the experiment, we apply the proposed method to tune the hyperparameters of the eXtreme Gradient Boosting on 101 tasks and convolutional neural networks on 2 tasks. The experimental results demonstrate that the proposed method is better than other methods in most tasks, especially in terms of latency. In addition, we verify the various components of the proposed method through ablation experiments. [ABSTRACT FROM AUTHOR]

In the context of natural language processing, accuracy of intention detection is the basis for subsequent research on human-machine speech interaction. However, the problem of ambiguity in word vectors reduces the accuracy of intent detection. Meantime, there is a disconnection between local features and global features as well, resulting in text feature extraction that cannot fully reflect semantic information. These issues are all barriers of intention detection. Therefore, this paper proposes an attention-based convolutional neural network for self-media data learning (called A-CNN) for marketing intention. We cascade the traditional CNN with the self-attention model in the Attention networks to form a new network structure called A-CNN, and put forward a fast feature extraction method based on skip-gram-based learning called FSLText, to represent the high-dimension word vectors in the A-CNN. On the premise of maintaining the advantages of the CNN, A-CNN can not only solve the problem of local and global features disconnection caused by the CNN pooling layer, but also avoid the increase of algorithm complexity. The Self-Attention mechanism in the Attention model can effectively optimize the weight of local features of the information in global features, and retain local features that are more useful for intention detection. A fast feature extraction method which is based on Skip-gram can retain the semantic and word order information of the text. The method is beneficial to the marketing intention detection. According to the experiment, our A-CNN, compared with traditional machine learning methods, can improve 12.32% accuracy. Contrast to the dual-channel CNN, the accuracy rate is improved by 9.68%, and compared with the ATT-CNN, it is improved by 9.97%. On the F1 score, the A-CNN can improve the F1 score by about 9.37% in comparison with the traditional machine learning methods, the accuracy rate is increased by 9.68% compared with the dual-channel CNN, and 9.68% in contrast with ATT-CNN. It illustrates that our A-CNN can effectively address semantic and feature selection for marketing intention detection. [ABSTRACT FROM AUTHOR]

A 1U CubeSat has severe limitations on size, power and downlink capabilities. Transferring images taken by imaging payload from orbit can be a challenging. To save time and effort in downlinking and post-processing, a mechanism must be in place to sort quality data before transmitting it to the ground station. This paper presents an innovative approach combining a novel CubeSat image dataset and a lightweight Convolutional Neural Network architecture for automatically selecting images for downlink on a 1U CubeSat. Coined as CubeSatNet, the neural network is trained on 60,000 augmented images, is tiny enough to run on an ARM Cortex MCU and is tested on on-orbit data from Kyushu Institute of Technology's BIRDS-3 CubeSats with an accuracy of 90% and F1 score of 0.92. CubeSatNet outperformed SVM, DBN and AE trained to classify CubeSat images. If implemented, the CNN could cut down operation time by about 2/3 while significantly improving the quality of received data. [ABSTRACT FROM AUTHOR]