Search

Marine ecosystems and their fish habitats are becoming increasingly important due to their integral role in providing a valuable food source and conservation outcomes. Due to their remote and difficult to access nature, marine environments and fish habitats are often monitored using underwater cameras to record videos and images for understanding fish life and ecology, as well as for preserve the environment. There are currently many permanent underwater camera systems deployed at different places around the globe. In addition, there exists numerous studies that use temporary cameras to survey fish habitats. These cameras generate a massive volume of digital data, which cannot be efficiently analysed by current manual processing methods, which involve a human observer. Deep Learning (DL) is a cutting-edge Artificial Intelligence (AI) technology that has demonstrated unprecedented performance in analysing visual data. Despite its application to a myriad of domains, its use in underwater fish habitat monitoring remains under explored. In this paper, we provide a tutorial that covers the key concepts of DL, which help the reader grasp a high-level understanding of how DL works. The tutorial also explains a step-by-step procedure on how DL algorithms should be developed for challenging applications such as underwater fish monitoring. In addition, we provide a comprehensive survey of key deep learning techniques for fish habitat monitoring including classification, counting, localisation, and segmentation. Furthermore, we survey publicly available underwater fish datasets, and compare various DL techniques in the underwater fish monitoring domains. We also discuss some challenges and opportunities in the emerging field of deep learning for fish habitat processing. This paper is written to serve as a tutorial for marine scientists who would like to grasp a high-level understanding of DL, develop it for their applications by following our step-by-step tutorial, and see how it is evolving to facilitate their research efforts. At the same time, it is suitable for computer scientists who would like to survey state-of-the-art DL-based methodologies for fish habitat monitoring. • Marine environments and fish habitats are widely surveyed using underwater cameras. • Deep learning (DL) offers an effective solution for processing underwater videos. • We write a tutorial on the key concepts and steps of DL for underwater monitoring. • We provide a survey of key DL-based visual fish monitoring methods/datasets. • We shed light on challenges/opportunities of DL for underwater fish monitoring. [ABSTRACT FROM AUTHOR]

Skin diseases are reported to contribute 1.79% of the global burden of disease. The accurate diagnosis of specific skin diseases is known to be a challenging task due, in part, to variations in skin tone, texture, body hair, etc. Classification of skin lesions using machine learning is a demanding task, due to the varying shapes, sizes, colors, and vague boundaries of some lesions. The use of deep learning for the classification of skin lesion images has been shown to help diagnose the disease at its early stages. Recent studies have demonstrated that these models perform well in skin detection tasks, with high accuracy and efficiency. Our paper proposes an end-to-end framework for skin lesion classification, and our contributions are two-fold. Firstly, two fundamentally different algorithms are proposed for segmenting and extracting features from images during image preprocessing. Secondly, we present a deep convolutional neural network model, S-MobileNet that aims to classify 7 different types of skin lesions. We used the HAM10000 dataset, which consists of 10000 dermatoscopic images from different populations and is publicly available through the International Skin Imaging Collaboration (ISIC) Archive. The image data was preprocessed to make it suitable for modeling. Exploratory data analysis (EDA) was performed to understand various attributes and their relationships within the dataset. A modified version of a Gaussian filtering algorithm and SFTA was applied for image segmentation and feature extraction. The processed dataset was then fed into the S-MobileNet model. This model was designed to be lightweight and was analyzed in three dimensions: using the Relu Activation function, the Mish activation function, and applying compression at intermediary layers. In addition, an alternative approach for compressing layers in the S-MobileNet architecture was applied to ensure a lightweight model that does not compromise on performance. The model was trained using several experiments and assessed using various performance measures, including, loss, accuracy, precision, and the F1-score. Our results demonstrate an improvement in model performance when applying a preprocessing technique. The Mish activation function was shown to outperform Relu. Further, the classification accuracy of the compressed S-MobileNet was shown to outperform S-MobileNet. To conclude, our findings have shown that our proposed deep learning-based S-MobileNet model is the optimal approach for classifying skin lesion images in the HAM10000 dataset. In the future, our approach could be adapted and applied to other datasets, and validated to develop a skin lesion framework that can be utilized in real-time. [ABSTRACT FROM AUTHOR]

• The proposed method had fused multi-level information compensation and U-Net. • The module designed for multi-level information compensation and compression. • The method had fused compressed features and correlation features. Recently, Deep Convolutional Neural Networks have demonstrated high-quality reconstruction in image super-resolution procedure. In this paper, we propose improved image super-resolution reconstruction via multi-level information compensation and U-Net network to address the problem that the image super-resolution reconstruction algorithm based on deep neural networks tends to lose feature information in the feature extraction process, resulting in the lack of texture and edge details in the reconstructed image. Firstly, we design the U-net like network for image super-resolution reconstruction, which performs multi-level feature extraction and channel compression for the input features through the down-channel branch. It fuses the compressed features and extracts the correlation features of different channels through the bottom module, and performs multi-level feature extraction and channel recovery for the compressed correlation features through the up-channel branch. The multi-level information compensation model is then designed to compensate for the information lost in the channel compression process and the information that is difficult to recover in the channel recovery process of U-net like network. The experimental results can show that the proposed algorithm achieves a significant improvement in Peak Signal-to-Noise Ratio and Structure Similarity Index and visual effect compared with the state-of-arts algorithms. The average experimental results of PSNR from proposed method had improved by 1.63 dB, 1.53 dB, 0.97 dB and 0.94 dB compared to SRCNN, HAT, DAT and CARN, respectively. [ABSTRACT FROM AUTHOR]

Hardware Trojans (HT) are the most malicious components attacking modern integrated circuits (ICs). Information leakage, incorrect functionality, and overheating are the major effects of HT insertion. Due to the outsourcing of multi-stage digital circuit design and fabrication, HTs can be inserted by rogues at every stage. The types of HTs and insertion methods evolve continuously and their detection becomes more complex. Consequently, designing integrated circuits robust to HT insertion seems efficient. A prerequisite for such a strategy is the evaluation of integrated circuit vulnerability to HT insertion. There are several factors involved in the vulnerability of fabricated integrated circuits such as the distribution of white spaces in the IC layout, the ratio of unutilized routing resources, the amount of activity of the circuit's nodes, the geometrical properties of the circuit's gates, the delay of various paths, and etc. The interrelation of these diverse factors makes IC vulnerability modeling a challenging problem. In this paper, a deep neural network (DNN) based approach is developed to combine all the effective factors in IC vulnerability analysis. Firstly, we generate a comprehensive dataset containing various types and sizes of hardware Trojans inserted into benchmark circuits. The benchmark circuits used in this study are ISCAS 85, ISCAS 89, and ITC 99. Then using the transfer learning concept seven state-of-the-art deep convolutional neural networks are trained and verified using the constructed dataset to classify every integrated circuit into three vulnerability levels (low, moderate, and highly vulnerable classes). Simulation results show that our proposed method achieves almost 95 % accuracy in the most successful case (VGG16). The lowest accuracy belongs to Inception V3 (∼87.65 %) which is much better than the most successful previous studies (72 %). This is mainly because the DNN-based method handles shortcomings (such as incomplete modeling of vulnerability-related factors) in the previous state-of-the-art methods efficiently. [ABSTRACT FROM AUTHOR]

Classification methods that are based on hyperspectral images (HSIs) are playing an increasingly significant role in the processes of target detection, environmental management, and mineral mapping as a result of the fast development of hyperspectral remote sensing technology. Improving classification performance is still a significant problem, however, as a result of the high dimensionality and redundancy of hyperspectral image sets (HSIs), as well as the presence of class imbalance in hyperspectral datasets. In the past few years, convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have achieved good results in HSI classification, but CNNs struggle to achieve good accuracy in low samples, while GCNs have a huge computational cost. To resolve these issues, this paper proposes a Multi-Feature Fusion of 3D-CNN and Graph Attention Network MFFCG. The algorithm consists of two elements: the 3D-CNN, which produces good classification for 3D HSI cube data, and GAT-based encoder and decoder modules that help in improving the classification accuracy of the 3D-CNN. Finally, the multiple features are merged with the help of two neural network models. We further develop two optimized GAT models named GAT1 and GAT2, which are used with different layers of 3D-CNN. Algorithms after merging with 3D-CNN are named MFFCG-1 and MFFCG-2, which produce better classification results then other developed methods. Experiments on three public HSI datasets show that the proposed methods perform better than other state-of-the-art methods using the limited training samples and in low classification time. [ABSTRACT FROM AUTHOR]

In recent years different types of Residual Neural Networks (ResNets, for short) have been introduced to improve the performance of deep Convolutional Neural Networks. To cope with the possible redundancy of the layer structure of ResNets and to use them on devices with limited computational capabilities, several tools for exploring and compressing such networks have been proposed. In this paper, we provide a contribution in this setting. In particular, we propose an approach for the representation and compression of a ResNet based on the use of a multilayer network. This is a structure sufficiently powerful to represent and manipulate a ResNet, as well as other families of deep neural networks. Our compression approach uses a multilayer network to represent a ResNet and to identify the possible redundant convolutional layers belonging to it. Once such layers are identified, it prunes them and some related ones obtaining a new compressed ResNet. Experimental results demonstrate the suitability and effectiveness of the proposed approach. • Representation of a ResNet model through a multilayer network. • An approach to compress a ResNet through its multilayer network representation. • A compression approach tested on ResNet20,ResNet56,ResNet110 and CIFAR10, CIFAR100. [ABSTRACT FROM AUTHOR]

• Employ accumulated gradient normalization to compensate for our small batch size. • Identify redundant filters of a U-Net-based network using the genetic algorithm. • Remove trivial filters of the network to reduce its inference costs. • Use the pruned network for brain tumor segmentation and overall survival prediction. • Pruned network works as well as the original network but with less inference cost. The most common and aggressive malignant brain tumor in adults is glioma, which leads to short life expectancy. A reliable and efficient automatic segmentation method is beneficial for clinical practice. Deep neural networks have achieved great success in brain tumor segmentation recently. However, their computational complexity and storage costs hinder their deployment in real-time applications or on resource-constrained devices in clinics. Network pruning, which has attracted many researchers recently, alleviates this limitation by removing trivial parameters of the network. Network pruning is challenging in the medical field because pruning should not degrade the performance of models. As a result, it is vital to choose unimportant parts of networks correctly. In this paper, we employ the genetic algorithm to identify redundant filters of our U-Net-based network. We consider filter pruning a multiobjective optimization problem in which performance and inference time are optimized simultaneously. Then, we use our compressed network for brain tumor segmentation. Predicted segmentation masks are often used to predict patients' survival time. Although several studies have recently achieved good results, they require different feature engineering techniques to extract suitable features, which is difficult and time-consuming. To tackle this problem, we easily extract deep features from the endpoint of the encoder of our compact network and use them for survival prediction. Regarding the popularity of U-Net-based models for brain tumor segmentation, many researchers can employ our technique to predict the survival time without spending lots of time on feature engineering. The experimental results on the BraTS 2018 dataset demonstrate that filter pruning is a reliable technique to reduce the storage cost and accelerate the network during inference while maintaining performance. Furthermore, our survival time prediction technique achieves high efficiency compared to state-of-the-art methods. Preprocessed data, the full implementation of the project, and the trained networks are available at https://github.com/Fbehrad/Evo_conv. [ABSTRACT FROM AUTHOR]

• We propose an Improvised Patch-based Deep CNN for facial retouching detection. • The input image is processed to extract 6 patches using 68 facial landmarks. • Our model uses dual skip connection to maximize the information flow. • The proposed scheme outperforms the existing schemes on ND-IIITD dataset. With the advancement of photo editing softwares, nowadays facial retouching becomes a common practice across different social media platforms, Curriculum Vitae (CV) related websites, photo sharing applications, and magazines publishing flawless facial images of celebrities. In this paper, we propose an improvised patch-based deep convolution neural network (IPDCN2) to classify whether a facial image is original or retouched. The proposed network comprises of three stages i.e., pre-processing, high-level features extraction, and classification. Initially, we propose a pre-processing stage to extract only relevant patches from the input image by using 68 facial landmarks. In the second stage, an efficient and robust CNN based on residual learning is employed to extract the high-level hierarchical features from these patches. The proposed network uses the concept of residual learning with the help of max pooling layers to maximize the information flow across the neural network. Lastly, the extracted high-level features are passed to fully-connected layers for classification. The experimental results show that proposed network outperforms the existing state-of-the-art techniques by providing an accuracy of 99.84% on ND-IIITD dataset. Moreover, proposed network provides a classification accuracy of 95.80%, 83.70%, and 97.30% on YMU, VMU, and MIW make-up datasets, respectively. [ABSTRACT FROM AUTHOR]

• We propose a cross-domain collaborative learning framework for image deraining. • A cross-domain pseudo label generation method is presented. • A Multi-Scale Attention Residual Block for improving the representation ability. • The state-of-the-art results are reported on four deraining datasets. Deep Convolutional Neural Networks (DCNN) have achieved outstanding performance in image deraining tasks. However, current most methods regard rain streak removal as a one-to-one problem, and intra domain shift of different synthetic datasets is usually ignored. Therefore, the deraining models trained on one synthetic dataset cannot effectively remove the rain streak of other synthetic datasets. Also, image deraining models which are trained on the labeled synthetic datasets mostly suffer from performance degradation when tested on the unlabeled real datasets due to the inter domain gap. To address this issue, this paper proposes a Cross-Domain Collaborative Learning (CDCL) framework to minimize the intra domain shift and inter domain gap. Firstly, a dual branch deraining network with collaborative learning is proposed to eliminate the distribution shift of rain streaks of images within synthetic domains. Then, a Cross-Domain Pseudo Label Generation (CDPLG) method is designed to obtain more accurate and robust pseudo labels for real-world rainy images, and the online generated pseudo labels are utilized to train the dual branch deraining network for reducing the domain gap between synthetic domain and real domain. Extensive experiments are conducted on the public benchmark datasets including synthetic datasets and real datasets in image deraining, and experimental results demonstrate that our proposed framework performs favorably compared with the state-of-the-art models. [ABSTRACT FROM AUTHOR]

The ongoing COVID-19 pandemic has created an unprecedented predicament for global supply chains (SCs). Shipments of essential and life-saving products, ranging from pharmaceuticals, agriculture, and healthcare, to manufacturing, have been significantly impacted or delayed, making the global SCs vulnerable. A better understanding of the shipment risks can substantially reduce that nervousness. Thenceforth, this paper proposes a few Deep Learning (DL) approaches to mitigate shipment risks by predicting "if a shipment can be exported from one source to another", despite the restrictions imposed by the COVID-19 pandemic. The proposed DL methodologies have four main stages: data capturing, de-noising or pre-processing, feature extraction, and classification. The feature extraction stage depends on two main variants of DL models. The first variant involves three recurrent neural networks (RNN) structures (i.e., long short-term memory (LSTM), Bidirectional long short-term memory (BiLSTM), and gated recurrent unit (GRU)), and the second variant is the temporal convolutional network (TCN). In terms of the classification stage, six different classifiers are applied to test the entire methodology. These classifiers are SoftMax, random trees (RT), random forest (RF), k-nearest neighbor (KNN), artificial neural network (ANN), and support vector machine (SVM). The performance of the proposed DL models is evaluated based on an online dataset (taken as a case study). The numerical results show that one of the proposed models (i.e., TCN) is about 100% accurate in predicting the risk of shipment to a particular destination under COVID-19 restrictions. Unarguably, the aftermath of this work will help the decision-makers to predict supply chain risks proactively to increase the resiliency of the SCs. • Proposes a wide range of DL approaches to predict supply chain risks. • Introducing a temporal convolutional network (TCN) by combining RNN and CNN models. • Identification of the most promising DL approach in terms of performance. • Performance demonstration of the selected classifiers on the advanced DL networks. [ABSTRACT FROM AUTHOR]

• A novel hand gesture identification is proposed using CNN, ORB and Gabor filter. • It can be used as a pre-trained structure for any type of the hand gesture dataset. • Remarkable results are obtained on the famous databases. • Less computational intricacy in the hardware implementation and online application. In this paper, a new structure of deep learning neural network is introduced to identify the static hand gesture in the sign language. The proposed structure includes the convolutional neural network (CNN) and the classical non-intelligent feature extraction method. In the proposed structure, the hand gesture image, after preprocessing and removing its background, passes through three different streams of feature extraction, to well extract of effective features and determine the hand gesture class. These three streams, that independently extract their own specific features, consist of three widely used methods in the hand gesture classification named CNN, Gabor filter and ORB feature descriptor. Then these features are merged and formed the final feature vector. By combining these efficient methods, in addition to achieving a very high accuracy in hand gestures classifying, the proposed structure becomes more resistant to uncertainties such as rotation and ambiguity in the hand gestures. Another prominent feature of the proposed structure is its comprehensiveness on different image databases, compared to the similar methods. The transfer learning technique demonstrates that the proposed structure has the ability to be used as a pre-trained structure for any type of image database. Finally, the proposed structure is applied to the three different databases of Massey, ASL Alphabet and ASL, which have 2520, 87,000 and 23,400 of hand gesture images, respectively. The results show the mean accuracy of the proposed structure for the Massey test set of 758 images, ASL with 7020 test images, and ASL Alphabet with 26,100 test images, at 99.92%, 99.8%, and 99.80% respectively. [ABSTRACT FROM AUTHOR]

Predictive Maintenance has become an important component in modern industrial scenarios, as a way to minimize down-times and fault rate for different equipment. In this sense, while machine learning and deep learning approaches are promising due to their accurate predictive abilities, their data-heavy requirements make them significantly limited in real world applications. Since one of the main issues to overcome is lack of consistent training data, recent work has explored the possibility of adapting well-known deep-learning models for image recognition, by exploiting techniques to encode time series as images. In this paper, we propose a framework for evaluating some of the best known time series encoding techniques, together with Convolutional Neural Network -based image classifiers applied to predictive maintenance tasks. We conduct an extensive empirical evaluation of these approaches for the failure prediction task on two real-world datasets (PAKDD2020 Alibaba AI OPS Competition and NASA bearings), also comparing their performances with respect to the state-of-the-art approaches. We further discuss advantages and limitation of the exploited models when coupled with proper data augmentation techniques. • We analyze Predictive Maintenance task aiming to minimize down-times of an equipment. • We use time series encoding techniques with CNN-based models in different scenarios. • An extensive evaluation has been performed for HDD and bearings failure prediction. • Performance has been evaluated w.r.t. other benchmarking neural network models. [ABSTRACT FROM AUTHOR]

• The systematic failure pattern recognition method for wafer map is explored. • A deep convolutional neural network model is established. • This model is an end-to-end 19-layer network structure. • This model can automatically extract effective classification features. • The mode can enhance the reliability and efficiency of fault pattern recognition. The objective of this paper is to propose a systematic failure pattern recognition for wafer map based on neural networks. A deep convolutional neural network (DCNN) model which includes the convolutional layer, batch normalization layer, Relu layer, maximum pooling layer, full connection layer, Softmax layer and classification layer is established for the problem of failure pattern recognition of wafer map. This model is an end-to-end 19-layer network, which can actively learn and automatically extract effective classification features. After grayscale and median filtering, the wafer map can be imported into the network for automatic failure classification without special feature extraction. On this basis, we build a dual-source DCNN structure by combining decision-level information entropy fusion. The verification results of the model in the actual wafer map database WM-811K show that the model exhibits good performance in identifying nine kinds of common failure patterns, and has advantages in identifying non-pattern wafer patterns without failure patterns. The dual-source DCNN structure has a better classification effect than the single-source DCNN structure, and the overall recognition accuracy of the dual-source DCNN structure reaches 98.34%. [ABSTRACT FROM AUTHOR]

Recent studies have shown that deep convolutional neural networks (CNNs) have been successfully used for texture representation and recognition. One of the most successful texture recognition methods is the deep texture encoding network (DeepTEN), which has been shown to be effective. However, this network directly uses redundant CNN features with generality and ignores the role of multiorder information during the encoding and learning processes. To address these issues, this paper proposes a double-order knowledge fusion and attentional encoding network for texture recognition (DFAEN). First, crucial texture features are encoded by an embedded attention mechanism. Second, double-order modeling is implemented in the encoding and learning stage to make full use of convolution feature information with different orders, enabling the network to focus on and learn more texture domain information. Our method can stably and effectively perform end-to-end optimization. Evaluation experiments conducted on several widely used benchmark datasets (e.g., the FMD, MINC-2500, the DTD, KTH-TISP-2b, and GTOS-mobile) show that our method clearly demonstrates superior performance to that of competing approaches. • A deep multi-order texture encoding end-to-end network is proposed. • Attention-based texture encoding mechanism for texture representation learning. • The double orders information is modeled effectively in encoding learning stage. • Our approach achieves excellent experimental results in five challenging datasets. [ABSTRACT FROM AUTHOR]

In this paper, the computational complexity of the probabilistic neural network for the classification of high-dimensional data is improved. At first, the class probability densities are estimated by using only a few principal components of an observed point. The Gaussian–Parzen kernel is replaced by the orthogonal series estimates of class-conditional densities for each principal component using the Fourier series to speed up a decision-making procedure. The unreliable classes are found for which a likelihood ratio to the maximal likelihood does not exceed a certain threshold. The next components are used to refine these estimates only for other classes, and such a sequential analysis of principal components is repeated until only one reliable class is obtained. Experimental study for image recognition with features extracted by deep convolutional neural networks including EfficientNets demonstrates that our approach is more accurate and 15–60 times faster than the baseline instance-based learning methods. • Image recognition with high-dimensional deep embeddings may be slow. • Fourier series estimates improves performance of probabilistic neural network (PNN). • Sequential Fourier PNN is proposed for principal components of deep embeddings. • Sequential Fourier PNN is faster and more accurate than known modifications of PNN. [ABSTRACT FROM AUTHOR]

• Computing on edge end improves the efficiency and reliability of data analysis. • A lightweight CNN model is efficient for real-time crowd density estimation on edge. • Better crowd density inference speed with a slight increase in estimation accuracy. • Equip the model in an IoT device to monitor the crowd density in a Subway Station. Crowd stampedes and incidents are critical threats to public security that have caused countless deaths during the past few decades. To avoid crowd stampedes, real-time crowd density estimation can help monitor crowd movements, and thus support a timely evacuation strategy development. In previous studies, scholars and engineers developed multiple video-based crowd density estimation algorithms based on deep neural networks. The excessive computational complexity of deep learning algorithms exacerbated the algorithm's efficiency, causing unacceptable real-time performance. In the Internet of Things era, deploying the crowd density estimation task with edge computing is an advanced strategy to maintain the real-time performance of the entire system. Considering the limited computational resources on the edge devices, deep learning-based crowd density estimation algorithms normally cannot be handled. To fulfill the deployment on the edge device, the algorithms need to be optimized with a smaller model size. Therefore, this paper proposes a lightweight Convolutional Neural Networks (CNN) based crowd density estimation model by combining the modified MobileNetv2 and the dilated convolution. Public crowd image data sets are used to conduct experiments for evaluating the performance of the proposed algorithm in terms of accuracy and inference speed. The results show that our model achieves much better inference speed accompanied by a slight increase in accuracy. The proposed method of this study can enhance the performance of the crowd monitoring system, and therefore help avoid crowd stampedes and incidents. [ABSTRACT FROM AUTHOR]

The number and efficiency of seismic networks have steadily increase over time delivering large datasets to be analyzed for earthquake occurrence. Automatic tools for accurate earthquake detection are under emerging and intense development. This paper first proposes a new windowing procedure of seismic traces that highly facilitates earthquake detection. This procedure applies regular trace filtering and normalization, but also performs a strict window alignment to P wave onset. These event-aligned windows represent the input data to our P wave detection networks, with relatively small or moderate number of layers. We then develop Feed-Forward (FFNN) and Convolutional (CNN) neural networks and explore multiple architecture configurations to find relevant hyperparameter patterns for better detection. To assess network performance, we adopt the widely used metrics of accuracy (ACC) and the area under the curve (AUC) of the Receiver Operating Characteristic function. In terms of ACC, the best FFNN and CNN reach performances of 91% and 98%, respectively. On the other hand, the best FFNN and CNN in terms of AUC achieve performances of 96% and 99%, respectively. Thus, our novel trace windowing procedure allows developing networks with few hyperparameters, for correct earthquake detection under low computational costs. Finally, we use the CNN with best AUC performance as an effective trace filtering with the purpose of P wave arrival time estimation. • Small-layered neural networks with high detection efficiency of seismic events. • Useful data preprocessing to align P wave onset with a trace window starting time. • Event alignment on network input simplifies hyperparameterization and training. • Novel applications on challenging datasets of labeled P wave phases in Venezuela. [ABSTRACT FROM AUTHOR]

• The resource-constrained devices in Cyber-Physical Systems are considered. • The KD-TCNN model is utilized with knowledge distillation and metric learning. • A neural network training method called K-fold cross training is proposed. • The proposed model is tested using benchmark intrusion detection datasets. • Proposed mothed outperforms many state-of-the-art models. With the rapid development of technology and science, machine learning approaches and deep learning methods have been widely applied in industrial Cyber-Physical Systems. However, there are still some challenging issues for anomaly detection to classify various attacks in industrial CPS to ensure the cyber security, especially when dealing with resource-constrained IoT devices. In this paper, we propose a Knowledge Distillation model based on Triplet Convolution Neural Network to improve the model performance and greatly enhance the speed of anomaly detection for industrial CPS as well as reduce the complexity of the model. Specifically, during the training process, we design a robust model loss function to improve the training stability of the model. A new neural network training method called K-fold cross training is also proposed to enhance the accuracy of anomaly detection. A lot of experimental results demonstrate that the performance metrics of KD-TCNN on the benchmark datasets NSL-KDD and CIC IDS2017 have significant advantages over traditional deep learning approaches and the recent state-of-the-art models. Furthermore, when compared to the original model, our model's computational cost and size are both reduced by roughly 86% with just 0.4% accuracy loss. [ABSTRACT FROM AUTHOR]

• Dynamic flexible job shop scheduling problem with machine breakdown is studied. • A two-stage algorithm based on convolutional neural network is proposed. • The improved imperialist competition algorithm is proposed to generate schedules. • A predictive model is proposed to predict the robustness of scheduling. In the actual manufacturing process, the environment of the job shop is complex. There will be many kinds of uncertainties such as random job arrivals, machine breakdowns, order cancellations and other dynamic events. In this paper, an effective two-stage algorithm based on convolutional neural network is proposed to solve the flexible job shop scheduling problem (FJSP) with machine breakdown. A bi-objective dynamic flexible job shop scheduling problem (DFJSP) model with the objective of maximum completion time and robustness is established. In the two-stage algorithm, the first stage is to train the prediction model by convolutional neural network (CNN). The second stage is to predict the robustness of scheduling through the model trained in the first stage. First, an improved imperialist competition algorithm (ICA) is proposed to generate training data. Then, a predictive model constructed by CNN was proposed, and an alternative metric called RMn was developed to evaluate robustness. RMn evaluates that the float time has an effect on the robustness through the information of machine breakdown, workload and float time of the operation. The experimental results show that the proposed two-stage algorithm is effective for solving DFJSP, and RMn can evaluate the robustness of scheduling more quickly, efficiently and accurately. [ABSTRACT FROM AUTHOR]

The early detection of drowsiness has become vital to ensure the correct and safe development of several industries' tasks. Due to the transient mental state of a human subject between alertness and drowsiness, automated drowsiness detection is a complex problem to tackle. The electroencephalography signals allow us to record variations in an individual's brain's electrical potential, where each of them gives specific information about a subject's mental state. However, due to this type of signal's nature, its acquisition, in general, is complex, so it is hard to have a large volume of data to apply techniques of Deep Learning for processing and classification optimally. Nevertheless, Capsule Neural Networks are a brand-new Deep Learning algorithm proposed for work with reduced amounts of data. It is a robust algorithm to handle the data's hierarchical relationships, which is an essential characteristic for work with biomedical signals. Therefore, this paper presents a Deep Learning-based method for drowsiness detection with CapsNet by using a concatenation of spectrogram images of the electroencephalography signals channels. The proposed CapsNet model is compared with a Convolutional Neural Network, which is outperformed by the proposed model, which obtains an average accuracy of 86,44 % and 87,57% of sensitivity against an average accuracy of 75,86% and 79,47% sensitivity for the CNN, showing that CapsNet is more suitable for this kind of datasets and tasks. • A Capsule Network for drowsiness detection method is proposed. • The system is based on spectrogram images concatenate information from Fz and Pz. • The traditional drowsiness detection methods need a big number of data. • The proposed method improves the results even with a small number of images. • The proposed method outperforms state of the art in comparison with CNN and ML. [ABSTRACT FROM AUTHOR]

Recently, there is an increasing demand for small drones owing to their small size and agility in complex indoor environments. Accordingly, safety issues for navigating small drones become of significant importance. For drones to be able to navigate safely through complex environments, it would be useful to estimate accurate time-to-collision (TTC) to obstacles. To this end, in this paper, we propose a deep learning-based TTC estimation algorithm. To train generalizable neural networks for TTC estimation, large datasets including collision cases are needed. However, in real-world environments, it is impractical and infeasible to collide drones with obstacles to collect a significant amount of data. Simulation environments could facilitate the data acquisition procedure, but the data from simulated environments could be quite different from those of real environments, which is commonly termed as reality-gap. In this study, to reduce this reality-gap, sim-to-real methods based on a variant of the generative adversarial network are used to convert simulated images into real world-like synthetic images. Besides, to consider the uncertainties that come from using the synthetic dataset, the aleatoric loss function and Monte Carlo dropout method are employed. Furthermore, we improve the performance of the deep learning-based TTC estimation algorithm by replacing conventional convolutional neural networks (CNNs) with convolutional long short-term memory (ConvLSTM) layers which are known to be better at handling time-series data than CNNs. To validate the performance of the proposed framework, real flight experiments have been carried out in various indoor environments. Our proposed framework decreases the average TTC estimation error by 0.21 s compared with the baseline approach with CNNs. • A vision-based time-to-collision estimation algorithm using deep learning. • Convert simulated images into real-like synthetic images using sim-to-real method. • Proposed an uncertainty and times-series characteristic aware neural network model. • Verified the proposed model in various indoor environments. • Compared the performance with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

• Saffron adulterants detected and classified using a deep learning algorithm. • RGB photos took under uncontrolled/unstructured conditions. • Five CNN models were proposed for classification. • The best-proposed model can process an image in 36.26 ms with 99.67% accuracy. Saffron is the most expensive spice in the world which is traded internationally. Hence, Saffron adulterants is always a challenging issue. It should be noted that traditional methods that are being used to solve this problem, are costly and time-consuming. In this study, for the first time, Saffron adulterants was detected using a deep neural network and RGB photos taken under uncontrolled/unstructured conditions. There were five classes of fake Saffron include mixed saffron stamen and dyed straw, mixed stigma and stamens, dyed orange blossom, Safflower and dyed stamens, and two classes of genuine Saffron consisting of freeze-drying and microwave-drying saffron used to design, develop and optimize a Convolutional Neural Network (CNN). 60% of the images were used to train and optimize the neural network model. For preventing over-training, the number of images used in the training phase increased by applying the augmentation method. The general structure of the model to detect saffron adulterants consisted of multiple convolutional (input layer), pooling layers and fully-connected layers, respectively. In this study, five structures (S1, S2, S3, S4 and S5) were proposed for CNN using Batch Normalization methods. Additionally, this paper compared these five structures with Popular Convolutional Networks consisted of VGG11, ResNet18, ResNet50, Inception V3 and DarkNet53. According to the results, the best configuration was S5 that achieved the accuracy of 99.8% and the cross-entropy loss of 0.019. Although the time process of this structure was 36.26 ms, the shortest time process was 19.38 ms related to the S1. This number was more than 300 ms for Popular CNN. Based on the results of this study, imaging without restrictions with CNN can detect Saffron adulterants. [ABSTRACT FROM AUTHOR]

To combat the recent coronavirus disease 2019 (COVID-19), academician and clinician are in search of new approaches to predict the COVID-19 outbreak dynamic trends that may slow down or stop the pandemic. Epidemiological models like Susceptible–Infected–Recovered (SIR) and its variants are helpful to understand the dynamics trend of pandemic that may be used in decision making to optimize possible controls from the infectious disease. But these epidemiological models based on mathematical assumptions may not predict the real pandemic situation. Recently the new machine learning approaches are being used to understand the dynamic trend of COVID-19 spread. In this paper, we designed the recurrent and convolutional neural network models: vanilla LSTM, stacked LSTM, ED_LSTM, BiLSTM, CNN, and hybrid CNN+LSTM model to capture the complex trend of COVID-19 outbreak and perform the forecasting of COVID-19 daily confirmed cases of 7, 14, 21 days for India and its four most affected states (Maharashtra, Kerala, Karnataka, and Tamil Nadu). The root mean square error (RMSE) and mean absolute percentage error (MAPE) evaluation metric are computed on the testing data to demonstrate the relative performance of these models. The results show that the stacked LSTM and hybrid CNN+LSTM models perform best relative to other models. • Various variants of LSTM and CNN deep learning architectures have been designed. • Predicted COVID-19 confirmed cases for India and its four most affected states. • RMSE and MAPE are computed to compare the performance of the designed models. • Experimental results show that predicted cases are very close to actual cases. [ABSTRACT FROM AUTHOR]

Deep learning can play a pivotal role in early fault detection in squirrel cage induction motors (SCIMs) and achieving Industry 4.0. SCIM finds application in industries like mining, textile, manufacturing, and many more. Early fault detection in SCIM can significantly reduce downtime and optimize productivity. This paper proposes a novel fault detection technique for bearing faults and broken rotor bar detection in SCIM using the dilated convolutional neural network-based model. A simple 1-D signal to image conversion technique is also proposed for transforming the 1-D vibration signal acquired from multiple accelerometers to images. The proposed method provides an end-to-end learning solution for fault detection. The propounded approach has accomplished an average accuracy of more than 99.50%. A comparison has also been made between different convolutional neural network (CNN) models and conventional machine learning models to show the proposed method's efficiency. The complete experimental work has been carried out on a 5 kW, 3-phase, 415 V, 50 Hz SCIM. The dilated CNN model development has been done using python software, and the packages used are Keras and TensorFlow. • Dilated convolutional neural network-based model is used for fault detection. • Developed model expedites high accuracy with less number of layers. • Proposed model provides faster convergence owing to dilated convolutions. • Model facilitates self and automatic fault feature learning. [ABSTRACT FROM AUTHOR]

Male infertility is a disease that affects approximately 7% of men. Sperm morphology analysis (SMA) is one of the main diagnosis methods for this problem. However, manual SMA is an inexact, subjective, non-reproducible, and hard to teach process. Therefore, in this paper, we introduce a novel automatic SMA technique that is based on the neural architecture search algorithm, named Genetic Neural Architecture Search (GeNAS). For this purpose, we used a collection of images termed MHSMA dataset, which contains 1540 sperm images that have been collected from 235 patients with infertility problems. In detail, GeNAS consists of a special genetic algorithm that acts as a meta-controller which explores the constrained search space of plain convolutional neural network architectures. Every individual of this genetic algorithm is a convolutional neural network trained to predict morphological deformities in different segments of human sperm (head, vacuole, and acrosome). The fitness of each individual is calculated by a novel proposed method, named GeNAS Weighting Factor (GeNAS-WF). This technique is specially designed to evaluate the fitness of neural networks which, during their learning process, validation accuracy highly fluctuates. To speed up the algorithm, a hashing method is practiced to save each trained neural architecture fitness, so we could reuse them during fitness evaluation. In terms of running time and computational power, our proposed architecture search method is far more efficient than most of the other existing neural architecture search algorithms. Moreover, whereas most of the existing neural architecture search algorithms are designed to work well with well-prepared benchmark datasets, the overall paradigm of GeNAS is specially designed to address the challenges of real-world datasets, particularly shortage of data and class imbalance. In our experiments, the best neural architecture found by GeNAS has reached an accuracy of 91.66%, 77.33%, and 77.66% in the vacuole, head, and acrosome abnormality detection, respectively. In comparison to other proposed algorithms for MHSMA dataset, GeNAS achieved state-of-the-art results. • A novel neural architecture search based on Genetic Algorithm. • A novel neural architecture encoding for exploration of search space. • A specific Crossover and Mutation operations for neural architecture search. • Work on imbalanced datasets, low resolution images, and non-stained sperms. • State-of-the-art accuracy & Real-time sperm morphological analysis. [ABSTRACT FROM AUTHOR]

• A combination of a CNN and Capsule Neural Networks helps improve verification. • A single branch network is trained simultaneously by two images at the same. • A CapsNet can detect the details of angular and spatial changes in signature. • The verification model size is reduced by half compared to Siamese networks. • A composite network architecture can dramatically increase verification accuracy. Offline Signature verification is a biometric method with important applications in financial, legal and administrative procedures. The verification process includes comparing the extracted features of a questioned signature with those of genuine signatures of a certain individual. There are many challenges in designing offline signature verification as dynamic temporal features of signatures are not available. Deep Convolutional Neural Networks (DCNNs) have the great capability of extracting features from signature images. Despite the important advantages of these networks, they are unable to recognize the spatial properties of each feature in a signature. In addition, max-pooling layers usually eliminate some features that are crucial for forgery detection. In this paper, we propose a novel signature verification model with a combination of a CNN and Capsule Neural Networks (CapsNet) in order to capture spatial properties of signature features, improve the feature extraction phase, and reduce the complexity of the network. Moreover, we designed a new training mechanism in which a single network is trained simultaneously by two images at the same level so that the training parameters are reduced by half. Such mechanism does not require two separate networks for learning the features. Finally, a composite backbone architecture is presented with the hybrid of the proposed CNN-CapsNet models which we name CBCapsNet. The evaluation results demonstrate that our proposed model can improve accuracy and outperform prevalent signature verification methods in the community. [ABSTRACT FROM AUTHOR]

Nowadays, traffic situation prediction is a major concern. Travel time index prediction is one of the representative tasks in traffic situation prediction. Most research of the current prediction focuses on road-level speed, but the travel time index prediction of complex road network at the regional level has not been well solved. In this paper, we proposed a novel model with convolutional neural network called Seq2Img-DRNET. The sequence data with 10 min interval are converted into image data as the input of our model. The model is constructed by fusing dense connection network and residual network to solve the travel time index prediction of complex road network at the regional level. Taking two actual traffic networks of commercial district and scenic district in Chengdu as the example, we compared our model with common sequential model and convolution neural network model, and the results show that our model can effectively capture the spatial–temporal relationship characteristics of complex road network at the regional level and make accurate prediction. • Our method transforms time series data into image data for spatiotemporal information fusion. • A convolutional neural network model is constructed to accurately predict the travel time index. • Aiming at urban business districts and scenic spots prone to traffic congestion. • The prediction accuracy is significantly higher than the existing baseline model. [ABSTRACT FROM AUTHOR]

• Using a CNN model to classify investor sentiments from a major Chinese stock forum. • Using a LTSM model to build a stock price prediction model. • We showed that the hybrid model with sentiments outperforms the baseline model. • The results support that investor sentiment is a driver of stock prices. Whether stock prices are predictable has been the center of debate in academia. In this paper, we propose a hybrid model that combines a deep learning approach with a sentiment analysis model for stock price prediction. We employ a Convolutional Neural Network model for classifying the investors' hidden sentiments, which are extracted from a major stock forum. We then propose a hybrid research model by applying the Long Short-Term Memory (LSTM) Neural Network approach for analyzing the technical indicators from the stock market and the sentiment analysis results from the first step. Furthermore, this work has conducted real-life experiments from six key industries of three time intervals on the Shanghai Stock Exchange (SSE) to validate the effectiveness and applicability of the proposed model. The experiment results indicate that the proposed model has achieved better performance in classifying investor sentiments than the baseline classifiers, and this hybrid approach performs better in predicting stock prices compared to the single model and the models without sentiment analysis. [ABSTRACT FROM AUTHOR]