Search

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60–70% and the average correlation of 3-by-1 ECGs achieved 80–90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects. [ABSTRACT FROM AUTHOR]

For the limitations of global feature-based deep learning point cloud registration algorithms in partial point cloud registration, this paper proposes a partial point cloud registration algorithm NcPE-PNLK combining global features and correspondence. The NcPE-PNLK algorithm introduces a feature interaction module to complete the information interaction between two point clouds in the feature extraction stage, which can improve the credibility of the feature. Moreover, the algorithm predicts the correspondence through the non-corresponding point estimation module, which reduces the influence of non-overlapping regions on the global feature and effectively solves the problem of performance degradation of the global feature registration algorithms in partial point cloud registration. We test the registration performance of NcPE-PNLK on synthetic scene dataset and real dataset in this paper. The experimental results show that NcPE-PNLK can effectively reduce the impact of non-overlapping regions in the registration process and achieve better performance compared with the global feature-based registration algorithms. In addition, compared with the correspondence-based registration algorithms, the NcPE-PNLK algorithm does not need to calculate correspondence precisely, which can achieve high-precision partial point cloud registration with guaranteed efficiency. [ABSTRACT FROM AUTHOR]

Over the years the number of research publications per year is growing exponentially. Finding research papers of quality from the massive literature of relevant articles is a challenging and time-consuming task. The approaches in the latest literature address citation recommendation by utilizing large bibliographic information and use machine learning and deep learning methods for the task. These techniques clearly require a large amount of training data as well as machines with high processing power. To overcome these issues, we propose a novel method by modifying the popular hyperlink induced topic search (HITS), a web page ranking algorithm, as citation recommendation using hyperlink induced topic search (CR-HITS) that works on a directed and weighted heterogeneous bibliographic network containing diverse types of nodes and edges. We define effective scoring schemes for nodes and edges based on basic bibliographic information like citations of papers, number of publications of an author, etc. Given a few seed papers, the citation recommendation algorithm CR-HITS is run on small neighborhoods of the seed papers and hence the time taken by the execution is very small to yield the final recommendations. To the best of our knowledge, HITS has been used for the first time for the citation recommendation problem. We perform extensive experimentation on DBLP (version-11) and ACM (version-9) datasets and compare the results with many baseline methods in terms of MAP, MRR, and recall@N measures. The performance of the proposed algorithms is superior with respect to the MAP metric and matches the second best for the other two metrics. Since the top two algorithms use deep learning methods and use much larger bibliographic information including abstracts of the papers, we claim that our approach utilizes very low resources, yet yields recommendations that are very close to the top recommendations. [ABSTRACT FROM AUTHOR]

In the petroleum and coal industries, digital image technology and acoustic emission technology are employed to study rock properties, but both exhibit flaws during data processing. Digital image technology is vulnerable to interference from fractures and scaling, leading to potential loss of image data; while acoustic emission technology is not hindered by these issues, noise from rock destruction can interfere with the electrical signals, causing errors. The monitoring errors of these techniques can undermine the effectiveness of rock damage analysis. To address this issue, this paper focuses on the restoration of image data acquired through digital image technology, leveraging deep learning techniques, and using soft and hard rocks made of similar materials as research subjects, an improved Incremental Transformer image algorithm is employed to repair distorted or missing strain nephograms during uniaxial compression experiments. The concrete implementation entails using a comprehensive training set of strain nephograms derived from digital image technology, fabricating masks for absent image segments, and predicting strain nephograms with full strain detail. Additionally, we adopt deep separable convolutional networks to optimize the algorithm's operational efficiency. Based on this, the analysis of rock damage is conducted using the repaired strain nephograms, achieving a closer correlation with the actual physical processes of rock damage compared to conventional digital image technology and acoustic emission techniques. The improved incremental Transformer algorithm presented in this paper will contribute to enhancing the efficiency of digital image technology in the realm of rock damage, saving time and money, and offering an innovative approach to traditional rock damage analysis. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) is one of the well-known deep learning algorithms that uses convolutional filters to extract the features in the images. The most important issue when training CNN is the overfitting which prevents the model from generalization to unseen data. This paper addressed this issue by proposing a novel hybrid approach that uses bees algorithm (BA) to optimize the regularization parameter and weight regularization factor to adjust the regularization value in each convolutional layer and fully connected layer resulting in a hybrid algorithm called bees algorithm regularized convolutional neural network (BA-RCNN). It was applied to three different datasets for classification or predictions purposes and showed an improvement in the validation and testing accuracy leading to a lower difference with the training accuracy which means the overfitting is reduced comparing to the original CNN. Applying the BA-RCNN algorithm to 'Cifar10DataDir' improved the validation accuracy from 80.34% for the original CNN to 82.80% for the hybrid BA-RCNN algorithm, in the electrocardiogram the improvement was from 87.80 to 90.47% and both datasets were used for classification. Furthermore, the hybrid BA-RCNN algorithm was applied to predict the porosity percentage based on artificial porosity images and the results showed that the validation accuracy was improved from 81.67% for the original CNN to 87.33% for the hybrid BA-RCNN algorithm. [ABSTRACT FROM AUTHOR]

Email phishing is a social engineering scheme that uses spoofed emails intended to trick the user into disclosing legitimate business and personal credentials. Many phishing email detection techniques exist based on machine learning, deep learning, and word embedding. In this paper, we propose a new technique for the detection of phishing emails using word embedding (Word2Vec, FastText, and TF-IDF) and deep learning techniques (DNN and BiLSTM network). Our proposed technique makes use of only four header based (From, Returnpath, Subject, Message-ID) features of the emails for the email classification. We applied several word embeddings for the evaluation of our models. From the experimental evaluation, we observed that the DNN model with FastText-SkipGram achieved an accuracy of 99.52% and BiLSTM model with FastText-SkipGram achieved an accuracy of 99.42%. Among these two techniques, DNN outperformed BiLSTM using the same word embedding (FastText-SkipGram) techniques with an accuracy of 99.52%. [ABSTRACT FROM AUTHOR]

Animation compression is a key process in replicating and streaming animated 3D models. Linear Blend Skinning (LBS) facilitates the compression of an animated sequence while maintaining the capability of real-time streaming by deriving vertex to proxy bone assignments and per frame bone transformations. We introduce a innovative deep learning approach that learns how to assign vertices to proxy bones with persistent labeling. This is accomplished by learning how to correlate vertex trajectories to bones of fully rigged animated 3D models. Our method uses these pretrained networks on dynamic characteristics (vertex trajectories) of an unseen animation sequence (a sequence of meshes without skeleton or rigging information) to derive an LBS scheme that outperforms most previous competent approaches by offering better approximation of the original animation sequence with fewer bones, therefore offering better compression and smaller bandwidth requirements for streaming. This is substantiated by a thorough comparative performance evaluation using several error metrics, and compression/bandwidth measurements. In this paper, we have also introduced a persistent bone labeling scheme that (i) improves the efficiency of our method in terms of lower error values and better visual outcome and (ii) facilitates the fusion of two (or more) LBS schemes by an innovative algorithm that combines two arbitrary LBS schemes. To demonstrate the usefulness and potential of this fusion process, we have combined the outcome of our deep skinning method with that of Rignet—which is a state-of-the-art method that performs rigging on static meshes—with impressive results. [ABSTRACT FROM AUTHOR]

Regional debris flow susceptibility assessment is an effective method to prevent debris flow hazards, and deep learning is emerging as a novel approach in this discipline with the development of computers. However, when debris flow samples are insufficient, there will be problems like overfitting or misclassification. To overcome these problems, this paper proposes a semi-supervised deep neural network model (LPA-DNN) combined with label propagation algorithm (LPA), which utilizes high confidence unlabeled samples as pseudo-samples reasonably in few-label scenarios. Xinzhou, Shanxi Province, was selected as the study area, and a dataset containing 292 debris flow samples and 10 types of impact factors was compiled based on watershed units. Using the dataset and pseudo-samples, the LPA-DNN model was built to get debris flow susceptibility map. Meanwhile, DNN and SVM were set up for comparison to demonstrate that the proposed LPA-DNN model has excellent performance and higher accuracy. LPA-DNN alleviates the problem of low accuracy that caused by samples lacking in deep learning to a certain extent, and obtains great classification results, which proves that it is quite potential in regional debris flow susceptibility assessment. [ABSTRACT FROM AUTHOR]

Fruit recognition and location are the premises of robot automatic picking. YOLOv3 has been used to detect different fruits in complex environment. However, for the object with definite features, the complex network structure will increase the computing time and may cause overfitting. Therefore, this paper has carried out a lightweight design for the YOLOv3. This paper proposed an improved T-Net to detect tomato images. Firstly, the T-Net reduces the residual network layers. This paper changed the number of cycles in each group of the residual unit to 1, 2, 2, 1, and 1. Second, two feature layers with different scales are selected according to the features of tomatoes. Meanwhile, the convolutional layer at the neck has been reduced by two layers. Finally, the location and approximate diameter of the ripe tomato are obtained by combining the node information of the Intel D435i camera and T-Net in the Robot Operation System. T-Net obtains mean average precision (mAP) of 99.2%, F1-score of 98.9%, precision of 99.0%, and recall of 98.8% at a detection rate of 104.2 FPS. The proposed T-Net has outperformed the YOLOv3 with 0.4%, 0.1%, and 0.2% increase in precision, mAP, and F1-score. The detection speed of T-Net is 1.8 times faster than YOLOv3. The mean errors of the center coordinates and diameter of the tomato are 8.5 mm and 2.5 mm, respectively. This model provides a method for efficient real-time detection and location of tomatoes. [ABSTRACT FROM AUTHOR]

This paper aims to propose a table tennis target detection (TD) method based on deep learning (DL) and multi-scale feature fusion (MFF) to improve the detection accuracy of the ball in table tennis competition, optimize the training process of athletes, and improve the technical level. In this paper, DL technology is used to improve the accuracy of table tennis TD through MFF guidance. Initially, based on the FAST Region-based Convolutional Neural Network (FAST R-CNN), the TD is carried out in the table tennis match. Then, through the method of MFF guidance, different levels of feature information are fused, which improves the accuracy of TD. Through the experimental verification on the test set, it is found that the mean Average Precision (mAP) value of the target detection algorithm (TDA) proposed here reaches 87.3%, which is obviously superior to other TDAs and has higher robustness. The DL TDA combined with the proposed MFF can be applied to various detection fields and can help the application of TD in real life. [ABSTRACT FROM AUTHOR]

Conventional wireless sensors have difficulty solving the problem of energy limitation, especially in sensor networks in hard-to-reach extreme areas. In order to solve the problem that it is difficult to charge wireless sensors in the field using conventional energy sources, the energy harvesting wireless senor is designed to use renewable energy sources for power supply. Considering the uncertainty and unknown nature of renewable energy generation, and the need for effective energy management of the sensor. In this paper, an Node Power Control Optimization (NPCO) power allocation algorithm is proposed to adjust the power allocation problem of wireless sensor nodes within each time slot. In addition, to address the unknown and random nature of energy arrival, this paper proposes a CLSTM model based on deep learning to predict the energy arrival. The continuous autonomous energy management of wireless sensor nodes is achieved by combining the CLSTM prediction results using the NPCO algorithm. The algorithm is applicable to continuous states and is able to show good performance in the verification of real solar data. The algorithm achieves better performance in terms of long-term average net bit rate compared to the current DDPG algorithm, AC algorithm, and Lyapunov optimization algorithm. [ABSTRACT FROM AUTHOR]

One of the most important strategies used to mitigate the adverse impacts of traffic growth on mobile networks is caching. By caching at the edge, the backhaul traffic load is reduced, and the quality of service for the user is increased. Developing an effective caching algorithm requires accurate prediction of the future popularity of the content, which is a challenging issue. In recent years, deep learning models have achieved high predictive accuracy due to advancements in data availability and increased computing power. In this paper, we present a caching algorithm called the user preference-aware content caching algorithm (UPACA). This algorithm is specifically designed for an edge content delivery platform where users can access content services provided by a remote content provider. UPACA operates in two steps. In the first step, the proposed collaborative filtering-based popularity prediction algorithm (CFPA) is used to predict future content popularities. CFPA utilizes a gated residual variational autoencoder collaborative filtering model to predict users' future preferences and calculate the future popularity of content. This algorithm considers the popularity of the content as well as the number and timing of content requests. Experimental results demonstrate that UPACA outperforms previous methods in terms of cache hit rates and user utilities. [ABSTRACT FROM AUTHOR]

One of the most popular techniques for changing the purpose of an image or resizing a digital image with content awareness is the seam-carving method. The performance of image resizing algorithms based on seam machining shows that these algorithms are highly dependent on the extraction of importance map techniques and the detection of salient objects. So far, various algorithms have been proposed to extract the importance map. In this paper, a new method based on Rényi entropy is proposed to extract the importance map. Also, a deep learning network has been used to detect salient objects. The simulator results showed that combining Rényi's importance map with a deep network of salient object detection performed better than classical seam-carving and other extended seam-carving algorithms based on deep learning. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

This paper proposes a bidirectional feature fusion pyramid (B-FPN) Single Shot Multiple Frame Detector (SSD) algorithm. First, a bidirectional feature pyramid (B-FPN) structure is constructed, which realizes the bidirectional fusion of the feature layers and improves the accuracy of detection. Second, we introduce coordinate attention (CA) to focus on the important channel features while preserving their location information, thereby increasing the focus on the important information. Finally, optimizing the loss function speeds up the convergence of the model and further improves the detection accuracy of the network. The experimental results show that on the VOC2007 dataset, the mAP of the algorithm in this paper is 76.48%, which is 3.52% higher than that of the SSD algorithm. On the COCO 2017 dataset, the mAP of the proposed algorithm is 3.85% higher than that of the SSD algorithm. Compared with other mainstream target detection algorithms, the algorithm in this paper has certain advantages in detection accuracy, and can also achieve satisfactory results in detection speed. Finally, the accuracy of foreign object recognition in the special environment of iron ore transportation is 98.26%. [ABSTRACT FROM AUTHOR]

Multimedia data have increased dramatically today, making the distinction between desirable information and other types of information extremely important. Speech/music discrimination is a field of audio analytics that aims to detect and classify speech and music segments in an audio file. This paper proposes a novel feature extraction method called Long-Term Multi-band Frequency-Domain Mean-Crossing Rate (FDMCR). The proposed feature computes the average frequency-domain mean-crossing rate along the frequency axis for each of the perceptual Mel-scaled frequency bands of the signal power spectrum. In this paper, the class-separation capability of this feature is first measured by well-known divergence criteria such as Maximum Fisher Discriminant Ratio (MFDR), Bhattacharyya divergence, and Jeffreys/Symmetric Kullback–Leibler (SKL) divergence. The proposed feature is then applied to the speech/music discrimination (SMD) process on two well-known speech-music datasets—GTZAN and S &S (Scheirer and Slaney). The results obtained on the two datasets using conventional classifiers, including k-NN, GMM, and SVM, as well as deep learning-based classification methods, including CNN, LSTM, and BiLSTM, show that the proposed feature outperforms other features in speech/music discrimination. [ABSTRACT FROM AUTHOR]

Microwave imaging is one of the rapidly developing frontier disciplines in the field of modern medical imaging. The development of microwave imaging algorithms for reconstructing stroke images is discussed in this paper. Compared with traditional stroke detection and diagnosis techniques, microwave imaging has the advantages of low price and no ionizing radiation hazards. The research hotspots of microwave imaging algorithms in the field of stroke are mainly reflected in the design and improvement of microwave tomography, radar imaging, and deep learning imaging. However, the current research lacks the analysis and combing of microwave imaging algorithms. In this paper, the development of common microwave imaging algorithms is reviewed. The concept, research status, current research hotspots and difficulties, and future development trends of microwave imaging algorithms are systematically expounded. The microwave antenna is used to collect scattered signals, and a series of microwave imaging algorithms are used to reconstruct the stroke image. The classification diagram and flow chart of the algorithms are shown in this Figure. (The classification diagram and flow chart are based on the microwave imaging algorithms.) [ABSTRACT FROM AUTHOR]

As the scale and complexity of networks grow rapidly, management, maintenance, and optimization of them are becoming increasingly challenging tasks for network administrators. Software-Defined Networking (SDN) was introduced to facilitate these tasks as it offers logically centralized control, a global view of the network, and software-based traffic analysis, thus, it is widely adopted of SDN to manage large-scale networks. On the other hand, SDN is not immune to cyber attacks. In fact, its centralized architecture makes it more vulnerable to certain types of attacks, such as denial of service. Various attack mitigation strategies are proposed to strengthen the security of SDNs including statistical, threshold-based, and Machine Learning (ML) methods. Among them, Deep Learning (DL)-based models attained the best results as they were able to extract the complex relationship between input parameters and output that could not be achieved with other solutions. Hence, this paper presents a comprehensive survey of the literature on the utilization of different DL algorithms for the security of SDN. We first explain the types of attacks that SDNs are exposed to, then present papers that applied DL to detect and/or mitigate these attacks. We further discuss the public datasets used to train DL models and evaluate their advantages and disadvantages. Finally, we share insights into future research directions to improve the efficiency of DL methods for SDN security. [ABSTRACT FROM AUTHOR]

During the manufacturing process of printed circuit boards (PCBs), quality defects can occur, which can affect the performance and reliability of PCBs. Existing deep learning-based PCB defect detection methods are difficult to simultaneously achieve the goals of high detection accuracy, fast detection speed, and small number of parameters. Therefore, this paper proposes a PCB defect detection algorithm based on CDI-YOLO. Firstly, the coordinate attention mechanism (CA) is introduced to improve the backbone and neck network of YOLOv7-tiny, enhance the feature extraction capability of the model, and thus improve the accuracy of model detection. Secondly, DSConv is used to replace part of the common convolution in YOLOv7-tiny to achieve lower computing costs and faster detection speed. Finally, Inner-CIoU is used as the bounding box regression loss function of CDI-YOLO to speed up the bounding box regression process. The experimental results show that the method achieves 98.3% mAP on the PCB defect dataset, the detection speed is 128 frames per second (FPS), the parameters is 5.8 M, and the giga floating-point operations per second (GFLOPs) is 12.6 G. Compared with the existing methods, the comprehensive performance of this method has advantages. [ABSTRACT FROM AUTHOR]

Deep learning shows great potential in low-light image enhancement, which can improve image brightness and contrast while keeping image natural. However, due to the lack of prior knowledge extracted manually or excessive amplification of noise, these methods result in poor quality of enhanced images. To solve these challenging problems, this paper proposes a dual-branch grayscale image enhancement network based on dense residual and attention mechanism. Low-light grayscale image is used as input. Firstly, features that fuse deep and shallow information are extracted through dense residual convolution branch network; secondly, texture features are extracted through U-Net branch network combined with attention mechanism; then the extracted features are integrated, and finally luminance is adjusted by a brightness adjustment module to output an enhanced grayscale image. In addition, a joint loss function is designed to measure the network training loss from brightness, texture, contrast and noise. A large number of quantitative and qualitative experiments on LOL and VE-LOL datasets show that the proposed method improves Peak Signal to Noise Ratio Index and Structural Similarity Index by 19.65 - 59.76% and 5.61 - 85.53%, respectively, compared with EnlightenGAN, KinD++, RUAS, LLFlow, etc. The proposed method is superior to the most famous methods, thanks to the deep feature extraction and fusion capability of dense residual convolutional network and texture extraction capability of U-Net network combined with attention mechanism. [ABSTRACT FROM AUTHOR]

Precise neurosurgical guidance is critical for successful brain surgeries and plays a vital role in all phases of image-guided neurosurgery (IGN). Neuronavigation software enables real-time tracking of surgical tools, ensuring their presentation with high precision in relation to a virtual patient model. Therefore, this work focuses on the development of a novel multimodal IGN system, leveraging deep learning and explainable AI to enhance brain tumor surgery outcomes. The study establishes the clinical and technical requirements of the system for brain tumor surgeries. NeuroIGN adopts a modular architecture, including brain tumor segmentation, patient registration, and explainable output prediction, and integrates open-source packages into an interactive neuronavigational display. The NeuroIGN system components underwent validation and evaluation in both laboratory and simulated operating room (OR) settings. Experimental results demonstrated its accuracy in tumor segmentation and the success of ExplainAI in increasing the trust of medical professionals in deep learning. The proposed system was successfully assembled and set up within 11 min in a pre-clinical OR setting with a tracking accuracy of 0.5 (± 0.1) mm. NeuroIGN was also evaluated as highly useful, with a high frame rate (19 FPS) and real-time ultrasound imaging capabilities. In conclusion, this paper describes not only the development of an open-source multimodal IGN system but also demonstrates the innovative application of deep learning and explainable AI algorithms in enhancing neuronavigation for brain tumor surgeries. By seamlessly integrating pre- and intra-operative patient image data with cutting-edge interventional devices, our experiments underscore the potential for deep learning models to improve the surgical treatment of brain tumors and long-term post-operative outcomes. [ABSTRACT FROM AUTHOR]

Purpose: Artifacts in magnetic resonance imaging (MRI) scans degrade image quality and thus negatively affect the outcome measures of clinical and research scanning. Considering the time-consuming and subjective nature of visual quality control (QC), multiple (semi-)automatic QC algorithms have been developed. This systematic review presents an overview of the available (semi-)automatic QC algorithms and software packages designed for raw, structural T1-weighted (T1w) MRI datasets. The objective of this review was to identify the differences among these algorithms in terms of their features of interest, performance, and benchmarks. Methods: We queried PubMed, EMBASE (Ovid), and Web of Science databases on the fifth of January 2023, and cross-checked reference lists of retrieved papers. Bias assessment was performed using PROBAST (Prediction model Risk Of Bias ASsessment Tool). Results: A total of 18 distinct algorithms were identified, demonstrating significant variations in methods, features, datasets, and benchmarks. The algorithms were categorized into rule-based, classical machine learning-based, and deep learning-based approaches. Numerous unique features were defined, which can be roughly divided into features capturing entropy, contrast, and normative measures. Conclusion: Due to dataset-specific optimization, it is challenging to draw broad conclusions about comparative performance. Additionally, large variations exist in the used datasets and benchmarks, further hindering direct algorithm comparison. The findings emphasize the need for standardization and comparative studies for advancing QC in MR imaging. Efforts should focus on identifying a dataset-independent measure as well as algorithm-independent methods for assessing the relative performance of different approaches. [ABSTRACT FROM AUTHOR]

After 70 years of intricate development, machine learning, represented by deep learning, is based on the multilevel structure of the human brain and the layer-by-layer analysis and processing mechanism of neuron connection and interaction information. The powerful parallel information processing ability of self-adaptation and self-learning has allowed for breakthroughs in many fields, among which the most representative is image recognition. Therefore, this paper proposed optimizing the RBF algorithm with machine learning (ML) to improve the recognition rate of spectrum sensing. The results showed that the average detection success rates of the RBF algorithm were 93.62%, 95.07%, 96.91%, 98.78% and 99.37% when the SNRs were − 8 dB, − 4 dB, 0 dB, 4 dB and 8 dB, respectively, and the other conditions were kept the same. The average detection success rates of the SVM/RBF algorithm were 97.65%, 99.63%, 99.76%, 99.91% and 99.88%, respectively. The average detection success rate of the SVM/RBF algorithm was significantly higher than that of the RBF algorithm. This indicates that analyzing the RBF neural network algorithm through ML can improve the success rate of spectrum sensing, which highlights a new direction for the application of ML and neural networks. [ABSTRACT FROM AUTHOR]

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

Distributed learning, as the most popular solution for training large-scale data for deep learning, consists of multiple participants collaborating on data training tasks. However, the malicious behavior of some during the training process, like Byzantine participants who would interrupt or control the learning process, will trigger the crisis of data security. Although recent existing defense mechanisms use the variability of Byzantine node gradients to clear Byzantine values, it is still unable to identify and then clear the delicate disturbance/attack. To address this critical issue, we propose an algorithm named consensus aggregation in this paper. This algorithm allows computational nodes to use the information of verification nodes to verify the effectiveness of the gradient in the perturbation attack, reaching a consensus based on the effective verification of the gradient. Then the server node uses the gradient as the valid gradient for gradient aggregation calculation through the consensus reached by other computing nodes. On the MNIST and CIFAR10 datasets, when faced with Drift attacks, the proposed algorithm outperforms common existing aggregation algorithms (Krum, Trimmed Mean, Bulyan), with accuracies of 93.3%, 94.06% (MNIST dataset), and 48.66%, 51.55% (CIFAR10 dataset), respectively. This is an improvement of 3.0%, 3.8% (MNIST dataset), and 19.0%, 26.1% (CIFAR10 dataset) over the current state-of-the-art methods, and successfully defended against other attack methods. [ABSTRACT FROM AUTHOR]

Adaptive algorithms are widely used in deep learning because of their fast convergence. Among them, Adam is the most widely used algorithm. However, studies have shown that Adam's generalization ability is weak. AdaX is a variant of Adam, which introduces a novel second-order momentum, modifies the second-order moment of Adam, and has good generalization ability. However, these algorithms may fail to converge due to instability and extreme learning rates during training. In this paper, we propose a new adaptive and momental bound algorithm, called AdaXod, which characterizes of exponentially averaging the learning rate and is particularly useful for training deep neural networks. By setting an adaptively limited learning rate in the AdaX algorithm, the resultant AdaXod can effectively eliminate the problem of excessive learning rate in the later stage of neural networks training and thus results in stable training. We conduct extensive experiments on different datasets and verify the advantages of the AdaXod algorithm by comparing with other advanced adaptive optimization algorithms. AdaXod eliminates large learning rates during neural networks training and outperforms other optimizers, especially for some neural networks with complex structures, such as DenseNet. [ABSTRACT FROM AUTHOR]

In this paper, the quantum technology is exploited to empower the OPTICS unsupervised learning algorithm, which is a density-based clustering algorithm with numerous applications in the real world. We design an algorithm called Quantum Ordering Points To Identify the Clustering Structure (QOPTICS) and demonstrate that its computational complexity outperforms that of its classical counterpart. On the other hand, we propose a Deep self-learning approach for modeling the improvement of two Swarm Intelligence Algorithms, namely Artificial Orca Algorithm (AOA) and Elephant Herding Optimization (EHO) in order to improve their effectiveness. The deep self-learning approach is based on two well-known dynamic mutation operators, namely Cauchy mutation operator and Gaussian mutation operator. And in order to improve the efficiency of these algorithms, they are hybridized with QOPTICS and executed on just one cluster it yields. This way, both effectiveness and efficiency are handled. To evaluate the proposed approaches, an intelligent application is developed to manage the dispatching of emergency vehicles in a large geographic region and in the context of Covid-19 crisis in order to avoid an important loss in human lives. A theoretical model is designed to describe the issue mathematically. Extensive experiments are then performed to validate the mathematical model and evaluate the performance of the proposed deep self-learning algorithms. Comparison with a state-of-the-art technique shows a significant positive impact of hybridizing Quantum Machine Learning (QML) with Deep Self Learning (DSL) on solving the Covid-19 EMS transportation. [ABSTRACT FROM AUTHOR]

Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images. [ABSTRACT FROM AUTHOR]

Detection of small objects is one of the main challenges to be improved in deep learning, mainly due to the small number of pixels and scene's context, leading to a loss in performance. In this paper, we present an optimized approach based on deep object detection models that allow the detection of a higher number of elements and improve the score obtained for their class inference. The main advantage of the presented methodology is that it is not necessary to modify the internal structure of the selected convolutional neural network model or re-training for a specific scene. Our proposal is based on detecting initial regions to generate several sub-images using super-resolution (SR) techniques, increasing the number of pixels of the elements, and re-infer over these areas using the same pre-trained model. A reduced set of windows is calculated in the super-resolved image by analyzing a computed graph that describes the distances among the preliminary object detections. This analysis is done by finding maximal cliques on it. This way, the number of windows to be examined is diminished, significantly speeding up the detection process. This framework has been successfully tested on real traffic sequences obtained from the U.S. Department of Transportation. An increase of up to 44.6% is achieved, going from an average detection rate for the EfficientDet D4 model of 14.5% compared to 59.1% using the methodology presented for the first sequence. Qualitative experiments have also been performed over the Cityscapes and VisDrone datasets. [ABSTRACT FROM AUTHOR]

Distributed learning, as the most popular solution for training large-scale data for deep learning, consists of multiple participants collaborating on data training tasks. However, the malicious behavior of some during the training process, like Byzantine participants who would interrupt or control the learning process, will trigger the crisis of data security. Although recent existing defense mechanisms use the variability of Byzantine node gradients to clear Byzantine values, it is still unable to identify and then clear the delicate disturbance/attack. To address this critical issue, we propose an algorithm named consensus aggregation in this paper. This algorithm allows computational nodes to use the information of verification nodes to verify the effectiveness of the gradient in the perturbation attack, reaching a consensus based on the effective verification of the gradient. Then the server node uses the gradient as the valid gradient for gradient aggregation calculation through the consensus reached by other computing nodes. On the MNIST and CIFAR10 datasets, when faced with Drift attacks, the proposed algorithm outperforms common existing aggregation algorithms (Krum, Trimmed Mean, Bulyan), with accuracies of 93.3%, 94.06% (MNIST dataset), and 48.66%, 51.55% (CIFAR10 dataset), respectively. This is an improvement of 3.0%, 3.8% (MNIST dataset), and 19.0%, 26.1% (CIFAR10 dataset) over the current state-of-the-art methods, and successfully defended against other attack methods. [ABSTRACT FROM AUTHOR]

The ridge beast is a beast placed on the ridge of the roof of ancient Chinese buildings, not only has a decorative function, and has a strict hierarchical meaning, the number and form of the ridge beast placed on different levels of buildings are strictly limited. The detection technology of ridge beast decorative parts has important application value in the fields of fine 3D reconstruction of ancient buildings, historical dating and cultural and tourism services. Aiming at the problem of poor detection performance of traditional detection algorithms due to high texture similarity and poor discrimination of ridge beast, this paper proposed an improved YOLOv3 based detection algorithm for ridge beast decorative pieces. In terms of basic network improvement, local features are aggregated to the deep separable convolution internal embedding summation layer, and point convolution is used to connect the channel information of original features and aggregated features, so as to expand the receptive field and learn more diverse features. The residual structure of the feature extraction network was constructed by using the convolution, and the extraction effect of the model on the fine-grained features of the ridge beast was optimized, so that the detection accuracy was improved. In the prediction head improvement of the model, the original linear structure was reconstructed, and the extrusion and excitation modules were introduced to model the channel relationship of multi-scale feature map, which suppressed the response of interference signals and made the feature more directivity. The parallel 1 × 1 and 3 × 3 convolution are used to construct a multi-size convolution structure, which enhances the semantic information extraction ability of the model and further improves the detection effect. Experiments were conducted on the constructed ridge-beast dataset, and the results showed that the mAP of the improved algorithm can reach 86.48%, which is 3.05% higher than YOLO-v3, and the model parameters are reduced by 70%, which has a better detection performance and can provide a reference for the automated detection of ancient building components. [ABSTRACT FROM AUTHOR]

In sports, advance sensing technologies generate massive amount of unstructured telemedicine data that need to be refined for accurate diagnosis of underlying diseases. For accurate prediction of diseases and classification of athletes' data, deep learning algorithms are frequently used at the cloud. However, the transmission of raw data of athletes to the cloud faces numerous challenges. Among them, security and privacy are a major challenge in view of the sensitive and personal information present within the unstructured data. In this paper, first we present a data block scrambling algorithm (without key management) for secured transmission and storage of ECG (electrocardiogram) data of table tennis players at the cloud. A small piece of original data stored at the cloud is used for scrambling the massive amount of remaining ECG data. The secured telemedicine data is then imported into Hadoop Distributed File System for data management, which is read by Spark framework to form Resilient Distributed Datasets. Finally, a deep learning approach is used that extracts useful features, learns the related information, and weights and sums the feature vectors at different layers for classification. Theoretical analysis proves that our proposed approach is highly robust and resilient to brute force attacks and at the same time has a much better accuracy, sensitivity, and specificity as compared to the existing approaches. [ABSTRACT FROM AUTHOR]

Ultrasonic vocalizations (USVs) analysis represents a fundamental tool to study animal communication. It can be used to perform a behavioral investigation of mice for ethological studies and in the field of neuroscience and neuropharmacology. The USVs are usually recorded with a microphone sensitive to ultrasound frequencies and then processed by specific software, which help the operator to identify and characterize different families of calls. Recently, many automated systems have been proposed for automatically performing both the detection and the classification of the USVs. Of course, the USV segmentation represents the crucial step for the general framework, since the quality of the call processing strictly depends on how accurately the call itself has been previously detected. In this paper, we investigate the performance of three supervised deep learning methods for automated USV segmentation: an Auto-Encoder Neural Network (AE), a U-NET Neural Network (UNET) and a Recurrent Neural Network (RNN). The proposed models receive as input the spectrogram associated with the recorded audio track and return as output the regions in which the USV calls have been detected. To evaluate the performance of the models, we have built a dataset by recording several audio tracks and manually segmenting the corresponding USV spectrograms generated with the Avisoft software, producing in this way the ground-truth (GT) used for training. All three proposed architectures demonstrated precision and recall scores exceeding 90 % , with UNET and AE achieving values above 95 % , surpassing other state-of-the-art methods that were considered for comparison in this study. Additionally, the evaluation was extended to an external dataset, where UNET once again exhibited the highest performance. We suggest that our experimental results may represent a valuable benchmark for future works. [ABSTRACT FROM AUTHOR]

Hyperparameter optimization plays a significant role in the overall performance of machine learning algorithms. However, the computational cost of algorithm evaluation can be extremely high for complex algorithm or large dataset. In this paper, we propose a model-based reinforcement learning with experience variable and meta-learning optimization method to speed up the training process of hyperparameter optimization. Specifically, an RL agent is employed to select hyperparameters and treat the k-fold cross-validation result as a reward signal to update the agent. To guide the agent's policy update, we design an embedding representation called "experience variable" and dynamically update it during the training process. Besides, we employ a predictive model to predict the performance of machine learning algorithm with the selected hyperparameters and limit the model rollout in short horizon to reduce the impact of the inaccuracy of the model. Finally, we use the meta-learning technique to pre-train the model for fast adapting to a new task. To prove the advantages of our method, we conduct experiments on 25 real HPO tasks and the experimental results show that with the limited computational resources, the proposed method outperforms the state-of-the-art Bayesian methods and evolution method. [ABSTRACT FROM AUTHOR]

Video Snapshot compressive imaging (SCI) is a promising technique to capture high-speed videos, which transforms the imaging speed from the detector to mask modulating and only needs a single measurement to capture multiple frames. The algorithm to reconstruct high-speed frames from the measurement plays a vital role in SCI. In this paper, we consider the promising reconstruction algorithm framework, namely plug-and-play (PnP), which is flexible to the encoding process comparing with other deep learning networks. One drawback of existing PnP algorithms is that they use a pre-trained denoising network as a plugged prior while the training data of the network might be different from the task in real applications. Towards this end, in this work, we propose the online PnP algorithm which can adaptively update the network's parameters within the PnP iteration; this makes the denoising network more applicable to the desired data in the SCI reconstruction. Furthermore, for color video imaging, RGB frames need to be recovered from Bayer pattern or named demosaicing in the camera pipeline. To address this challenge, we design a two-stage reconstruction framework to optimize these two coupled ill-posed problems and introduce a deep demosaicing prior specifically for video demosaicing in SCI. Extensive results on both simulation and real datasets verify the superiority of our adaptive deep PnP algorithm. Code is available at https://github.com/xyvirtualgroup/AdaptivePnP_SCI. [ABSTRACT FROM AUTHOR]

Traditional navigation systems rely mainly on satellite navigation, but internal positioning and navigation cannot be achieved. This is mainly due to the inability to penetrate the wall due to the complex internal environment and the signal reaching the ground. Therefore, this paper proposes the research of indoor positioning algorithm based on improved convolutional neural network. The main method of this paper is based on the monocular vision indoor positioning based on the improved convolutional neural network. This method is an intelligent solution to the problems of traditional methods such as high cost, poor anti-interference ability, weak robustness, and poor compatibility. Positioning aids. The traditional computer vision camera pose estimation method is affected by the complex background in the image. When extracting feature corners, it is very affected by non-interest corners, so this paper adds an improved convolutional neural network algorithm to add in complex indoor scenes. With the region limitation, camera pose estimation in the region of interest is better to achieve low-cost, high accuracy and more stability. The improved model in this paper was tested on a test set of indoor datasets with markers, and the recognition accuracy reached 98.1%. In addition, this paper improves the PnP solution method, compares and analyzes the traditional RPnP, EPnP, and CEPPnP algorithms, and seeks the optimal camera pose estimation algorithm to locate the world coordinates of the current shooting position. The experimental results show that this paper proposes the positioning algorithm has high stability. [ABSTRACT FROM AUTHOR]

Face anti-spoofing has been attracting attention because of its prominent role in the security of face recognition systems. A face spoofing attack is launched on the authentication system by the attacker using the picture or video of the genuine user to get access to the services or information. This paper proposes local binary pattern (LBP) and convolutional neural network (CNN) based feature fusion model for classifying spoof face images. Initially, the images are pre-processed to remove the effect of the background in the feature extraction. The Viola-Jones algorithm is used for detecting and cropping the faces from the images. The color features of the pre-processed RGB images and LBP features are provided to the CNN. This feature combination reduces the requirement of a CNN-based deep learning architecture for providing a good classification performance. To validate the proposed model, it is trained and tested on NUAA and MSU-MFSD datasets. The experiment recorded the ACER of 0.21 and 0.20 on the MSU-MFSD and NUAA datasets, respectively. [ABSTRACT FROM AUTHOR]

Clustering is a fundamental task in the field of data analysis. With the development of deep learning, deep clustering focuses on learning meaningful representation with neural networks. Ensemble clustering algorithms combine multiple base partitions into a robust and better consensus clustering. Current deep ensemble clustering algorithms usually neglect shallow and original features. Besides, rarel algorithms use graph attention networks to explore clustering structures. This paper proposes a novel Clustering algorithm based on Multi-layer Features and Graph attention Networks (CMFGN). CMFGN obtains multi-layer features through the hierarchical convolutional layers. Moreover, CMFGN combines the co-association matrix with original features as the Graph Attention Networks (GAT) input to obtain consensus clustering, which reuses original information and leverages GAT to inherit a good clustering structure. Extensive experimental results show that CMFGN remarkably outputs competitive methods on four challenging image datasets. In particular, CMFGN achieves the ACC of 82.14% on the Digits dataset, which is almost up to 6% performance improvement compared with the best baseline. [ABSTRACT FROM AUTHOR]

At construction sites, wearing hard hats is an important and effective measure to protect workers from accidental injury. In order to remind workers to wear hard hats at all times, it is necessary to automate the detection process of hard hat-wearing. Limited to the environment, human posture, personal privacy and other elements, traditional detection methods often cannot detect the wearing of hard hats in a handy and quick manner. In the paper, an improved deep learning model based on yolov4 is proposed to detect hard hat-wearing. The accuracy and speed of the model are optimized by replacing the cumbersome overlapping of multiple convolution modules in the feature pyramid of yolov4 with cross-stage hierarchy modules. At the same time, since hard hat detection is to detect small targets, we improve the performance of yolov4 to detect small targets by changing the yolov4 feature layer output and linear transformation of anchors. The final algorithm obtains a mean average precision of 93.37% in hard hat detection, with an increase of 3.15% compared with that of the original yolov4. [ABSTRACT FROM AUTHOR]

Digitizing image-format piping and instrumentation diagrams (P&IDs) consists of a step for detecting the information objects that constitute P&IDs, which identifies connection relationships between the detected objects, and a step for creating digital P&IDs. This paper presents a P&ID line object extraction method that uses an improved continuous line detection algorithm to extract the information objects that constitute P&IDs. The improved continuous line detection algorithm reduces the time spent performing line extraction by edge detection that employs a differential filter. It is also used to detect continuous lines in the vertical, horizontal, and diagonal directions. Additionally, it processes diagonal continuous lines after performing image differentiation to handle short continuous lines, which are a major cause of misdetection when detecting diagonal continuous lines. The P&ID line object extraction method that incorporates this algorithm consists of three steps. The preprocessing step removes the diagram's outline borders and heading areas. Second, the detection step detects continuous lines and then detects the special signs that are needed to distinguish different types of lines. Third, the postprocessing step uses the detected line signs to identify detected continuous lines, which must be converted to other types of lines, and their types are changed. Finally, the lines and the flow arrow detection information are merged. To verify the proposed method, an image-format P&ID line extraction system prototype was implemented, and line extraction tests were conducted. In nine test P&IDs, the overall average precision and recall were 95.26 % and 91.25 %, respectively, demonstrating good line extraction performance. [ABSTRACT FROM AUTHOR]

In deep learning, asynchronous parallel stochastic gradient descent (APSGD) is a broadly used algorithm to speed up the training process. In asynchronous system, the time delay of stale gradients in asynchronous algorithms is generally proportional to the total number of workers. When the number of workers is too large, the time delay will bring additional deviation from the accurate gradient due to delayed gradients and may cause a negative influence on the convergence speed of the algorithm. One may ask: How many workers can be used at most to achieve both the convergence and the speedup? In this paper, we consider the asynchronous training problem with the non-convex case. We theoretically study this problem to find an approximating second-order stationary point using asynchronous algorithms in non-convex optimization and investigate the behaviors of APSGD near-saddle points. This work gives the first theoretical guarantee to find an approximating second-order stationary point in asynchronous algorithms and a provable upper bound for the time delay. The techniques we provide can be generalized to analyze other types of asynchronous algorithms to understand the behaviors of asynchronous algorithms in distributed asynchronous parallel training. [ABSTRACT FROM AUTHOR]

Multiobjective evolutionary algorithms (MOEAs) have received much attention in multiobjective optimization in recent years due to their practicality. With limited computational resources, most existing MOEAs cannot efficiently solve large-scale multiobjective optimization problems (LSMOPs) that widely exist in the real world. This paper innovatively proposes a dual decomposition strategy (DDS) that can be embedded into many existing MOEAs to improve their performance in solving LSMOPs. Firstly, the outer decomposition uses a sliding window to divide large-scale decision variables into overlapped subsets of small-scale ones. A small-scale multiobjective optimization problem (MOP) is generated every time the sliding window slides. Then, once a small-scale MOP is generated, the inner decomposition immediately creates a set of global direction vectors to transform it into a set of single-objective optimization problems (SOPs). At last, all SOPs are optimized by adopting a block coordinate descent strategy, ensuring the solution's integrity and improving the algorithm's performance to some extent. Comparative experiments on benchmark test problems with seven state-of-the-art evolutionary algorithms and a deep learning-based algorithm framework have shown the remarkable efficiency and solution quality of the proposed DDS. Meanwhile, experiments on two real-world problems show that DDS can achieve the best performance beyond at least one order of magnitude with up to 3072 decision variables. [ABSTRACT FROM AUTHOR]

Deep learning has become the main solution for face recognition applications due to its high accuracy and robustness. In recent years, a batch of research on lightweight convolutional neural networks (CNNs) has emerged, bringing new ideas to the economic application of face recognition systems. In this paper, a lightweight face recognition algorithm is proposed to reduce the number of parameters and calculations of the face feature extraction network. The most important part of our approach lies in designing a novel inverted residual shuffle unit (IR-Shuffle). After being trained by ArcFace loss on a GPU workstation, our model built on improved IR-Shuffle blocks of size 1.45 MB achieves an accuracy of 98.65%. In terms of running time, our model is 5 ms faster than the current fastest MobileFaceNet, with only about 0.5% drop in accuracy. The proposed algorithm is implemented and optimized on the Jetson Nano embedded platform, and accurate and real-time deployment of the face recognition system is realized. The system takes 37 ms to perform the complete face detection and recognition and is robust to complex backgrounds and ambient light changes. Experimental results show that our system is of practical application value. [ABSTRACT FROM AUTHOR]

This paper presents a digital image dataset of historical handwritten birth records stored in the archives of several parishes across Sweden, together with the corresponding metadata that supports the evaluation of document analysis algorithms' performance. The dataset is called SHIBR (the Swedish Historical Birth Records). The contribution of this paper is twofold. First, we believe it is the first and the largest Swedish dataset of its kind provided as open access (15,000 high-resolution colour images of the era between 1800 and 1840). We also perform some data mining of the dataset to uncover some statistics and facts that might be of interest and use to genealogists. Second, we provide a comprehensive survey of contemporary datasets in the field that are open to the public along with a compact review of word spotting techniques. The word transcription file contains 17 columns of information pertaining to each image (e.g., child's first name, birth date, date of baptism, father's first/last name, mother's first/last name, death records, town, job title of the father/mother, etc.). Moreover, we evaluate some deep learning models, pre-trained on two other renowned datasets, for word spotting in SHIBR. However, our dataset proved challenging due to the unique handwriting style. Therefore, the dataset could also be used for competitions dedicated to a large set of document analysis problems, including word spotting. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have evolved as a beneficial machine learning method that has been successfully used in various applications. Currently, DNN is a superior technique of extracting information from massive sets of data in a self-organized method. DNNs have different structures and parameters, which are usually produced for particular applications. Nevertheless, the training procedures of DNNs can be protracted depending on the given application and the size of the training set. Further, determining the most precise and practical structure of a deep learning method in a reasonable time is a possible problem related to this procedure. Meta-heuristics techniques, such as swarm intelligence (SI) and evolutionary computing (EC), represent optimization frames with specific theories and objective functions. These methods are adjustable and have been demonstrated their effectiveness in various applications; hence, they can optimize the DNNs models. This paper presents a comprehensive survey of the recent optimization methods (i.e., SI and EC) employed to enhance DNNs performance on various tasks. This paper also analyzes the importance of optimization methods in generating the optimal hyper-parameters and structures of DNNs in taking into consideration massive-scale data. Finally, several potential directions that still need improvements and open problems in evolutionary DNNs are identified. [ABSTRACT FROM AUTHOR]

The automatic detection of software vulnerabilities is considered a complex and common research problem. It is possible to detect several security vulnerabilities using static analysis (SA) tools, but comparatively high false-positive rates are observed in this case. Existing solutions to this problem depend on human experts to identify functionality, and as a result, several vulnerabilities are often overlooked. This paper introduces a novel approach for effectively and reliably finding vulnerabilities in open-source software programs. In this paper, we are motivated to examine the potential of the clonal selection theory. A novel deep learning-based vulnerability detection model is proposed to define features using the clustering theory of the clonal selection algorithm. To our knowledge, this is the first time we have used deep-learned long-lived team-hacker features to process memories of sequential features and mapping from the entire history of previous inputs to target vectors in theory. With an immune-based feature selection model, the proposed approach aimed to improve static analyses' detection abilities. A real-world SA dataset is used based on three open-source PHP applications. Comparisons are conducted based on using a classification model for all features to measure the proposed feature selection methods' classification improvement. The results demonstrated that the proposed method got significant enhancements, which occurred in the classification accuracy also in the true positive rate. [ABSTRACT FROM AUTHOR]

The goal of steganalysis is to unearth a concealed message hidden inside an innocent carrier by steganography. Steganography in the hands of unlawful people can pose a great threat to society. Secret message is embedded as a noise (residue) which silently disrupts the statistical nature of the carrier without visual transformation. For the purpose of unearthing covert communication, modeling this noise (residue) is a crucial factor. In this paper, a hybrid deep learning framework is proposed with convolutional neural network (CNN) to emphasize the need for residual based investigation for digital image steganalysis. In order to model the noise residuals, five types of handcrafted features are extracted, in which the first four types rely on acquiring noise residuals based on filtering by linear and nonlinear filters, and the fifth type relies on residual acquisition method based on Empirical Mode Decomposition (EMD). The extracted features are categorized using a robust CNN with a new parallel architecture that is capable of learning intricate details from input features to classify it as cover or stego. Mostly CNNs are trained with raw images, but in the proposed method, the 1-dimensional residual features are stacked into 2-dimensional grid and are then used to train the CNN. Three spatial content-adaptive and four spatial non-content-adaptive algorithms are used to evaluate the performance of the proposed architecture. The experimental results show the versatility and robustness of the proposed hybrid architecture towards these algorithms when compared to existing state-of-the-art steganalytic methods. A practical issue prevalent in deploying steganalysis in real-world is 'mismatch scenario,' and based on the experimentation done in this paper, the proposed architecture performs well under stego algorithm mismatch and payload mismatch scenarios. [ABSTRACT FROM AUTHOR]

With the leaps and bounds of computer performance and the advent of the era of big data, deep learning has drawn more and more attention from all walks of life. It can combine low-level features to form more abstract high-level features and describe the data more essentially. Therefore, it is widely used in various fields such as computer vision. Image segmentation is one of the most basic research topics in the field of computer vision. The main purpose is to extract regions of interest from images for later image processing research. In 3D reconstruction based on sequence images, the segmentation accuracy and speed of sequence images determine the quality and efficiency of target reconstruction. Therefore, when facing large-scale sequence images, the biggest problem is how to improve the segmentation speed while ensuring accuracy. Based on the above background, the research content of this article is an indoor scene segmentation algorithm based on full convolutional neural network. According to the characteristics of indoor application scenes, this paper proposes a fast convolutional neural network image segmentation method to segment the indoor scene image and construct the fast fully convolutional networks (FFCN) for indoor scene image segmentation uses inter-layer fusion to reduce the amount of network calculation parameters and avoid the loss of picture feature information by continuous convolution. In order to verify the effectiveness of the network, in this paper, a basic living object data set (XAUT data set) in an indoor environment is created. The XAUT data set is used to train the FFCN network under the Caffe framework to obtain an indoor scene segmentation model. In order to compare the effectiveness of the model, the structure of the worn FCN8s, FCN16s, and FCN32s models was fine-tuned, and the corresponding algorithm model for indoor scene segmentation was obtained by training with the XAUT data set. The experimental results show that the pixel recognition accuracy of all types of networks has reached 86%, and the mean IU ratio has reached more than 63%. The mean IU of the FCN8s network is the highest at 70.38%, but its segmentation speed is only 1/5 of FFCN. On the premise that other types of indicators are not much different, the average segmentation speed on FFCN fast segmentation convolutional neural network reaches 40 fps. It can be seen that the scale fusion technology can well avoid the loss of image feature information in the network convolution and reddening process. Compared with other FCN networks, it has a faster speed and is conducive to real-time image preprocessing. [ABSTRACT FROM AUTHOR]

Recently, phishing attacks have become one of the most prominent social engineering attacks faced by public internet users, governments, and businesses. In response to this threat, this paper proposes to give a complete vision to what Machine learning is, what phishers are using to trick gullible users with different types of phishing attacks techniques and based on our survey that phishing emails is the most effective on the targeted sectors and users which we are going to compare as well. Therefore, more effective phishing detection technology is needed to curb the threat of phishing emails that are growing at an alarming rate in recent years, thus will discuss the techniques of mitigation of phishing by Machine learning algorithms and technical solutions that have been proposed to mitigate the problem of phishing and valuable awareness knowledge users should be aware to detect and prevent from being duped by phishing scams. In this work, we proposed a detection model using machine learning techniques by splitting the dataset to train the detection model and validating the results using the test data , to capture inherent characteristics of the email text, and other features to be classified as phishing or non-phishing using three different data sets, After making a comparison between them, we obtained that the most number of features used the most accurate and efficient results achieved. the best ML algorithm accuracy were 0.88, 1.00, and 0.97 consecutively for boosted decision tree on the applied data sets. [ABSTRACT FROM AUTHOR]

In dark or poorly lit environments, it is often difficult for the naked eye to distinguish low-light-level images because of low brightness, low contrast and noise, and it is difficult to perform subsequent image processing (such as video surveillance and target detection). To solve these problems, this paper proposes a low-light-level image enhancement algorithm based on deep learning. First, the low-light-level image is segmented into several super-pixels, and the noise level of each super-pixel is estimated by the ratio of the local standard deviation to the local gradient. Then, the image is inverted and smoothed by a BM3D filter, and the structural filter adaptive method is used to obtain complete images without noise but with the correct texture. Finally, the noise-free image and texture-complete images are applied to the integrated network, which can not only enhance the contrast but also effectively prevent the over-enhancement of the contrast. The experimental results show that this method is superior to traditional methods in terms of both subjective and objective evaluation, and the peak signal–noise ratio and improved structural similarity are 31.64 dB and 91.2%, respectively. [ABSTRACT FROM AUTHOR]