Multi-Objective Equilibrium Optimizer for Feature Selection in High-Dimensional English Speech Emotion Recognition

Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.

Automatic modulation recognition of radio fuzes using a DR2D-based adaptive denoising method and textural feature extraction

The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.

Fine-Grained Ship Recognition Based on Visible and Near-Infrared Multimodal Remote Sensing Images: Dataset,Methodology and Evaluation

Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.

Workout Action Recognition in Video Streams Using an Attention Driven Residual DC-GRU Network

Regular exercise is a crucial aspect of daily life, as it enables individuals to stay physically active, lowers thelikelihood of developing illnesses, and enhances life expectancy. The recognition of workout actions in videostreams holds significant importance in computer vision research, as it aims to enhance exercise adherence, enableinstant recognition, advance fitness tracking technologies, and optimize fitness routines. However, existing actiondatasets often lack diversity and specificity for workout actions, hindering the development of accurate recognitionmodels. To address this gap, the Workout Action Video dataset (WAVd) has been introduced as a significantcontribution. WAVd comprises a diverse collection of labeled workout action videos, meticulously curated toencompass various exercises performed by numerous individuals in different settings. This research proposes aninnovative framework based on the Attention driven Residual Deep Convolutional-Gated Recurrent Unit (ResDCGRU)network for workout action recognition in video streams. Unlike image-based action recognition, videoscontain spatio-temporal information, making the task more complex and challenging. While substantial progresshas been made in this area, challenges persist in detecting subtle and complex actions, handling occlusions,and managing the computational demands of deep learning approaches. The proposed ResDC-GRU Attentionmodel demonstrated exceptional classification performance with 95.81% accuracy in classifying workout actionvideos and also outperformed various state-of-the-art models. The method also yielded 81.6%, 97.2%, 95.6%, and93.2% accuracy on established benchmark datasets, namely HMDB51, Youtube Actions, UCF50, and UCF101,respectively, showcasing its superiority and robustness in action recognition. The findings suggest practicalimplications in real-world scenarios where precise video action recognition is paramount, addressing the persistingchallenges in the field. TheWAVd dataset serves as a catalyst for the development ofmore robust and effective fitnesstracking systems and ultimately promotes healthier lifestyles through improved exercise monitoring and analysis.

Spatial Distribution Feature Extraction Network for Open Set Recognition of Electromagnetic Signal

This paper proposes a novel open set recognition method,the Spatial Distribution Feature Extraction Network(SDFEN),to address the problem of electromagnetic signal recognition in an open environment.The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors.The designed hybrid loss function considers both intra-class distance and inter-class distance,thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training.Consequently,this method allows unknown classes to occupy a larger space in the feature space.This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct.Additionally,the feature comparator threshold can be used to reject unknown samples.For signal open set recognition,seven methods,including the proposed method,are applied to two kinds of electromagnetic signal data:modulation signal and real-world emitter.The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment.Specifically,compared to the state-of-the-art Openmax method,the novel method achieves up to 8.87%and 5.25%higher micro-F-measures,respectively.

Recent Advances on Deep Learning for Sign Language Recognition

Sign language,a visual-gestural language used by the deaf and hard-of-hearing community,plays a crucial role in facilitating communication and promoting inclusivity.Sign language recognition(SLR),the process of automatically recognizing and interpreting sign language gestures,has gained significant attention in recent years due to its potential to bridge the communication gap between the hearing impaired and the hearing world.The emergence and continuous development of deep learning techniques have provided inspiration and momentum for advancing SLR.This paper presents a comprehensive and up-to-date analysis of the advancements,challenges,and opportunities in deep learning-based sign language recognition,focusing on the past five years of research.We explore various aspects of SLR,including sign data acquisition technologies,sign language datasets,evaluation methods,and different types of neural networks.Convolutional Neural Networks(CNN)and Recurrent Neural Networks(RNN)have shown promising results in fingerspelling and isolated sign recognition.However,the continuous nature of sign language poses challenges,leading to the exploration of advanced neural network models such as the Transformer model for continuous sign language recognition(CSLR).Despite significant advancements,several challenges remain in the field of SLR.These challenges include expanding sign language datasets,achieving user independence in recognition systems,exploring different input modalities,effectively fusing features,modeling co-articulation,and improving semantic and syntactic understanding.Additionally,developing lightweight network architectures for mobile applications is crucial for practical implementation.By addressing these challenges,we can further advance the field of deep learning for sign language recognition and improve communication for the hearing-impaired community.

Deep Learning Approach for Hand Gesture Recognition:Applications in Deaf Communication and Healthcare

Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.

Attention Guided Food Recognition via Multi-Stage Local Feature Fusion

The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.

Abnormal Action Recognition with Lightweight Pose Estimation Network in Electric Power Training Scene

Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.

KurdSet: A Kurdish Handwritten Characters Recognition Dataset Using Convolutional Neural Network

Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format for subsequent processing.Successfully recognizing complex and intricately shaped handwritten characters remains a significant obstacle.The use of convolutional neural network(CNN)in recent developments has notably advanced HCR,leveraging the ability to extract discriminative features from extensive sets of raw data.Because of the absence of pre-existing datasets in the Kurdish language,we created a Kurdish handwritten dataset called(KurdSet).The dataset consists of Kurdish characters,digits,texts,and symbols.The dataset consists of 1560 participants and contains 45,240 characters.In this study,we chose characters only from our dataset.We utilized a Kurdish dataset for handwritten character recognition.The study also utilizes various models,including InceptionV3,Xception,DenseNet121,and a customCNNmodel.To show the performance of the KurdSet dataset,we compared it to Arabic handwritten character recognition dataset(AHCD).We applied the models to both datasets to show the performance of our dataset.Additionally,the performance of the models is evaluated using test accuracy,which measures the percentage of correctly classified characters in the evaluation phase.All models performed well in the training phase,DenseNet121 exhibited the highest accuracy among the models,achieving a high accuracy of 99.80%on the Kurdish dataset.And Xception model achieved 98.66%using the Arabic dataset.

An Approach for Human Posture Recognition Based on the Fusion PSE-CNN-BiGRU Model

This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home environments.Firstly,the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton,thereby obtaining a human posture feature set.Thereafter,a double-layer BiGRU algorithm is utilized to extract multi-layer,bidirectional temporal features from the human posture feature set,and a CNN network with an exponential linear unit(ELU)activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human posture.Furthermore,a squeeze and excitation networks(SENet)module is introduced to adaptively learn the importance weights of each channel,enhancing the network’s focus on important features.Finally,comparative experiments are performed on available datasets,including the public human activity recognition using smartphone dataset(UCIHAR),the public human activity recognition 70 plus dataset(HAR70PLUS),and the independently developed home abnormal behavior recognition dataset(HABRD)created by the authors’team.The results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%,89.42%,and 98.90%,respectively,which are 5.24%,5.83%,and 3.19%higher than the average accuracy of the five models proposed in the comparative literature,including CNN,GRU,and others.The F1-score for abnormal posture recognition reaches 98.84%(heartache),97.18%(fall),99.6%(bellyache),and 98.27%(climbing)on the self-builtHABRDdataset,thus verifying the effectiveness,generalization,and robustness of the proposed model in enhancing human posture recognition.

TransTM:A device-free method based on time-streaming multiscale transformer for human activity recognition

RFID-based human activity recognition(HAR)attracts attention due to its convenience,noninvasiveness,and privacy protection.Existing RFID-based HAR methods use modeling,CNN,or LSTM to extract features effectively.Still,they have shortcomings:1)requiring complex hand-crafted data cleaning processes and 2)only addressing single-person activity recognition based on specific RF signals.To solve these problems,this paper proposes a novel device-free method based on Time-streaming Multiscale Transformer called TransTM.This model leverages the Transformer's powerful data fitting capabilities to take raw RFID RSSI data as input without pre-processing.Concretely,we propose a multiscale convolutional hybrid Transformer to capture behavioral features that recognizes singlehuman activities and human-to-human interactions.Compared with existing CNN-and LSTM-based methods,the Transformer-based method has more data fitting power,generalization,and scalability.Furthermore,using RF signals,our method achieves an excellent classification effect on human behaviorbased classification tasks.Experimental results on the actual RFID datasets show that this model achieves a high average recognition accuracy(99.1%).The dataset we collected for detecting RFID-based indoor human activities will be published.

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

Adaptive Segmentation for Unconstrained Iris Recognition

In standard iris recognition systems,a cooperative imaging framework is employed that includes a light source with a near-infrared wavelength to reveal iris texture,look-and-stare constraints,and a close distance requirement to the capture device.When these conditions are relaxed,the system’s performance significantly deteriorates due to segmentation and feature extraction problems.Herein,a novel segmentation algorithm is proposed to correctly detect the pupil and limbus boundaries of iris images captured in unconstrained environments.First,the algorithm scans the whole iris image in the Hue Saturation Value(HSV)color space for local maxima to detect the sclera region.The image quality is then assessed by computing global features in red,green and blue(RGB)space,as noisy images have heterogeneous characteristics.The iris images are accordingly classified into seven categories based on their global RGB intensities.After the classification process,the images are filtered,and adaptive thresholding is applied to enhance the global contrast and detect the outer iris ring.Finally,to characterize the pupil area,the algorithm scans the cropped outer ring region for local minima values to identify the darkest area in the iris ring.The experimental results show that our method outperforms existing segmentation techniques using the UBIRIS.v1 and v2 databases and achieved a segmentation accuracy of 99.32 on UBIRIS.v1 and an error rate of 1.59 on UBIRIS.v2.

Blind Recognition of Non-Binary LDPC Codes Based on Ant Colony Optimization

This paper introduces a novel blind recognition of non-binary low-density parity-check(LDPC)codes without a candidate set,using ant colony optimization(ACO)algorithm over additive white Gaussian noise(AWGN)channels.Specifically,the scheme that effectively combines the ACO algorithm and the non-binary elements over finite fields is proposed.Furthermore,an improved,simplified elitist ACO algorithm based on soft decision reliability is introduced to recognize the parity-check matrix over noisy channels.Simulation results show that the recognition rate continuously increases with an increased signalto-noise ratio(SNR)over the AWGN channel.

Enhancing Security and Privacy in Distributed Face Recognition Systems through Blockchain and GAN Technologies

The use of privacy-enhanced facial recognition has increased in response to growing concerns about data securityand privacy in the digital age. This trend is spurred by rising demand for face recognition technology in a varietyof industries, including access control, law enforcement, surveillance, and internet communication. However,the growing usage of face recognition technology has created serious concerns about data monitoring and userprivacy preferences, especially in context-aware systems. In response to these problems, this study provides a novelframework that integrates sophisticated approaches such as Generative Adversarial Networks (GANs), Blockchain,and distributed computing to solve privacy concerns while maintaining exact face recognition. The framework’spainstaking design and execution strive to strike a compromise between precise face recognition and protectingpersonal data integrity in an increasingly interconnected environment. Using cutting-edge tools like Dlib for faceanalysis,Ray Cluster for distributed computing, and Blockchain for decentralized identity verification, the proposedsystem provides scalable and secure facial analysis while protecting user privacy. The study’s contributions includethe creation of a sustainable and scalable solution for privacy-aware face recognition, the implementation of flexibleprivacy computing approaches based on Blockchain networks, and the demonstration of higher performanceover previous methods. Specifically, the proposed StyleGAN model has an outstanding accuracy rate of 93.84%while processing high-resolution images from the CelebA-HQ dataset, beating other evaluated models such asProgressive GAN 90.27%, CycleGAN 89.80%, and MGAN 80.80%. With improvements in accuracy, speed, andprivacy protection, the framework has great promise for practical use in a variety of fields that need face recognitiontechnology. This study paves the way for future research in privacy-enhanced face recognition systems, emphasizingthe significance of using cutting-edge technology to meet rising privacy issues in digital identity.

Squeeze and Excitation Convolution with Shortcut for Complex Plasma Image Recognition

Complex plasma widely exists in thin film deposition,material surface modification,and waste gas treatment in industrial plasma processes.During complex plasma discharge,the configuration,distribution,and size of particles,as well as the discharge glow,strongly depend on discharge parameters.However,traditional manual diagnosis methods for recognizing discharge parameters from discharge images are complicated to operate with low accuracy,time-consuming and high requirement of instruments.To solve these problems,by combining the two mechanisms of attention mechanism(strengthening the extraction of the channel feature)and shortcut connection(enabling the input information to be directly transmitted to deep networks and avoiding the disappearance or explosion of gradients),the network of squeeze and excitation convolution with shortcut(SECS)for complex plasma image recognition is proposed to effectively improve the model performance.The results show that the accuracy,precision,recall and F1-Score of our model are superior to other models in complex plasma image recognition,and the recognition accuracy reaches 97.38%.Moreover,the recognition accuracy for the Flowers and Chest X-ray publicly available data sets reaches 97.85%and 98.65%,respectively,and our model has robustness.This study shows that the proposed model provides a new method for the diagnosis of complex plasma images and also provides technical support for the application of plasma in industrial production.

Low-Brightness Object Recognition Based on Deep Learning

This research focuses on addressing the challenges associated with image detection in low-light environments,particularly by applying artificial intelligence techniques to machine vision and object recognition systems.The primary goal is to tackle issues related to recognizing objects with low brightness levels.In this study,the Intel RealSense Lidar Camera L515 is used to simultaneously capture color information and 16-bit depth information images.The detection scenarios are categorized into normal brightness and low brightness situations.When the system determines a normal brightness environment,normal brightness images are recognized using deep learning methods.In low-brightness situations,three methods are proposed for recognition.The first method is the SegmentationwithDepth image(SD)methodwhich involves segmenting the depth image,creating amask from the segmented depth image,mapping the obtained mask onto the true color(RGB)image to obtain a backgroundreduced RGB image,and recognizing the segmented image.The second method is theHDVmethod(hue,depth,value)which combines RGB images converted to HSV images(hue,saturation,value)with depth images D to form HDV images for recognition.The third method is the HSD(hue,saturation,depth)method which similarly combines RGB images converted to HSV images with depth images D to form HSD images for recognition.In experimental results,in normal brightness environments,the average recognition rate obtained using image recognition methods is 91%.For low-brightness environments,using the SD method with original images for training and segmented images for recognition achieves an average recognition rate of over 82%.TheHDVmethod achieves an average recognition rate of over 70%,while the HSD method achieves an average recognition rate of over 84%.The HSD method allows for a quick and convenient low-light object recognition system.This research outcome can be applied to nighttime surveillance systems or nighttime road safety systems.

Sparse representation scheme with enhanced medium pixel intensity for face recognition

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.

Rethinking multi-spatial information for transferable adversarial attacks on speaker recognition systems

Adversarial attacks have been posing significant security concerns to intelligent systems,such as speaker recognition systems(SRSs).Most attacks assume the neural networks in the systems are known beforehand,while black-box attacks are proposed without such information to meet practical situations.Existing black-box attacks improve trans-ferability by integrating multiple models or training on multiple datasets,but these methods are costly.Motivated by the optimisation strategy with spatial information on the perturbed paths and samples,we propose a Dual Spatial Momentum Iterative Fast Gradient Sign Method(DS-MI-FGSM)to improve the transferability of black-box at-tacks against SRSs.Specifically,DS-MI-FGSM only needs a single data and one model as the input;by extending to the data and model neighbouring spaces,it generates adver-sarial examples against the integrating models.To reduce the risk of overfitting,DS-MI-FGSM also introduces gradient masking to improve transferability.The authors conduct extensive experiments regarding the speaker recognition task,and the results demonstrate the effectiveness of their method,which can achieve up to 92%attack success rate on the victim model in black-box scenarios with only one known model.