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.

Japanese Sign Language Recognition by Combining Joint Skeleton-Based Handcrafted and Pixel-Based Deep Learning Features with Machine Learning Classification

Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities.In Japan,approximately 360,000 individualswith hearing and speech disabilities rely on Japanese Sign Language(JSL)for communication.However,existing JSL recognition systems have faced significant performance limitations due to inherent complexities.In response to these challenges,we present a novel JSL recognition system that employs a strategic fusion approach,combining joint skeleton-based handcrafted features and pixel-based deep learning features.Our system incorporates two distinct streams:the first stream extracts crucial handcrafted features,emphasizing the capture of hand and body movements within JSL gestures.Simultaneously,a deep learning-based transfer learning stream captures hierarchical representations of JSL gestures in the second stream.Then,we concatenated the critical information of the first stream and the hierarchy of the second stream features to produce the multiple levels of the fusion features,aiming to create a comprehensive representation of the JSL gestures.After reducing the dimensionality of the feature,a feature selection approach and a kernel-based support vector machine(SVM)were used for the classification.To assess the effectiveness of our approach,we conducted extensive experiments on our Lab JSL dataset and a publicly available Arabic sign language(ArSL)dataset.Our results unequivocally demonstrate that our fusion approach significantly enhances JSL recognition accuracy and robustness compared to individual feature sets or traditional recognition methods.

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.

Behaviour recognition based on the integration of multigranular motion features in the Internet of Things

With the adoption of cutting-edge communication technologies such as 5G/6G systems and the extensive development of devices,crowdsensing systems in the Internet of Things(IoT)are now conducting complicated video analysis tasks such as behaviour recognition.These applications have dramatically increased the diversity of IoT systems.Specifically,behaviour recognition in videos usually requires a combinatorial analysis of the spatial information about objects and information about their dynamic actions in the temporal dimension.Behaviour recognition may even rely more on the modeling of temporal information containing short-range and long-range motions,in contrast to computer vision tasks involving images that focus on understanding spatial information.However,current solutions fail to jointly and comprehensively analyse short-range motions between adjacent frames and long-range temporal aggregations at large scales in videos.In this paper,we propose a novel behaviour recognition method based on the integration of multigranular(IMG)motion features,which can provide support for deploying video analysis in multimedia IoT crowdsensing systems.In particular,we achieve reliable motion information modeling by integrating a channel attention-based short-term motion feature enhancement module(CSEM)and a cascaded long-term motion feature integration module(CLIM).We evaluate our model on several action recognition benchmarks,such as HMDB51,Something-Something and UCF101.The experimental results demonstrate that our approach outperforms the previous state-of-the-art methods,which confirms its effective-ness and efficiency.

A Support Data-Based Core-Set Selection Method for Signal Recognition

In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic environment.However,training deep learning-based classifiers on large signal datasets with redundant samples requires significant memory and high costs.This paper proposes a support databased core-set selection method(SD)for signal recognition,aiming to screen a representative subset that approximates the large signal dataset.Specifically,this subset can be identified by employing the labeled information during the early stages of model training,as some training samples are labeled as supporting data frequently.This support data is crucial for model training and can be found using a border sample selector.Simulation results demonstrate that the SD method minimizes the impact on model recognition performance while reducing the dataset size,and outperforms five other state-of-the-art core-set selection methods when the fraction of training sample kept is less than or equal to 0.3 on the RML2016.04C dataset or 0.5 on the RML22 dataset.The SD method is particularly helpful for signal recognition tasks with limited memory and computing resources.

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.

Exploring Sequential Feature Selection in Deep Bi-LSTM Models for Speech Emotion Recognition

Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.

Automatic modulation recognition of radiation source signals based on two-dimensional data matrix and improved residual neural network

Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.

Open World Recognition of Communication Jamming Signals

To improve the recognition ability of communication jamming signals,Siamese Neural Network-based Open World Recognition(SNNOWR)is proposed.The algorithm can recognize known jamming classes,detect new(unknown)jamming classes,and unsupervised cluseter new classes.The network of SNN-OWR is trained supervised with paired input data consisting of two samples from a known dataset.On the one hand,the network is required to have the ability to distinguish whether two samples are from the same class.On the other hand,the latent distribution of known class is forced to approach their own unique Gaussian distribution,which is prepared for the subsequent open set testing.During the test,the unknown class detection process based on Gaussian probability density function threshold is designed,and an unsupervised clustering algorithm of the unknown jamming is realized by using the prior knowledge of known classes.The simulation results show that when the jamming-to-noise ratio is more than 0d B,the accuracy of SNN-OWR algorithm for known jamming classes recognition,unknown jamming detection and unsupervised clustering of unknown jamming is about 95%.This indicates that the SNN-OWR algorithm can make the effect of the recognition of unknown jamming be almost the same as that of known jamming.

Adaptive Multi-Feature Fusion for Vehicle Micro-Motor Noise Recognition Considering Auditory Perception

The deployment of vehicle micro-motors has witnessed an expansion owing to the progression in electrification and intelligent technologies.However,some micro-motors may exhibit design deficiencies,component wear,assembly errors,and other imperfections that may arise during the design or manufacturing phases.Conse-quently,these micro-motors might generate anomalous noises during their operation,consequently exerting a substantial adverse influence on the overall comfort of drivers and passengers.Automobile micro-motors exhibit a diverse array of structural variations,consequently leading to the manifestation of a multitude of distinctive auditory irregularities.To address the identification of diverse forms of abnormal noise,this research presents a novel approach rooted in the utilization of vibro-acoustic fusion-convolutional neural network(VAF-CNN).This method entails the deployment of distinct network branches,each serving to capture disparate features from the multi-sensor data,all the while considering the auditory perception traits inherent in the human auditory sys-tem.The intermediary layer integrates the concept of adaptive weighting of multi-sensor features,thus affording a calibration mechanism for the features hailing from multiple sensors,thereby enabling a further refinement of features within the branch network.For optimal model efficacy,a feature fusion mechanism is implemented in the concluding layer.To substantiate the efficacy of the proposed approach,this paper initially employs an augmented data methodology inspired by modified SpecAugment,applied to the dataset of abnormal noise sam-ples,encompassing scenarios both with and without in-vehicle interior noise.This serves to mitigate the issue of limited sample availability.Subsequent comparative evaluations are executed,contrasting the performance of the model founded upon single-sensor data against other feature fusion models reliant on multi-sensor data.The experimental results substantiate that the suggested methodology yields heightened recognition accuracy and greater resilience against interference.Moreover,it holds notable practical significance in the engineering domain,as it furnishes valuable support for the targeted management of noise emanating from vehicle micro-motors.

Behavior Recognition of the Elderly in Indoor Environment Based on Feature Fusion of Wi-Fi Perception and Videos

With the intensifying aging of the population,the phenomenon of the elderly living alone is also increasing.Therefore,using modern internet of things technology to monitor the daily behavior of the elderly in indoors is a meaningful study.Video-based action recognition tasks are easily affected by object occlusion and weak ambient light,resulting in poor recognition performance.Therefore,this paper proposes an indoor human behavior recognition method based on wireless fidelity(Wi-Fi)perception and video feature fusion by utilizing the ability of Wi-Fi signals to carry environmental information during the propagation process.This paper uses the public WiFi-based activity recognition dataset(WIAR)containing Wi-Fi channel state information and essential action videos,and then extracts video feature vectors and Wi-Fi signal feature vectors in the datasets through the two-stream convolutional neural network and standard statistical algorithms,respectively.Then the two sets of feature vectors are fused,and finally,the action classification and recognition are performed by the support vector machine(SVM).The experiments in this paper contrast experiments between the two-stream network model and the methods in this paper under three different environments.And the accuracy of action recognition after adding Wi-Fi signal feature fusion is improved by 10%on average.

Radar Signal Recognition by CWD Picture Features

In this paper a system for automatic recognition of radar waveform is introduced. This technique is used in many spectrum management, surveillance, and cognitive radio and radar applications. For instance the transmitted radar signal is coded into six codes based on pulse compression waveform such as linear frequency modulation (LFM), Frank code, P1, P2, P3 and P4 codes, the latter four are poly phase codes. The classification system is based on drawing Choi Willliams Distribution (CWD) picture and extracting features from it. In this study, various new types of features are extracted from CWD picture and then a pattern recognition method is used to recognize the spectrum. In fact, signals from CWD picture are defined using biometric techniques. We also employ false reject rate (FRR) and false accept rate (FAR) which are two types of fault measurement criteria that are deploy in biometric papers. Fairly good results are obtained for recognition of Signal to Noise Ratio (-11 dB).

Automatic depression recognition by intelligent speech signal processing:A systematic survey

Depression has become one of the most common mental illnesses in the world.For better prediction and diagnosis,methods of automatic depression recognition based on speech signal are constantly proposed and updated,with a transition from the early traditional methods based on hand‐crafted features to the application of architectures of deep learning.This paper systematically and precisely outlines the most prominent and up‐to‐date research of automatic depression recognition by intelligent speech signal processing so far.Furthermore,methods for acoustic feature extraction,algorithms for classification and regression,as well as end to end deep models are investigated and analysed.Finally,general trends are summarised and key unresolved issues are identified to be considered in future studies of automatic speech depression recognition.

A New Pattern Recognition Method for Detection and Localization of Myocardial Infarction Using T-Wave Integral and Total Integral as Extracted Features from One Cycle of ECG Signal

In this paper we used two new features i.e. T-wave integral and total integral as extracted feature from one cycle of normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our previous work we used some features of body surface potential map data for this aim. But we know the standard ECG is more popular, so we focused our detection and localization of MI on standard ECG. We use the T-wave integral because this feature is important impression of T-wave in MI. The second feature in this research is total integral of one ECG cycle, because we believe that the MI affects the morphology of the ECG signal which leads to total integral changes. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI, because this method has very good accuracy for classification of normal signal and abnormal signal. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 76% for accuracy in test data for localization and over 94% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve the accuracy of classification by adding more features in this method. A simple method based on using only two features which were extracted from standard ECG is presented and has good accuracy in MI localization.

Automatic recognition of sonar targets using feature selection in micro-Doppler signature

Currently,the use of intelligent systems for the automatic recognition of targets in the fields of defence and military has increased significantly.The primary advantage of these systems is that they do not need human participation in target recognition processes.This paper uses the particle swarm optimization(PSO)algorithm to select the optimal features in the micro-Doppler signature of sonar targets.The microDoppler effect is referred to amplitude/phase modulation on the received signal by rotating parts of a target such as propellers.Since different targets'geometric and physical properties are not the same,their micro-Doppler signature is different.This Inconsistency can be considered a practical issue(especially in the frequency domain)for sonar target recognition.Despite using 128-point fast Fourier transform(FFT)for the feature extraction step,not all extracted features contain helpful information.As a result,PSO selects the most optimum and valuable features.To evaluate the micro-Doppler signature of sonar targets and the effect of feature selection on sonar target recognition,the simplest and most popular machine learning algorithm,k-nearest neighbor(k-NN),is used,which is called k-PSO in this paper because of the use of PSO for feature selection.The parameters measured are the correct recognition rate,reliability rate,and processing time.The simulation results show that k-PSO achieved a 100%correct recognition rate and reliability rate at 19.35 s when using simulated data at a 15 dB signal-tonoise ratio(SNR)angle of 40°.Also,for the experimental dataset obtained from the cavitation tunnel,the correct recognition rate is 98.26%,and the reliability rate is 99.69%at 18.46s.Therefore,the k-PSO has an encouraging performance in automatically recognizing sonar targets when using experimental datasets and for real-world use.

HRNetO:Human Action Recognition Using Unified Deep Features Optimization Framework

Human action recognition(HAR)attempts to understand a subject’sbehavior and assign a label to each action performed.It is more appealingbecause it has a wide range of applications in computer vision,such asvideo surveillance and smart cities.Many attempts have been made in theliterature to develop an effective and robust framework for HAR.Still,theprocess remains difficult and may result in reduced accuracy due to severalchallenges,such as similarity among actions,extraction of essential features,and reduction of irrelevant features.In this work,we proposed an end-toendframework using deep learning and an improved tree seed optimizationalgorithm for accurate HAR.The proposed design consists of a fewsignificantsteps.In the first step,frame preprocessing is performed.In the second step,two pre-trained deep learning models are fine-tuned and trained throughdeep transfer learning using preprocessed video frames.In the next step,deeplearning features of both fine-tuned models are fused using a new ParallelStandard Deviation Padding Max Value approach.The fused features arefurther optimized using an improved tree seed algorithm,and select the bestfeatures are finally classified by using the machine learning classifiers.Theexperiment was carried out on five publicly available datasets,including UTInteraction,Weizmann,KTH,Hollywood,and IXAMS,and achieved higheraccuracy than previous techniques.

Vote-Based Feature Selection Method for Stratigraphic Recognition in Tunnelling Process of Shield Machine

Shield machines are currently the main tool for underground tunnel construction. Due to the complexity and variability of the underground construction environment, it is necessary to accurately identify the ground in real-time during the tunnel construction process to match and adjust the tunnel parameters according to the geological conditions to ensure construction safety. Compared with the traditional method of stratum identifcation based on staged drilling sampling, the real-time stratum identifcation method based on construction data has the advantages of low cost and high precision. Due to the huge amount of sensor data of the ultra-large diameter mud-water balance shield machine, in order to balance the identifcation time and recognition accuracy of the formation, it is necessary to screen the multivariate data features collected by hundreds of sensors. In response to this problem, this paper proposes a voting-based feature extraction method (VFS), which integrates multiple feature extraction algorithms FSM, and the frequency of each feature in all feature extraction algorithms is the basis for voting. At the same time, in order to verify the wide applicability of the method, several commonly used classifcation models are used to train and test the obtained efective feature data, and the model accuracy and recognition time are used as evaluation indicators, and the classifcation with the best combination with VFS is obtained. The experimental results of shield machine data of 6 diferent geological structures show that the average accuracy of 13 features obtained by VFS combined with diferent classifcation algorithms is 91%;among them, the random forest model takes less time and has the highest recognition accuracy, reaching 93%, showing best compatibility with VFS. Therefore, the VFS algorithm proposed in this paper has high reliability and wide applicability for stratum identifcation in the process of tunnel construction, and can be matched with a variety of classifer algorithms. By combining 13 features selected from shield machine data features with random forest, the identifcation of the construction stratum environment of shield tunnels can be well realized, and further theoretical guidance for underground engineering construction can be provided.

Human Gait Recognition Based on Sequential Deep Learning and Best Features Selection

Gait recognition is an active research area that uses a walking theme to identify the subject correctly.Human Gait Recognition(HGR)is performed without any cooperation from the individual.However,in practice,it remains a challenging task under diverse walking sequences due to the covariant factors such as normal walking and walking with wearing a coat.Researchers,over the years,have worked on successfully identifying subjects using different techniques,but there is still room for improvement in accuracy due to these covariant factors.This paper proposes an automated model-free framework for human gait recognition in this article.There are a few critical steps in the proposed method.Firstly,optical flow-based motion region esti-mation and dynamic coordinates-based cropping are performed.The second step involves training a fine-tuned pre-trained MobileNetV2 model on both original and optical flow cropped frames;the training has been conducted using static hyperparameters.The third step proposed a fusion technique known as normal distribution serially fusion.In the fourth step,a better optimization algorithm is applied to select the best features,which are then classified using a Bi-Layered neural network.Three publicly available datasets,CASIA A,CASIA B,and CASIA C,were used in the experimental process and obtained average accuracies of 99.6%,91.6%,and 95.02%,respectively.The proposed framework has achieved improved accuracy compared to the other methods.

Improved Speech Emotion Recognition Focusing on High-Level Data Representations and Swift Feature Extraction Calculation

The performance of a speech emotion recognition(SER)system is heavily influenced by the efficacy of its feature extraction techniques.The study was designed to advance the field of SER by optimizing feature extraction tech-niques,specifically through the incorporation of high-resolution Mel-spectrograms and the expedited calculation of Mel Frequency Cepstral Coefficients(MFCC).This initiative aimed to refine the system’s accuracy by identifying and mitigating the shortcomings commonly found in current approaches.Ultimately,the primary objective was to elevate both the intricacy and effectiveness of our SER model,with a focus on augmenting its proficiency in the accurate identification of emotions in spoken language.The research employed a dual-strategy approach for feature extraction.Firstly,a rapid computation technique for MFCC was implemented and integrated with a Bi-LSTM layer to optimize the encoding of MFCC features.Secondly,a pretrained ResNet model was utilized in conjunction with feature Stats pooling and dense layers for the effective encoding of Mel-spectrogram attributes.These two sets of features underwent separate processing before being combined in a Convolutional Neural Network(CNN)outfitted with a dense layer,with the aim of enhancing their representational richness.The model was rigorously evaluated using two prominent databases:CMU-MOSEI and RAVDESS.Notable findings include an accuracy rate of 93.2%on the CMU-MOSEI database and 95.3%on the RAVDESS database.Such exceptional performance underscores the efficacy of this innovative approach,which not only meets but also exceeds the accuracy benchmarks established by traditional models in the field of speech emotion recognition.

GaitDONet: Gait Recognition Using Deep Features Optimization and Neural Network

Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not easy and makes the system difficult if any object is carried by a subject,such as a bag or coat.This article proposes an automated architecture based on deep features optimization for HGR.To our knowledge,it is the first architecture in which features are fused using multiset canonical correlation analysis(MCCA).In the proposed method,original video frames are processed for all 11 selected angles of the CASIA B dataset and utilized to train two fine-tuned deep learning models such as Squeezenet and Efficientnet.Deep transfer learning was used to train both fine-tuned models on selected angles,yielding two new targeted models that were later used for feature engineering.Features are extracted from the deep layer of both fine-tuned models and fused into one vector using MCCA.An improved manta ray foraging optimization algorithm is also proposed to select the best features from the fused feature matrix and classified using a narrow neural network classifier.The experimental process was conducted on all 11 angles of the large multi-view gait dataset(CASIA B)dataset and obtained improved accuracy than the state-of-the-art techniques.Moreover,a detailed confidence interval based analysis also shows the effectiveness of the proposed architecture for HGR.