Face Recognition (FR) is used in a variety of application domains, from entertainment and; to security and surveillance. Such applications rely on the FR model to be robust and perform well in a variety of settings. To achieve this, state-of-the-art FR models typically use expressive adaptive margin loss functions, which tie the feature norm to concepts related to sample quality, such as recognizability and perceptual image quality. Recently, through the development of Face Image Quality Assessment (FIQA) techniques, biometric utility has become the preferred measure of face-image quality and has been shown to be a better predictor of the usefulness of samples for face recognition compared to more human-centric aspects, such as resolution, blur, and lighting, tied to general image quality. While image quality expressed through feature norms exhibits a certain level of correlation with biometric utility, it does not fully encapsulate all aspects of utility. To address this point, we propose a new adaptive margin loss, FunFace (Face Recognition Through Utility and Norm Estimation), which incorporates biometric utility, estimated by the Certainty Ratio, into the adaptive margin, taking inspiration from AdaFace. We show that FunFace (when used to train a face recognition model) achieves competitive results to other state-of-the-art FR models on benchmarks containing high-quality samples, while surpassing them on low quality benchmarks. The code is available at https://github.com/LSIbabnikz/FunFace.

Facial emotion detection has witnessed a surge in demand across numerous applications, including human-computer interaction, healthcare, and security. Accurate expression recognition is crucial for improving human-computer interactions and understanding human behavior. Existing facial emotion detection models face challenges in achieving both high accuracy and real-time processing due to complex architectures. Our goal is to create an efficient yet accurate solution that can work on resource-constrained devices. To address the challenge of accurately recognizing emotions from facial expressions, we propose a novel hybrid approach that combines the strengths of pretrained Lightweight Convolutional Neural Networks (CNN), and Attention-based Vision Models. The pretrained Lightweight CNN serves as a feature extractor, efficiently capturing facial features, while the attention model refines the feature representation to focus on crucial regions of the face associated with different expressions. This enables our model to achieve state-of-the-art (SOTA) accuracy with reduced computational requirements. The proposed model, EmoVisioNet, achieves superior performance across multiple datasets, attaining 99.97 % accuracy on CK+, 96.23 % on RAF-DB, 93.88 % on FER2013, and 96.91 % on FERPlus. The obtained results surpass the current state-of-the-art in this field, demonstrating the EmoVisioNet’s superior performance in facial expression recognition.

Next-generation wireless networks aim to deliver transformative improvements in data rates, latency, and reliability. Among critical enabling technologies, rate-splitting multiple access (RSMA) combined with intelligent reflecting surfaces (IRS) mounted on unmanned aerial vehicles (UAV) has gained considerable attention. In this paper, we address the secrecy energy efficiency (SEE) maximization problem for short-packet communications in UAV-mounted IRS-assisted RSMA networks operating under finite block length (FBL) conditions. Unlike traditional scenarios optimized for long packets, our approach explicitly incorporates the significant impact of decoding errors and strict latency constraints inherent to short-packet transmission. We propose a comprehensive framework that jointly optimizes UAV deployment, IRS phase shifts, transmit precoding vectors, and common rate allocation. The formulated non-convex optimization problem is effectively solved via iterative decomposition and efficient approximation methods. Numerical evaluations demonstrate notable improvements in SEE compared to existing benchmark methods, underscoring the efficacy of UAV-mounted IRS and RSMA integration in addressing practical constraints of short-packet communication.

Speech represents a fundamental medium for conveying human emotions and, as a result, speech-based emotion recognition (SER) systems have become pivotal in advancing human-computer interaction (HCI) across a range of applications. While significant progress has been made in speech emotion recognition over recent years, existing solutions still face several key challenges, in that they:$(i)$rely excessively on subjectively annotated (discrete) labels during training,$(ii)$often overlook the label ambiguity of speech samples that express more than one class of emotions, and$(iii)$underutilize unlabeled or ambiguous speech, for which typically a label distribution (or so-called soft labels) is available. To address these issues, we propose in this paper a novel SER model that explicitly handles ambiguous speech samples and overcomes the shortcomings outlined above. Central to our approach is a novel real-time soft-label correction strategy designed to refine the annotations assigned to ambiguous speech. The proposed model leverages both, (explicitly) labeled as well as ambiguous samples and applies the dynamic soft-label correction strategy alongside an enhanced inter-class difference loss function to iteratively optimize the label distributions during training. We theoretically demonstrate that our method is capable of approximating the true emotional distribution of speech even in the presence of label noise, suggesting that utilizing ambiguous speech samples without explicit emotion labels still contributes toward more effective emotion recognition. Furthermore, we integrate the representational power of convolutional neural networks (CNNs) with the contextual modeling capabilities of Wav2Vec 2.0 to enable a comprehensive extraction of spatio-temporal speech features. Experimental results on the IEMOCAP multi-label dataset confirm the effectiveness of our approach, achieving state-of-the-art performance with significant improvements in weighted accuracy (WA) and unweighted accuracy (UA) over competing methods.

Robust multi-object tracking (MOT) is hindered by the instability of appearance features under visual corruptions such as occlusion and motion blur. These perturbations introduce high-variance noise into feature trajectories, weakening temporal representations and causing identity switches. We address this challenge by learning more stable appearance representations under feature corruption. To this end, we propose the Causal Interaction Module (CIM), a causal architecture that follows a filter then reconstruct design for online tracking. A temporal filtering stage summarizes the historical feature trajectory into a stable anchor, and a contextual enhancement stage uses that anchor to refine frame-level features before association. Integrated into standard trackers, CIM improves association robustness while preserving the host tracking formulation. Experiments on multiple MOT benchmarks and corruption stress tests show consistent gains, especially on association-related metrics.

With the continuous advancement of generative models, face morphing attacks have become a significant challenge for existing face verification systems due to their potential use in identity fraud and other malicious activities. Contemporary Morphing Attack Detection (MAD) approaches frequently rely on supervised, discriminative models trained on examples of bona fide and morphed images. These models typically perform well with morphs generated with techniques seen during training, but often lead to sub-optimal performance when subjected to novel unseen morphing techniques. While unsupervised models have been shown to perform better in terms of generalizability, they typically result in higher error rates, as they struggle to effectively capture features of subtle artifacts. To address these shortcomings, we present SelfMAD, a novel self-supervised approach that simulates general morphing attack artifacts, allowing classifiers to learn generic and robust decision boundaries without overfitting to the specific artifacts induced by particular face morphing methods. Through extensive experiments on widely used datasets, we demonstrate that SelfMAD significantly outperforms current state-of-theart MADs, reducing the detection error by more than $\mathbf{6 4} \%$ in terms of EER when compared to the strongest unsupervised competitor, and by more than $66 \%$, when compared to the best performing discriminative MAD model, tested in crossmorph settings. The source code for SelfMAD is available at https://github.com/LeonTodorov/SelfMAD.

Face Recognition (FR) plays a crucial role in many critical (high-stakes) applications, where errors in the recognition process can lead to serious consequences. Face Image Quality Assessment (FIQA) techniques enhance FR systems by providing quality estimates of face samples, enabling the systems to discard samples that are unsuitable for reliable recognition or lead to low-confidence recognition decisions. Most state-of-the-art FIQA techniques rely on extensive supervised training to achieve accurate quality estimation. In contrast, unsupervised techniques eliminate the need for additional training but tend to be slower and typically exhibit lower performance. In this paper, we introduce FROQ1(Face Recognition Observer of Quality), a semi-supervised, training-free approach that leverages specific intermediate representations within a given FR model to estimate face-image quality, and combines the efficiency of supervised FIQA models with the training-free approach of unsupervised methods. A simple calibration step based on pseudo-quality labels allows FROQ to uncover specific representations, useful for quality assessment, in any modern FR model. To generate these pseudo-labels, we propose a novel unsupervised FIQA technique based on sample perturbations. Comprehensive experiments with four state-of-the-art FR models and eight benchmark datasets show that FROQ leads to highly competitive results compared to the state-of-the-art, achieving both strong performance and efficient runtime, without requiring explicit training. The code for FROQ is available from: https://github.com/LSIbabnikz/FROQ

Abstract In the Internet of Medical Things (IoMT), the vulnerability of federated learning (FL) to single points of failure, low‐quality nodes, and poisoning attacks necessitates innovative solutions. This article introduces a FL‐driven dual‐blockchain approach to address these challenges and improve data sharing and reputation management. Our approach comprises two blockchains: the Model Quality Blockchain (MQchain) and the Reputation Incentive Blockchain (RIchain). MQchain utilizes an enhanced Proof of Quality (PoQ) consensus algorithm to exclude low‐quality nodes from participating in aggregation, effectively mitigating single points of failure and poisoning attacks by leveraging node reputation and quality thresholds. In parallel, RIchain incorporates a reputation evaluation, incentive mechanism, and index query mechanism, allowing for rapid and comprehensive node evaluation, thus identifying high‐reputation nodes for MQchain. Security analysis confirms the theoretical soundness of the proposed method. Experimental evaluation using real medical datasets, specifically MedMNIST, demonstrates the remarkable resilience of our approach against attacks compared to three alternative methods.

Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including the fashion industry. While numerous methods have been proposed to benefit buyers, particularly in virtual try-on applications, there has been relatively less focus on facilitating fast prototyping for designers and customers seeking to order new designs. To address this gap, we introduce DiCTI (Diffusion-based Clothing Designer via Text-guided Input), a straightforward yet highly effective approach that allows designers to quickly visualize fashion-related ideas using text inputs only. Given an image of a person and a description of the desired garments as input, DiCTI automatically generates multiple high-resolution, photorealistic images that capture the expressed semantics. By leveraging a powerful diffusion-based inpainting model conditioned on text inputs, DiCTI is able to synthesize convincing, high-quality images with varied clothing designs that viably follow the provided text descriptions, while being able to process very diverse and challenging inputs, captured in completely unconstrained settings. We evaluate DiCTI in comprehensive experiments on two different datasets (VITON-HD and Fashionpedia) and in comparison to the state-of-the-art (SoTa). The results of our experiments show that DiCTI convincingly outperforms the SoTA competitor in generating higher quality images with more elaborate garments and superior text prompt adherence, both according to standard quantitative evaluation measures and human ratings, generated as part of a user study. The source code of DiCTI will be made publicly available.

Facial Emotion Recognition (FER) is a challenging problem due to various challenges such as variability in expressions and ambiguity in data. Several popular benchmarking datasets, specifically employed for FER tasks exhibit bias towards ethnicity, demography and image capture mechanisms. More specifically, the images in such datasets are captured in a controlled environment and are taken in good light, with straight head orientation, no occlusion or other facial artefacts. When employed for FER, these biases may impair a model's generalizability, rendering it ineffective for FER in novel and unseen datasets. Especially, in applications involving security (access control) and identification of mal-intentions from facial expressions, it may prove inefficient. A criminal may disguise their face with make-up, headgear, and religious facial accessories and can fool the FER models trained on these biased datasets. To that end, this work focuses on understanding these datasets better by identifying such “good-image” bias. Methods to mitigate such bias which allows the FER models to perform better and improve the robustness are also demonstrated. A simple yet effective FER framework for studying bias mitigation is proposed. Using this framework, the performance on popular dataset is analyzed and a significant difference in model performance is observed. Additionally, a knowledge transfer technique and a synthetic image generation technique are proposed to mitigate the identified bias. Finally, using the SFEW dataset, the findings are validated on the FER task, demonstrating the effectiveness of our techniques in mitigating real-world “good-image” bias. The experiments show that the proposed techniques outperform baseline methods by averaged fourfold improvement.

Abstract Purpose Human monkeypox (MPX) is a viral infection that transmits between individuals via direct contact with animals, bodily fluids, respiratory droplets, and contaminated objects like bedding. Traditional manual screening for the MPX infection is a time‐consuming process prone to human error. Therefore, a computer‐aided MPX screening approach utilizing skin lesion images to enhance clinical performance and alleviate the workload of healthcare providers is needed. The primary objective of this work is to devise an expert system that accurately classifies MPX images for the automatic detection of MPX subjects. Methods This work presents a multi‐modal deep learning system through the fusion of convolutional neural network (CNN) and machine learning algorithms, which effectively and autonomously detect MPX‐infected subjects using skin lesion images. The proposed framework, termed MPXCN‐Net is developed by fusing deep features of three pre‐trained CNNs: MobileNetV2, DarkNet19, and ResNet18. Three classifiers—K‐nearest neighbour, support vector machine (SVM), and ensemble classifier—with various kernel functions, are used to identify infected patients. To validate the efficacy of our proposed system, we employ a publicly accessible MPX skin lesion dataset. Results By amalgamating features extracted from all three CNNs and utilizing the medium Gaussian kernel of the SVM classifier, our proposed system achieves an outstanding average classification accuracy of 90.4%. Conclusions Developed MPXCN‐Net is suitable for testing with a large diversified dataset before being used in clinical settings.

In this work, we investigate content delivery and target sensing problem in unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) networks where UAVs are allowed storing user-requested contents, delivering the content to users and performing target sensing as well. To jointly address the performance of content transmission and target sensing, we define utility function and formulate the UAV deployment, communication and sensing precoder design problem as a constrained utility maximization problem. As the formulated problem is a mixed-integer nonlinear programming problem, which cannot be solved conveniently, we transform it into two subproblems, namely, user grouping and UAV deployment subproblem, and communication and sensing precoder design subproblem, and solve the two subproblems by using an alternate iteration-based algorithm. Specifically, we first design a mean-shift-based user grouping strategy which divides users into different groups and then propose a UAV deployment strategy based on successive convex approximation (SCA)-based iterative algorithm and the first order Taylor expansion method. To solve communication and sensing precoder design subproblem, we propose a two-layer penalty-based SCA algorithm. Simulation results demonstrate the effectiveness of the proposed algorithms.

Simple authentication protocols based on conventional physical unclonable functions (PUFs) are vulnerable to modeling attacks and other security threats. This article proposes an arbiter PUF based on a linear feedback shift register (LFSR-APUF). Different from the previously reported linear feedback shift register (LFSR) for challenge extension, the proposed scheme feeds the external random challenges into the LFSR module to obfuscate the linear mapping relationship between the challenge and response. It can prevent attackers from obtaining valid challenge–response pairs (CRPs), increasing its resistance to modeling attacks significantly. A 64-stage LFSR-APUF has been implemented on a field programmable gate array (FPGA) board. The experimental results reveal that the proposed design can effectively resist various modeling attacks, such as logistic regression (LR), evolutionary strategy (ES), artificial neuro network (ANN), and support vector machine (SVM) with a prediction rate of 51.79% and a slight effect on the randomness, reliability, and uniqueness. Further, a lightweight authentication protocol is established based on the proposed LFSR-APUF. The protocol incorporates a low-overhead, ultralightweight, novel private bit conversion Cover function that is uniquely bound to each device in the authentication network. The proposed authentication protocol not only resists spoofing attacks, physical attacks, and modeling attacks effectively but also ensures the security of the entire authentication network by transferring important information in encrypted form from the server to the database even when the attacker completely controls the server.

Conversational emotion recognition represents an important machine-learning problem with a wide variety of deployment possibilities. The key challenge in this area is how to properly capture the key conversational aspects that facilitate reliable emotion recognition, including utterance semantics, temporal order, informative contextual cues, speaker interactions as well as other relevant factors. In this paper, we present a novel Graph Neural Network approach for conversational emotion recognition at the utterance level. Our method addresses the outlined challenges and represents conversations in the form of graph structures that naturally encode temporal order, speaker dependencies, and even long-distance context. To efficiently capture the semantic content of the conversations, we leverage the zero-shot feature-extraction capabilities of pre-trained large-scale language models and then integrate two key contributions into the graph neural network to ensure competitive recognition results. The first is a novel context filter that establishes meaningful utterance dependencies for the graph construction procedure and removes low-relevance and uninformative utterances from being used as a source of contextual information for the recognition task. The second contribution is a feature-correction procedure that adjusts the information content in the generated feature representations through a gating mechanism to improve their discriminative power and reduce emotion-prediction errors. We conduct extensive experiments on four commonly used conversational datasets, i.e., IEMOCAP, MELD, Dailydialog, and EmoryNLP, to demonstrate the capabilities of the developed graph neural network with context filtering and error-correction capabilities. The results of the experiments point to highly promising performance, especially when compared to state-of-the-art competitors from the literature.

Micro-expression recognition (MER) is a challenging computer vision problem, where the limited amount of available training data and insufficient intensity of the facial expressions are among the main issues adversely affecting the performance of existing recognition models. To address these challenges, this paper explores a transfer–learning enabled MER model using a densely connected feature extraction module with mixed attention. Unlike previous works that utilize transfer learning to facilitate MER and extract local facial-expression information, our model relies on pretraining with three diverse macro-expression datasets and, as a result, can: ( i ) overcome the problem of insufficient sample size and limited training data availability, ( i i ) leverage (related) domain-specific information from multiple datasets with diverse characteristics, and ( i i i ) improve the model adaptability to complex scenes. Furthermore, to enhance the intensity of the micro-expressions and improve the discriminability of the extracted features, the Euler video magnification (EVM) method is adopted in the preprocessing stage and then used jointly with a densely connected feature extraction module and a mixed attention mechanism to derive expressive feature representations for the classification procedure. The proposed feature extraction mechanism not only guarantees the integrity of the extracted features but also efficiently captures local texture cues by aggregating the most salient information from the generated feature maps, which is key for the MER task. The experimental results on multiple datasets demonstrate the robustness and effectiveness of our model compared to the state-of-the-art.

Natural Language Processing (NLP) aids the empowerment of intelligent machines by enhancing human language understanding for linguistic-based human-computer communication. Recent developments in processing power, as well as the availability of large volumes of linguistic data, have enhanced the demand for data-driven methods for automatic semantic analysis. This paper proposes multilingual data processing using feature extraction with classification using deep learning architectures. Here, the input text data has been collected based on various languages and processed to remove missing values and null values. The processed data has been extracted using Histogram Equalization based Global Local Entropy (HEGLE) and classified using Kernel-based Radial basis Function (Ker_Rad_BF). These architectures could be utilized to process natural language. We present solutions to the multilingual sentiment analysis issue in this research article by implementing algorithms, and we compare precision factors to discover the optimum option for multilingual sentiment analysis. For the HASOC dataset, the proposed HEGLE_ Ker_Rad_BF achieved an accuracy of 98%, a precision of 97%, a recall of 90.5%, an f-1 score of 85%, RMSE of 55.6%, and a loss curve analysis attained 44%. For the TRAC dataset, the accuracy of 98%, the precision attained is 97%, the Recall is 91%, the F-1 score is 87%, and the RMSE of the proposed neural network is 55%.

When tested with popular datasets, sentiment categorization using deep learning (DL) algorithms will produce positive results. Building a corpus on novel themes to train machine learning methods in sentiment classification with high assurance, however, will be difficult. This study proposes a way for representing efficient features of a dataset into a word embedding layer of DL methods in sentiment classification known as KPRO (knowledge processing and representation based on ontology), a procedure to embed knowledge in the ontology of opinion datasets. This research proposes novel methods in ontology-based natural language processing utilizing feature extraction as well as classification by a DL technique. Here, input text has been taken as web ontology based text and is processed for word embedding. Then the feature mapping is carried out for this processed text using least square mapping in which the sentiment-based text has been mapped for feature extraction. The feature extraction is carried out using a Markov model based auto-feature encoder (MarMod_AuFeaEnCod). Extracted features are classified by utilizing hierarchical convolutional attention networks. Based on this classified output, the sentiment of the text obtained from web data has been analyzed. Results are carried out for Twitter and Facebook ontology-based sentimental analysis datasets in terms of accuracy, precision, recall, F-1 score, RMSE, and loss curve analysis. For the Twitter dataset, the proposed MarMod_AuFeaEnCod_HCAN attains an accuracy of 98%, precision of 95%, recall of 93%, F-1 score of 91%, RMSE of 88%, and loss curve of 70.2%. For Facebook, ontology web dataset analysis is also carried out with the same parameters in which the proposed MarMod_AuFeaEnCod_HCAN acquires accuracy of 96%, precision of 92%, recall of 94%, F-1 score of 91%, RMSE of 77%, and loss curve of 68.2%.

Deep neural nets are opaque black-box models with little to no understanding of underlying model dynamics. This issue is more prevalent in the case of multimodal artificial intelligence (AI) systems, where model explainability and interpretability are prime concerns due to data integration from heterogeneous data streams and complex inter and intramodal interactions. However, the traditional explainable models are challenging to apply in the multimodal scenario. We propose a co-learning-based solution for fostering model explainability for the natural language processing (NLP)-based multimodal sentiment analysis application to address this issue. The proposed approach employs explainability by obeying the co-learning principles of dealing with noisy and missing modality either at train or test time to find the modality dominance by extracting the local and global model explanations. The proposed approach is validated with post hoc explainability methods such as local interpretable model-agnostic explanations (LIME) and SHapley Additive exPlanations (SHAP) gradient-based explanations to model the modality contributions and interactions at the fusion level. The co-learning-based system ensures trust and robustness in the model by providing some degree of model explainability along with robustness. The kind of explanations provided is multifaceted and is obtained through a peek inside the black box, hence is specifically helpful for the system designers and model developers to understand the complex model dynamics that are far more challenging in the case of multimodal applications.

The paper provides a summary of the 2023 Unconstrained Ear Recognition Challenge (UERC), a benchmarking effort focused on ear recognition from images acquired in uncontrolled environments. The objective of the challenge was to evaluate the effectiveness of current ear recognition techniques on a challenging ear dataset while analyzing the techniques from two distinct aspects, i.e., verification performance and bias with respect to specific demographic factors, i.e., gender and ethnicity. Seven research groups participated in the challenge and submitted a seven distinct recognition approaches that ranged from descriptor-based methods and deep-learning models to ensemble techniques that relied on multiple data representations to maximize performance and minimize bias. A comprehensive investigation into the performance of the submitted models is presented, as well as an in-depth analysis of bias and associated performance differentials due to differences in gender and ethnicity. The results of the challenge suggest that a wide variety of models (e.g., transformers, convolutional neural networks, ensemble models) is capable of achieving competitive recognition results, but also that all of the models still exhibit considerable performance differentials with respect to both gender and ethnicity. To promote further development of unbiased and effective ear recognition models, the starter kit of UERC 2023 together with the baseline model, and training and test data is made available from: http://ears.fri.uni-lj.si/

Speech, as a necessary way to express emotions, plays a vital role in human communication. With the continuous deepening of research on emotion recognition in human–computer interaction, speech emotion recognition (SER) has become an essential task to improve the human–computer interaction experience. When performing emotion feature extraction of speech, the method of cutting the speech spectrum will destroy the continuity of speech. Besides, the method of using the cascaded structure without cutting the speech spectrum cannot simultaneously extract speech spectrum information from both temporal and spatial domains. To this end, we propose a spatial–temporal parallel network for speech emotion recognition without cutting the speech spectrum. To further mix the temporal and spatial features, we design a novel fusion method (called multiple fusion) that combines the concatenate fusion and ensemble strategy. Finally, the experimental results on five datasets demonstrate that the proposed method outperforms state-of-the-art methods.

IoT-aided smart grid heavily depends on the most innovative communication technologies that could make the grid system susceptible to false data injection attacks (FDIAs). The main objective of the FDI attackers remains in damaging or corrupting the state estimation strategy in the smart grid resulting in blackouts and/or to influence the electricity market. With a number of features involved in the smart grid system, FDIA detection is said to be complicated. By the conventional bad data detection systems, the FDIA detection accuracy and validation made by the receiver operating characteristic (ROC) curve were marginally acceptable. However, due to the time complexity and overhead incurred, the detection of FDIA is a hot research topic. In this work, we design an efficient FDIA detection method by coupling cooperative paired swarm optimization and relational vector learning techniques (CPSO-RVL), to address the above-said issues. First, the cooperative paired particle swarm optimization model is proposed to attain an appropriate feature for improving the computational efficiency of FDIA detection. Next, with the obtained significant features, the relational vector learning-based FDIA detection model is designed for robust classification between FDIA and non-FDIA with minimum overhead. The extensive experiments show that the proposed method outperforms existing baseline approaches by 16% and 34% in terms of computation time and computation overhead, respectively.

Fingerprint recognition has emerged as one of the most reliable biometric authentication methods , owing to its uniqueness and permanence. However, the security and confidentiality of the user’s data are key considerations in modern biometric systems. In this study, we describe an intelligent computational technique for automatically validating fingerprints for identification and verification purposes. The feature vector is created by fusing Gabor filtering features with deep learning techniques like the faster region-based convolutional neural network (Faster R-CNN). This study uses linear and decision-based median filtering (DBMF) techniques to minimize visual impulse noise. Faster-R-CNN with DBMF was applied to the feature vectors to reduce overfitting problems while improving classification precision and reliability. For fingerprint matching, the Euclidean distance between the associated Harris-SURF feature vectors of two feature points is used to measure feature-matching similarity between two fingerprint images . Furthermore, for fine-tuned matching an iterative technique known as RANSAC (Random Sample Consensus) is used. The experimental results collected from the public-domain fingerprint databases FVC-2002 DB1 and FVC-2000 DB1 show that the proposed design is viable and performs well with an accuracy of 99.43%, MSE value of 43.321%, and an execution time of 3.102 ms which was more exact than existing models.

To balance the trade-off between contextual information and fine-grained information in identifying specific emotions during a dialogue and combine the interaction of hierarchical feature related information, this paper proposes a hierarchical feature interactive fusion network (named DHF-Net), which not only can retain the integrity of the context sequence information but also can extract more fine-grained information. To obtain a deep semantic information, DHF-Net processes the task of recognizing dialogue emotion and dialogue act/intent separately, and then learns the cross-impact of two tasks through collaborative attention. Also, a bidirectional gate recurrent unit (Bi-GRU) connected hybrid convolutional neural network (CNN) group method is designed, by which the sequence information is smoothly sent to the multi-level local information layers for feature exaction. Experimental results show that, on two open session datasets, the performance of DHF-Net is improved by 1.8% and 1.2%, respectively.

Social media can render content circulating to reach millions with a knack to influence people, despite the questionable authencity of the facts. Internet sources are the most convenient and easy approach to obtain any information these days. Fake news has become the topic of interest for academicians and the rest of society. This kind of propaganda has the power to influence the general perception, offering political groups the ability to control the results of democratic affairs such as elections. Automatic identification of fake news has emerged as one of the significant problems due to the high risks involved. It is challenging in a way because of the complexity levels of accurately interpreting the data. An extensive search has already been performed on English language news data. Our work presents a comparative analysis of fake news classifiers on the low resource Bengali language ‘ban fake news’ dataset from Kaggle. The analysis presented compares deep learning techniques such as LSTM (Long short-term Memory) and BiLSTM (Bi-directional Long short-term Memory) and machine learning methods like Naive Bayes, Passive Aggressive Classifier (PAC), and Random Forest. The comparison has been drawn based on classification metrics such as accuracy, precision, recall, and F1 score. The deep learning method BiLSTM shows 55.92% accuracy while Random Forest, in contrast, has outperformed all the other methods with an accuracy of 62.37%. The work presented in this paper sets a basis for researchers to select the optimum classifiers for their approach towards fake news detection.

The fifth industrial revolution (Industry 5.0) integrates humans and machines to satisfy the increasing customization demands of the manufacturing complexity using an optimized robotized manufacturing process. Industry 5.0 make use of collaborative robots (cobots) for optimizing productivity and ensuring safety. At the same time, unmanned aerial vehicles (UAVs) are predicted to be the main part of industry 5.0 in the forthcoming days. Regardless of high mobility and energy-limited UAVs for wireless communication as significant advantages, different issues are also existing in the UAV networks, such as security, reliability, etc. Several research works have focused on resolving security issues in UAV communication to support safety-critical applications. With this motivation, this article presents an artificial intelligence-based UAV-borne secure communication with classification (AIUAV-SCC) framework for industry 5.0 environment. The proposed AIUAV-SCC model involves two major phases namely image steganography-based secure communication and deep learning (DL)-based classification. At the initial stage, a new image steganography technique with multilevel discrete wavelet transformation, quantum bacterial colony optimization based optimal pixel selection, and encryption processes take place. Next, in the second stage, the Bayesian optimization (BO)-based SqueezeNet model is applied for the classification of securely received UAV images where the parameters in the SqueezeNet method are optimally tuned by the utilize of the BO technique. To validate the performance of the presented model, extensive simulations are applied using the UC Merced dataset (UCM) aerial dataset and the outcomes are investigated under several dimensions. The outcomes make sure the goodness of the presented model on test UCM aerial dataset over the compared methods.

Rapid advancements of sixth-generation (6G) network and Internet of Everything (IoE) supports numerous emerging services and application. Increasing mobile internet traffic and services, on the other hand, presented a number of challenges that could not be addressed with the current network design. The cybertwin is equipped with a variety of capabilities, including communication assistants, network data loggers, and digital asset owners, to address these difficulties. While spectrum resources are limited, effective resource management and sharing are essential in achieving these requirements. With this motivation, this article presents a new metaheuristic with blockchain based resource allocation technique (MWBA-RAT) for cybertwin driven 6G on IoE environment. The incorporation of the blockchain in 6G enables the network to monitor, manage, and share resources effectively. The proposed MWBA-RAT technique designs a new quasi-oppositional search and rescue optimization (QO-SRO) algorithm for the optimal resource allocation process and this shows the novelty of the work. The QO-SRO algorithm involves the integration of the quasi oppositional based learning concept with the traditional SRO algorithm to improve its convergence rate. A wide range of experiments are performed to highlight the enhanced outcomes of the MWBA-RAT technique.

Optical cloud radio access network (O-CRAN) is an emerging solution for IIoT, where numerous different devices/nodes are networked together. O-CRAN provides pool of shareable computing facility, equipped with hundreds of general-purpose processor (GPP). The GPPs process massive big data exerted by nodes via remote radio heads (RRHs), regarded as RRH-requests, which are bandwidth-intensive and deadline-constrained digitized base-band signals. Computing resource (CR) optimization has been widely investigated in O-CRAN. However, the existing optimizations may not guarantee workload and thermal balance among the active GPPs while satisfying RRH-request's deadline, which are necessary to efficiently leverage virtualization GPP capacity in a manner that provides the greatest uniform CR utilization (CRU). Due to varying network-load a single optimal solution does not exist. Therefore, in this article, we propose a modified-first-fit decreasing (MFFD) algorithm to obtain a suboptimal solution for each time_stage. The MFFD evenly assigns RRH-requests among GPPs that maximizes individual CRU uniformly contrasting with FFD.

In the past few years, the intelligent driving systems have witnessed rapid development, either it is self-driving cars or driver assistant systems. All these systems are built around perceiving the environment of the vehicle and taking appropriate steps in the given context. Computer vision has been playing a significant role in reducing the number of costly sensors used to perceiving the environment. In the past, the velocity of the vehicle was major estimated using sensors. In this paper, we propose a data-based methodology to estimate the relative velocity of vehicles using monocular cameras hence omitting the need for costly sensors such as lidars. Our proposed methods achieve a low mean velocity square error of 1.806, for estimating the velocity of the vehicle in a real-time environment.

In this paper, we tackle the issue of timbre transfer on a given monophonic music sample. The objective is to change the timbre of source audio from one instrument to another while preserving features such as loudness, pitch, and rhythm. Existing approaches use image-to-image translation techniques on the entire region of time-frequency representations of the raw audio wave, which may lead to the addition of unwanted elements in the final audio waveform. We propose Attention-based Timbre Transfer (ATT), an attention-based pipeline for transferring timbre. To the best of our knowledge, ATT is the first approach which leverages attention for achieving timbre transfer. Further, ATT uses MelGAN for spectrogram inversion, which provides a fast and parallel alternative to other autoregressive music generation approaches, without compromising on the quality. ATT shows promising results, thus efficaciously transferring timbre with minimal offset to other physical characteristics.

Alzheimer's disease (AD) is a neurodegenerative disorder resulting in memory loss and cognitive decline caused due to the death of brain cells. It is the most common form of dementia and accounts for 60-80% of all dementia cases. There is no single test for diagnosis of AD, the doctors rely on medical history, neuropsychological assessments, computed tomography (CT) or magnetic resonance imaging (MRI) scan of the brain, etc. to confirm a diagnosis. In terms of the treatment, currently, there is neither a cure nor any way to slow the progression of AD. However, for people with mild or moderate stages of this disease, there are some medications available to temporarily reduce symptoms and help to improve quality of life. Hence, early diagnosis of AD is extremely crucial for overall better management of the disease. The researches have shown some relation between neuropsychological scores and atrophies of the brain. This can be leveraged for the early diagnosis of AD. This paper makes use of feature selection techniques to extract the most important features in the diagnosis of AD. This paper demonstrates the need to combine neuropsychological scores like mini-mental state examination (MMSE) with MRI features to provide better decisional space for early diagnosis of AD. Through the experiments, including MMSE along with other features are found to improve the classification of AD, significantly.

Surface detection of small defects plays a vital role in manufacturing and has attracted broad interest. It remains challenging primarily due to the small size of the defect relative to the large surface and the rare occurrence of defects. To address this problem, in this article we propose a novel machine vision approach for automatically identifying the tiny flaws that may appear in a single image. First, the presented defect exaggeration approach produces both the flawless image and the corresponding exaggerated version of the defect by taking the variations in the image as regularization terms. Second, a generative adversarial network (GAN) in conjunction with a convolutional neural network (CNN) is proposed to guarantee the accuracy of tiny surface defect detection by producing exaggerated defect image samples. Furthermore, the limited dataset of the training samples for defect detection is enlarged by exploiting the GAN technique with the variation exaggerated images. To evaluate the performance of our proposed method, we conduct comparison experiments between the state-of-the-art techniques with and without the proposed algorithm as well as comparison experiments between the state-of-the-art techniques and our method. The experimental results on different types of surface image samples demonstrate that the proposed method can significantly improve the performance of the state-of-the-art approaches while achieving a defect detection accuracy of 99.2%.

With rapid development of computing technologies, large amount of data are gathered from edge terminals or Internet of Things (IoT) devices, however data trust and security in edge computing environment are very important issues to be considered, especially when the gathered data are fraud or dishonest, or the data are misused or spread without any authorization, which may lead to serious problems. In this article, a blockchain-based trusted data management scheme (called BlockTDM) in edge computing is proposed to solve the above problems, in which we proposed a flexible and configurable blockchain architecture that includes mutual authentication protocol, flexible consensus, smart contract, block and transaction data management, blockchain nodes management, and deployment. The BlockTDM scheme can support matrix-based multichannel data segment and isolation for sensitive or privacy data protection, and moreover, we have designed user-defined sensitive data encryption before the transaction payload stores in blockchain system, and have implemented conditional access and decryption query of the protected blockchain data and transactions through smart contract. Finally, we have evaluated the proposed BlockTDM scheme security, availability, and efficiency with large amount of experiments. Analysis and evaluations manifest that the proposed BlockTDM scheme provides a general, flexible, and configurable blockchain-based paradigm for trusted data management with tamper-resistance, which is suitable for edge computing with high-level security and creditability.