Multimodal emotion analysis is pivotal in decoding complex human affect by integrating diverse data sources such as text, audio, and visual signals. In this article, we introduce contextual interaction-based multimodal emotion analysis with enhanced semantic information (CIME), a novel spatio-temporal interaction network that significantly improves emotion recognition accuracy and robustness. CIME employs a text-centric cross-modal attention mechanism to refine semantic representations, while simultaneously leveraging a graph convolutional network to model contextual dialog information by capturing both intraspeaker and interspeaker relationships. This dual approach enables the effective fusion of modality-specific cues and the mining of latent emotional associations across modalities. Extensive experiments conducted on benchmark datasets—including IEMOCAP and MOSEI—demonstrate that CIME consistently outperforms existing state-of-the-art methods in terms of overall classification accuracy and weighted F1-scores. Furthermore, detailed ablation studies underscore the critical contributions of both the cross-modal attention and graph-based contextual modules.

Abstract The most prevalent type of cancer worldwide is mouth cancer. Around 2.5% of deaths are reported annually due to oral cancer in 2023. Early diagnosis of oral squamous cell carcinoma (OSCC), a prevalent oral cavity cancer, is essential for treating and recovering patients. A few computerized techniques exist but are focused on traditional machine learning methods, such as handcrafted features. In this work, we proposed a fully automated architecture based on Self‐Attention convolutional neural network and Residual Network information fusion and optimization. In the proposed framework, the augmentation process is performed on the training and testing samples, and then two developed deep models are trained. A self‐attention MobileNet‐V2 model is developed and trained using an augmented dataset. In parallel, a Self‐Attention DarkNet‐19 model is trained on the same dataset, whereas the hyperparameters have been initialized using the whale optimization algorithm (WOA). Features are extracted from the deeper layers of both models and fused using a canonical correlation analysis (CCA) approach. The CCA approach is further optimized using an improved WOA version named Quantum WOA that removes the irrelevant features and selects only important ones. The final selected features are classified using neural networks such as wide neural networks. The experimental process is performed on the augmented dataset that includes two sets: 100× and 400×. Using both sets, the proposed method obtained an accuracy of 98.7% and 96.3%. Comparison is conducted with a few state‐of‐the‐art (SOTA) techniques and shows a significant improvement in accuracy and precision rate.

Abstract Detection of abandoned and stationary objects like luggage, boxes, machinery, and so forth, in public places is one of the challenging and critical tasks in the video surveillance system. These objects may contain weapons, bombs, or other explosive materials that threaten the public. Though various applications have been developed to detect stationary objects, different challenges, like occlusions, changes in geometrical features of things, and so forth, are still to be addressed. Considering the complexity of scenarios in public places and the variety of objects, a context‐aware model is developed based on mask region‐based convolution network (M‐RCNN) for detecting abandoned objects. A modified convolution operation is implemented in the Backbone network to understand features from geometric variations near objects. These modified operation layers can be adapted based on geometric interpretations to extract required features. Finally, a bounding box operation is performed to locate the abandoned object and mask the particular thing. Experiments have been performed on the benchmark dataset like ABODA and our dataset, which shows that an mAP of 0. 0.699 is achieved for model 1, 0.675 is achieved for model 2, and 0.734 mAP is completed for model 3. An ablation analysis has also been performed and compared with other state‐of‐the‐art methods. Based on the results, the proposed model better detects abandoned objects than existing state‐of‐the‐art methods.

Artificial Intelligence-of-Things (AIoT)-enabled supply chain systems (SCS) face critical challenges in balancing operational efficiency with privacy preservation. While federated learning (FL) offers a decentralized solution for collaborative model training without raw data sharing, it still remains vulnerable to adversarial attacks, such as gradient inversion and poisoning attacks, which would raise the risk of privacy leakage in SCS. This paper proposes a novel privacy-preserving FL framework that leverages meta-knowledge training to address these limitations. The proposed framework introduces two key innovations. First, a meta-knowledge extraction mechanism is designed to extract meta-knowledge from the training neural networks. Second, a meta-knowledge-based FL method that exchanges only meta-knowledge instead of full gradients is proposed. Since meta-knowledge is just condensed information from the whole network, exchanging it preserves privacy. Finally, we conduct experiments for smart healthcare applications. The experimental results justify that the proposed framework obtains better performance and convergence. Overall, the proposed framework could enable secure AIoT deployments for SCS, offering a scalable solution for real-world applications.

The interactive attention graph convolution network (IAGCN), a novel model proposed in this article, will revolutionize aspect-level sentiment analysis (SA). IAGCN effectively addresses these key features, in contrast to prior research that ignored the meaning of aspect terms and their relationship with context. The model combines a modified dynamic weighting layer with bidirectional long short-term memory (BiLSTM) to accurately acquire context. It takes use of graph convolutional networks (GCNs) to encrypt syntactic information from the syntactic dependency tree. Furthermore, a method for interactive attention is employed to discover the intricate relationships between context and aspect terms, which results in the reconstruction of those terms’ representations. Comparing the proposed IAGCN model to baseline models, impressive gains are made. Across five datasets, the model beats previous methods with an amazing improvement in F1 scores that ranges from 1.34% to 4.04% and an impressive improvement in accuracy that ranges from 0.56% to 1.75%. Additionally, the IAGCN model outperforms the global vectors (GloVe)-based strategy when the potent pretrained model bidirectional encoder representations from transformers (BERT) is included in the challenge, resulting in even greater improvements. The F1 score considerably increases from 2.59% to 7.55%, and accuracy increases from 1.47% to 3.95%, making the IAGCN model a standout performer in aspect-level SA.

Many problems related to natural language processing are solved by neural networks and big data. Researchers have previously focused on single-task supervised goals with limited data management to train slogan classification. A multi-task learning framework is used to learn jointly across several tasks related to generating multi-class slogan types. This study proposes a multi-task model named slogan generative adversarial network systems (Slo-GAN) to enhance coherence and diversity in slogan generation, utilizing generative adversarial networks and recurrent neural networks (RNN). Slo-GAN generates a new text slogan-type corpus, and the training generalization process is improved. We explored active learning (AL) and meta-learning (ML) for dataset labeling efficiency. AL reduced annotations by 10% compared to ML but still needed about 70% of the full dataset for baseline performance. The whole framework of Slo-GAN is supervised and trained together on all of these tasks. The text with the higher reporting score level is filtered by Slo-GAN, and a classification accuracy of 87.2% is achieved. We leveraged relevant datasets to perform a cross-domain experiment, reinforcing our assertions regarding both the distinctiveness of our dataset and the challenges of adapting bilingual dialects to one another.

There is a need to prevent the use of modulated voice signals to conduct criminal activities. Voice signal change detection based on convolutional neural networks is proposed. We use three commonly used voice processing software (Audacity, CoolEdit, and RTISI) to change tones in voice libraries. The research further raises each voice by five semitones and are recorded at different levels (+4, +5, +6, +7, and +8, respectively). Simultaneously, every voice is lowered by five halftones, represented as –4, –5, –6, –7, and –8, respectively. The convolution neural network corresponding to network b-3 is determined as the final classifier in this article through experiments. The average accuracy A1 of its three categories has reached more than 97%, the detection accuracy A2 of electronic tone sandhi speech has reached more than 97%, and the false alarm rate of the original speech is less than 1.9%. The outcomes obtained shows that the detection algorithm in this article is effective, and it has good generalization ability.

Diabetic retinopathy (DR) is on the increase nowadays due to the high sugar level in the blood, and it is the reason for blindness that mainly occurs in middle-aged people. Furthermore, the Internet of Medical Things (IoMT) enabled computer-aided diagnostic (CAD) systems record DR-related data online and give patients with reassuring information. The internet allows for the interconnection of a variety of smart devices, enabling remote healthcare systems based on the IoMT to link patients with medical professionals. The proper diagnosis of diabetic patients and detection of DR severity in earlier stages help in preventing blindness. Therefore, the basic aim of this study is to prevent the diabetic patient from losing vision by detecting and classifying the severity of DR fundus images using the IoMT-enabled CAD system. This article designed a novel diabetic retinopathy classification (DRC) system by hybridizing the DL model with optimization algorithms to classify the DR images based on severity. This system begins with preprocessing phase for removing the noise from edges. Next, the proposed K-mean cluster-based growing region segmentation is employed to extract the useful region from the images. Then, pretrained convolutional neural network (CNN) model, i.e., RESnet with the proposed hybrid genetic and ant colony optimization (HGACO) algorithm, is applied to extract the features from the region of interest (ROI) and classify them into four severity levels. Performance indices such as AUC,$F$-measure, accuracy, sensitivity, and specificity are analyzed to evaluate the performance on MESSIDOR dataset. The performance of the proposed DRC system is compared with state-of-the-art classification systems. The proposed HGACO algorithm is also compared with Adam and gradient descent (GD) optimizers. The system is also evaluated by employing different parameters of CNN and HGACO. Additionally, for the determination of the classification accuracy of the DRC system, the confidence interval statistical test is implemented considering various parameters and configurations of the neural network. The results revealed that the proposed DR system provides higher classification results by achieving 95.78%, 91.98%, 97.7%, and 94.56% AUC, sensitivity, accuracy, and specificity rate, respectively. CNN alleviates the difficulty of developing image features, whereas the HGACO algorithm-based technique automates CNN hyperparameter design.

Traditional classification algorithms struggle to categorize hypertensive retinopathy (HR) lesions correctly because they lack obvious characteristics. A regional IoT-enabled federated learning-based HR categorization approach (IoT-FHR) incorporating global and local attributes is suggested as a solution to this issue. The local feature arterial and venous nicking (AVN) classification model is fused with the overall IoT-FHR classification model to enhance the effect of the classification of IoT-FHR. The AVN classification model’s local lesion characteristics and the IoT-FHR classification model’s global lesion characteristics were combined using feature mean. After that, the results of the global IoT-FHR classification model are averaged with the results of the local AVN classification model. An easy neural network receives its input from the final outcome. The probability value of IoT-FHR in the fundus image is output by the sigmoid classifier after the neural network’s two fully connected and one dropout layer. The AVN classification makes a new kind of intersection detection algorithm suggestion. To determine the intersection points, the algorithm applies a logical AND operation to the classified arteries and veins. It takes HR fundus pictures and extracts AVN image blocks using the region of interest extraction approach. The accuracy, sensitivity, and specificity of the suggested fusion model are 93.50%, 69.83%, and 98.33%, respectively, when tested on a private dataset. It is clear from the experiments and results that the suggested model leads the currently used methods when the single-stage classification model is compared with them.

Abstract Medical internet of things (IoT) includes various devices, sensor, machines, equipment which exchange data over wide network. Industry 5.0 and 5G technology have ramped mIoT data and cost‐effective sensors. There is sudden upsurge in the medical IoT for enhancing the medical care. Integration of cloud server for data storage and cloud computing has led to the emergence of time and cost‐effective management of medical resources and improved patient lifestyle. However, cloud data is always at risk of data leak and malicious attack by unwanted users for their personal gains and agenda. With the increase of data exchange in the medical field, there is an urgency of keeping all the transaction safe and secure. There is a growing malicious data attacks and vulnerability. Therefore, to overcome such situations, the proposed model is a step towards sustainable technology. Keeping the focus on cost effective data security, the present work has developed a framework of modified Lamport Merkle Digital Signature method for signature generation and verification. It makes use of central healthcare controller (CHC) which determine the root of generated signature along with verification and authentication. For verification, the validation hash public key with generate key is required to validate the signature. This led to the efficient, cost effective and faster security when compared to the existing methods.

Modern big data applications tend to prefer a cluster computing approach as they are linked to the distributed computing framework that serves users jobs as per demand. It performs rapid processing of tasks by subdividing them into tasks that execute in parallel. Because of the complex environment, hardware and software issues, tasks might run slowly leading to delayed job completion, and such phenomena are also known as stragglers. The performance improvement of distributed computing framework is a bottleneck by straggling nodes due to various factors like shared resources, heavy system load, or hardware issues leading to the prolonged job execution time. Many state-of-the-art approaches use independent models per node and workload. With increased nodes and workloads, the number of models would increase, and even with large numbers of nodes. Not every node would be able to capture the stragglers as there might not be sufficient training data available of straggler patterns, yielding suboptimal straggler prediction. To alleviate such problems, we propose a novel collaborative learning-based approach for straggler prediction, the alternate direction method of multipliers (ADMM), which is resource-efficient and learns how to efficiently deal with mitigating stragglers without moving data to a centralized location. The proposed framework shares information among the various models, allowing us to use larger training data and bring training time down by avoiding data transfer. We rigorously evaluate the proposed method on various datasets with high accuracy results.

The advancement of Internet technologies has led to the availability of audios, images, and videos in different forms. The unauthorized users are exploiting the use of multimedia by transmitting them on various Internet sites to earn money unethically without the intervention of the original copyright holder. Watermarking is a technique used to hide the signal known as watermark inside multimedia data that is not visible to the intruder to manipulate any information. In this paper, a secured watermarking approach is developed to tackle issues related to copyright protection and ownership identification. A Secured Graph Based Transform, Singular Valued Decomposition, and Hyperchaotic Encryption hybrid techniques are proposed. The watermark cannot be embedded in every frame of the video as it adds to the size of the video and watermark can be easily retrieved by an intruder. Therefore, the frame selection algorithm has been proposed in the given work. Adding watermark in the frame adds to the challenge of quality loss. The quality loss is addressed in this work. Various attacks have been applied on the watermarked frames to calculate the performance of the proposed technique using quality metrics: Peak Signal to Noise Ratio, Structural Similarity Index, Normalized Correlation, and Bit Error Rate. The results indicate that the proposed technique is effective against various attack scenarios.

The existing work on unsupervised segmentation frequently does not present any statistical extent to estimating and equating procedures, gratifying a qualitative calculation. Furthermore, regardless of the datum that enormous research is dedicated to the advancement of a novel segmentation approach and upgrading the deep learning techniques, there is an absence of research comprehending the assessment of eminent conventional segmentation methodologies for HSI. In this paper, to moderately fill this gap, we propose a direct method that diminishes the issues to some extent with the deep learning methods in the arena of a HSI space and evaluate the proposed segmentation techniques based on the method of the clustering‐based profound iterating deep learning model for HSI segmentation termed as CPIDM. The proposed model is an unsupervised HSI clustering technique centered on the density of pixels in the spectral interplanetary space and the distance concerning the pixels. Furthermore, CPIDM is a fully convolutional neural network. In general, fully convolutional nets remain spatially invariant preventing them from modeling position‐reliant outlines. The proposed network maneuvers this by encompassing an innovative position inclined convolutional stratum. The anticipated unique edifice of deep unsupervised segmentation deciphers the delinquency of oversegmentation and nonlinearity of data due to noise and outliers. The spectrum efficacy is erudite and incidental from united feedback via deep hierarchy with pooling and convolutional strata; as a consequence, it formulates an affiliation among class dissemination and spectra along with three‐dimensional features. Moreover, the anticipated deep learning model has revealed that it is conceivable to expressively accelerate the segmentation process without substantive quality loss due to the existence of noise and outliers. The proposed CPIDM approach outperforms many state‐of‐the‐art segmentation approaches that include watershed transform and neuro‐fuzzy approach as validated by the experimental consequences.

In today’s era of technology, especially in the Internet commerce and banking, the transactions done by the Mastercards have been increasing rapidly. The card becomes the highly useable equipment for Internet shopping. Such demanding and inflation rate causes a considerable damage and enhancement in fraud cases also. It is very much necessary to stop the fraud transactions because it impacts on financial conditions over time the anomaly detection is having some important application to detect the fraud detection. A novel framework which integrates Spark with a deep learning approach is proposed in this work. This work also implements different machine learning techniques for detection of fraudulent like random forest, SVM, logistic regression, decision tree, and KNN. Comparative analysis is done by using various parameters. More than 96% accuracy was obtained for both training and testing datasets. The existing system like Cardwatch, web service‐based fraud detection, needs labelled data for both genuine and fraudulent transactions. New frauds cannot be found in these existing techniques. The dataset which is used contains transaction made by credit cards in September 2013 by cardholders of Europe. The dataset contains the transactions occurred in 2 days, in which there are 492 fraud transactions out of 284,807 which is 0.172% of all transaction.