Explore the vast range of titles available.

Accurate emotion recognition in social media text is critical for applications such as sentiment analysis, mental health monitoring, and human-computer interaction. However, existing approaches face challenges like computational complexity and class imbalance, limiting their deployment in resource-constrained environments. While transformer-based models achieve state-of-the-art performance, their size and latency hinder real-time applications. To address these issues, we propose a novel knowledge distillation framework that transfers knowledge from a fine-tuned BERT-base teacher model to lightweight DistilBERT and ALBERT student models, optimised for efficient emotion recognition. Our approach integrates a hybrid loss function combining focal loss and Kullback-Leibler (KL) divergence to enhance minority class recognition, attention-head alignment for effective contextual knowledge transfer, and semantic-preserving data augmentation to mitigate class imbalance. Experiments on two datasets, Twitter Emotions 416 K samples, six classes, and Social Media Emotion 75 K samples, five classes, show that our distilled models achieve near-teacher performance 97.35% and 73.86% accuracy, respectively. with only a < 1% and < 6% accuracy drop, while reducing model size by 40% and inference latency by 3.2×. Notably, our method significantly improves F1-scores for minority classes. Our work sets a new state-of-the-art in efficient emotion recognition, enabling practical deployment in edge computing and mobile applications.

Robotic manipulation refers to how robots intelligently interact with the objects in their surroundings, such as grasping and carrying an object from one place to another. Dexterous manipulating skills enable robots to assist humans in accomplishing various tasks that might be too dangerous or difficult to do. This requires robots to intelligently plan and control the actions of their hands and arms. Object manipulation is a vital skill in several robotic tasks. However, it poses a challenge to robotics. The motivation behind this review paper is to review and analyze the most relevant studies on learning-based object manipulation in clutter. Unlike other reviews, this review paper provides valuable insights into the manipulation of objects using deep reinforcement learning (deep RL) in dense clutter. Various studies are examined by surveying existing literature and investigating various aspects, namely, the intended applications, the techniques applied, the challenges faced by researchers, and the recommendations adopted to overcome these obstacles. In this review, we divide deep RL-based robotic manipulation tasks in cluttered environments into three categories, namely, object removal, assembly and rearrangement, and object retrieval and singulation tasks. We then discuss the challenges and potential prospects of object manipulation in clutter. The findings of this review are intended to assist in establishing important guidelines and directions for academics and researchers in the future.

Arabic dialect identification (ADI) aims to automatically determine the specific regional dialect of a given Arabic text. State-of-the-art ADI solutions often rely on fine-tuning Arabic-specific pre-trained language models (PLMs). Although effective, these PLMs are predominantly trained on modern standard Arabic (MSA), which limits their performance on dialectal data. Furthermore, the high degree of similarity among Arabic dialects makes it difficult to learn accurate dialect-specific representations without large volumes of labeled data. However, labeling such data is both costly and labor-intensive, particularly for low-resource languages like Arabic. To address these challenges, we propose a self-training neural approach that independently learns Dialectal Indicators . Our method leverages unlabeled data to construct a matrix that captures dialectal tokens frequently co-occurring in similar contexts. This matrix provides dialect-specific representations, which are integrated with PLM outputs to enhance ADI performance. We evaluate our approach on multiple ADI and related datasets. Results show that our method significantly improves PLM performance over direct fine-tuning, achieving gains of up to 36.2% in accuracy and 11.52% in macro-F1-score.

The exponential growth in the number of smart devices connected to the Internet of Things (IoT) that are associated with various IoT-based smart applications and services, raises interoperability challenges. Service-oriented architecture for IoT (SOA-IoT) solutions has been introduced to deal with these interoperability challenges by integrating web services into sensor networks via IoT-optimized gateways to fill the gap between devices, networks, and access terminals. The main aim of service composition is to transform user requirements into a composite service execution. Different methods have been used to perform service composition, which has been classified as trust-based and non-trust-based. The existing studies in this field have reported that trust-based approaches outperform non-trust-based ones. Trust-based service composition approaches use the trust and reputation system as a brain to select appropriate service providers (SPs) for the service composition plan. The trust and reputation system computes each candidate SP’s trust value and selects the SP with the highest trust value for the service composition plan. The trust system computes the trust value from the self-observation of the service requestor (SR) and other service consumers’ (SCs) recommendations. Several experimental solutions have been proposed to deal with trust-based service composition in the IoT; however, a formal method for trust-based service composition in the IoT is lacking. In this study, we used the formal method for representing the components of trust-based service management in the IoT, by using higher-order logic (HOL) and verifying the different behaviors in the trust system and the trust value computation processes. Our findings showed that the presence of malicious nodes performing trust attacks leads to biased trust value computation, which results in inappropriate SP selection during the service composition. The formal analysis has given us a clear insight and complete understanding, which will assist in the development of a robust trust system.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that is marked by a lack of communication skills in social situations and repetitive and stereotypical Behaviors. The most widespread form of diagnosing ASD among children is based on psychological screening test along with monitoring of the Behavioral pattern, especially repetitive Behaviors. Some of these Behaviors include hand-flapping, head banging and spinning which are common among ASD children. In our research, we examine abnormal Behavioral patterns that may reflect ASD through the videos of children engaged in the everyday activities in the unstructured settings. A publicly available multiclass Self-Stimulatory Behavior Dataset (SSBD) is use in classify autistic Behavior. Before training the model, the dataset is thoroughly pre-processed (region-of-interest (ROI) detection and image cropping to eliminate irrelevant background objects). Moreover, information-augmenting methods are used to reduce overfitting and increase training efficiency and generalization effectiveness. In order to obtain spatiotemporal details successfully, a number of deep learning models are tested, such as studied CNN-GRU model, 3D-CNN + LSTM, MobileNet, VGG16, and EfficientNet-B7. The findings of the experiment prove that the proposed CNN-GRU model is superior to all competing methods. The model with a k-fold cross-validation provides a steady accuracy of 0.9284 ± 0.0039–0.9294 ± 0.0038, which means that the model is robust and consistent across the folds. The effectiveness of the proposed approach is additionally justified by the comparisons with state-of-the-art methods. The results show that the systems based on the action recognition can help clinicians monitor the Behavioral trends and facilitate the quick, accurate, and effective screening of ASD. The proposed approach works effectively in predicting Behavior in real-life, uncontrolled videos and shows tremendous potential for real-world clinical implementation as a decision-support tool.

In recent years, several strategies have been introduced to enhance early warning systems and lower the risk of rock-falls. In this regard, this paper introduces a deep learning- and IoT-based framework for rock-fall early warning, devoted to reducing rock-fall risk with high accuracy. In this framework, the prediction accuracy was augmented by eliminating the uncertainties and confusion plaguing the prediction model. In order to achieve augmented prediction accuracy, this framework fused prediction model-based deep learning with a detection model-based Internet of Things. This study utilized parameters, namely, overall prediction performance measures based on a confusion matrix, to assess the performance of the framework in addition to its ability to reduce the risk. The result indicates an increase in prediction model accuracy from 86% to 98.8%. In addition, the framework reduced the risk probability from 1.51 × 10−3 to 8.57 × 10−9. Our findings demonstrate the high prediction accuracy of the framework, which also offers a reliable decision-making mechanism for providing early warning and reducing the potential hazards of rock falls.

Requirement elicitation represents one of the most vital phases in information system (IS) and software development projects. Selecting suitable elicitation techniques is critical for eliciting the correct specification in various projects. Recent studies have revealed that improper novice practices in this phase have increased the failure rate in both IS and software development projects. Previous research has primarily relied on creating procedural systems based on contextual studies of elicitation properties. In contrast, this paper introduces a deep learning model for selecting suitable requirement elicitation. An experiment was conducted wherein a collected dataset of 1684 technique selection attributes were investigate with respect to 14 elicitation techniques. The study adopted seven criteria to evaluate predictive model performance using confusion matrix accuracy, precision, recall, F1 Score, and area under the ROC curve (AUC) and loss curve. The model scored prediction accuracy of 82%, precision score of 0.83, recall score of 0.83, F1 score of 0.82, cross-validation score of 0.82 (± 0.10), One-vs-One ROC AUC score of 0.74, and One-vs-Rest ROC AUC score of 0.75 for each label. Our results indicate the model’s high prediction ability. The model provides a robust decision-making process for delivering correct elicitation techniques and lowering the risk of project failure. The implications of this study can be used to promote the automatization of the elicitation technique selection process, thereby enhancing current required elicitation industry practices.

Rock-fall is a natural threat resulting in many annual economic costs and human casualties. Constructive measures including detection or prediction of rock-fall and warning road users at the appropriate time are required to prevent or reduce the risk. This article presents a hybrid early warning system (HEWS) to reduce the rock-fall risks. In this system, the computer vision model is used to detect and track falling rocks, and the logistic regression model is used to predict the rock-fall occurrence. In addition, the hybrid risk reduction model is used to classify the hazard levels and delivers early warning action. In order to determine the system’s performance, this study adopted parameters, namely overall prediction performance measures, based on a confusion matrix and reliability. The results show that the overall system accuracy was 97.9%, and the reliability was 0.98. In addition, a system can reduce the risk probability from (6.39 × 10−3) to (1.13 × 10−8). The result indicates that this system is accurate, reliable, and robust; this confirms the purpose of the HEWS to reduce rock-fall risk.

The Internet of Things (IoT) has become a popular computing technology paradigm. It is increasingly being utilized to facilitate human life processes through a variety of applications, including smart healthcare, smart grids, smart finance, and smart cities. Scalability, interoperability, security, and privacy, as well as trustworthiness, are all issues that IoT applications face. Blockchain solutions have recently been created to help overcome these difficulties. The purpose of this paper is to provide a survey and tutorial on the use of blockchain in IoT systems. The importance of blockchain technology in terms of features and benefits for constituents of IoT applications is discussed. We propose a blockchain taxonomy for IoT applications based on the most significant factors. In addition, we examine the most widely used blockchain platforms for IoT applications. Furthermore, we discuss how blockchain technology can be used to broaden the spectrum of IoT applications. Besides, we discuss the recent advances and solutions offered for IoT environments. Finally, we discuss the challenges and future research directions of the use of blockchain for the IoT.

This paper proposes an ultrahigh voltage gain nonisolated DC–DC converter based on a modified double boost mode (MDBM), combined with a modified switched inductor‐switched capacitor (MSLSC) technique. The modified voltage multiplier technique (MVMT) is integrated with the MSLSC and MDBM using a second main metal‐oxide‐semiconductor field‐effect transistor (MOSFET) and an auxiliary third MOSFET to achieve ultrahigh voltage gain while reducing voltage stress across power devices. The primary objective is to achieve a voltage gain exceeding 21, thereby minimizing voltage stress on power devices, such as diodes and MOSFETs, as well as reducing current stress on all power switches and diodes in the proposed converter (PC). The MSLSC works in conjunction with the auxiliary third MOSFET and the double main MOSFETs to double the voltage gain and further reduce voltage stress on power devices. Notably, all diodes in the MVMT operate under zero current switching (ZCS), and the double main MOSFETs in the MDBM, along with the auxiliary third MOSFET, experience minimal current stress even at ultrahigh voltage gain levels. This converter offers several advantages, including high efficiency, reduced voltage stress on power devices, and lower current stress on power switches compared to previous nonisolated high step up DC–DC converters. The PC is designed to boost input voltages from 30V to a variable output range of 400–650 V, delivering up to 550 W with a peak efficiency of 96.5%.