Explore the vast range of titles available.

With the rapid integration of instant messaging systems (IMS) into critical domains such as finance, public services, and enterprise operations, ensuring the confidentiality, integrity, and availability of communication data has become a pressing concern. Existing IMS security solutions commonly employ traditional public-key cryptography, centralized authentication servers, or single-layer encryption, each of which is susceptible to single-point failures and provides only limited resistance against sophisticated attacks. This study addresses the research gap regarding the complementary advantages of SM2, SM3, and SM4 algorithms, as well as hybrid collaborative security schemes in IMS security. This paper presents a hybrid encryption security framework that combines the SM2, SM3, and SM4 algorithms to address emerging threats in IMS. The proposed framework adopts a decentralized architecture with certificateless authentication and performs all encryption and decryption operations on the client side, eliminating reliance on centralized servers and mitigating single-point failure risks. It further enforces an encrypt-before-store policy to enhance data security at the storage layer. The framework integrates SM2 for key exchange and authentication, SM4 for message encryption, and SM3 for integrity verification, forming a multi-layer defense mechanism capable of countering Man-in-the-Middle (MITM) attacks, credential theft, database intrusions, and other vulnerabilities. Experimental evaluations demonstrate the system’s strong security performance and communication efficiency: SM2 achieves up to 642 times faster key generation and 2.2 times faster decryption compared to RSA-3072; SM3 improves hashing performance by up to 11.5% over SHA-256; and SM4 delivers up to 22% higher encryption efficiency than AES-256 for small data blocks. These results verify the proposed framework’s practicality and performance advantages in lightweight, real-time IMS applications.

High efficiency and safety are critical factors in ensuring the optimal performance and reliability of systems and equipment across various industries. Fault monitoring (FM) techniques play a pivotal role in this regard by continuously monitoring system performance and identifying the presence of faults or abnormalities. However, traditional FM methods face limitations in fully capturing the complex interactions within a system and providing real-time monitoring capabilities. To overcome these challenges, Digital Twin (DT) technology has emerged as a promising solution to enhance existing FM practices. By creating a virtual replica or digital copy of a physical equipment or system, DT offers the potential to revolutionize fault monitoring approaches. This paper aims to explore and discuss the diverse range of predictive methods utilized in DT and their implementations in FM across industries. Furthermore, it will showcase successful implementations of DT in FM across a wide array of industries, including manufacturing, energy, transportation, and healthcare. The utilization of DT in FM enables a comprehensive understanding of system behavior and performance by leveraging real-time data, advanced analytics, and machine learning algorithms. By integrating physical and virtual components, DT facilitates the monitoring and prediction of faults, providing valuable insights into the system’s health and enabling proactive maintenance and decision making.

Contemporary advancements in wearable equipment have generated interest in continuously observing stress utilizing various physiological indicators. Early stress detection can improve healthcare by lessening the negative effects of chronic stress. Machine learning (ML) methodologies have been modified for healthcare equipment to monitor user health situations utilizing sufficient user information. Nevertheless, more data are needed to make applying Artificial Intelligence (AI) methodologies in the medical field easier. This research aimed to detect stress using a stacking model based on machine learning algorithms using chest-based features from the Wearable Stress and Affect Detection (WESAD) dataset. We converted this natural dataset into a convenient format for the suggested model by performing data visualization and preprocessing using the RESP feature and feature analysis using the Z-score, SelectKBest feature, the Synthetic Minority Over-Sampling Technique (SMOTE), and normalization. The efficiency of the proposed model was estimated regarding accuracy, precision, recall, and F1-score. The experimental outcome illustrated the efficacy of the proposed stacking technique, achieving 0.99% accuracy. The results revealed that the proposed stacking methodology performed better than traditional methodologies and previous studies.

[...].

Additive manufacturing (AM) has emerged as a transformative technology for various industries, enabling the production of complex and customized parts. However, ensuring the quality and reliability of AM parts remains a critical challenge. Thus, image-based fault monitoring has gained significant attention as an efficient approach for detecting and classifying faults in AM processes. This paper presents a comprehensive survey of image-based fault monitoring in AM, focusing on recent developments and future directions. Specifically, the proponents garnered relevant papers from 2019 to 2023, gathering a total of 53 papers. This paper discusses the essential techniques, methodologies, and algorithms employed in image-based fault monitoring. Furthermore, recent developments are explored such as the use of novel image acquisition techniques, algorithms, and methods. In this paper, insights into future directions are provided, such as the need for more robust image processing algorithms, efficient data acquisition and analysis methods, standardized benchmarks and datasets, and more research in fault monitoring. By addressing these challenges and pursuing future directions, image-based fault monitoring in AM can be enhanced, improving quality control, process optimization, and overall manufacturing reliability.

In the real world, most of the data obtained are hybrid data. Fully labeling such hybrid data is often time-consuming, labor intensive, and costly, while focusing solely on labeled samples may lead to the loss of critical information due to the limited number of labeled data. Research on feature selection using partially labeled data offers significant advantages, such as reducing dependency on labeled data and improving learning efficiency and performance. To address this issue, a semi-supervised feature selection method capable of handling partially labeled data is proposed based on the conditional discrimination index. First, by analyzing the characteristics of hybrid data, the distances between objects in the feature space are constructed, leading to the information granules with respect to feature subsets. Subsequently, in the label space, the missing labels are filled with the set composed of all existing labels, forming new partially labeled hybrid data. Considering the label distances between objects, a new tolerance relation is established to derive decision classes. Based on the information granules and decision classes, the significance of feature subsets is characterized using the discrimination index method. Then, a feature selection algorithm is designed depending on the significance. Experiments conducted on twelve real-world partially labeled hybrid datasets demonstrate that the proposed algorithm outperforms several existing feature selection algorithms in terms of classification accuracy and F1 score. Additionally, to validate the robustness of the algorithm, varying degrees of perturbations are introduced and tested on six of these datasets. The experimental results show that the algorithm still exhibits high stability, proving its applicability and reliability in complex and noisy environments. Statistical analyses further validate these findings. Finally, to further validate the practicality of the algorithm, it is deployed on an actual production line in a factory for fault detection, and significant results are achieved in the experimental tests.

Task-oriented dialogue systems face a tension between comprehensive constraint elicitation (task adequacy) and conversational efficiency (minimizing turns). Current preference learning frameworks treat preferences as static, unable to capture the dynamic evolution of interaction states that evolve across dialogue progression. We present Dual-DPO, a framework that embeds multi-objective preferences into data construction via turn-aware scoring. Our approach decouples objective balancing from policy updates through offline preference scalarization, addressing the optimization instability challenges in online multi-objective reinforcement learning. Experiments on MultiWOZ 2.4 demonstrate 28–35% dialogue turn reduction while maintaining Joint Goal Accuracy > 89% (p<0.001). Pareto frontier analysis shows 94% coverage with hypervolume HV=0.847. Independent expert evaluation by 10 PhD-level researchers (n=300 assessments, inter-rater agreement α=0.78) confirms 32% user satisfaction improvement (p<0.001). Theoretical analysis demonstrates that offline scalarization, which correlates with improved optimization stability, achieves 3.2× lower gradient variance than online multi-reward optimization by eliminating sampling stochasticity. Our approach enables balanced treatment of competing objectives through Pareto-optimal trade-offs. These results highlight a symmetric and balanced treatment of competing objectives within a Pareto-optimal optimization framework.

This study addresses the challenges of high-dimensional data, such as the curse of dimensionality and feature redundancy, which can be viewed as an inherent asymmetry in the data space. To restore a balanced symmetry and build a more complete feature representation, we propose an enhanced feature engineering model (EFEM) that employs a novel dual-strategy approach. First, we present a symmetrical feature selection algorithm that combines an improved Dolphin Swarm Algorithm (DSA) with the Maximum Relevance–Minimum Redundancy (mRMR) criterion. This method not only selects an optimal, high-relevance feature subset, but also identifies the remaining features as a complementary, redundant subset. Second, an ensemble learning-based feature reconstruction algorithm is introduced to mine potential information from these redundant features. This process transforms fragmented, redundant information into a new, synthetic feature, thereby establishing a form of information symmetry with the selected optimal subset. Finally, the EFEM constructs a high-performance feature space by symmetrically integrating the optimal feature subset with the synthetic feature. The model’s superior performance is extensively validated on nine standard UCI regression datasets, with comparative analysis showing that it significantly outperforms similar algorithms and achieves an average goodness-of-fit of 0.9263. The statistical significance of this improvement is confirmed by the Wilcoxon signed-rank test. Comprehensive analyses of parameter sensitivity, robustness, convergence, and runtime, as well as ablation experiments, further validate the efficiency and stability of the proposed algorithm. The successful application of the EFEM in a real-world product demand forecasting task fully demonstrates its practical value in complex scenarios.

With the most recent developments in wearable technology, the possibility of continually monitoring stress using various physiological factors has attracted much attention. By reducing the detrimental effects of chronic stress, early diagnosis of stress can enhance healthcare. Machine Learning (ML) models are trained for healthcare systems to track health status using adequate user data. Insufficient data is accessible, however, due to privacy concerns, making it challenging to use Artificial Intelligence (AI) models in the medical industry. This research aims to preserve the privacy of patient data while classifying wearable-based electrodermal activities. We propose a Federated Learning (FL) based approach using a Deep Neural Network (DNN) model. For experimentation, we use the Wearable Stress and Affect Detection (WESAD) dataset, which includes five data states: transient, baseline, stress, amusement, and meditation. We transform this raw dataset into a suitable form for the proposed methodology using the Synthetic Minority Oversampling Technique (SMOTE) and min-max normalization pre-processing methods. In the FL-based technique, the DNN algorithm is trained on the dataset individually after receiving model updates from two clients. To decrease the over-fitting effect, every client analyses the results three times. Accuracies, Precision, Recall, F1-scores, and Area Under the Receiver Operating Curve (AUROC) values are evaluated for each client. The experimental result shows the effectiveness of the federated learning-based technique on a DNN, reaching 86.82% accuracy while also providing privacy to the patient’s data. Using the FL-based DNN model over a WESAD dataset improves the detection accuracy compared to the previous studies while also providing the privacy of patient data.

Existing traffic flow prediction research lacks adaptability to complex traffic scenarios and has limited prediction accuracy. This paper introduces an improved LSTM (Long Short-Term Memory) algorithm and sliding window technology to improve the accuracy and stability of traffic flow prediction. This article discussed the enhancement of traffic flow (TF) prediction using a hybrid LSTM-BiGRU-Attention model aimed at improving the accuracy of traditional LSTM models. By integrating BiGRU (Bidirectional Gated Recurrent Unit) and Attention mechanisms, the proposed model captured complex TF patterns and long-term dependencies more effectively. The hybrid model is applied to Beijing urban road data with a time granularity (TG) of 10 min and a window size of 30 min, achieving an RMSE (root mean square error) of 4.478, an MAE (mean absolute error) of 3.609, and an R2 of 0.965. The LSTM-BiGRU-Attention model had similar prediction errors in TF during peak and off-peak periods and maintained high stability under different TF conditions. LSTM-BiGRU-Attention outperformed a single LSTM model and other benchmark models in multiple performance metrics. When the TG is 10 min, the window size of 30 min has the best performance, with 4.478, 3.609, and 0.965, respectively. The combination of LSTM, BiGRU, and Attention provides an effective solution for the development of intelligent transportation systems, which helps to achieve more accurate TF prediction and optimized management.HighlightsThis model combines LSTM, BiGRU and Attention mechanisms to improve the accuracy of traffic flow prediction, especially when dealing with long-term dependencies and nonlinear features.The data covers indicators such as traffic volume, speed and lane occupancy, and resamples at different time granularities.This paper optimizes the input of time series data by setting different window sizes, and finally selects appropriate sliding windows and time granularity to improve the performance of the prediction model.