Multivariate time series classification (MTSC) plays a critical role in a wide range of real-world applications, such as healthcare, finance, and industrial monitoring. This paper proposes a triple-fusion network (TriFusNet), a novel convolutional network designed to address the challenges of MTSC. TriFusNet employs a specialized architecture that captures both variable-specific features and features shared across variables through the parallel use of standard, depth-wise, and shared-kernel convolutions. A hierarchical triple-fusion strategy is introduced to enhance representation learning across three stages: input-level fusion transforms raw variables, intermediate-level fusion integrates heterogeneous features, and output-level fusion improves decision robustness. Extensive experiments on 26 benchmark datasets show that TriFusNet outperforms 15 competitive baselines, achieving the best average rank (4.3077) with a Win/Draw/Loss of 5/4/17. The effectiveness of its architectural design and parameter settings is empirically validated, and a qualitative theoretical discussion is conducted to support the proposed fusion strategy. These results highlight TriFusNet's strong potential for real-world applications involving complex and high-dimensional time series data.

Federated learning (FL) is a machine learning technique in which a large number of clients collaborate to train models without sharing private data. However, FL’s integrity is vulnerable to unreliable models; for instance, data poisoning attacks can compromise the system. In addition, system preferences and resource disparities preclude fair participation by reliable clients. To address this challenge, we propose a novel client selection strategy that introduces a security‐fairness value to measure client performance in FL. The value in question is a composite metric that combines a security score and a fairness score. The former is dynamically calculated from a beta distribution reflecting past performance, while the latter considers the client’s participation frequency in the aggregation process. The weighting strategy based on the deep deterministic policy gradient (DDPG) determines these scores. Experimental results confirm that our method fairly effectively selects reliable clients and maintains the security and fairness of the FL system.

Federated learning (FL) has shown promise in smart industries as a means of training machine-learning models while preserving privacy. However, it contradicts FL’s low communication latency requirement to rely on the cloud to transmit information with data owners in model training tasks. Furthermore, data owners may not be willing to contribute their resources for free. To address this, we propose a single contract to dual contract approach to incentivize both model owners and workers to participate in FL-based machine learning tasks. The single-contract incentivizes model owners to contribute their model parameters, and the dual contract incentivizes workers to use their latest data to participate in the training task. The latest data draw out the trade-off between data quantity and data update frequency. Performance evaluation shows that our dual contract satisfies different preferences for data quantity and update frequency, and validates that the proposed incentive mechanism is incentive compatible and flexible.

Federated learning (FL) has emerged as a promising framework for collaborative machine learning, allowing the training of machine learning models on distributed devices without centralizing sensitive data. However, FL falls short in terms of fairness, as each client receives the same model regardless of their individual contributions. This unfairness discourages active client participation in FL. To address this challenge, we propose a contribution‐based differentiated global model mechanism. Specifically, we introduce the contribution score as a metric to assess client contributions in FL and utilize deep Q‐networks (DQN) to dynamically update the contribution scores. Subsequently, we allocate clients to different clusters based on their contributions by using a clustering algorithm, where each cluster is associated with a distinct global model. This mechanism encourages clients to make greater contributions for improved global models. Experimental results confirm the effectiveness of our approach in enhancing fairness in FL.

Social trust assessment that characterizes a pairwise trustworthiness relationship can spur diversified applications. Extensive efforts have been put in exploration, but mainly focusing on applying graph convolutional network to establish a social trust evaluation model, overlooking user feature factors related to context-aware information on social trust prediction. In this article, we aim to design a new trust assessment framework GATrust which integrates multi-aspect properties of users, including user context-specific information, network topological structure information, and locally-generated social trust relationships. GATrust can assigns different attention coefficients to multi-aspect properties of users in online social networks, for improving the prediction accuracy of social trust evaluation. The framework can then learn multiple latent factors of each trustor-trustee pair to establish a social trust evaluation model, by fusing graph attention network and graph convolution network. We conduct extensive experiments on two popular real-world datasets and the results exhibit that our proposed framework can improve the precision of social trust prediction, outperforming the state-of-the-art in the literature by 4.3% and 5.5% on both two datasets, respectively.

Three-dimensional (3D) medical images are prone to overlap, and there are some problems, such as low detection efficiency and inconsistent with the actual situation. Therefore, a 3D medical image surface reconstruction method based on data mining and machine learning is proposed. The 3D medical images were classified according to different ways, the information frame of 3D medical images was established and the surface overlapping information model of 3D images was given. Based on this information framework, the nonlinear function of overlapping area information of 3D medical images was constructed. The weight of the nonlinear function was used to calculate the input and output results of overlapping area information. Combined with the input mode of 3D medical image information, the error between the information output and the expected output was set. The nonlinear function weight of the overlapping area information of 3D medical images was modified by using the learning rate and the use time of the overlapping area information, and the influence factors of the overlapping information detection were obtained by increasing the situation terms, so as to complete the detection of the surface reconstruction information of 3D medical images. The experimental results show that the information detection results of the proposed method fit well with the actual situation, and the information detection efficiency is high.

The recommender system is of great significance to alleviate information overload. The rise of online social networks leads to a promising direction—social recommendation. By injecting the interaction influence among social users, recommendation performance has been further improved. Successful as they are, we argue that most social recommendation methods are still not sufficient to make full use of social network information. Existing solutions typically either considered only the local neighbors or treat neighbors’ information equally, even or both. However, few studies have attempted to solve these social recommendation problems jointly from both the perspective of social depth and social strength. Recently, graph convolutional neural networks have shown great potential in learning graph data by modeling the information propagation and aggregation process. Thus, we propose an attention-based social aggregation neural networks (abbreviated as SAN) model to build a recommendation system. Different from previous work, our proposed SAN model simulates the recursive social aggregation process to spread the global social influence, and simultaneously introduces social attention mechanism to incorporate the heterogeneous influences for better model user embedding. Instead of a shallow linear interaction function, we adopt multi-layer perception to model the complex user–item interaction. Extensive experiments on two real-world datasets show the effectiveness of our proposed model SAN, and further analysis verifies the generalization and flexibility of the model.

In recent years, the appearance of graph convolutional networks (GCNs) provides a new idea for graph structure data processing. Because of that, they can learn excellent user and item embedding by using cooperative signals of high-order neighbors, and the GCNs technique shows great potential in the recommendation. The common problem with the bulk of GCN-based models is that it appears the situation of performance degradation during the stacking of network layers. The recently proposed IMP-GCN alleviates this problem to some extent. It aims to avoid the influence of downside information from high-order propagation on embedding learning. However, we consider that it ignores the multi-interest factor, in which users may have different interests. In this paper, we present a multi-interest GCN(MI-GCN) model for a recommendation, and it conducts high-order graph convolution operations in three sets of subgraphs. Users with similar interests and the corresponding interaction items belong to the identical subgraph. As for the formation of the subgraph, we adopt two varied clustering methods and the user feature to form a subgraph generation mechanism. This mechanism can generate three groups of differential subgraphs to divide users into multi-interest groups and make subgraph division more reasonable. We carry out massive experiments on three real-world datasets, demonstrating the effectiveness of our model. Experimental results confirm that our presented MI-GCN outperforms the state-of-the-art GCN-based recommendation models.

Cover Caption: The cover image is based on the Research Article Active forgetting via influence estimation for neural networks by Xianjia Meng et al., https://doi.org/10.1002/int.22981.

The rapidly exploding of user data, especially applications of neural networks, involves analyzing data collected from individuals, which brings convenience to life. Meanwhile, privacy leakage in the applications as a potential threat needs to be addressed urgently. However, removing private information from models is difficult once the user's sensitive data enters machine learning models, particularly neural networks. Most of the previous amnestic methods based on retraining require full access to the training set of the target model and have limited improvements in computational resources and time improvement. In this paper, we propose Scrubber, which removes sensitive data from the original model via influence estimation to produce an unlearning model that is approximately indistinguishable from the retrained model. S crubber builds on the essential concept of influence function and reformulates the influence estimation as a closed-form update of forgetting. For learned models with strictly convex loss functions, our approach theoretically guarantees the effectiveness of forgetting while empirically demonstrating forgetting performance. For models with non-convex losses, we relax strictly convex assumptions by applying a damping term that allows us to make approximate estimates with negligible errors from the original assumption. Furthermore, experiments show that S crubber only causes less than 1% and 3% accuracy drop with more than 80% forgetting rate on average for logistic regression models and convolutional neural networks. The accuracy drop is reduced by 2%–3% compared to most state-of-the-art methods.

Gradient-based optimizer (GBO) is a metaphor-free mathematic-based algorithm proposed in recent years. Encouraged by the gradient-based Newton's method, this algorithm combines with population-based evolutionary methods. The disadvantage of the traditional GBO algorithm is that the global search ability of the algorithm is too strong, and the local search ability is too weak; accordingly, it is difficult to obtain the global optimal solution efficiently. Therefore, a new improved GBO algorithm (GOMGBO) is developed to mitigate such performance concerns by introducing a Gaussian bare-bones mechanism, an opposition-based learning mechanism, and a moth spiral mechanism enhanced GBO algorithm. The proposed GOMGBO has been compared against many famous methods and improved variants on 30 benchmark functions. The experimental results show that GOMGBO has apparent advantages in convergence speed and precision. In addition, this paper analyzes the balance and diversity of the GOMGBO algorithm and compares GOMGBO with other algorithms on several engineering problems. The experimental results show that the GOMGBO algorithm is also better than the competitive algorithm in engineering problems. This study uses the GOMGBO algorithm to optimize kernel extreme learning machine (KELM), and a new GOMGBO-KELM model is proposed. The model is used to deal with four clinical disease diagnosis problems. Compared with GBO-KELM, back propagation neural network algorithm, and other models, comparative experiments show that GOMGBO-KELM has high performance in dealing with practical cases. We invite the community to investigate further our method for solving problems more efficiently with reasonable speed and efficiency. Readers of this study can refer to https://aliasgharheidari.com for any guidance about the proposed GOMGBO method.

Using inertial measurement units mounted on foot is a feasible approach to improve the positioning accuracy for the human motion capture system. This paper presents a lightweight and low cost wireless inertial motion capture system for the simultaneous reconstruction of human body attitude and displacement. First of all, the device is based on human sensor networks and distributes 15 sensor nodes on the key human limbs. Then, after an initial sensor alignment with the reduced error, a zero-speed update algorithm is used to calculate foot displacement. In addition, to constantly update the human posture information, a kind of motion reconstruction method based on the gradient descent method was used to fuse the sensor data. Finally, a new method of three-dimensional human body reconstruction is proposed, which is different from the traditional motion capture system. Through unconstrained traversal of the root, the human posture and foot trajectory are combined to realize the synchronous reconstruction of posture and displacement. It is concluded from the experiment results that the estimation errors are well controlled, and motion patterns are consistent with the actual situation.

To understand the operating status of the road network and measure the traffic congestion problem, an intelligent calculation method for the intelligent traffic flow index based on big data mining is proposed. According to the error data discriminating rules, the error data in the traffic flow data is discriminated, all lanes are detected according to the data discriminating result, the traffic data of each lane are recorded in chronological order, and the traffic data is converted. Fuzzy data mining technology is used to predict the converted traffic flow, combined with traffic flow sequence segmentation and BP neural network model to realize the intelligent calculation of the smart traffic flow index. Experimental results show that the method can achieve accurate calculation of daily and weekly smart traffic index, and the calculation time is short, indicating that it can provide a reliable data basis for traffic operation state estimation and traffic early warning mechanism formulation.

The aim of temporal action localization (TAL) is to determine the start and end frames of an action in a video. In recent years, TAL has attracted considerable attention because of its increasing applications in video understanding and retrieval. However, precisely estimating the duration of an action in the temporal dimension is still a challenging problem. In this paper, we propose an effective one-stage TAL method based on a self-defined motion data structure, called a dense joint motion matrix (DJMM), and a novel temporal detection strategy. Our method provides three main contributions. First, compared with mainstream motion images, DJMMs can preserve more pre-processed motion features and provides more precise detail representations. Furthermore, DJMMs perfectly solve the temporal information loss problem caused by motion trajectory overlaps within a certain time period. Second, a spatial pyramid pooling (SPP) layer, which is widely used in the object detection and tracking fields, is innovatively incorporated into the proposed method for multi-scale feature learning. Moreover, the SPP layer enables the backbone convolutional neural network (CNN) to receive DJMMs of any size in the temporal dimension. Third, a large-scale-first temporal detection strategy inspired by a well-developed Chinese text segmentation algorithm is proposed to address long-duration videos. Our method is evaluated on two benchmark data sets and one self-collected data set: Florence-3D, UTKinect-Action3D and HanYue-3D. The experimental results show that our method achieves competitive action recognition accuracy and high TAL precision, and its time efficiency and few-shot learning capabilities enable it to be utilized for real-time surveillance.

To accurately detect and identify whether there are abnormalities in the information of the expressway networking system, an information security event reasoning and traceability method based on deep learning is proposed to build a data security protection system that includes the data life periodicity of the expressway networking system. In this system, the information security event model based on intrusion detection message exchange format is established. The model uses the information risk event reasoning method based on a deep convolution neural network to infer the risk event during data sharing of the expressway networking system, reorganize and standardize the risk event information according to the format of the information security event standardization model, and store it in the risk event database in the form of Extensible Markup Language data document. The information risk event traceability method based on the electronic fingerprint takes all risk events in the database as the target. After designing the electronic fingerprint of risk events, the original network attack tree is constructed to realize risk event traceability combined with fingerprint information. Testing indicates that the reasoning and traceability results of this method to the information security events of the expressway networking system are consistent with those in reality and our method has good usability.

Recently recommender systems become more and more significant in the daily life such as event recommendation, content recommendation and commodity recommendation, and so forth. Although the recommender systems based on the generative adversarial network (GAN) are competent, the user trust information is seldom taken into consideration to improve the recommendation accuracy. In this paper, we propose a Trust-Aware GAN with recurrent neural network (RNN) for RECommender systems named TagRec, which makes use of the user trust information for top-N recommendation. In the framework, the discriminative model is a multilayer perceptron to distinguish whether a sample is from the real data or fake data generated by the generative model. The discriminator helps to guide the training of the generative model to make it fit the data distribution of the user trust information. The generative model is a RNN with long short-term memory cells, aiming to confuse the discriminative model by generating samples as similar as possible to the real data. Through the adversarial training between the discriminative and generative models, the user trust information can be fully used to improve the recommendation performance. We conduct extensive experiments on real-word data sets to validate the effectiveness of the TagRec by comparing it with the benchmarks.

With the rise of the Internet of Things (IoT) and fifth-generation (5G) networks, which have led to a surge in data processing and increased data transfer time, traditional cloud computing could no longer meet the needs of workers, so edge computing has emerged. Edge computing could meet the demand for low time consumption by processing data at the edge of the network and then transmitting it to a third-party platform. However, since the credibility of the third-party platform is unknown which can easily leak the privacy of workers. For the transparent mechanism of blockchain, a two-stage privacy protection mechanism based on blockchain is proposed to solve this problem. In the first stage, this paper proposes a double disturbance localized differential privacy (DDLDP) algorithm to disturb the location information of workers. In the second stage, all the sensing data are uploaded to the blockchain through edge nodes, processed by the edge cloud, and fed back to the requester. Blockchain technology not only guarantees the integrity of sensing data, but also prevents the possibility of third-party platforms from leaking workers' privacy. Through extensive performance evaluation and comparative experiments on real data sets, the DDLDP algorithm could effectively protect the privacy of workers and has higher service quality and data availability.