检索结果-内蒙古大学图书馆

Adversarial Graph Convolutional Network for Skeleton-Based Early Action Prediction

Journal of computer science & technology 2024年第6期39卷 1269-1280页

作者： Xian-Shan Li Neng Zhang Bin-Quan Cai Jing-Wen Kang Feng-Da Zhao School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China School of Information Science and Engineering Xinjiang University of Science and TechnologyKorla 841000China Key Laboratory for Software Engineering of Hebei Province Yanshan UniversityQinhuangdao 066004China

This paper proposes a novel method for early action prediction based on 3D skeleton data. Our method combines the advantages of graph convolutional networks (GCNs) and adversarial learning to avoid the problems of insufficient spatio-temporal feature extraction and difficulty in predicting actions in the early execution stage of actions. In our method, GCNs, which have outstanding performance in the field of action recognition, are used to extract the spatio-temporal features of the skeleton. The model learns how to optimize the feature distribution of partial videos from the features of full videos through adversarial learning. Experiments on two challenging action prediction datasets show that our method performs well on skeleton-based early action prediction. State-of-the-art performance is reported in some observation ratios.

关键词： graph convolutional network adversarial learning skeleton-based action prediction

来源：评论

学校读者我要写书评

暂无评论

Design of a ML-based trust prediction model using intelligent TrustBoxes in challenged networks

引用

International Journal of Systems, Control and Communications 2024年第3期15卷 209-234页

作者： Barai, Smritikona Kundu, Anindita Bhaumik, Parama Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu India Department of Information Technology Jadavpur University Kolkata India

Challenged networks (CNs) contain resource-constrained nodes deployed in regions where human intervention is difficult. Opportunistic networks (OppNets) are CNs with no predefined source-to-destination paths. Due to their inherent properties, CNs and OppNets are highly susceptible to black-hole (BH) attacks, resulting in degraded packet-delivery ratio. In this work, an ML-based trust prediction model (MLTPM) is proposed to identify potential BH nodes in OppNets. MLTPM uses a novel function to calculate the total-trust-value (TTV) of each node. Intelligent TrustBoxes are introduced in the network to identify possible BH nodes, using TTV, along with five more node-behaviour features. TrustBoxes reduce the computational overhead of the resource-constrained nodes. Three simulated scenarios are compared - no detection, non-ML-based detection, and MLTPM, each using epidemic, prophet, and spray-and-wait routing protocols. MLTPM performs best with spray-and-wait, exhibiting about 25.21% and 80% mean improvement in delivery-ratio and dropped-message numbers respectively, compared to non-ML-based detection. An overall 12.62% improvement in delivery-ratio and 26.7% improvement in dropped messages is observed using MLTPM, compared to the above-mentioned scenarios. © 2024 Inderscience Enterprises Ltd.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Leaving None Behind: Data-Free Domain Incremental Learning for Major Depressive Disorder Detection

引用

IEEE Transactions on Affective Computing 2025年第2期16卷 758-770页

作者： Chen, Tao Guo, Yanrong Hao, Shijie Hong, Richang Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei230009 China

While deep learning techniques have shown promising performance in the Major Depressive Disorder (MDD) detection task, they still face limitations in real-world scenarios. Specifically, given the data scarcity, some efforts have resorted to aggregating data from different domains to expand the data volume. However, their effectiveness is currently limited by the domain gap and data privacy. Additionally, the class imbalance issue is particularly severe in our application, leading to biased classifying performance accordingly. To address these challenges, we propose Data-Free Domain Incremental Learning for the MDD detection (DIL-MDD) task, accommodating multiple feature distributions by only accessing well-trained models from previous domains and the data in the current domain. Specifically, DIL-MDD consists of two key modules: Adaptive Class-tailored Threshold Learning (ACTL) and Data-Free Domain Alignment (DFDA). The first module measures the discrepancy between the outputs of two sequential domains, based on which we learn a class-tailored threshold adaptively. Building on this, we differentiate between samples that either exhibit similarities or dissimilarities with the previous domain, where this similar sample set is identified to investigate the feature distribution of the historical data. The second module imposes an alignment constraint to narrow the gap between these two sample sets, thereby exploring the expertise of the previous domain. To validate the effectiveness of the proposed method, we conduct extensive experiments on the public MDD datasets, i.e., DAIC-WOZ, MODMA, and CMDC. We also apply our method to another mental health condition, Autism Spectrum Disorder (ASD), to further demonstrate its applicability. Finally, the ablation studies validate the superiority of the proposed modules. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

SSF: Sparse point cloud object detection based on self-adaptive voxel encoding and focal-sparse convolution

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 11041-11054页

作者： Zhang, Yu Wang, Zilong Zhu, Yongjian Li, Jianxin School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai China College of Engineering Physics Shenzhen Technology University Guangdong Province Shenzhen China

Point cloud object detection is gradually playing a key role in autonomous driving tasks. To address the issue of insensitivity to sparse objects in point cloud object detection, we have made improvements to the voxel encoding and 3D backbone network of the PVRCNN++. We have introduced adaptive pooling operations during voxel feature encoding to expand the point cloud information within each voxel, followed by the utilization of multi-layer perceptrons to extract richer point cloud features. On the 3D backbone network, we have employed adaptive sparse convolution operations to make the backbone network's channel count more flexible, allowing it to accommodate a wider range of input data types. Furthermore, we have integrated Focal Loss to tackle the issue of class imbalance in detection tasks. Experimental results on the public KITTI dataset demonstrate significant improvements over the PVRCNN++, particularly in pedestrian and bicycle detection tasks. Specifically, we have observed 1% increase in detection accuracy for pedestrians and 2.1% improvement for bicycles. Our detection performance also surpasses that of other comparative detection algorithms. © 2024 - IOS Press. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

CoDetect: cooperative anomaly detection with privacy protection towards UAV swarm

引用

science China(information sciences) 2024年第5期67卷 325-326页

作者： Teng LI Weiguo LIN Ruichen MA Zhuo MA Yulong SHEN Jianfeng MA School of Cyber Engineering Xidian University School of Computer Science and Technology Xidian University

As mission scenarios grow more complex, the role of a single unmanned aerial vehicle(UAV) is limited. The UAV swarm,surpassing the single UAV, dynamically establishes temporary communication networks, ensuring high transmission rates and expansive communication coverage [1]. Unlike a single UAV, a swarm faces increased security risks, requiring specific capabilities.(1) Anomalies detection.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Knowledge Distillation in Latency-Critical Federated Task Offloading for Consumer IoT Networks

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 239-251页

作者： Chen, Yishan Zhang, Jianwei Wang, Zhiqiang Dai, Wenshuo Gao, Honghao Deng, Shuiguang Jiangxi University of Science and Technology College of Information Engineering China Shanghai University School of Computer Engineering and Science China Gachon University College of Future Industry Korea Republic of Zhejiang University College of Computer Science and Technology China

Along with the explosive demand for massive data computation, federated local-edge-cloud computing enables many IoT task offloading processes and has recently gained widespread attention in consumer-centric healthcare. However, existing approaches for latency-critical task offloading do not pay sufficient attention to patient privacy data and thus are far from being ready for large-scale practical deployment. In this paper, a novel local-edge-cloud based federated learning framework with one-way knowledge distillation for latency-critical and security-aware task offloading is proposed, while a task offloading scheme based on deep reinforcement learning is presented. Then, based on the consideration of privacy guarantees, computing resources and offloading decisions, an optimization problem is formulated to minimize the overall latency of all tasks for local medical devices. Additionally, a pseudo-task mechanism is adopted in the federated framework for the uploaded weights to aggregate the models on the edges and the cloud. Besides, a one-way knowledge distillation mechanism is proposed to transfer knowledge from a teacher model to student models, which compresses the network parameters and reduces the model latency. Finally, experiments based on Chest X-Ray Images of Pneumonia are conducted for corroborating the theoretical results. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Image Guidance Encoder-Decoder Model in Image Captioning and Its Application

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第9期51卷 1385-1392页

作者： Yang, Zhen Zhou, Ziwei Wang, Chaoyang Xu, Liang School of Applied Technology University of Science and Technology Liaoning Anshan China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan China

This paper introduces a new network model - the Image Guidance Encoder-Decoder Model (IG-ED), designed to enhance the efficiency of image captioning and improve predictive accuracy. IG-ED, a fusion of the convolutional network VGGNet-16 and the long short-term memory network (LSTM), is designed based on the encoder-decoder structure. The image captioning performance sees significant enhancements when leveraging the IG-ED network model. The network training process unfolds in a series of steps. Initially, the input image undergoes convolution via the VGGNet-16 network, producing a 512-dimensional vector. Concurrently, each word in the image's caption is encoded to generate a corresponding 512-dimensional vector consistent with the image feature dimension. These two vectors form the input for the decoding process. Subsequently, the vectors are fed into the redesigned fusion LSTM (F-LSTM) network at different time steps to gradually train the parameters of the IG-ED framework. The training process is completed by utilizing a loss function for determining convergence. Evaluation of the IG-ED model's performance is conducted using CIDEr and seven other evaluation metrics on the MSCOCO 2014 dataset. The results exhibit substantial improvements over the "Adaptive Attention Mode" network and "Neural Talk" network. Additionally, the parameter count of the IG-ED architecture is significantly reduced compared to the "Adaptive Attention Mode" network, leading to decreased computational resource requirements and enabling edge computing on the neural network. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Developing a Consumer Electronics Robotics With a Large Language Model Based on a Trustworthy AI Framework

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 2027-2038页

作者： Wu, Hsin-Te Wei, Wei Li, Syuan-Hao Chen, Mu-Yen National Taitung University Computer Science and Information Engineering Taitung950309 Taiwan Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China National Cheng Kung University Department of Engineering Science Tainan70142 Taiwan

As many countries face the challenges of an aging population and declining birth rates, the demand for labor, particularly for assisting the elderly, is increasing. Traditional robots, being standardized products, require engineers to adjust parameters to fit the unique lifestyle of each household, which is time-consuming and inconvenient. However, with the rapid development of artificial intelligence and consumer electronics, there is a growing need for home robots with smarter interfaces to achieve the goal of intelligent living. This paper proposes a home robot based on a trustworthy AI framework, integrated with large language models (LLM). These LLM can perform natural language processing and object recognition, allowing users to control the robot's operations through natural language commands. This innovation further advances consumer electronics. The robot's arm can remember these actions and operate according to instructions. Additionally, the robot arm is equipped with monitoring functions, capable of overseeing the operation of other robots and using cameras to detect errors. This development is significant in the field of consumer electronics. The robot also uses Long Short-Term Memory (LSTM) networks to predict the motion paths of the robotic arm, ensuring smooth and efficient operation. This integration of AI and robotics aims to enhance the adaptability and functionality of home robots, making them more suitable for the diverse needs of modern households, improving the quality of life for the elderly, and driving innovation in the consumer electronics field. © 1975-2011 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

A Vulnerability Detection Method for Smart Contracts Based on Dynamic Meta Optimizer

引用

IEEE Internet of Things Journal 2025年第13期12卷 24904-24915页

作者： He, Daojing Gong, Wei Chan, Sammy Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Jiangxi University of Science and Technology School of Information Engineering Jiangxi Ganzhou China City University of Hong Kong Department of Electrical Engineering Hong Kong Hong Kong

With the increasingly complex blockchain technology environment and emerging security threats, the detection and prevention of vulnerabilities in blockchain smart contracts have become crucial for ensuring the healthy development of blockchain technology and avoiding substantial economic losses. Recently developed vulnerability detection methods for smart contracts suffer from the drawbacks of insufficient feature extraction and inadequate multitask detection. This paper proposes a multifaceted learning model, DLR, based on a dual-loop architecture of meta learning to address these issues by adopting model-agnostic meta-learning techniques. This model employs a syntax analyzer for targeted feature extraction, with graph information used as a supporting tool during the initial stage of feature engineering. Combined with an improved optimizer algorithm in the inner loop, the model can effectively learn and adjust based on the specific requirements of each task. In the outer loop, the model achieves efficient learning rate adjustment for multi-task learning by integrating the adaptive learning rate of the Adam optimizer with a global adjustment using simulated annealing strategy, thereby enhancing performance across diverse tasks. Experimental results demonstrate significant improvements in detection accuracy over state-of-the-art methods for three types of vulnerabilities, with our method achieving detection accuracies of 94.40%, 93.36%, and 94.33% for reentrancy, timestamp dependence, and integer overflow vulnerabilities, respectively. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Chinese Relation Extraction Based on Cross-Attention and Multi-feature Perception

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1837-1853页

作者： Xu, Shiao Sun, Shuihua Zhang, Zhiyuan Zhou, Huan School of Electronics and Information Engineering Jingchu University of Technology Jingmen448000 China School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China

Relation extraction aims at extracting semantic relations between given pairs of entities from unstructured textual data and is a critical task in information extraction. A relation extraction model based on cross-attention and multi-feature perception is proposed to address the limitations of Chinese relation extraction models that rely solely on characters, which struggle to capture rich semantic information, and the inability to ful ly utilize the textual structural information during neural network feature extraction. First, the model uses BERT to encode sentences and entities to obtain character vector sequences and word vector sequences of sentences, and uses word cross-attention mechanism to capture the key word and word information in sentences to form character and word cross-fused sentence sequences. Second, uses graph convolutional network and deep separable convolutional network to capture syntactic information between nodes and multi-granularity local semantic information in sentence sequences, respectively, and forms sentence features for classification by attention mechanism. Final ly, combines with Softmax classifier for relation classification. Experimental results on the Chinese SanWen dataset demonstrate the superiority of the proposed method over mainstream neural network-based relation extraction methods, with an F1-score of 71.57%. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：