检索结果-内蒙古大学图书馆

VT-SGN:Spiking Graph Neural Network for Neuromorphic Visual-Tactile Fusion

IEEE Transactions on Haptics 2024年 PP卷 PP-PP页

作者： Wu, Peiliang Zhang, Haozhe Li, Yao Chen, Wenbai Gao, Guowei Yanshan University School of Information Science and Engineering Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao066004 China Beijing Information Science and Technology University School of Automation Beijing100192 China

Current issues with neuromorphic visual-tactile perception include limited training network representation and inadequate cross-modal fusion. To address these two issues, we proposed a dual network called visual-tactile spiking graph neural network (VT-SGN) that combines graph neural networks and spiking neural networks to jointly utilize the neuromorphic visual and tactile source data. First, the neuromorphic visual-tactile data were expanded spatiotemporally to create a taxel-based tactile graph in the spatial domain, enabling the complete exploitation of the irregular spatial structure properties of tactile information. Subsequently, a method for converting images into graph structures was proposed, allowing the vision to be trained alongside graph neural networks and extracting graph-level features from the vision for fusion with tactile data. Finally, the data were expanded into the time domain using a spiking neural network to train the model and propagate it backwards. This framework effectively utilizes the structural differences between sample instances in the spatial dimension to improve the representational power of spiking neurons, while preserving the biodynamic mechanism of the spiking neural network. Additionally, it effectively solves the morphological variance between the two perceptions and further uses complementary data between visual and tactile. To demonstrate that our approach can improve the learning of neuromorphic perceptual information, we conducted comprehensive comparative experiments on three datasets to validate the benefits of the proposed VT-SGN framework by comparing it with state-of-the-art studies. © 2008-2011 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards self-interpretable review spammer group detection

引用

Information sciences 2025年 716卷

作者： Huo, Chenghang Zhang, Fuzhi School of Information Science and Engineering Yanshan University Hebei Province Qinhuangdao China Hebei Key Laboratory of Computer Virtual Technology and System Integration Hebei Province Qinhuangdao China

Due to data imbalance, existing spammer group detection methods often yield suboptimal performance. Moreover, many of these approaches operate as black boxes, offering little to no interpretability for their detection results. To address these issues, we propose a self-interpretable approach for detecting review spammer groups. Our method begins by constructing a user-product bipartite graph with edge attributes. We integrate user review information with a novel fitness function to develop an adaptive genetic algorithm that effectively identifies high-quality candidate groups. Next, we introduce a hybrid graph neural network enhanced with active learning to generate vector representations of these candidate groups. We then design and construct a prototype layer and a group classification layer to detect spammer groups accurately. To provide interpretability, we incorporate prototype learning to create an interpretation mechanism that explains detection outcomes. Experimental results demonstrate that our method achieves substantial improvements in Precision@k and Recall@k at the top-1000 ranking, outperforming state-of-the-art solutions on the Amazon, YelpChi, YelpNYC, and YelpZip datasets by [11.53 %, 97.36 %, 51.37 %, 32.06 %] and [12.65 %, 54.65 %, 64.19 %, 47.37 %], respectively. Additionally, the Fidelity of our interpretability results under varying Sparsity levels is approximately 4 %, 9 %, 8 %, and 8 % higher than those of existing methods on the same datasets. © 2025 Elsevier Inc.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Short mid-infrared watt-level all-fiber nonlinear pulse compressor above 100-MHz pulse repetition rate

引用

High Power Laser science and Engineering 2023年第1期11卷 107-113页

作者： Jingcheng Shang Chao Mei Shengzhi Zhao Yizhou Liu Kejian Yang Chun Wang Tao Li Tianli Feng School of Information Science and Engineering Shandong Provincial Key Laboratory of Laser Technology and ApplicationShandong UniversityQingdaoChina Key Laboratory of Laser&Infrared System(Shandong University) Ministry of EducationQingdaoChina Institute of Novel Semiconductors State Key Laboratory of Crystal MaterialsShandong UniversityJinanChina Beijing Engineering and Technology Center for Convergence Networks and Ubiquitous Services SCCEUniversity of Science and Technology BeijingBeijingChina

We firstly report a 2-μm all-fiber nonlinear pulse compressor based on two pieces of normal dispersion fiber(NDF),which enables a high-power scaling ability of watt-level and a high pulse compression ratio of *** the NDFbased all-fiber nonlinear pulse compressor,the 450-fs laser pulses with a repetition rate of 101.4 MHz are compressed to 35.1 fs,corresponding to a 5.2 optical oscillation cycle at the 2-μm wavelength *** output average power reaches 1.28 W,which is believed to be the highest value never achieved from the previous 2-μm all-fiber nonlinear pulse compressors with a high pulse repetition rate above 100 *** dynamic evolution of the ultrafast pulse inside the all-fiber nonlinear pulse compressor is numerically analyzed,matching well with the experimental results.

关键词： few-optical-cycle pulses high pulse repetition rate nonlinear pulse compression

来源：评论

学校读者我要写书评

暂无评论

Joint DNN Partition and Thread Allocation Optimization for Energy-Harvesting MEC systems

Joint DNN Partition and Thread Allocation Optimization for E...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Yizhou Shi Liying Li Yue Zeng Peijin Cong Junlong Zhou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Mobile Communications Research Laboratory Southeast University Nanjing China Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%.

关键词： Energy consumption Instruction sets Heuristic algorithms Artificial neural networks Predictive models Prediction algorithms Inference algorithms Partitioning algorithms Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction

arXiv

引用

arXiv 2022年

作者： Wang, Zixiao Guo, Yuluo Zhao, Jin Zhang, Yu Yu, Hui Liao, Xiaofei Wang, Biao Yu, Ting National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China

In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avoid the large amount of computations caused by complex network structures. We evaluate GIDN model on Open Graph Benchmark(OGB) datasets, reached an 11% higher performance than AGDN on ogbl-collab dataset. Copyright © 2022, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Phase apodized silicon Bragg grating filter with varying sidewall ridge width 29

Phase apodized silicon Bragg grating filter with varying sid...

引用

29th Opto-Electronics and Communications Conference, OECC 2024

作者： Zhang, Xinyu Jiang, Wei Yuan, Shuo Liu, Haipeng Ren, Wenbo Xia, Xincheng Feng, Jijun University of Shanghai for Science and Technology Shanghai Key Laboratory of Modern Optical System Engineering Research Center of Optical Instrument and System (Ministry of Education) School of Optical-Electrical and Computer Engineering Shanghai 200093 China China University of Geosciences School of Mathematics and Physics Wuhan 430074 China

ISBN: (纸本)9798350308396

In this work, phase apodized silicon Bragg grating filters with varying sidewall ridge width and location were investigated, while the resonance wavelength, extinction ratio and rejection bandwidth can be tuned flexibly. The grating filters with a waveguide width of 500 nm and grating period of 400 nm were fabricated and characterized for a proof of concept. The presented sidewall ridge modulated apodized grating can be expected to have great application prospects for optical communications and semiconductor lasers. © 2024 IEEE.

关键词： Apodized Bragg grating grating filter sidewall ridge silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Efficiently Verifying Mutually Exclusive Inconsistency of Requirements for Embedded systems 9

Efficiently Verifying Mutually Exclusive Inconsistency of Re...

引用

9th International Symposium on system Security, Safety, and Reliability, ISSSR 2023

作者： Chen, Xiaohong Ruan, Kun Jin, Zhi Li, Junhu Zheng, Lingling East China Normal University Shanghai Key Laboratory of Trustworthy Computing Shanghai China Jilin University School of Software Changchun China Peking University School of Computer Science and Technology Beijing China Southwest China Research Institute of Electronic Equipment Chengdu China

ISBN: (纸本)9798350302479

Formal methods have demonstrated tremendous potential for verifying requirements consistency, particularly for safety-critical systems. In our previous research, we included environment characteristics in the scope of formal specification verification for embedded systems and proposed a requirement consistency verification method based on an environment model. However, we found that this method was not sufficiently efficient. To address this issue, this paper defines this environment model introduced inconsistency as mutually exclusive inconsistency, based on its representation characteristics, and proposes an efficient static verification approach for embedded systems. We reduce the consistency verification problem to the traversal of a graph. To support the proposed approach, we implement a requirement consistency verification tool, called Env-Consistency, and apply it to industrial cases. To illustrate the advantages of this approach, several sets of comparative experiments are designed, which demonstrates our approach is both effective and efficient. © 2023 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit

arXiv

引用

arXiv 2023年

作者： Wan, Yao He, Yang Bi, Zhangqian Zhang, Jianguo Zhang, Hongyu Sui, Yulei Xu, Guandong Jin, Hai Yu, Philip S. National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Simon Fraser University Vancouver Canada School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Salesforce Research United States Chongqing University China University of New South Wales Australia University of Technology Sydney Australia University of Illinois at Chicago Chicago United States

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is already a thriving research community focusing on code intelligence, with efforts ranging from software engineering, machine learning, data mining, natural language processing, and programming languages. In this paper, we conduct a comprehensive literature review on deep learning for code intelligence, from the aspects of code representation learning, deep learning techniques, and application tasks. We also benchmark several state-of-the-art neural models for code intelligence, and provide an open-source toolkit tailored for the rapid prototyping of deep-learning-based code intelligence models. In particular, we inspect the existing code intelligence models under the basis of code representation learning, and provide a comprehensive overview to enhance comprehension of the present state of code intelligence. Furthermore, we publicly release the source code and data resources to provide the community with a ready-to-use benchmark, which can facilitate the evaluation and comparison of existing and future code intelligence models (https://***). At last, we also point out several challenging and promising directions for future research. Copyright © 2023, The Authors. All rights reserved.

关键词： computer programming languages

来源：评论

学校读者我要写书评

暂无评论

Debiased Distillation for Consistency Regularization 39

Debiased Distillation for Consistency Regularization

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Lu Xu, Liuchi Yang, Xiong Huang, Zhenhua Cheng, Jun School of Computer Science and Engineering Northeastern University Shenyang China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen China School of Computer Science South China Normal University Guangzhou China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology CAS China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Knowledge distillation transfers "dark knowledge" from a large teacher model to a smaller student model, yielding a highly efficient network. To improve the network's generalization ability, existing works use a larger temperature coefficient for knowledge distillation. Nevertheless, these methods may reduce the confidence of the target category and lead to ambiguous recognition of similar samples. To mitigate this issue, some studies introduce intra-batch distillation to reduce prediction discrepancy. However, these methods overlook the inconsistency between background information and the target category, which may increase prediction bias due to noise disturbance. Additionally, label imbalance from random sampling and batch size can undermine network generalization reliability. To tackle these challenges, we propose a simple yet effective Intra-class Knowledge Distillation (IKD) method that facilitates knowledge sharing within the same class to ensure consistent predictions. First, we initialize the matrix and the vector to store logits and class counts provided by the teacher, respectively. Then, in the first epoch, we calculate the sum of logits and sample counts per class and perform KD to prevent knowledge omission. Finally, in subsequent training, we update the matrix to obtain the average logits and compute the KL divergence between the student's output and the updated matrix according to the label index. This process ensures intra-class consistency and improves the student's performance. Furthermore, this method theoretically reduces prediction bias by ensuring intra-class consistency. Extensive experiments on the CIFAR-100, ImageNet-1K, and Tiny-ImageNet datasets validate the superiority of IKD. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Single Block Encoder-Decoder Transformer Model for Multi-Step Traffic Flow Forecasting 6

Single Block Encoder-Decoder Transformer Model for Multi-Ste...

引用

6th IEEE Symposium on computers and Informatics, ISCI 2024

作者： Omar, Mas Yakub, Fitri Talip, Mohamad Sofian Abu Maslan, Mohd Nazmin Sinha, Vijay Kumar Muljono, Muljono Universiti Teknologi Malaysia Wee Laboratory Malaysia-Japan International Institute of Technology Kuala Lumpur Malaysia Universiti Teknologi Malaysia Malaysia-Japan International Institute of Technology Department of Electronic System Engineering Kuala Lumpur Malaysia University of Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur Malaysia Universiti Teknikal Malaysia Faculty of Industrial and Manufacturing Technology and Engineering Melaka Malaysia Chitkara University School of Engineering & Technology Department of Computer Science & Engineering Himachal Pradesh India Universitas Dian Nuswantoro Faculty of Computer Science Semarang Indonesia

ISBN: (纸本)9798350353853

Accurate traffic flow forecasting is crucial for managing and planning urban transportation systems. Despite the widespread use of sequence modelling models like Long Short-Term Memory (LSTM) for this purpose, the potential of Transformer models remains underexplored. This is particularly true for the simplest form of a single block encoder-decoder Transformer model, which can be finely tuned through optimised hyperparameters. This paper examines the performance of a singular horizon-step forecasting method for multi-step traffic flow forecasting using a proposed Single Block Encoder-Decoder Transformer model optimised with a Grid Search algorithm. Results demonstrate that this model can enhance forecasting accuracy compared to the state-of-the-art LSTM model typically used for multi-step forecasting. The model effectively captures long-range temporal dependencies within a single road traffic flow dataset. It was tested on hourly traffic flow data to forecast the next 24 hours for the I5-North freeway in California, sourced from the Caltrans Performance Measurement system. The optimal configuration included an embedding dimension of 32, a feed-forward dimension of 128, and 8 attention heads. Results show a significant improvement, with a 4.7% reduction in Root Mean Squared Error compared to an LSTM model with two hidden layers of 100 neurons each, showcasing the potential of Single Block Encoder-Decoder Transformer models for real-world traffic prediction applications. © 2024 IEEE.

关键词： Mean square error

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：