检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Chuanhao Zang Anming Dong Jiguo Yu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Trajectory tracking of zebrafish is an important requirement in studying neurological disorders and developing new psychoactive drug. However, many challenges emerge for stable tracking, since zebrafish are similar in appearance, occlusion, agile, non-linear in moving and easy to swarm, all of which will lead to mistrack for multiple fish. And there is no precedent for tracking zebrafish through embedded edge artificial intelligence device. To overcome these difficulties, we present a tracking system for zebrafish based on RK3588-S. First, We construct an embedded edge AI hardware system consisting of two cameras driven by the RK3588-S, one for the front view and the other for top view of the fish. Then, we develop a 2D tracking algorithm based on YOLOv5 and the Observation-Centric Simple online and real-time tracking (OC-SORT) algorithm, which are transplanted to the RK3588-S for tracking the top and front views of the fish at the edge device. Compared with the previous methods, our method has fewer ID exchanges and highly real-time. Moreover, we apply the MQTT mechanism to establish communication links between the edge and the cloud to reliably transmit data to the cloud. The correspondence between cloud server and embedded AI is 1: N. Finally, we design a multi-view data fusion association algorithm to fuse the data of the two views in the cloud, which are further utilized to build the 3D tracklets of the zebrafish.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Language Binary-Source Code Matching with Intermediate Representations

arXiv

引用

arXiv 2022年

作者： Gui, Yi Wan, Yao Zhang, Hongyu Huang, Huifang Sui, Yulei Xu, Guandong Shao, Zhiyuan Jin, Hai 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 The University of Newcastle Australia School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China School of Computer Science University of Technology Sydney Australia

Binary-source code matching plays an important role in many security and software engineering related tasks such as malware detection, reverse engineering and vulnerability assessment. Currently, several approaches have been proposed for binary-source code matching by jointly learning the embeddings of binary code and source code in a common vector space. Despite much effort, existing approaches target on matching the binary code and source code written in a single programming language. However, in practice, software applications are often written in different programming languages to cater for different requirements and computing platforms. Matching binary and source code across programming languages introduces additional challenges when maintaining multi-language and multi-platform applications. To this end, this paper formulates the problem of cross-language binary-source code matching, and develops a new dataset for this new problem. We present a novel approach XLIR, which is a Transformer-based neural network by learning the intermediate representations for both binary and source code. To validate the effectiveness of XLIR, comprehensive experiments are conducted on two tasks of cross-language binary-source code matching, and cross-language source-source code matching, on top of our curated dataset. Experimental results and analysis show that our proposed XLIR with intermediate representations significantly outperforms other state-of-the-art models in both of the two tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Localization of Dummy data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach

arXiv

引用

arXiv 2024年

作者： Qu, Zhaoyang Dong, Yunchang Li, Yang Song, Siqi Jiang, Tao Li, Min Wang, Qiming Wang, Lei Bo, Xiaoyong Zang, Jiye Xu, Qi School of Electrical Engineering Northeast Electric Power University Jilin China Jilin Electric Power Research Institute of State Grid Changchun China Northeast Electric Power Design and Institute Co. Ltd. China Power Engineering Consulting Group China School of Computer Northeast Electric Power University Jilin China Jilin Engineering Technology Research Center of Intelligent Electric Power Big Data Processing Jilin China Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong

The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial separation between the injected malicious data and legitimate data, rendering their precise detection challenging using conventional distance-based methods. Furthermore, existing research predominantly focuses on various machine learning techniques, often analyzing the temporal data sequences post-attack or relying solely on Euclidean spatial characteristics. Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization. To address this issue, this study takes a comprehensive approach. Initially, it examines the underlying principles of these new DDIAs on power systems. Here, an intricate mathematical model of the DDIA is designed, accounting for incomplete topological knowledge and alternating current (AC) state estimation from an attacker's perspective. This model aims to mitigate the vulnerabilities associated with direct current (DC) flow-based attack data generation methods that can be readily detected. Subsequently, by integrating a priori knowledge of grid topology and considering the temporal correlations within measurement data and the topology-dependent attributes of the power grid, this study introduces temporal and spatial attention matrices. These matrices adaptively capture the spatio-temporal correlations within the attacks. Leveraging gated stacked causal convolution and graph wavelet sparse convolution, the study jointly extracts spatio-temporal DDIA features. This methodology significantly enhances the dynamic correlation mining capability while improving computational efficiency in the neighborhood. Finally, the research proposes a DDIA localization method based on spatio-temporal graph

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

arXiv

引用

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Environmental Impacts and Health Benefits of Clean Winter Heating Policies in Northern China

SSRN

引用

SSRN 2025年

作者： Weng, Qinnan Zhu, Suling Luo, Lijiao Liu, Bowen Zhang, Zhenhua Institute of Health Statistics and Intelligent Analysis School of Public Health Lanzhou University Lanzhou730000 China Department of Epidemiology and Health Statistics School of Public Health Lanzhou University Lanzhou730000 China Big Data Research Center Lanzhou University Lanzhou730000 China School of Mathematics and Statistics Lanzhou University Lanzhou730000 China Department of Management University of Birmingham BirminghamB15 2TT United Kingdom School of Economics Lanzhou University Lanzhou730000 China

Evaluating the synergistic environmental and health effects of energy control policies is essential for scientifically informed policy optimization. Given that air quality is affected by factors such as meteorological conditions and economic growth, relying solely on air quality monitoring data is insufficient to assess the environmental impacts of these policies accurately. To objectively examine the synergistic effects of energy control policies on both environment and public health, this study introduces the CEEMDAN-OA-SVR-DID model from a predictive perspective. The model forecasts PM2.5 concentrations as a counterfactual scenario without the implementation of the Northern Winter Clean Heating Policy (NWCHP). By integrating the difference-in-difference approach, exposure-response functions, and economic evaluation methods, including the value of statistical life and the cost of illness, the model evaluates the environmental and health outcomes of the policy. Results demonstrate the CEEMDAN-GWO-SVR model’s high predictive accuracy, with mean absolute percentage error values ranging from 3.2% to 8.8% across 10 pilot cities. Overall, the NWCHP significantly reduced PM2.5 concentrations (by 3.7% to 31.7%) in these cities, reducing premature deaths, respiratory and cardiovascular hospitalizations, outpatient visits, and other health issues related to PM2.5 exposure (decreased by 7.7% to 52.9%). The policy also averted approximately 3.197 billion yuan in economic losses. These findings offer essential evidence to refine heating policies further and provide valuable insights for developing countries advancing environmental governance and energy transitions. © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards on Blockchain data Privacy Protection with Cryptography and Software Architecture Approach 2nd

Towards on Blockchain Data Privacy Protection with Cryptogra...

引用

2nd International Conference on Blockchain and Trustworthy Systems, Blocksys 2020

作者： Wang, Zexu Wen, Bin Luo, Ziqiang School of Information Science and Technology Hainan Normal University Haikou China Cloud Computing and Big Data Research Center Hainan Normal University Haikou China Key Laboratory of Data Science and Intelligence Education of Ministry of Education Hainan Normal University Haikou571158 China

ISBN: (纸本)9789811592126

The essence of blockchain is to solve trust problems and realize value transfer. The traditional centralized processing method adopts centralized transmission and storage of users’ data privacy, which improves the security and reliability of processing. The non central blockchain technology uses distributed ledger technology to realize the characteristics of disintermediation, data tampering, traceability, work audit, etc. encryption algorithm is used to encrypt the data, and consensus mechanism makes the data sharing of blockchain system more fair and stable. The current passive data privacy schemes are basically based on cryptography. On the premise of satisfying the constraint mechanism of blockchain, this paper studies the technical framework, encryption mechanism and empirical analysis of blockchain, and discusses the information privacy protection method of hiding the original big data as much as possible, so as to improve the system performance and protect the security and privacy of user data. At the same time, we study data privacy protection from the perspective of software architecture, and propose a data privacy protection scheme through algorithm decomposition multi center collaboration method, which provides guidance for big data sharing and transaction based on blockchain. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Visualizing nonlinear resonance in nanomechanical systems via single-electron tunneling

引用

Nano research 2021年第4期14卷 1156-1161页

作者： Xinhe Wang Lin Cong Dong Zhu Zi Yuan Xiaoyang Lin Weisheng Zhao Zaiqiao Bai Wenjie Liang Ximing Sun Guang-Wei Deng Kaili Jiang Fert Beijing Research Institute School of Microelectronics&Beijing Advanced Innovation Centre for Big Data and Brain Computing(BDBC)Beihang UniversityBeijing 100191China State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics and Tsinghua-Foxconn Nanotechnology Research CenterTsinghua UniversityBeijing 100084China Key Laboratory of Quantum Information CASUniversity of Science and Technology of ChinaHefei 230026China Department of Physics Beijing Normal UniversityBeijing 100875China Institute of Physics Chinese Academy of SciencesBeijing 100080China Institute of Nuclear and New Energy Technology Collaborative Innovation Center of Advanced Nuclear Energy TechnologyKey Laboratory of Advanced Reactor EngineeringTsinghua UniversityBeijing 100084China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 610054China

Numerous reports have elucidated the importance of mechanical resonators comprising quantum-dot-embedded carbon nanotubes(CNTs)for studying the effects of single-electron ***,there is a need to investigate the single-electron transport that drives a large amplitude into a nonlinear ***,a CNT hybrid device has been investigated,which comprises a gate-defined quantum dot that is embedded into a mechanical resonator under strong actuation *** Coulomb peak positions synchronously oscillate with the mechanical vibrations,enabling a single-electron Chopper*1 ***,the vibration amplitude of the CNT versus its frequency can be directly visualized via detecting the time-averaged single-electron tunneling *** understand this phenomenon,a general formula is derived for this time-averaged single-electron tunneling current,which agrees well with the experimental *** using this visualization method,a variety of nonlinear motions of a CNT mechanical oscillator have been directly recorded,such as Duffing nonlinearity,parametric resonance,and double-,fractional-,mixed-frequency *** approach opens up burgeoning opportunities for investigating and understanding the nonlinear motion of a nanomechanical system and its interactions with electron transport in quantum regimes.

关键词： carbon nanotube mechanical resonator quantum dot nonlinear coupling

来源：评论

学校读者我要写书评

暂无评论

Two-Month Cognitive Changes Enhance Prediction of Nonremission in Clinical High-Risk Individuals

引用

Biological Psychiatry 2025年第2期98卷 175-185.0页

作者： Zhang, TianHong Wei, YanYan Tang, XiaoChen Xu, LiHua Cui, HuiRu Hu, YeGang Liu, HaiChun Wang, ZiXuan Chen, Tao Tang, YingYing Yi, ZhengHui Li, ChunBo Wang, JiJun Shanghai Mental Health Center Shanghai Jiaotong University School of Medicine Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention Shanghai Key Laboratory of Psychotic Disorders Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai China Shanghai Xinlianxin Psychological Counseling Center Shanghai China Big Data Research Laboratory University of Waterloo Waterloo ON Canada Labor and Worklife Program Harvard University Cambridge Massachusetts United States Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Institute of Psychology and Behavioral Science Shanghai Jiao Tong University Shanghai China

Background: Longitudinal changes in cognitive function may be crucial in predicting clinical outcomes in clinical high-risk (CHR) individuals. In this study, we aimed to investigate the predictive value of baseline cognitive impairment and short-term cognitive changes for nonremission and conversion to psychosis in individuals at CHR for psychosis compared with healthy control individuals (HCs). Methods: This study used a multiple-group prospective design with a 3-year follow-up. CHR individuals and HCs were assessed at baseline and at a 2-month follow-up. Neuropsychological performance was evaluated using the Chinese version of the MATRICS (Measurement and Treatment research to Improve Cognition in Schizophrenia) Consensus Cognitive Battery. Results: The study included 310 CHR individuals and 93 HCs. Significant improvements in predicting nonremission in CHR individuals were observed when incorporating cognitive changes over 2 months (area under the receiver operating characteristic curve [AUC] for baseline cognition, 0.690;AUC for changes, 0.819;z = 3.365, p < .001). Key predictors included the Hopkins Verbal Learning Test–Revised (β = 0.083, p = .003), Wechsler Memory Scale-III spatial span (β = 0.330, p < .001), and Brief Visuospatial Memory Test–Revised (β = 0.127, p < .001). Conversely, predicting conversion to psychosis showed no significant difference between baseline and 2-month cognitive changes (AUC for baseline cognition, 0.667;AUC for changes, 0.666;z = 0.021, p = .242). Conclusions: The findings underscore the importance of dynamic cognitive monitoring in CHR individuals. Short-term cognitive changes significantly enhanced the prediction of nonremission but did not add predictive value for conversion to psychosis beyond baseline assessments. Specific cognitive domains, such as verbal learning and working memory, were particularly valuable for predicting clinical outcomes. © 2025 Society of Biological Psychiatry

关键词： Cognition Functional outcome Prodromal psychosis Remission Transition Ultra-high risk

来源：评论

学校读者我要写书评

暂无评论

Stochastic computing Implemented by Skyrmionic Logic Devices

引用

Physical Review Applied 2020年第5期13卷 054049-054049页

作者： Haoyang Zhang Daoqian Zhu Wang Kang Youguang Zhang Weisheng Zhao Fert Beijing Research Institute Beijing Advanced Innovation Center for Big Data and Brain Computing School of Microelectronics Beihang University Beijing 100191 China

Magnetic skyrmions, which are a topologically nontrivial spin texture, have been considered as promising information carriers in future electronic devices because of their nanoscale size, low depinning current density, and high motion velocity. Despite the broad interest in skyrmion racetrack memory, researchers have recently been exploiting logic functions enabled by using the particlelike behavior of skyrmions. These functions can be applied to unconventional computing, such as stochastic computing (SC), which treats data as probabilities and is superior to binary computing due to its simplicity of logic operation. In this paper, we demonstrate SC implemented by the use of skyrmionic logic devices. We propose a skyrmionic and-or logic device as a multiplier in the stochastic domain and two skyrmionic multiplexer (MUX) logic devices as stochastic adders. With the assistance of voltage-controlled magnetic anisotropy (VCMA), precise control of skyrmion collisions is not required in the skyrmionic and-or logic device, thus improving the operational robustness. In the two MUX logic devices, skyrmions can be driven by the Zhang-Li torque or the spin-orbit torque (SOT). In particular, we can regulate the skyrmion motion flexibly by using VCMA or voltage-controlled Dzyaloshinskii-Moriya interaction in the SOT case. Furthermore, a 3-bit stochastic multiplier and adder are demonstrated by micromagnetic simulations. Simulations in synthetic antiferromagnets show that the performance of our skyrmionic logic gates can be optimized through the use of advanced materials. Our work opens up possibilities for implementing SC using skyrmionic logic devices.

关键词： Magnetic anisotropy Skyrmions Spin dynamics Spin torque Spintronics Devices Nanostructures Stochastic networks

来源：评论

学校读者我要写书评

暂无评论

research on Engineering Certification-Oriented Course Design for Software Engineering under the Background of New Engineering

Research on Engineering Certification-Oriented Course Design...

引用

International Conference on Educational and Information Technology (ICEIT)

作者： Xian Chen Feng Hu Jun Lai Chunmei Tao Hyoseop Shin Chongqing Engineering Research Center for Spatial Big Data Intelligent Technology Chongqing University of Posts and Telecommunications Chongqing China Chongqing University of Posts and Telecommunications Chongqing China Konkuk University Seoul Korea

ISBN: (数字)9781665422956

ISBN: (纸本)9781665446471

With the appearance of the new engineering concept in 2017, the mode of talents development in colleges and universities has also changed. And the new engineering talents need to be more practical and innovative abilities. However, the professional certification of engineering education is an important guidance for the teaching of engineering majors in China, and it is the core idea of output-oriented, student-centered and continuous improvement to construct the quality control system of engineering education in colleges and universities in China. Combining with the core idea of engineering certification and the new requirements under the background of new engineering, in this paper, we put forward to a set of comprehensive software engineering course design for engineering certification in the new engineering environment, which is guided by engineering education, aims at improving students' engineering practical ability and innovation, provides a method of solution for the reform of software engineering course design under the new engineering background.

关键词： Knowledge engineering Technological innovation Quality control Engineering education Information technology Certification Software engineering

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：