检索结果-内蒙古大学图书馆

4th International Conference on Artificial Intelligence, Automation and High Performance Computing, AIAHPC 2024

作者： Ding, Shuyan Song, Chunlin Yao, Yu Guo, Jianhui Li, Lunbo School of Electronic and Optical Engineering Nanjing University of Science and Technology China Hangzhou Zhiyuan Research Institute Co. Ltd China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798400710049

Transformer has successfully replaced the CNN-based crosscorrelation operation on visual tracking tasks, significantly improving tracking performance. The attention mechanism, the core module of Transformer, can get rid of the long-range dependency dilemma while the CNN-based method cannot. However, the tracking performance is very susceptible to the interference from secondary background information since the global-level attention mechanism cannot concentrate on the primary target information. In our work, we propose a residual self-attention mechanism appropriate for object tracking tasks to concentrate on the primary target information. Furthermore, we design ResAT, an effective and concise tracker that adopts a residual attention mechanism and a residual strategy specifically tailored for object tracking tasks. Our tracker ResAT outperforms all previous SOTA trackers on challenging large-scale benchmarks, including GOT-10k, LaSOT, TrackingNet, and UAV123, while running at 45 FPS. © 2024 Copyright held by the owner/author(s).

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Distributed Super-Twisting Sliding Mode Protocol for Formation and Tracking of Multiple Quadcopters 11

Distributed Super-Twisting Sliding Mode Protocol for Formati...

引用

11th IEEE Region 10 Humanitarian technology Conference, R10-HTC 2023

作者： Modi, Akash Joshi, Nikita Mehta, Axaykumar Institute of Infrastructure Technology Research And Management Electrical and Computer Science Engineering Ahmedabad380026 India

ISBN: (纸本)9798350326147

In this paper, a distributed super-twisting sliding mode protocol (DSTSM) is designed for achieving the formation and tracking of non-linear model of multiple Quadcopters using multiagent system (MAS) concept. The undirected graph theory and leader-follower protocol is used to establishing the communication between the neighborhood Quadcopters and achieving the formation. The protocol is validated for the formation of five Q uadcopters f or t he given pattern. T he stability 0 f the formation protocol is also ensured using the Lyapunov function. The simulation results show that the formation is achieved in finite time a nd tracking t he predefined tr ajectory. Al so, the protocol is robust against disturbance and parameter variation. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Seven Sisters Optimization Algorithm 2

Seven Sisters Optimization Algorithm

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Saxena, Ayan Kumar Yadav, Anshul Kumar, Rajesh Srm Institute of Science and Technology Computer Science and Engineering Chennai India Research Institute Council of Scientific & Industrial Research Central Electronics Engineering Pilani India Malaviya National Institute of Technology Electrical Engineering Jaipur India

ISBN: (纸本)9798350308846

This research proposes a new swarm-based meta-heuristic algorithm named Seven Sisters Optimizer (SSO) in-spired by the Jungle Babbler bird flock (commonly known as Seven sisters or Seven Brothers (in Hindi)). Jungle Babbler's calls are structurally and functionally organized to serve as a coherent communication system. They have 15 different types of communication classified as affiliative (friendly), with seven call types, and agonistic (unfriendly), with eight call types. The flock head, the sentinel bird, is tasked with the keep tab on optimal habitat and orients the flock members as affiliative and agonistic. The proposed algorithm is tested on 13 well-known benchmark functions. The results of the proposed SSO are verified by a comparative study of of SSO with nine other existing optimization algorithms, which include the most widely used meta-heuristics, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) as well as Gravitational Search Algorithm (GSA), Flower Polli-nation Algorithm (FPA), Moth-Flame Optimization (MFO), Bat Algorithm (BOA), Firefly Algorithm (FA), Cuckoo Search Algorithm (CS) along with high-performance optimizer LSHADE-SPACMA (LSP). To evaluate the constraint handling capacity of the proposed algorithm ie SSO, it is further tested on a gear design problem, and the results are compared with different classical and swarm-based optimization approaches. The results demonstrate that the proposed SSO exploration and exploitation capabilities are superior as compared to the other optimizers. © 2023 IEEE.

关键词： algorithm metaheuristics optimization seven sisters

来源：评论

学校读者我要写书评

暂无评论

Thermo-hydro-poro-mechanical responses of a reservoir-induced landslide tracked by high-resolution fiber optic sensing nerves

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第3期16卷 1018-1032页

作者： Xiao Ye Hong-Hu Zhu Gang Cheng Hua-Fu Pei Bin Shi Luca Schenato Alessandro Pasuto School of Earth Sciences and Engineering Nanjing UniversityNanjing210023China School of Computer Science North China Institute of Science and Technology(National Safety Training Center of Coal Mines)Beijing101601China State Key Lab of Coastal and Offshore Engineering Department of Geotechnical EngineeringDalian University of TechnologyDalian116024China National Research Council-Research Institute for Geo-Hydrological Protection(CNR-IRPI) Padova35127Italy Department of Information Engineering University of PadovaPadova35131Italy

Thermo-poro-mechanical responses along sliding zone/surface have been extensively ***,it has not been recognized that the potential contribution of other crucial engineering geological interfaces beyond the slip surface to progressive ***,we aim to investigate the subsurface multiphysics of reservoir landslides under two extreme hydrologic conditions(*** and dry),particularly within sliding *** on ultra-weak fiber Bragg grating(UWFBG)technology,we employ specialpurpose fiber optic sensing cables that can be implanted into boreholes as“nerves of the Earth”to collect data on soil temperature,water content,pore water pressure,and *** Xinpu landslide in the middle reach of the Three Gorges Reservoir Area in China was selected as a case study to establish a paradigm for in situ thermo-hydro-poro-mechanical *** UWFBG-based sensing cables were vertically buried in a 31 m-deep borehole at the foot of the landslide,with a resolution of 1 m except for the pressure *** reported field measurements covering the period 2021 and 2022 and produced the spatiotemporal profiles throughout the *** show that wet years are more likely to motivate landslide motions than dry *** annual thermally active layer of the landslide has a critical depth of roughly 9 m and might move downward in warmer *** dynamic groundwater table is located at depths of 9e15 m,where the peaked strain undergoes a periodical response of leap and withdrawal to annual hydrometeorological *** interface behaviors may support the interpretation of the contribution of reservoir regulation to slope stability,allowing us to correlate them to local damage events and potential global *** paper also offers a natural framework for interpreting thermo-hydro-poro-mechanical signatures from creeping reservoir bank slopes,which may form the basis for a landslide monitoring and early warning system.

关键词： Reservoir landslide Thermo-hydro-poro-mechanical response Ultra-weak fiber bragg grating(UWFBG) subsurface evolution engineering geological interface Geotechnical monitoring

来源：评论

学校读者我要写书评

暂无评论

Industrial Control Anomaly Detection Based on Distributed Linear Deep Learning

引用

computers, Materials & Continua 2025年第1期82卷 1129-1150页

作者： Shijie Tang Yong Ding Huiyong Wang School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin541004China School of Electronic Engineering and Automation Guilin University of Electronic TechnologyGuilin541004China Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic TechnologyGuilin541004China Institute of Cyberspace Technology HKCT Institute for Higher EducationHong Kong999077China School of Mathematics&Computing Science Guilin University of Electronic TechnologyGuilin541004China

As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and fast and accurate attack detection techniques are *** key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time *** address this issue,we propose an anomaly detection method based on distributed deep *** method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series,which can maintain the edge of discrete *** use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation *** method can not only detect abnormal attacks but also locate the sensors that cause *** conducted experiments on the Secure Water Treatment(SWAT)and Water Distribution(WADI)public *** experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.

关键词： Anomaly detection CPS deep learning MLP(multi-layer perceptron)

来源：评论

学校读者我要写书评

暂无评论

Distributed Discrete-Time Exponential Sliding Mode Consensus Protocol for a Multi-Agent System 2

Distributed Discrete-Time Exponential Sliding Mode Consensus...

引用

2nd IEEE International Conference on Data, Decision and Systems, ICDDS 2023

作者： Joshi, Nikita Mehta, Axaykumar Institute of Infrastructure Technology Research and Management Electrical and Computer Science Engineering Ahmedabad380026 India

ISBN: (纸本)9798350314168

This paper presents a distributed discrete-Time exponential sliding mode consensus (DDESMC) protocol for a class of multi-Agent systems. A leader-following approach of a homogenous multi-Agent system (MAS) is exploited to derive the protocol. The discrete-Time exponential sliding mode control is proposed using the graph theory. The upper bound on the number of reaching steps for achieving the consensus among all the agents is derived. The protocol ensures the minimum width of the Quasi-Sliding Mode Band (QSMB) as compared to other classical approaches. Also, the protocol ensures the consensus effort in the order O (T3). The Lyapunov theory is then used to determine the global stability condition for the consensus, and finally, a numerical example is given to demonstrate the effectiveness of the protocol. Furthermore, the performance of the proposed protocol is compared to that of the standard DSMC protocol described in the literature for both the time and effort needed to reach consensus and the deviation from consensus after reaching consensus. It is inferred that the proposed DDESMC protocol outperforms the classical DSMC protocol. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Collaborative Service Provisioning for UAV-Assisted Mobile Edge Computing

引用

Chinese Journal of Electronics 2024年第6期33卷 1504-1514页

作者： Yuben QU Zhenhua WEI Zhen QIN Tao WU Jinghao MA Haipeng DAI Chao DONG The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Colllege of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Xi'an Research Institute of High Technology Department of Information and Communication Noncommissioned Officer Academy of PAP National University of Defense Technology Department of Computer Science and Technology Nanjing University

Unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC), as a way of coping with delaysensitive and computing-intensive tasks, is considered to be a key technology to solving the challenges of terrestrial MEC networks. In this work, we study the problem of collaborative service provisioning(CSP) for UAV-assisted MEC. Specifically, taking into account the task latency and other resource constraints, this paper investigates how to minimize the total energy consumption of all terrestrial user equipments, by jointly optimizing computing resource allocation, task offloading, UAV trajectory, and service placement. The CSP problem is a non-convex mixed integer nonlinear programming problem, owing to the complex coupling of mixed integral variables and non-convexity of CSP. To address the CSP problem, this paper proposes an alternating optimization-based solution with the convergence guarantee as follows. We iteratively deal with the joint service placement and task offloading subproblem, and UAV movement trajectory subproblem, by branch and bound and successive convex approximation, respectively,while the closed form of the optimal computation resource allocation can be efficiently obtained. Extensive simulations validate the effectiveness of the proposed algorithm compared to three baselines.

关键词： Energy consumption Multi-access edge computing Collaboration Programming Autonomous aerial vehicles Minimization Trajectory Resource management Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Evaluating Fairness in LLMs 1

Deep Learning Approach for Evaluating Fairness in LLMs

引用

1st International Conference on Sustainable Energy Technologies and Computational Intelligence, SETCOM 2025

作者： Kumari, Laxmi Serasiya, Shilpa Bharti, Santosh Kalol Institute of Technology & Research Center Gujarat Kalol India Pandit Deendayal Energy University Computer Science and Engineering Gandhinagar India

ISBN: (纸本)9798331520540

Large Language Models (LLMs) are prone to bias that can be introduced in the dataset itself or in the training phase. This can make their output lacking in fairness and hinder certain discriminated groups on the basis of stereotypes that the LLM may have been fed with or learnt. In today's day and age, LLMs are used to make major decisions and thus it is crucial to identify and remove such bias. In this paper, we have focused on identifying the bias present in medium-sized LLMs such as BERT, RoBERTA, DeBERTa and GPT-1 using bias evaluation metrics such as intrinsic and extrinsic. Both the metrics have been used and bias has been identified in the datasets that the LLMs are being trained on (intrinsic bias) as well as in the outputs of the LLMs for certain queries (extrinsic bias). © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Random Separating Hyperplane Theorem and Learning Polytopes 51

Random Separating Hyperplane Theorem and Learning Polytopes

引用

51st International Colloquium on Automata, Languages, and Programming, ICALP 2024

作者： Bhattacharyya, Chiranjib Kannan, Ravindran Kumar, Amit Department of Computer Science and Automation Indian Institute of Science Bangalore India Department of Operations Research Carnegie Mellon University Pittsburgh United States Department of Computer Science and Engineering Indian Institute of Technology Delhi India

ISBN: (纸本)9783959773225

The Separating Hyperplane theorem is a fundamental result in Convex Geometry with myriad applications. The theorem asserts that for a point a not in a closed convex set K, there is a hyperplane with K on one side and a strictly on the other side. Our first result, Random Separating Hyperplane Theorem (RSH), is a strengthening of this for polytopes. RSH asserts that if the distance between a and a polytope K with k vertices and unit diameter in ℜd is at least δ, where δ is a fixed constant in (0,1), then a randomly chosen hyperplane separates a and K with probability at least 1/poly(k) and margin at least Ω(δ/√d). RSH has algorithmic applications in learning polytopes. We consider a fundamental problem, denoted the "Hausdorff problem", of learning a unit diameter polytope K within Hausdorff distance δ, given an optimization oracle for K. Using RSH, we show that with polynomially many random queries to the optimization oracle, K can be approximated within error O(δ). To our knowledge, this is the first provable algorithm for the Hausdorff Problem in this setting. Building on this result, we show that if the vertices of K are well-separated, then an optimization oracle can be used to generate a list of points, each within distance O(δ) of K, with the property that the list contains a point close to each vertex of K. Further, we show how to prune this list to generate a (unique) approximation to each vertex of the polytope. We prove that in many latent variable settings, e.g., topic modeling, LDA, optimization oracles do exist provided we project to a suitable SVD subspace. Thus, our work yields the first efficient algorithm for finding approximations to the vertices of the latent polytope under the well-separatedness assumption. This assumption states that each vertex of K is far from the convex hull of the remaining vertices of K, and is much weaker than other assumptions behind algorithms in the literature which find vertices of the latent polytope. © Chiranjib Bhatt

关键词： Set theory

来源：评论

学校读者我要写书评

暂无评论

scNovel: a scalable deep learning-based network for novel rare cell discovery in single-cell transcriptomics

引用

BRIEFINGS IN BIOINFORMATICS 2024年第3期25卷 bbae112-bbae112页

作者： Zheng, Chuanyang Wang, Yixuan Cheng, Yuqi Wang, Xuesong Wei, Hongxin King, Irwin Li, Yu Department of Computer Science and Engineering CUHK Hong Kong SAR China College of Computing Georgia Institute of Technology Atlanta GA USA MLR Lab Southern University of Science and Technology The CUHK Shenzhen Research Institute Hi-Tech Park Nanshan Shenzhen 518057 China Institute for Medical Enginering and Science Massachusetts Institute of Technology Cambridge MA USA Wyss Institute for Biologically Inspired Engineering Harvard University Boston MA USA Broad Institute of MIT and Harvard Cambridge MA USA

Single-cell RNA sequencing has achieved massive success in biological research fields. Discovering novel cell types from single-cell transcriptomics has been demonstrated to be essential in the field of biomedicine, yet is time-consuming and needs prior knowledge. With the unprecedented boom in cell atlases, auto-annotation tools have become more prevalent due to their speed, accuracy and user-friendly features. However, existing tools have mostly focused on general cell-type annotation and have not adequately addressed the challenge of discovering novel rare cell types. In this work, we introduce scNovel, a powerful deep learning-based neural network that specifically focuses on novel rare cell discovery. By testing our model on diverse datasets with different scales, protocols and degrees of imbalance, we demonstrate that scNovel significantly outperforms previous state-of-the-art novel cell detection models, reaching the most AUROC performance(the only one method whose averaged AUROC results are above 94%, up to 16.26% more comparing to the second-best method). We validate scNovel's performance on a million-scale dataset to illustrate the scalability of scNovel further. Applying scNovel on a clinical COVID-19 dataset, three potential novel subtypes of Macrophages are identified, where the COVID-related differential genes are also detected to have consistent expression patterns through deeper analysis. We believe that our proposed pipeline will be an important tool for high-throughput clinical data in a wide range of applications.

关键词： novel rare cell discovery single-cell analysis neural network

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：