检索结果-内蒙古大学图书馆

18th Conference on computer science and Intelligence Systems, FedCSIS 2023

作者： Zielosko, Beata Stanczyk, Urszula Jablonski, Kamil Institute of Computer Science University of Silesia in Katowice Bedzínska 39 Sosnowiec41-200 Poland Department of Graphics Silesian University of Technology Computer Vision and Digital Systems Akademicka 2A Gliwice44-100 Poland

ISBN: (纸本)9788396744784

The paper presents investigations concerning the decision rule filtering process controlled by the estimated relevance of available attributes. In the conducted study, two search directions were used, sequential forward selection and sequential backward elimination. The steps of sequential search were governed by three rankings obtained for variables, all related to characteristics of data and rules that can be induced, as follows, (i) a ranking based on the weighting factor referring to the occurrence of attributes in generated decision reducts, (ii) the OneR ranking exploiting short rule properties, and (iii) the proposed ranking defined through the operation of greedy algorithm for rule induction. The three rankings were confronted and compared from the perspective of their usefulness for the selection of rules performed in the two directions and with two strategies for rule selection. The resulting sets of rules were analysed with respect to the properties of the constituent decision rules and from the point of performance for all constructed rule-based classifiers. Substantial experiments were carried out in the stylometric domain, treating the task of authorship attribution as classification. The results obtained indicate that for all three rankings and search paths it was possible to obtain a noticeable reduction of attributes while at least maintaining the power of inducers, at the same time improving characteristics of rule sets. © 2023 Polish Information Processing Society.

关键词： Information use

来源：评论

学校读者我要写书评

暂无评论

SaTrack: LoS/NLoS State-Aware WiFi Indoor Tracking System 21

SaTrack: LoS/NLoS State-Aware WiFi Indoor Tracking System

引用

21st Annual IEEE International Conference on Sensing, Communication, and Networking, SECON 2024

作者： Zhou, Yinnan Zhou, Hao Li, Luowei Chen, Siming Liu, Zhi Li, Xiang-Yang LINKE Lab School of Computer Science and Technology University of Science and Technology of China China CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China China Department of Computer and Network Engineering The University of Electro-Communications Tokyo182-8585 Japan

ISBN: (纸本)9798331519186

WiFi-based technology is appealing for indoor localization due to the widely deployed infrastructures. Recently, path separation solutions have been proposed to address the multipath effects and achieve decimeter-level localization accuracy in line-of-sight (LoS) scenarios. However, these solutions experience serious performance degradation in non-line-of-sight (NLoS) scenarios, and couldn’t be used for mobile device tracking where continuous LoS/NLoS switching happens. In this paper, we propose SaTrack, a LoS/NLoS state-aware mobile device tracking system. SaTrack identifies LoS/NLoS states based on the diversity of the strongest estimated paths when using different reference antennas. With the observation of spatial aggregation and temporal continuity for the Tx-Rx direct path, SaTrack chooses the direct path through two-step clustering, i.e., clustering in the spatial domain to form candidates and clustering again in the temporal domain to select the winner. Extensive experiments are conducted to evaluate the effectiveness of SaTrack. In a typical indoor environment with abundant multipath, SaTrack achieves 0.64m and 1.27m for the median and 90th percentile tracking errors, outperforming the state-of-the-art (SOTA) solutions. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Software Vulnerability Detection with GPT and In-Context Learning 8

Software Vulnerability Detection with GPT and In-Context Lea...

引用

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Liu, Zhihong Liao, Qing Gu, Wenchao Gao, Cuiyun School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory Shenzhen China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350331035

Code vulnerability detection is a software security analysis technique that focuses on recognizing and resolving possible code vulnerabilities and weaknesses. Its primary objective is to mitigate the chances of malicious attacks and system failures. Vulnerabilities encompass mistakes, defects, or insecure programming methodologies found within the code, which can lead to security risks, service denials, data leaks, and various other concerns. Previous research has predominantly focused on deep learning models such as VulDeePecker, Russell, and SySeVR. With the advent of large language models, impressive advancements have been made in various domains, including natural language generation, text classification, and sentiment analysis. However, there is currently no effective method for utilizing large language models in vulnerability detection. Therefore, this study explores and validates the application of such models for code vulnerability detection. In this paper we present a context-based learning approach to enhance the capability of code vulnerability detection named VUL-GPT. Our method combines code retrieval and code analysis, leveraging in-context learning to improve the performance of the GPT model in vulnerability detection. Specifically, we use GPT to generate analysis content for the test code and employ code retrieval methods such as BM-25 and TF-IDF to retrieve the most similar code snippet and its vulnerability information from the training set. Subsequently, we input them along with the test code and its analysis into the GPT model, leveraging the contextual learning ability of the large language model for vulnerability detection. Our experiments demonstrate that combining with code retrieval and code analysis, the GPT models can detect code vulnerability detection more effectively. © 2023 IEEE.

关键词： code retrieval in-content learning large language models

来源：评论

学校读者我要写书评

暂无评论

Boosting Meaningful Dependency Mining with Clustering and Covariance Analysis 40

Boosting Meaningful Dependency Mining with Clustering and Co...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Wang, Xi Jin, Ruochun Huang, Wanrong Tang, Yuhua Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Computer Science and Technology Department of Intelligent Data Science National University of Defense Technology Changsha China

ISBN: (纸本)9798350317152

Functional dependencies (FDs) form a valuable ingredient for various data management tasks. However, existing methods can hardly discover practical and interpretable FDs, especially in large noisy real-life datasets. This paper studies the problem of discovering meaningful functional dependencies (FDms) that utilize support and error parameters to capture interesting dependencies in such datasets and proposes an efficient discovery algorithm called FDM?. In order to scale with large datasets, FDM ? employs an efficient sampling method with accuracy guarantees to capture the differences between tuple pairs and to quantify the connection between support/error of dependencies on samples and those on the entire dataset. Moreover, it adopts a clustering-based correlated attributes extraction to divide the exponentially large search space into multiple small sub-spaces and proposes an easy-first traversal strategy with covariance-based guidance that quickly detects candidate dependencies and validates them. Additionally, we prove a covariance lower bound as an additional pruning criterion to reduce the search space. Extensive experiments on real-life and synthetic datasets demonstrate that FDM ? is 14 times faster than existing discovery algorithms on average, up to 31 times, and scales to larger datasets with the least memory cost. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

A Multi-Threshold Energy approach for Energy Harvesting WSN 2

A Multi-Threshold Energy approach for Energy Harvesting WSN

引用

2nd IEEE International Conference on New Technologies of Information and Communication, NTIC 2022

作者： Bengheni, Abdelmalek Lim Research Laboratory Ibn Khaldoun University Mathematics and Computer Science Faculty Department of Computer Science Tiaret Algeria

ISBN: (纸本)9781665489744

This article offers a Multi-threshold Energy approach for Energy-Harvesting Wireless Sensor Network (MTE-EHWSN) to enhance the lifetime and Wireless Sensor Network (WSN) performance by minimizing the duty-cycle more radically and profoundly of each sensor node. The use of MTE-EHWSN by any sensor node in the WSN allows for energy harvesting management and energy consumption, helping it to ensure its balance and to dynamically regulate its duty-cycle through calculating its sleep interval more radically and profoundly according on the amount of current remaining energy. In addition, our proposed approach allows WSN to function well in the case of low energy harvesting. Through OMNeT++/MiXiM simulations, we demonstrated that MTE-EHWSN approach enhances the WSN performance compared to other current energy harvesting administration approach such as EH2M by incorporating these two approaches into the sender-initiated MAC mode of communication. © 2022 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm 41

On the Emergence of Cross-Task Linearity in Pretraining-Fine...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Zhanpeng Chen, Zijun Chen, Yilan Zhang, Bo Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China Shanghai Artificial Intelligence Laboratory China Computer Science and Engineering University of California San Diego United States

The pretraining-finetuning paradigm has become the prevailing trend in modern deep *** this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on different tasks1, termed as Cross-Task Linearity (CTL).Specifically, we show that if we linearly interpolate the weights of two finetuned models, the features in the weight-interpolated model are often approximately equal to the linear interpolation of features in two finetuned models at each *** provide comprehensive empirical evidence supporting that CTL consistently occurs for finetuned models that start from the same pretrained *** conjecture that in the pretraining-finetuning paradigm, neural networks approximately function as linear maps, mapping from the parameter space to the feature *** on this viewpoint, our study unveils novel insights into explaining model merging/editing, particularly by translating operations from the parameter space to the feature ***, we delve deeper into the root cause for the emergence of CTL, highlighting the role of *** released our source code at https://***/zzp1012/Cross-Task-Linearity. Copyright 2024 by the author(s)

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Maximum Polygon Packing: The CG:SHOP Challenge 2024

arXiv

引用

arXiv 2024年

作者： Fekete, Sándor P. Keldenich, Phillip Krupke, Dominik Schirra, Stefan Department of Computer Science TU Braunschweig Germany Department for Simulation and Graphics OvGU Magdeburg Germany

We give an overview of the 2024 Computational Geometry Challenge targeting the problem Maximum Polygon Packing: Given a convex region P in the plane, and a collection of simple polygons Q1, . . ., Qn, each Qi with a respective value ci, find a subset S ⊆ {1, . . ., n} and a feasible packing within P of the polygons Qi (without rotation) for i ∈ S, maximizing Pi∈S ci. Geometric packing problems, such as this, present significant computational challenges and are of substantial practical importance. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Deepdive:a learning-based approach for virtual camera in immersive contents

引用

Virtual Reality & Intelligent Hardware 2022年第3期4卷 247-262页

作者： Muhammad IRFAN Muhammad MUNSIF Department of Computer Science Oakland UniversityMichiganUSA Digital Image Processing Laboratory Islamia CollegePeshawarPakistan

A 360°video stream provide users a choice of viewing one's own point of interest inside the immersive *** head or hand manipulations to view the interesting scene in a 360°video is very tedious and the user may view the interested frame during his head/hand movement or even lose *** automatically extracting user's point of interest(UPI)in a 360°video is very challenging because of subjectivity and difference of *** handle these challenges and provide user's the best and visually pleasant view,we propose an automatic approach by utilizing two CNN models:object detector and aesthetic score of the *** proposed framework is three folded:pre-processing,Deepdive architecture,and view selection *** first fold,an input 360°video-frame is divided into three sub frames,each one with 120°*** second fold,each sub-frame is passed through CNN models to extract visual features in the sub-frames and calculate aesthetic ***,decision pipeline selects the sub frame with salient object based on the detected object and calculated aesthetic *** compared to other state-of-the-art techniques which are domain specific approaches i.e.,support sports 360°video,our syste m support most of the 360°videos *** evaluation of proposed framework on our own collected data from various websites indicate performance for different categories of 360°videos.

关键词： Virtual reality Immersive contents Deep learning Aesthetic Saliency

来源：评论

学校读者我要写书评

暂无评论

A Gradient-Guided Evolutionary Approach to Training Deep Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4861-4875页

作者： Yang, Shangshang Tian, Ye He, Cheng Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Department of Computer Science University of Surrey Guildford U.K

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

关键词： Artificial neural networks Training Optimization Search problems Scalability Complexity theory Genetic algorithms Deep neural networks (DNNs) evolutionary algorithm (EA) genetic operator gradient descent sparsity

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Knowledge Transfer Framework for Heterogeneous Federated Learning 42

A Hierarchical Knowledge Transfer Framework for Heterogeneou...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Deng, Yongheng Ren, Ju Tang, Cheng Lyu, Feng Liu, Yang Zhang, Yaoxue Tsinghua University Department of Computer Science and Technology BNRist Beijing China Zhongguancun Laboratory Beijing China Central South University School of Computer Science and Engineering Changsha China Beijing China

ISBN: (纸本)9798350334142

Federated learning (FL) enables distributed clients to collaboratively learn a shared model while keeping their raw data private. To mitigate the system heterogeneity issues of FL and overcome the resource constraints of clients, we investigate a novel paradigm in which heterogeneous clients learn uniquely designed models with different architectures, and transfer knowledge to the server to train a larger server model that in turn helps to enhance client models. For efficient knowledge transfer between client models and server model, we propose FedHKT, a Hierarchical Knowledge Transfer framework for FL. The main idea of FedHKT is to allow clients with similar data distributions to collaboratively learn to specialize in certain classes, then the specialized knowledge of clients is aggregated to a super knowledge covering all specialties to train the server model, and finally the server model knowledge is distilled to client models. Specifically, we tailor a hybrid knowledge transfer mechanism for FedHKT, where the model parameters based and knowledge distillation (KD) based methods are respectively used for client-edge and edge-cloud knowledge transfer, which can harness the pros and evade the cons of these two approaches in learning performance and resource efficiency. Besides, to efficiently aggregate knowledge for conducive server model training, we propose a weighted ensemble distillation scheme with server-assisted knowledge selection, which aggregates knowledge by its prediction confidence, selects qualified knowledge during server model training, and uses selected knowledge to help improve client models. Extensive experiments demonstrate the superior performance of FedHKT compared to state-of-the-art baselines. © 2023 IEEE.

关键词： Distillation

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：