检索结果-内蒙古大学图书馆

2023 International Symposium of Electronics Design Automation, ISEDA 2023

作者： Sun, Shuyuan Chen, Xuelian Yang, Fan Yu, Bei Li, Shang Zeng, Xuan School of Microelectronics Fudan University State Key Lab of ASIC and System China Cogenda Inc China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350304510

As feature size continues to shrink and light source wavelengths remain unchanged, the optical diffraction effects seriously degrade chip yield. Optical proximity correction (OPC) has become an essential step for chip manufacturability. However, OPC cannot achieve satisfactory mask correction results in an affordable number of iterations on some layouts, delaying the chip design cycle. In this paper, we propose to use the Graph Neural Network (GNN) to predict the initial mask correction and speed up model-based OPC. We design a graph model to represent the chip layout, with segments represented as graph nodes and the diffraction effects between them represented as graph edges. The GNN is used to obtain the embedding of the segment, and we predict the shift value based on its output. The proposed GNN-based predictor enhances the original OPC to find a good correction solution for full-chip-size masks in fewer iterations. compared with the original OPC method, experimental results on 55nm and 32nm full chip designs show that the proposed GNN-based OPC method reduces the number of iterations up to 75% and the acquired mask of comparable quality. © 2023 IEEE.

关键词： Diffraction

来源：评论

学校读者我要写书评

暂无评论

Object Detection for Autonomous Vehicles in Urban Areas Using Deep Learning 1

引用

9th Future Technologies Conference, FTC 2024

作者： Arslan, Muhammad Mubeen, Muhammad Usman, Syed Muhammad Data Lab - Doyle 206 Loyola University Chicago Chicago United States University of the People Pasadena United States Department of Computer Science Bahria School of Engineering and Applied Sciences Bahria University Islamabad44000 Pakistan

ISBN: (数字)9783031731259

ISBN: (纸本)9783031731242

This study details the development of a reliable automated system for detecting urban traffic using a custom dataset, designed specifically for this research. We developed a novel architecture based on the YOLOv8 framework, featuring a vehicle-mounted camera on a rotatable platform to continuously stream video data via a 4G network to a control center. The system processes this data using advanced deep learning techniques, achieving an impressive 85.5% accuracy rate in real-time identification of pedestrians, vehicles, and bicycles. This accuracy surpasses current state-of-the-art methods and demonstrates exceptional speed and reliability, crucial for the safety and efficiency of autonomous vehicles. By significantly reducing misclassification, our method not only enhances the safety of urban navigation but also sets a new benchmark in the application of deep learning technologies. This work bridges the technological divide between developed and developing nations, marking a substantial advancement in the field of autonomous vehicle technologies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood

arXiv

引用

arXiv 2024年

作者： Xu, Yang Wang, Yu An, Hao Liu, Zhichen Li, Yongyuan Department of Computer Science and Engineering Southern University of Science and Technology China Digital Linguistics Lab Department of Linguistics Bielefeld University Germany

Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model’s capabilities of generating human-like texts keep evolving. This study provides a new perspective by using the relative likelihood values instead of absolute ones, and extracting useful features from the spectrum-view of likelihood for the human-model text detection task. We propose a detection procedure with two classification methods, supervised and heuristic-based, respectively, which results in competitive performances with previous zero-shot detection methods and a new state-of-the-art on short-text detection. Our method can also reveal subtle differences between human and model languages, which find theoretical roots in psycholinguistics studies. Our code is available at https://***/CLCS-SUSTech/FourierGPT. © 2024, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Triple-Fault-Tolerant Binary MDS Array Codes with Lower Encoding Complexity 18

Triple-Fault-Tolerant Binary MDS Array Codes with Lower Enco...

引用

18th International Symposium on Problems of Redundancy in Information and Control Systems, REDUNDANCY 2023

作者： Hou, Hanxu Song, Linqi Dongguan University of Technology Dongguan Key Lab of Artificial Information Network School of Electrical Engineering & Intelligentization China City University of Hong Kong Department of Computer Science Hong Kong

ISBN: (纸本)9798350381528

In this paper, we present a new construction of maximal distance separable (MDS) array codes with three parity columns. We present an efficient encoding algorithm for our new codes and show that our new codes have lower encoding complexity than all the existing MDS codes under the same parameters. The essential reasons of obtaining lower encoding complexity for our codes are of two-folds: (i) our codes are well-designed in a cyclic polynomial ring with only cyclic shifts and XORs being involved in the operations;(ii) our codes are designed based on the efficient schedule algorithm that can minimize the number of operations in the coding procedure. Moreover, our codes can support much more parameters compared with the existing MDS array codes, such as the EVENODD codes and STAR codes. We also present an efficient decoding method for the proposed codes. © 2023 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Employing Invisible Unicode Characters for Preserving Privacy and Enhancing Communication Security

Employing Invisible Unicode Characters for Preserving Privac...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Mahmoud A. Khalifa Iman Almomani Walid El-Shafai Computer Science Department Security Engineering Lab Prince Sultan University Riyadh Saudi Arabia Computer Science Department KASIT University of Jordan Amman Jordan Security Engineering Lab Prince Sultan University Riyadh Saudi Arabia

ISBN: (数字)9798350374131

ISBN: (纸本)9798350374148

In an era where digital privacy con-cerns are paramount, unconventional methods for safeguarding personal information have emerged. This paper delves into the innovative use of non-printable Unicode characters to bypass mandatory field requirements in online forms. This technique offers a new dimension to privacy protection in digital interactions. By exploiting invisible Unicode characters, such as $\mathrm{U}+202\mathrm{E}$ (RIGHT- TO-LEFT OVERRIDE) and $\mathrm{U}+200\mathrm{C}$ (ZERO WIDTH NON-JOINER), users can fulfill form requirements with-out disclosing some of their personal information, thus leaving no digital footprint. Our investigation not only catalogs these invisible characters but also evaluates their effectiveness across various platforms, including social media, online forms, and conference registration forms. Also, we in-vestigated the case of enhancing communication security by incorporating Advanced Encryption Standard (AES) with invisible Unicode characters. Overall, this research aims to shed light on the prospective privacy benefits afforded by these char-acters, explore the security implications of their application, and recommend strategies for users and developers to employ this method of privacy protection responsibly.

关键词： Privacy Data privacy Social networking (online) Data integrity Maintenance Encryption Security

来源：评论

学校读者我要写书评

暂无评论

SAMA: A Comprehensive Smart Automated Malware Analyzer Empowered by ChatGPT Integration

SAMA: A Comprehensive Smart Automated Malware Analyzer Empow...

引用

International Conference on Telecommunications (ICT)

ISBN: (数字)9798350356694

ISBN: (纸本)9798350356700

Smart Automated Malware Analyzer (SAMA) is a sophisticated automated tool designed to streamline and enhance the malware analysis process. With a comprehensive suite of features, the SAMA tool empowers security researchers and analysts to dissect and understand the behavior of malicious software efficiently. This paper presents each feature's design, implementation, and significance, highlighting their pivotal role in strengthening cybersecurity defenses. SAMA tool offers a holis-tic approach to malware analysis, leveraging heuristic analysis, string analysis, entropy analysis, API function analysis, signature-based detection, VirusTotal integration, GPT-assisted analysis, LOLBIN detection, and report generation capabilities. Experi-mental validations and real-world case studies demonstrate the efficacy and utility of the SAMA tool in combating evolving cyber threats.

关键词： computer viruses Chatbots Malware Entropy Telecommunications computer security

来源：评论

学校读者我要写书评

暂无评论

BNIMI: Boolean Gene Regulatory Network Inference Based on Mutual Information

BNIMI: Boolean Gene Regulatory Network Inference Based on Mu...

引用

2024 Multimedia University engineering Conference, MECON 2024

作者： Barman, Shohag Farid, Fahmid Al Sarker, Md. Tanjil Hafiz, Md Ferdous Bin Khan, Niaz Ashraf Gope, Hira Lal Karim, Hezerul Abdul Mansor, Sarina Bari, Ahsanul University of Liberal Arts Bangladesh Department of Computer Science & Engineering Dhaka Bangladesh Multimedia University Centre for Digital Home Faculty of Engineering Cyberjaya63100 Malaysia Multimedia University PV Energy Stroage Lab Faculty of Engineering Cyberjaya63100 Malaysia Sylhet Agricultural University Faculty of Agricultural & Engineering Technology Sylhet Bangladesh

ISBN: (纸本)9798331530747

Network inference is a challenging task in Bioinformatics. Numerous network inference approaches have been proposed, but most of them face scalability challenges when inferring a gene regulatory network because they typically limit the regulatory gene within a range of 1 to 3. Our solution to this issue is the BNIMI network inference approach, which uses mutual information to infer a gene regulatory network. The pairwise mutual information between a target gene and a regulatory gene is computed in the BNIMI. The regulatory and target gene pair is taken into consideration in the gene regulatory network if the mutual information surpasses a large threshold value. We do 100 random shuffles on the time series gene expression data to find the highest mutual information for each target gene in order to establish the threshold value. This maximum value is then considered as the threshold. We tested BNIMI against two popular existing methods (Context Likelihood Relatedness and REVEAL) by running numerous simulations on both artificial and real gene expression data. Our findings show that BNIMI significantly outperforms these established methods in both types of datasets. This means BNIMI is a powerful and effective tool for figuring out how genes regulate each other based on time-series gene expression information. © 2024 IEEE.

关键词： Gene expression regulation

来源：评论

学校读者我要写书评

暂无评论

Toward a Secure Industrial Wireless Body Area Network Focusing MAC Layer Protocols: An Analytical Review

引用

IEEE Transactions on Industrial Informatics 2023年第2期19卷 2028-2038页

作者： Javadpour, Amir Sangaiah, Arun Kumar Ja'Fari, Forough Pinto, Pedro Memarzadeh-Tehran, Hamidreza Rezaei, Samira Saghafi, Fatemeh Harbin Institute of Technology Department of Computer Science and Technology Shenzhen150001 China Instituto Politécnico de Viana Do Castelo ADiT-Lab Electrotechnics and Telecommunications Department Porto4900-347 Portugal National Yunlin University of Science and Technology International Graduate Institute of Ai Yunlin64002 Taiwan Sharif University of Technology Department of Computer Engineering Tehran11365-8639 Iran University of Tehran Faculty of New Sciences and Technologies Tehran14155-6619 Iran University of Groningen Bernoulli Institute for Mathematics and Computer Science Groningen9712 CP Netherlands University of Tehran Faculty of Management Tehran14155-6619 Iran

Monitoring security and quality of service is essential, due to the rapid growth of the number of nodes in wireless networks. In healthcare/industrial environments, especially in wireless body area networks (WBANs), this is even more important. Because the delays and errors can directly affect patients'/scientists' health. To increase the Monitoring Quality of Services (MQoS) in WBANs, a secure medium access control (MAC) protocol needs to be developed to provide optimal services. This article provides a comprehensive review of MAC protocols in WBANs with a technical security analysis approach. Time-based, contention-based, and hybrid protocols are compared in this article, regarding MQoS and their security vulnerabilities. We have considered delay, packet loss, and energy consumption as performance evaluation criteria in WBANs, which may be degraded under a cyberattack. This work shows that there is a research gap in the literature, which is the failure of covering security and privacy issues in the MAC layer protocols. © 2005-2012 IEEE.

关键词： Time division multiple access

来源：评论

学校读者我要写书评

暂无评论

Creating, Using and Assessing a Generative-AI-Based Human-Chatbot-Dialogue Dataset with User-Interaction Learning Capabilities

Creating, Using and Assessing a Generative-AI-Based Human-Ch...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Cuzzocrea, Alfredo Pilato, Giovanni Bringas, Pablo G. University of Calabria IDEA Lab Rende Italy University of Paris City Department of Computer Science Paris France National Research Council of Italy ICAR-CNR Palermo Italy University of Deusto Faculty of Engineering Bilbao Spain

ISBN: (纸本)9798350362480

The study illustrates a first step towards an ongoing work aimed at developing a dataset of dialogues potentially useful for customer service conversation management between humans and AI chatbots. The approach exploits ChatGPT 3.5 to generate dialogues. One of the requirements is that the dialogue is characterized by a specific language proficiency level of the user;the other one is that the user expresses a specific emotion during the interaction. The generated dialogues were then evaluated for overall quality. The complexity of the language used by both humans and AI agents, has been evaluated by using standard complexity measurements. Furthermore, the attitudes and interaction patterns exhibited by the chatbot at each turn have been stored for further detection of common conversation patterns in specific emotional contexts. The methodology could improve human-AI dialogue effectiveness and serve as a basis for systems that can learn from user interactions. © 2024 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

SSDC: A Scalable Sparse Differential Checkpoint for Large-scale Deep Recommendation Models

SSDC: A Scalable Sparse Differential Checkpoint for Large-sc...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Lingrui Xiang Xiaofen Lu Rui Zhang Zheng Hu Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China RAMS Lab Huawei Shenzhen China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

Today deep recommendation models have become increasingly large, with parameter sizes reaching hundreds of GB or even TB scale. As a result, it requires large-scale cluster computing resources to train such models. However, large-scale computing clusters tend to experience frequent failures during runtime, so fault-tolerance mechanisms such as checkpointing and restart are widely used in model training. Traditional checkpointing techniques periodically save all parameters of model, resulting in significant overhead. To address this issue, we propose an improved partial checkpointing mechanism for recommendation models named SSDC. SSDC uses an adaptive threshold strategy to reduce expensive operations when saving checkpoints, thereby having good scalability. Furthermore, SSDC saves the differential value of the model parameters, making it feasible to sparsify the otherwise dense embedding tables, thus reducing the bandwidth and time overhead to reconstruct checkpoints. Our evaluations show that compared to state-of-the-art methods, SSDC greatly reduces the time overhead of saving and reconstructing checkpoints, while achieving comparable training accuracy.

关键词： Checkpointing Training Adaptation models Fault tolerance Accuracy Computational modeling Scalability

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：