检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition

作者： Zhicheng Xu Che-Kai Liu Chao Li Ruibin Mao Jianyi Yang Thomas Kämpfe Mohsen Imani Can Li Cheng Zhuo Xunzhao Yin Department of Electrical and Electronic Engineering The University of Hong Kong Zhejiang University School of Electrical and Computer Engineering Georgia Institute of Technology ZJU-Hangzhou Global Scientific and Technological Innovation Center Center Nanoelectric Technologies Fraunhofer IPMS Department of Computer Science University of California Irvine Key Lab of CS&AUS of Zhejiang Province

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

Rapid advancements in artificial intelligence have given rise to transformative models, profoundly impacting our lives. These models demand massive volumes of data to operate effectively, exacerbating the data-transfer bottleneck inherent in the conventional von-Neumann architecture. Compute-in-memory (CIM), a novel computing paradigm, tackles these issues by seam-lessly embedding in-memory search functions, thereby obviating the need for data transfers. However, existing non-volatile memory (NVM)-based accelerators are application specific. During the similarity based associative search operation, they only support a single, specific distance metric, such as Hamming, Manhattan, or Euclidean distance in measuring the query against the stored data, calling for reconfigurable in-memory solutions adaptable to various applications. To overcome such a limitation, in this paper, we present FeReX, a reconfigurable associative memory (AM) that accommodates various distance metrics including Hamming, Manhattan, and Euclidean distances. Leveraging multi-bit ferroelectric field-effect transistors (FeFETs) as the proxy and a hardware-software co-design approach, we introduce a constrained satisfaction problem (CSP)-based method to automate AM search input voltage and stored voltage configurations for different distance based search functions. Device-circuit co-simulations first validate the effectiveness of the proposed FeReX methodology for reconfigurable search distance functions. Then, we benchmark FeReX in the context of k-nearest neighbor (KNN) and hyperdimensional computing (HDC), which highlights the robustness of FeReX and demonstrates up to 250× speedup and 10 4 energy savings compared with GPU.

关键词： Measurement Nonvolatile memory Computational modeling Graphics processing units Benchmark testing Search problems In-memory computing

来源：评论

学校读者我要写书评

暂无评论

ITAE Index Based Control Design Strategy to Mitigate Frequency Deviation of Renewable Integrated Islanded-Microgrid

ITAE Index Based Control Design Strategy to Mitigate Frequen...

引用

International Conference on Power Electronic Drives

作者： T. K. Bashishtha V. P. Singh Akhilesh Mathur Krishna Murari Mrityunjay Kumar Mishra Ameena Saad Al-Sumaiti Electrical En-gineering M. National Institute of Technology Jaipur India Electrical Engineering and Computer Science Department The University of Toledo Ohio USA EECS Department Smart OR Lab APEC Khalifa University Abu Dhabi UAE

ISBN: (数字)9798350372472

ISBN: (纸本)9798350372489

This work addresses the frequency stability issue of microgrids and eliminates frequency errors by incorporating a proportional-integral-derivative (PID) controller. PID controller mitigates frequency error by deriving controller gains with the help of integral time absolute error (ITAE) index as a key design criterion. To validate controller efficacy, various analyses are conducted. The results indicate that ITAE assisted-PID controller achieves good settling time, rise time, and requires minimum controller magnitude. The ITAE-PID controller provides a better frequency response of considered microgrid model.

关键词： Time-frequency analysis Transient response Control design Stability criteria Microgrids Frequency response Indexes PD control Frequency control Tuning

来源：评论

学校读者我要写书评

暂无评论

An Extended Convergence Result for Behaviour Tree Controllers

arXiv

引用

arXiv 2023年

作者： Sprague, Christopher Iliffe Ögren, Petter The Robotics Perception and Learning Lab. School of Electrical Engineering and Computer Science Royal Institute of Technology KTH StockholmSE-100 44 Sweden

Behavior trees (BTs) are an optimally modular framework to assemble hierarchical hybrid control policies from a set of low-level control policies using a tree structure. Many robotic tasks are naturally decomposed into a hierarchy of control tasks, and modularity is a well-known tool for handling complexity, therefor behavior trees have garnered widespread usage in the robotics community. In this paper, we study the convergence of BTs, in the sense of reaching a desired part of the state space. Earlier results on BT convergence were often tailored to specific families of BTs, created using different design principles. The results of this paper generalize the earlier results and also include new cases of cyclic switching not covered in the literature. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Approximate Multiagent Reinforcement Learning for On-Demand Urban Mobility Problem on a Large Map (extended version)

arXiv

引用

arXiv 2023年

作者： Garces, Daniel Bhattacharya, Sushmita Bertsekas, Dimitri Gil, Stephanie The REACT lab Harvard University BostonMA United States The Department of Electrical Engineering and Computer Science Arizona State University AZ United States

In this paper, we focus on the autonomous multiagent taxi routing problem for a large urban environment where the location and number of future ride requests are unknown a-priori, but can be estimated by an empirical distribution. Recent theory has shown that a rollout algorithm with a stable base policy produces a near-optimal stable policy. In the routing setting, a policy is stable if its execution keeps the number of outstanding requests uniformly bounded over time. Although, rollout-based approaches are well-suited for learning cooperative multiagent policies with considerations for future demand, applying such methods to a large urban environment can be computationally expensive due to the large number of taxis required for stability. In this paper, we aim to address the computational bottleneck of multiagent rollout by proposing an approximate multiagent rollout-based two phase algorithm that reduces computational costs, while still achieving a stable near-optimal policy. Our approach partitions the graph into sectors based on the predicted demand and the maximum number of taxis that can run sequentially given the user’s computational resources. The algorithm then applies instantaneous assignment (IA) for re-balancing taxis across sectors and a sector-wide multiagent rollout algorithm that is executed in parallel for each sector. We provide two main theoretical results: 1) characterize the number of taxis m that is sufficient for IA to be stable;2) derive a necessary condition on m to maintain stability for IA as time goes to infinity. Our numerical results show that our approach achieves stability for an m that satisfies the theoretical conditions. We also empirically demonstrate that our proposed two phase algorithm has equivalent performance to the one-at-a-time rollout over the entire map, but with significantly lower runtimes. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Overview of Tools and Techniques in Network Forensics

An Overview of Tools and Techniques in Network Forensics

引用

Information Technology (ACIT)

作者： Mahmoud Asassfeh Mohammad Rasmi Al-Mousa Hasan Al-Dweikat Malak Hamad Al-Mashagbeh Suha Afaneh Ghassan Samara Ali Abu Zaid Mohammed Khouj Essam Al Daoud Department of Cybersecurity Zarqa University Zarqa Jordan Cybersecurity and Cloud Computing Department Applied Science Private University Amman Jordan Department of Computer Science Zarqa University Zarqa Jordan Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia Faculty of Information Technology Zarqa University Zarqa Jordan

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Network forensics pertains to a subfield of digital forensics that deals with network security. It is utilized in conjunction with computer network traffic monitoring and analysis, which acts as an intrusion detection system and firewall and facilitates the collection of data and digital proof for network security. This platform is designed to analyze and monitor data in a real-time network environment. It is a crucial instrument for identifying and resolving instances of real-time network misuse. This research shows the differences between network forensics and digital forensics as well as the tools and techniques used in network forensics. It also discusses building forensics platforms, developing network analysis methodologies, and talking about the future of network forensics.

关键词： Performance evaluation Digital forensics Intrusion detection Network analyzers Network security Search problems Real-time systems Logic Monitoring Stress

来源：评论

学校读者我要写书评

暂无评论

Derandomized novelty detection with FDR control via conformal e-values

arXiv

引用

arXiv 2023年

作者： Bashari, Meshi Epstein, Amir Romano, Yaniv Sesia, Matteo Department of Electrical and Computer Engineering Technion IIT Haifa Israel Citi Innovation Lab Tel Aviv Israel Department of Electrical and Computer Engineering Department of Computer Science Technion IIT Haifa Israel Department of Data Sciences and Operations University of Southern California Los AngelesCA United States

Conformal inference provides a general distribution-free method to rigorously calibrate the output of any machine learning algorithm for novelty detection. While this approach has many strengths, it has the limitation of being randomized, in the sense that it may lead to different results when analyzing twice the same data, and this can hinder the interpretation of any findings. We propose to make conformal inferences more stable by leveraging suitable conformal e-values instead of p-values to quantify statistical significance. This solution allows the evidence gathered from multiple analyses of the same data to be aggregated effectively while provably controlling the false discovery rate. Further, we show that the proposed method can reduce randomness without much loss of power compared to standard conformal inference, partly thanks to an innovative way of weighting conformal e-values based on additional side information carefully extracted from the same data. Simulations with synthetic and real data confirm this solution can be effective at eliminating random noise in the inferences obtained with state-of-the-art alternative techniques, sometimes also leading to higher power. Copyright © 2023, The Authors. All rights reserved.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

EEG-based Affect Classification with Machine Learning Algorithms

引用

IFAC-PapersOnLine 2023年第2期56卷 11627-11632页

作者： Jianhua Zhang Zhong Yin Peng Chen AI Lab Department of Computer Science Oslo Metropolitan University 0166 Oslo Norway School of Optical-Electrical and Computer Eng. University of Shanghai for Science and Technology Shanghai 200093 P.R. China School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 P.R. China

In this paper, we aim to study the EEG-based emotion recognition problem. First, we use clustering algorithm to determine the target class of emotions and perform binary classification of emotion along its arousal and valence dimension. Then we compare two different feature extraction methods, i.e., wavelet transform (resulting in wavelet-based features) and nonlinear dynamics analysis (leading to features of approximate entropy and sample entropy). Five feature reduction algorithms are compared in terms of emotion classification accuracy. Furthermore, four types of machine learning classifiers, including k-nearest neighbor (KNN), naive bayes (NB), support vector machine (SVM) and random forest (RF), are also compared. The results on the DEAP physiological data show that the combination of kernel spectral regression (KSR) and random forest leads to the best binary classification of emotions and that the EEG gamma rhythm is closely correlated to variations in emotions.

关键词： Emotion recognition Affective computing Electroencephalogram (EEG) Nonlinear dynamics Wavelets Kernel Spectral Regression (KSR) Machine learning

来源：评论

学校读者我要写书评

暂无评论

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?

arXiv

引用

arXiv 2024年

作者： Lin, Zhengkai Fu, Zhihang Liu, Kai Xie, Liang Lin, Binbin Wang, Wenxiao Cai, Deng Wu, Yue Ye, Jieping State Key Lab of CAD&CG Zhejiang University China Alibaba Cloud College of Biomedical Engineering & Instrument Science Zhejiang University China College of Computer Science and Technology Zhejiang University of Technology China School of Software Technology Zhejiang University China Fullong Inc China

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when models, having been trained on the fact "A is B", struggle to generalize this knowledge to infer that "B is A". In this paper, we examine the manifestation of the reversal curse across various tasks and delve into both the generalization abilities and the problem-solving mechanisms of LLMs. This investigation leads to a series of significant insights: (1) LLMs are able to generalize to "B is A" when both A and B are presented in the context as in the case of a multiple-choice question. (2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents. For example, this generalization only applies to biographies structured in "[Name] is [Description]" but not to "[Description] is [Name]". (3) We propose and verify the hypothesis that LLMs possess an inherent bias in fact recalling during knowledge application, which explains and underscores the importance of the document structure to successful learning. (4) The negative impact of this bias on the downstream performance of LLMs can hardly be mitigated through training alone. These findings offer a novel perspective on interpreting LLMs' generalization through their intrinsic mechanisms and provide insights for developing more effective learning methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Data description

来源：评论

学校读者我要写书评

暂无评论

Optimizing Transistor Selection Using AH-TOR for Low Noise Amplifier Design in Sensing Applications

Optimizing Transistor Selection Using AH-TOR for Low Noise A...

引用

International Conference on Sensing Technology, ICST

作者： Dayarnab Baidya Karthick Thiyagarajan Mitradip Bhattacharjee Yang An Department of Electrical Engineering and Computer Science i-Lab Indian Institute of Science Education and Research Bhopal Bhopal Madhya Pradesh India Smart Sensing and Robotics Laboratory (SensR Lab) Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment Western Sydney University Penrith Australia

ISBN: (数字)9798350374827

ISBN: (纸本)9798350374834

The design of a wireless sensor network receiver requires an efficient Low Noise Amplifier (LNA), with the transistor being a critical component that influences its performance. Selecting an optimal transistor for LNA design is a complex and time-consuming process due to the conflicting criteria involved. This study utilizes the Analytic Hierarchy Trade-off Ranking Method (AH-TOR), an integrated Multi-Criteria Decision-Making (MCDM) approach, to facilitate the selection of a suitable transistor for LNA design. Four types of transistors were evaluated as alternatives based on four criteria, with the Pseudomorphic High Electron Mobility Transistor (PHEMT) emerging as the optimal choice. The weight of PHEMT was calculated to be 1.0787, and its performance was benchmarked against other existing methods. Further analysis demonstrated the robustness of the AH-TOR method across various scenarios, consistently identifying PHEMT as the most suitable option. These findings highlight the reliability of the AH-TOR method for transistor selection in diverse applications.

关键词： Low-noise amplifiers Wireless sensor networks PHEMTs Decision making Receivers Electron mobility Robustness Sensors Transistors Integrated circuit reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Defect Detection Algorithm for Solar Panels 5

Deep Learning based Defect Detection Algorithm for Solar Pan...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Li, Jiaqi Li, Hongxu Wu, Yifan Zhou, Hailiang Manfredi, Luigi Li, Peng Zhang, Hong Hebei Province Yanshan University Department of Key Lab of Industrial Computer Control Engineering Qinhuangdao066004 China University of Alberta Department of Computing Science EdmontonABT6G 2R3 Canada Hebei Baoding Jiasheng Photovoltaic Technology Co. Ltd. China United Kingdom Southern University of Science and Technology Department of Electronic and Electrical Engineering Shenzhen China

ISBN: (纸本)9798350307320

Defect detection of solar panels plays an essential role in guaranteeing product quality within automated production lines. However, traditional manual inspection of solar panel defects suffers from low efficiency. This paper proposes an enhanced YOLOv5 algorithm (EL-YOLOv5) fused with the CBAM hybrid attention module to ensure product quality. The algorithm focuses on detecting five common types of defects that frequently appear on photovoltaic production lines, namely hidden cracks, scratches, broken grids, black spots, and short circuits. This study utilizes publicly available solar panel datasets, as well as datasets collected from actual photovoltaic production lines. These datasets are annotated accordingly and used to train the proposed algorithm. The experimental results demonstrate that the proposed algorithm achieves good performance on both the public and actual solar panel defect datasets. Particularly in actual datasets, where defect features are often less apparent and defects are smaller in size, the proposed algorithm can still detect even minor black spots. © 2023 IEEE.

关键词： Solar panels

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：