检索结果-内蒙古大学图书馆

International Conference on Edge Computing and Applications (ICECAA)

作者： Gnanajeyaraman Rajaram T. Stephen Thangaraj A. Packialatha R. Deepa Department of Applied Machine Learning Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences Chennai Tamil Nadu India Department of Computer Science and Engineering Paavai Engineering College Namakkal Tamil Nadu India Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India

Adversary node detection systems have become a vital component due to the malware attacks. These systems are very important for network security due to internet's widespread development and increased accessibility to global data systems. This paper presents a Crow Search Optimization Algorithm (CSOA) to detect the adversary node in a wireless network. The Rivest, Shamir, Adleman (RSA) algorithm transmits secure data at first. It uses the public key to encrypt the data and the private key to decrypt the data and the adversary nodes can't access or modify the real data. One of the significant problems is when an unknown attack occurs on the network due to the high volume of data while the detection's accuracy and false alarm rate decline. The proposed system aims to improve accuracy by identifying the adversary nodes using CSOA algorithm. From the results, it is observed that the CSOA mechanism reduces the loss ratio and improves throughput of the network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tip-Enhanced Raman Spectroscopy of Cell Wall Heterogeneity for Aspergillus Fumigatus

arXiv

引用

arXiv 2025年

作者： Jiang, Zhenfei Wang, Jizhou He, Zhe Zhang, Peng Yi, Zhenhuan Sokolov, Alexei V. Scully, Marlan O. Institute for Quantum Science and Engineering Texas A&M University College StationTX77843 United States Department of Physics and Astronomy Texas A&M University College StationTX77843 United States Shandong Institute of Advanced Technology Shandong Jinan China Department of Electrical and Computer Engineering Texas A&M University College StationTX77843 United States Department of Electrical and Computer Engineering Princeton University PrincetonNJ08540 United States

Tip-enhanced Raman spectroscopy (TERS) enables nanoscale chemical mapping of biological structures, providing high-resolution, high-signal-to-noise ratio imaging into molecular distribution and interactions beyond the capabilities of conventional Raman imaging. However, challenges such as the deformation of fragile biological cells and the complexity of signal interpretation would increase the difficulty in investigating biological samples with TERS. Here, we demonstrate using TERS to investigate the cell wall heterogeneity of Aspergillus fumigatus spores. Using TERS imaging and spectral analysis, we map the chemical components including melanin within the fungal cell wall. The results reveal distinct spectral features associated with polysaccharides, lipids, and proteins. Furthermore, by comparing the wild-type and albino mutant spores, we illuminate the biochemical characteristics of Dihydroxynaphthalene melanin (DHN-melanin) in the fungal cell wall. © 2025, CC BY.

关键词： Melanin

来源：评论

学校读者我要写书评

暂无评论

Contactless Respiratory Rate Monitoring For ICU Patients Based On Unsupervised Learning

Contactless Respiratory Rate Monitoring For ICU Patients Bas...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Liu, Zimeng Huang, Bin Lin, Chun-Liang Wu, Chieh-Liang Zhao, Changchen Chao, Wen-Cheng Wu, Yu-Cheng Zheng, Yadan Wang, Zhiru Beihang University Hangzhou Innovataion Institute China Beihang University School of Automation Science and Electrical Engineering China National Chung Hsing University College of Electrical Engineering and Computer Science Taiwan Taichung Veterans General Hospital Department of Critical Care Medicine Taiwan National Chung Hsing University College of Medicine Department of Post-Baccalaureate Medicine Taiwan National Chung Hsing University Big Data Center Taiwan Beijing University of Posts and Telecommunications Computer Science School China Beijing Foreign Studies University Graduate School of Translation and Interpretation China

ISBN: (纸本)9798350302493

Recently, the task of contactless physiological signal monitoring based on deep learning technologies has attracted a large number of scholars. However, few studies focus on the application of real-world scenarios, especially in clinical medicine scenes. In this paper, a novel video-based contactless respiratory rate measurement algorithm is developed for the Intensive Care Unit (ICU) patients. Firstly, a large-scale clinical real-world database towards ICU patient is collected in this study. Then, based on the dataset, the unsupervised learning is first introduced to extract the respiration waveform from the chest area of patients. Lastly, a respiratory rate estimator based on neural networks is proposed and trained on a periodical physiological signal simulation dataset, and utilizes the transfer learning technique to extract the respiratory rate from only 10-second respiration waveform. We obtained estimated respiratory rate with an MAE of 2.8 breaths/min and an STD of 3.0 breaths/min against the reference value computed from the specialized medical device. Extensive experiments demonstrate that our proposed methods achieve competitive results over state-of-the-art (SOTA) method in the real-world scenario. © 2023 IEEE.

关键词： Intensive care units

来源：评论

学校读者我要写书评

暂无评论

LARGE LANGUAGE MODELS FOR FORECASTING AND ANOMALY DETECTION: A SYSTEMATIC LITERATURE REVIEW

arXiv

引用

arXiv 2024年

作者： Su, Jing Jiang, Chufeng Jin, Xin Qiao, Yuxin Xiao, Tingsong Ma, Hongda Wei, Rong Jing, Zhi Xu, Jiajun Lin, Junhong AT&T Center for Virtualization Southern Methodist University DallasTX United States Department of Computer Science and Engineering Ohio State University ColumbusOH United States Department of Computer Science The University of Texas at Austin AustinTX United States Department of Information System Universidad Internacional Isabel I de Castilla Burgos Spain Department of Computer & Information Science & Engineering University of Florida GainesvilleFL United States Academy for Advanced Interdisciplinary Studies Peking University Beijing China School of Computer Science Carnegie Mellon University PittsburghPA United States Department of Electrical and Computer Engineering University of Southern California Los AngelesCA United States Electrical Engineering & Computer Science Department Massachusetts Institute of Technology CambridgeMA United States

This systematic literature review comprehensively examines the application of Large Language Models (LLMs) in forecasting and anomaly detection, highlighting the current state of research, inherent challenges, and prospective future directions. LLMs have demonstrated significant potential in parsing and analyzing extensive datasets to identify patterns, predict future events, and detect anomalous behavior across various domains. However, this review identifies several critical challenges that impede their broader adoption and effectiveness, including the reliance on vast historical datasets, issues with generalizability across different contexts, the phenomenon of model hallucinations, limitations within the models’ knowledge boundaries, and the substantial computational resources required. Through detailed analysis, this review discusses potential solutions and strategies to overcome these obstacles, such as integrating multimodal data, advancements in learning methodologies, and emphasizing model explainability and computational efficiency. Moreover, this review outlines critical trends that are likely to shape the evolution of LLMs in these fields, including the push toward real-time processing, the importance of sustainable modeling practices, and the value of interdisciplinary collaboration. Conclusively, this review underscores the transformative impact LLMs could have on forecasting and anomaly detection while emphasizing the need for continuous innovation, ethical considerations, and practical solutions to realize their full potential. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimised Grouped-Query Attention Mechanism for Transformers

arXiv

引用

arXiv 2024年

作者： Chen, Yuang Zhang, Cheng Gao, Xitong Mullins, Robert D. Constantinides, George A. Zhao, Yiren Department of Computer Science University of Cambridge Cambridge United Kingdom Department of Electrical and Eletronic Engineering Imperial College London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong China

Grouped-query attention (GQA) has been widely adopted in LLMs to mitigate the complexity of multi-head attention (MHA). To transform an MHA to a GQA, neighbour queries in MHA are evenly split into groups where each group shares the value and key layers. In this work, we propose AsymGQA, an activation-informed approach to asymmetrically grouping an MHA to a GQA for better model performance. Our AsymGQA outperforms the GQA within the same model size budget. For example, AsymGQA LLaMA-2-7B has an accuracy increase of 7.5% on MMLU compared to neighbour grouping. Our approach addresses the GQA's trade-off problem between model performance and hardware efficiency. © 2024, CC BY.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of Semantic Communications for Users with Heterogeneous Knowledge

Performance Optimization of Semantic Communications for User...

引用

IEEE International Conference on Communications (ICC)

作者： Jiantong Zhang Mingzhe Chen Yujiao Zhu H. Shihao Tao Luo Zhilong Zhang Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering and Institute for Data Science and Computing University of Miami Coral Gables FL USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

In this paper, a semantic communication framework for a scenario where the transmitter and the receiver have different knowledge is proposed. In the proposed framework, the transmitter extracts semantic information from the data according to its knowledge and sends it to the receiver. The receiver requires to process the received semantic information based on its knowledge. Here, the knowledge implies a method which the transmitter or the receiver can use to process the semantic information. Since the transmitter or the receiver have different knowledge, they may have different understandings for the same information. To ensure the receiver can understand the semantic information, the transmitter requires to estimate the receiver's knowledge by asking a series of questions about the transmitted data. By evaluating the difference between the answers of the receiver and the answers of the transmitter, the transmitter can adjust the method of semantic information extraction. Since the size of the extracted semantic information and the number of the questions that the transmitter can ask are limited, the transmitter must adjust the method of semantic information extraction and select appropriate questions to transmit. This problem is formulated as an optimization problem whose goal is to maximize the similarity of answers of the transmitter and the receiver by determining semantic information while minimizing the semantic similarity of answers by determining the questions to be transmitted. To solve this problem, an adversarial reinforcement learning (ARL) algorithm is proposed. The proposed algorithm, which consists of a semantic information RL and a question RL, can find the optimal semantic information generation scheme and question selection scheme by a competitive game between two agents. Simulation results demonstrate that the proposed framework can improve the semantic similarity of answers by up to 3.7% gain and can achieve up to 15.2 % gain in terms of the aver

关键词： Transmitters Simulation Semantics Receivers Games Transforms Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Target Localization for Distributed Hybrid Active-Passive Radars

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Zhou, Qiyu Yuan, Ye Li, Hongbin Lai, Yangming Greco, Maria Sabrina Gini, Fulvio Yi, Wei University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ07030 United States Fuzhou University School of Advanced Manufacturing Fuzhou350108 China University of Pisa Department of Information Engineering Pisa56122 Italy

Hybrid active-passive radar (HAPR) can effectively reduce the radiation power of active nodes, thus improving the radar system's electromagnetic environmental friendliness and anti-interception capability. Meanwhile, active nodes in HAPR can provide cooperative transmitters with known signals for passive nodes, overcoming performance losses caused by non-cooperative illuminators of opportunity (IOs). Although the advantages of HAPR have been gradually recognized in recent years, there is currently almost no systematic solution to the joint localization problem involving active and passive nodes. To address this problem, we propose two target localization algorithms for distributed HAPRs based on two-step and, respectively, direct localization. In the two-step localization, we establish two geometric equation sets with consistent structures to handle different geometric relationships among the target, transmitters/IOs, and receivers associated with the active and passive measurements. In direct localization, we reduce the high-dimensional joint likelihood function constructed from active and passive received signals into a low-dimensional one through two dimensionality reductions, significantly reducing the complexity. These algorithms combine active and passive received signals, enhancing localization performance. We also derive the Cramér-Rao lower bound (CRLB), which provides a useful performance indicator. The results indicate that the two-step localization algorithm yields suboptimal performance, with localization errors approaching the CRLB only under specific conditions. The direct localization algorithm approaches the CRLB and outperforms systems using only active or passive nodes, thereby confirming its effectiveness and robustness. © 1965-2011 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

Core Loss Separation Method for High Q Inductors

Core Loss Separation Method for High Q Inductors

引用

Wireless Power Week (WPW)

作者： Aaron Wadsworth Wenting Zhang Matthew G.S. Pearce Duleepa J. Thrimawithana Lei Zhao Zongzhen Li Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand College of Automation Chongqing University Chongqing China Jiangsu JITRI Advanced Energy Materials Research Institute Changzhou China

ISBN: (数字)9798350349139

ISBN: (纸本)9798350349146

Magnetic components used in power electronics are typically the largest and least efficient part of the design. For designers of power magnetics it is necessary to have reliable measurements of loss so the appropriate core can be selected. However, this is a challenging task since small errors in phase measurements can cause large errors in core loss. This is particularly challenging for cores with a phase angle close to 90°, i.e. a high Q. In this work a loss separation method and new phase correction method are proposed. Experimental results show the proposed method has lower error than existing state of the art techniques.

关键词： Wireless communication Power measurement Phase measurement Magnetic cores Magnetic separation Core loss Measurement techniques

来源：评论

学校读者我要写书评

暂无评论

Circuit Optimization Techniques for Efficient Ex-Situ Training of Robust Memristor Based Liquid State Machine 22

Circuit Optimization Techniques for Efficient Ex-Situ Traini...

引用

Proceedings of the 17th ACM International Symposium on Nanoscale Architectures

作者： Alex Henderson Chris Yakopcic Steven Harbour Tarek Taha Cory Merkel Hananel Hazan Dayton Engineering Advanced Projects Lab Southwest Research Institute Beavercreek OH USA Department of Electrical and Computer Engineering University of Dayton Dayton OH USA Department of Computer Engineering Rochester Institute of Technology Rochester NY USA Allen Discovery Center Tufts University Medford MA USA

ISBN: (纸本)9781450399388

Spiking neural network hardware offers a high performance, power-efficient and robust platform for the processing of complex data. Many of these systems require supervised learning, which poses a challenge when using gradient-based algorithms due to the discontinuous properties of SNNs. Memristor based hardware can offer gains in portability, power reduction, and throughput efficiency when compared to pure CMOS. This paper proposes a memristor-based spiking liquid state machine (LSM). The inherent dynamics of the LSM permit the use of supervised learning without backpropagation for weight updates. To carry out the design space evaluation of the LSM for optimal hardware performance, several temporal signal classification tasks are performed. It is found that the binary neuron activations in the output layer improve testing accuracy by 3.7% and 5% for classification, while reducing training time. A power and energy analysis of the proposed hardware is presented, resulting in an approximately 50% reduction in power consumption and cycle energy.

关键词： spiking neural network liquid state machine memristor

来源：评论

学校读者我要写书评

暂无评论

A Study on the Efficient Design of Adders Using Adiabatic Quantum-Flux-Parametron Circuits 11

A Study on the Efficient Design of Adders Using Adiabatic Qu...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Yamauchi, Tomoharu San, Hao Yoshikawa, Nobuyuki Chen, Olivia Tokyo City University Graduate School of Integrative Science and Engineering Tokyo Japan Tokyo City University Department of Electrical Electronics and Communication Engineering Tokyo Japan Institute of Advanced Sciences Yokohama National University Kanagawa Japan Tokyo City University Department of Computer Science Tokyo Japan

ISBN: (纸本)9781665492324

Adiabatic quantum-flux-parametron (AQFP) logic is a promising technology for future energy-efficient, high-performance information processing systems. It has significantly low power consumption thanks to the adiabatic switching of Josephson junctions. In this paper, we proposed an AQFP-based Kogge-Stone adder (KSA) to achieve low energy consumption. Moreover, we proposed an offset buffer based XOR macro to improve the hardware overhead. The proposed work achieves a 21% and 6% reduction in total Josephson junction count and circuit area, respectively. © 2022 IEEE.

关键词： Timing circuits

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：