检索结果-内蒙古大学图书馆

Machine Learning-Aided Data Analysis in Single-Protein Conductance Measurement with Electron Tunneling Probes

Chinese Journal of Chemistry 2024年第1期42卷 67-72页

作者： Yuxin Yang Tao Jiang Ye Tian Biaofeng Zeng Longhua Tang State Key Laboratoryof Extreme Photonics and Instrumentation College of Optical Science and EngineeringZhejiang University HangzhouZhejiang 310027China Nanhu Brain-computer Interface Institute HangzhouZhejiang 311100China State Key Laboratory of Fluid Power and Mechatronic Systems College of Mechanical EngineeringZhejiang University HangzhouZhejiang 310027China

The electrical tunneling sensors have excellent potential in the next generation of single-molecule measurement and sequencing technologies due to their high sensitivity and spatial resolution *** tunneling signals that have been measured at a high sampling rate may provide detailed molecular *** the extraordinarily large amount of data that has been gathered,it is still difficult to correlate signal transformations with molecular processes,which creates great obstacles for signal *** learning is an effective tool for data analysis that is currently gaining more *** has demonstrated promising results when used to analyze data from single-molecule electrical *** order to extract meaningful information from raw measurement data,we have combined intelligent machine learning with tunneling electrical *** the purpose of analyzing tunneling electrical signals,we investigated the clustering approach,which is a classic algorithm in machine learning.A clustering model was built that combines the advantages of hierarchical clustering and Gaussian mixture model ***,customized statistical algorithms were *** has been proven to efficiently gather molecular information and enhance the effectiveness of data analysis.

关键词： Tunneling sensor Single-molecule measurement Machine learning Single-protein conductance Molecular electrochemistry Nanotechnology Molecular electronics

来源：评论

学校读者我要写书评

暂无评论

Poster Abstract: Enhancing Human Motion Sensing with synthesized Millimeter-Waves 23

Poster Abstract: Enhancing Human Motion Sensing with synthes...

引用

23rd ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2024

作者： Zhang, Xiaotong Wang, Kun Li, Zhenjiang Zhang, Jin City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Southern University of Science and Technology Res. Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Shenzhen China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798350362015

This poster introduces SynMotion, a novel mmWave-based human motion sensing system addressing the scarcity of training datasets. By synthesizing mmWave signals using existing vision-based human motion datasets, this system overcomes the challenge of collecting and labeling mmWave data, facilitating wider adoption of mmWave technology for applications like activity recognition, skeleton tracking and radar placement recommendation. © 2024 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Speech Extraction for Multiple Target Speakers Under Meeting Scenarios

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-7页

作者： Zeng, Bang Suo, Hongbin Wan, Yulong Li, Ming School of Computer Science Wuhan University Wuhan430027 China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan Jiangsu215316 China Data & amp AI Engineering System OPPO Beijing100125 China

The common target speech separation directly estimates the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation (MTSS) model to simultaneously extract each speaker’s voice from the mixed speech rather than just optimally estimating the target source. Moreover, we propose a speaker diarization (SD) aware MTSS system (SD-MTSS). By exploiting the target speaker voice activity detection (TSVAD) and the estimated mask, our SD-MTSS model can extract the speech signal of each speaker concurrently in a conversational recording without additional enrollment audio in advance. Experimental results show that our MTSS model achieves improvements of 1.38 dB signal-to-distortion ratio (SDR), 1.34 dB scale-invariant signal-to-distortion ratio (SISDR), and 0.13 perceptual evaluation of speech quality (PESQ) over the baseline on the WSJ0-2mix-extr dataset, separately. The SD-MTSS system makes a 19.2% relative speaker dependent character error rate reduction on the Alimeeting dataset. © Shanghai Jiao Tong University 2024.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis with LLMs: Evaluating QLoRA Fine-Tuning, Instruction Strategies, and Prompt Sensitivity 34

Sentiment Analysis with LLMs: Evaluating QLoRA Fine-Tuning, ...

引用

34th Annual International Conference on Collaborative Advances in Software and Computing, CASCON 2024

作者： Topal, Mustafa Burak Bozanta, Aysun Basar, Ayse Bogazici University Computer Engineering Istanbul Turkey Bogazici University Management Information Systems Istanbul Turkey Toronto Metropolitan University Data Science Laboratory TorontoON Canada

ISBN: (纸本)9798331504830

In this study, we explore the performance of large language models (LLMs) and provide insights into the strengths and weaknesses of these models in sentiment analysis. In addition, we explore the impact of various instruction methods and fine-tuning techniques on the models' performance and analyze how sensitive they are to different prompts. Although there are studies comparing LLMs on sentiment analysis tasks, there is a limited number of studies on fine-tuning strategies, instruction variety, and prompt sensitivity of LLMs for sentiment analysis. For this purpose, we used Llama2-7B, Lama3-8B, Mistral-7B, Gemma-7B, and Bloom-7B and compared them with BERT and Roberta. We evaluated fine-tuned and original chat versions with zero and few-shot experiments. We generated various instruction strategies and observed their effects on the performance of the models. We also compared Quantized Low-Rank Adapters (QLoRA) fine-tuning and full fine-tuning with all parameters. The fine-tuned versions performed better compared to the original chat versions on almost all tasks. The fine-tuned and chat versions of Llama3-8B and Mistral-7B outperformed others on these tasks, while the Llama2-7B-chat model often produced invalid responses. Our research indicates that QLoRA is a practical substitute for full fine-tuning, as it lessens computational demands without sacrificing performance. Fine-tuned models were less affected by variations in test prompts compared to chat models. This is likely because their specialized training allows them to better handle queries within their domain. In this exploratory study, we provide insights into the potential of LLMs in sentiment analysis tasks. © 2024 IEEE.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Smart laboratory: Building a smart laboratory environment by using AI 23

Smart laboratory: Building a smart laboratory environment by...

引用

6th International Conference on Networking, Intelligent systems and Security, NISS 2023

作者： Khaddor, Ranya Amrani, Mahacine Bakkali Yedri, Othman Laboratory of Valorization of Resources and Chemical Engineering Abdelmalek Essaadi University Tangier Morocco Computer Science Systems and Telecommunication Laboratory Abdelmalek Essaadi University Tangier Morocco

ISBN: (纸本)9798400700194

Nowadays, AI technologies are already revolutionizing many businesses sectors, transforming businesses and the labor market;change research and innovation practices and have a strong impact on our digital humanities. These include reflections on the role of AI in the future of education, science, culture and communication and information, and on the challenges of new forms of new models. Smart laboratories present a new challenge of application of the NTIC to reduce cost and improve the results and research quality. However, in this paper we will present the challenges of smart laboratory, related works, applications sectors. Then, we will present our vision model. Finally, we will close with a conclusion, and we will present the perspectives of future works. © 2023 ACM.

关键词： Laboratories

来源：评论

学校读者我要写书评

暂无评论

ZKP Protocols for Usowan,Herugolf,and Five Cells

引用

Tsinghua science and Technology 2024年第6期29卷 1651-1666页

作者： Daiki Miyahara Léo Robert Pascal Lafourcade Takaaki Mizuki Graduate School of Informatics and Engineering The University of Electro-CommunicationsTokyo 1828585Japan MIS Lab University of Picardy Jules VerneAmiens 80000France Laboratory of Computer Science Modelling and Systems OptimisationUniversity of Clermont AuvergneClermont-Ferrand 63178France Cyberscience Center Tohoku UniversitySendai 9808578Japan

A Zero-Knowledge Proof (ZKP) protocol allows a participant to prove the knowledge of some secret without revealing any information about it. While such protocols are typically executed by computers, there exists a line of research proposing physical instances of ZKP protocols. Up to now, many card-based ZKP protocols for pen-and-pencil puzzles, like Sudoku, have been designed. Those games, mostly edited by Nikoli, have simple rules, yet designing them in card-based ZKP protocols is non-trivial. In this work, we propose a card-based ZKP protocol for Usowan, a Nikoli game. In Usowan, for each room of a puzzle instance, there is exactly one piece of false information. The goal of the game is to detect this wrong data amongst the correct data and also to satisfy the other rules. Designing a card-based ZKP protocol to deal with the property of detecting a liar has never been done. In some sense, we propose a physical ZKP for hiding of a liar. This work extends a previous paper appearing in Ref. [1]. In this extension, we propose two other protocols, for Herugolf and Five Cells. The puzzles are specifically chosen because each of those three puzzles shares a common constraint, connectivity. However, showing the connected configuration cannot be done with generic approach and brings new construction to the existing connectivity ZKP protocol. Indeed, in Herugolf, the connectivity is handled with a given length of cell which is decremental (i.e., the length of each connected cell decreases by one at each step). For Five Cells, there is an additional step in the setup allowing to encode all the information needed to ensure a valid ZKP protocol.

关键词： Zero-Knowledge Proof(ZKP)protocol playing cards card-based cryptography physical assumptions Usowan Herugolf FiveCells

来源：评论

学校读者我要写书评

暂无评论

Optimizing Polynomial-Time Solutions to a Network Weighted Vertex Cover Game

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 512-523页

作者： Jie Chen Kaiyi Luo Changbing Tang Zhao Zhang Xiang Li the Adaptive Networks and Control Laboratory Department of Electronic EngineeringFudan UniversityShanghai 200433China the College of Mathematics and Computer Science Zhejiang Normal UniversityJinhua 321004 Yuxi Middle School Taizhou 317399China IEEE the College of Physics and Electronics Information Engineering Zhejiang Normal UniversityJinhua 321004China the College of Mathematics and Computer Science Zhejiang Normal UniversityJinhua 321004China the Adaptive Networks and Control Laboratory Department of Electronic EngineeringFudan UniversityShanghai 200433 the Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous SystemsTongji UniversityShanghai 201210China

Weighted vertex cover(WVC)is one of the most important combinatorial optimization *** this paper,we provide a new game optimization to achieve efficiency and time of solutions for the WVC problem of weighted *** first model the WVC problem as a general game on weighted *** the framework of a game,we newly define several cover states to describe the WVC ***,we reveal the relationship among these cover states of the weighted network and the strict Nash equilibriums(SNEs)of the ***,we propose a game-based asynchronous algorithm(GAA),which can theoretically guarantee that all cover states of vertices converging in an SNE with polynomial ***,we improve the GAA by adding 2-hop and 3-hop adjustment mechanisms,termed the improved game-based asynchronous algorithm(IGAA),in which we prove that it can obtain a better solution to the WVC problem than using a the ***,numerical simulations demonstrate that the proposed IGAA can obtain a better approximate solution in promising computation time compared with the existing representative algorithms.

关键词： Game-based asynchronous algorithm(GAA) game optimization polynomial time strict Nash equilibrium(SNE) weighted vertex cover(WVC)

来源：评论

学校读者我要写书评

暂无评论

RDM: A Light Field Super-Resolution Model Improved with Retinex Decomposition 16

RDM: A Light Field Super-Resolution Model Improved with Reti...

引用

16th International Conference on Signal Processing systems, ICSPS 2024

作者： Lyu, Wenqi Ke, Wei Sheng, Hao Ma, Xiao Liu, Lixue Faculty of Applied Sciences Macao Polytechnic University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China

ISBN: (纸本)9781510689251

Light field cameras hold significant value in applications such as depth estimation, 3D video acquisition, and image super-resolution. Compared to traditional single-image super-resolution methods, light field images can capture object information from multiple spatial and angular perspectives, which is more conducive to capturing detail information. However, current advanced light field super-resolution models still exhibit issues like blurriness, jaggedness, and dimness in 4x light field super-resolution. To address this, we propose a novel light field super-resolution framework that utilizes the Retinex decomposition concept to solve common problems such as ghosting and overlap, thereby improving image quality. By decomposing the light field image into illumination and reflection components and processing them separately, our model significantly enhances detail preservation and color consistency. Experimental results on multiple datasets demonstrate that our model exhibits outstanding performance, both subjectively and objectively, highlighting the effectiveness of this framework and its broad application potential in the field of computational imaging. © 2025 SPIE.

关键词： Image acquisition

来源：评论

学校读者我要写书评

暂无评论

XMeta-OS: A Conceptual Framework for Unified Resource Management in Distributed Edge-Cloud Environments 3rd

XMeta-OS: A Conceptual Framework for Unified Resource Manag...

引用

3rd International Conference on Advances in Computing Research, ACR 2025

作者： Zacharioudakis, Eleftherios Kakoulli, Elena Evripidou, Salomi Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos Pafos Cyprus National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9783031876462

This paper introduces XMeta-OS, a meta-operating system specially designed with Linux as its foundation to unify and optimize resource management for the distributed edge-cloud when dynamic use of GPU resources is possible. This approach offer a new GPU abstraction layer and dynamic edge-cloud allocation model that offer enhanced flexibility and resource utilization over existing systems like Kubernetes and OpenStack. By using likely sensitive data, the model applied cloud-pushed deployment model. XMeta-OS manages computer resources in real-time. Therefore, fulfilling high performance various needs. It allocates CPU and GPU in real-time to workloads requiring massive parallel processing, such as machine learning, scientific simulations, real-time data analytics, and transportation tasks. Fabrication in the laboratory of an edge-cloud environment can help to assess the scalability, fault tolerance and efficiency of the system. It showcases the overall architectural design of XMeta-OS. Changes to the kernel and security solutions for safe and effective distribution are suggested. This article presents the design of the XMeta-OS. The future of XMeta-OS entails usage and testing with which we see latency, energy, computation and other such measurements in labs. XMeta-OS is a solution to cost performance, emerging application, large-scale edge-cloud deployments, and distributed GPU-enabled infrastructures. Meta-Operating System in Edge-Cloud Continuum for dynamic resource management of GPU. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

GACP:graph neural networks with ARMA flters and a parallel CNN for hyperspectral image classification

引用

International Journal of Digital Earth 2023年第1期16卷 1770-1800页

作者： Jing Yang Jie Sun Yaping Ren Shaobo Li Shujie Ding Jianjun Hu School of Mechanical Engineering Guizhou UniversityGuiyangPeople’s Republic of China State Key Laboratory of Public Big Data Guizhou UniversityGuiyangPeople’s Republic of China School of Intelligent Systems Science and Engineering Jinan UniversityZhuhaiPeople’s Republic of China Department of Computer Science and Engineering University of South CarolinaColumbiaSCUSA

In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote sensing,geological exploration,and marine remote *** many generalization classification algorithms are designed for the purpose of learning a small number of samples,there is often a problem of a low utilization rate of position information in the empty spectral *** on this,a GNN with an autoregressive moving average(ARMA)-based smoothingfilter samples the node information in the null spectral domain and then captures the spatial information at the pixel level via spatial feature convolution;then,the null spectral domain position information lost by the CNN is located by a coordinate attention(CA)***,autoregressive,spatial convolution,and CA mechanisms are combined into multiscale features to enhance the learning capacity of the network for tiny *** conducted on the widely used Indian Pines(IP)dataset,the Botswana(BS)dataset,Houton 2013(H2013),and the WHU-Hi-HongHu(WHU)benchmark HSI dataset demonstrate that the proposed GACP technique can perform classification work with good accuracy even with a small number of training examples.

关键词： Graph neural networks word convolutional neural networks hyperspectral image classification attention mechanisms

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：