检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Yue, Sheng Liu, Jiani Hua, Xingyuan Ren, Ju Lin, Sen Zhang, Junshan Zhang, Yaoxue Department of Computer Science and Technology Tsinghua University Beijing China Zhongguancun Laboratory Beijing China Department of Computer Science University of Houston Texas United States Department of Electrical and Computer Engineering University of California Davis United States

Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) diverse state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their resultant states - a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on 20/21 benchmarks, typically by 2-5x, while maintaining a comparable runtime to Behavior Cloning (BC). Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning 41

OLLIE: Imitation Learning from Offline Pretraining to Online...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yue, Sheng Hua, Xingyuan Ren, Ju Lin, Sen Zhang, Junshan Zhang, Yaoxue Department of Computer Science and Technology Tsinghua University Beijing China Zhongguancun Laboratory Beijing China Department of Computer Science University of Houston Texas United States Department of Electrical and Computer Engineering University of California Davis United States

In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the naïve combination of existing offline IL and online IL methods tends to behave poorly in this context, because the initial discriminator (often used in online IL) operates randomly and discordantly against the policy initialization, leading to misguided policy optimization and unlearning of pretraining knowledge. To overcome this challenge, we propose a principled offline-to-online IL method, named OLLIE, that simultaneously learns a near-expert policy initialization along with an aligned discriminator initialization, which can be seamlessly integrated into online IL, achieving smooth and fast finetuning. Empirically, OLLIE consistently and significantly outperforms the baseline methods in 20 challenging tasks, from continuous control to vision-based domains, in terms of performance, demonstration efficiency, and convergence speed. This work may serve as a foundation for further exploration of pretraining and finetuning in the context of IL. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Model for Clinical Time Series Prediction: Enhancing ICU Readmission Prediction 14

An Attention-Based Model for Clinical Time Series Prediction...

引用

14th International Conference on computer and Knowledge engineering, ICCKE 2024

作者： Madinei, Hananeh Sadat Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Alzahra University Tehran Iran Department of Computer Engineering Faculty of Engineering Alzahra University Tehran Iran Department of Electrical Engineering Iranian Research Organization for Science and Technology Tehran Iran

ISBN: (纸本)9798331511272

— In recent years, time series prediction has become a highly interesting topic in various applied areas, including clinical time series analysis. Hospitals and other clinical healthcare systems collect Electronic Health Records. These records contain important information that needs to be mined. This information provides a solid basis for predicting hospital readmission, helping to improve healthcare, enhance patient outcomes, and optimize hospital resources. This study introduces a novel deep learning attention-based approach for predicting 30-day ICU readmissions using clinical time series information extracted from the MIMIC III dataset. This approach incorporates time-aware positional encoding into the attention mechanism to enhance predictive performance by capturing the temporal representation of data and considering the temporal order of clinical time series data. This model is compared with cutting-edge models. The significant enhancements in the model performance achieved by the proposed method highlight the effectiveness of incorporating time-aware positional encoding in capturing temporal dependencies and improving prediction outcomes. These results underscore the potential of advanced attention mechanisms in clinical time series analysis. ©2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Epileptic Seizure Diagnosis: Utilizing GRU-CNN Architectures in EEG Signal Analysis 20

A Robust Framework for Epileptic Seizure Diagnosis: Utilizin...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Nikoupour, Maryam Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Alzahra University Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Tehran Iran Alzahra University Faculty of Engineering Department of Computer Engineering Tehran Iran Iranian Research Organization for Science and Technology Department of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350383942

Seizures that take place repeatedly and without provocation are referred to as epilepsy. Epilepsy can be diagnosed with electroencephalography (EEG). One of the most influential challenges of the past few years has been the use of deep learning algorithms to replace manual inspection of medical signals by specialists, such as epilepsy signal classification. This paper presents a multi-label classification approach for epileptic seizures using deep learning. UCI machine learning repository's epileptic seizure dataset has been used to classify epileptic seizure patients. 178 features are present in each of the 11500 samples in the dataset. Based on a variety of criteria, the proposed method may have a positive impact on epilepsy diagnosis, in most cases by approximately 6% compared with existing methods utilizing long short-term memory (LSTM) and autoencoder. It is possible thus to develop and apply gated recurrent unit-based methods with good potential for categorizing EEG signals for epilepsy diagnosis based on gated recurrent unit (GRU)-CNN based methods. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A new predictive medical approach based on data mining and Symbiotic Organisms Search algorithm

引用

International Journal of computers and Applications 2022年第5期44卷 465-479页

作者： Noureddine, Samia Zineeddine, Baarir Toumi, Abida Betka, Abir Benharkat, Aïcha-Nabila Department of Electrical Engineering LESIA Laboratory University of Biskra Biskra Algeria Department of Computer Science INSA of Lyon Lyon France

Handling very large data, in order to make the best decision, is only possible through an extraction of knowledge. Data mining has become a widely used process in data analytics to extract the most important knowledge for predictive decision making. One of the important types of data mining is clustering mechanism;its purpose is dividing data into a set of clusters with very large data, the numbers of parameters are very high, and the clustering problem is more difficult. Metaheuristics have been widely used in clustering;they can provide satisfactory solutions for complex problems. The main objective of this paper is to propose a new clustering algorithm based on a metaheuristic technique called Symbiotic Organisms Search (SOS), it was inspired from a biological process, and it simulates the symbiotic interaction between organisms of the same population. The SOS method is used to find the optimal centers of a number of clusters, as a supervised data mining technique. Experimental results have been performed through two phases. Firstly, the SOS technique is benchmarked with six well-known test functions. Secondly, different medical datasets have been used to test our proposed clustering method based on SOS, and show its credibility of treatment. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Beyond 5G Networks: Integration of Communication, Computing, Caching, and Control

引用

China Communications 2023年第7期20卷 137-174页

作者： Musbahu Mohammed Adam Liqiang Zhao Kezhi Wang Zhu Han State Key Laboratory of Integrated Service Networks Xidian UniversityXi’an 710071China Department of Computer and Information Sciences Northumbria UniversityNewcastle upon TyneUK Department of Electrical and Computer Engineering University of HoustonHoustonTX 77004 USAand also with the Department of Computer Science and EngineeringKyung Hee UniversitySeoul 02447 South Korea

In recent years,the exponential proliferation of smart devices with their intelligent applications poses severe challenges on conventional cellular *** challenges can be potentially overcome by integrating communication,computing,caching,and control(i4C)*** this survey,we first give a snapshot of different aspects of the i4C,comprising background,motivation,leading technological enablers,potential applications,and use ***,we describe different models of communication,computing,caching,and control(4C)to lay the foundation of the integration *** review current stateof-the-art research efforts related to the i4C,focusing on recent trends of both conventional and artificial intelligence(AI)-based integration *** also highlight the need for intelligence in resources ***,we discuss the integration of sensing and communication(ISAC)and classify the integration approaches into various ***,we propose open challenges and present future research directions for beyond 5G networks,such as 6G.

关键词： 4C 6G integration of communication,computing,caching,and control i4C multi-access edge computing(MEC)

来源：评论

学校读者我要写书评

暂无评论

A Parallel Color Image Encryption Algorithm Based on a 2-D Logistic-Rulkov Neuron Map

引用

IEEE Internet of Things Journal 2025年第11期12卷 18115-18124页

作者： Gao, Suo Zhang, Zheyi Iu, Herbert Ho-Ching Ding, Siqi Mou, Jun Erkan, Uğur Toktas, Abdurrahim Li, Qi Wang, Chunpeng Cao, Yinghong Dalian Polytechnic University School of Information Science and Engineering Dalian116034 China The University of Western Australia School of Electrical Electronic and Computer Engineering PerthWA6009 Australia Dalian University of Technology School of Mathematical Sciences Dalian116024 China Karamanoglu Mehmetbey University Faculty of Engineering Department of Computer Engineering Karaman70200 Turkey Ankara University Engineering Faculty Department of Artificial Intelligence and Data Engineering Ankara06830 Turkey Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250000 China

Images are widely used in social networks, necessitating efficient and secure transmission, especially in bandwidth-constrained environments. This article aims to develop a color image encryption algorithm that enhances security while optimizing computational efficiency. A novel parallel color image encryption algorithm based on the 2-D logistic-Rulkov neuron map (2D-LRNM) is proposed. In this approach, the three channels of the color image are first separated. Cross-channel information interaction is introduced to form three new channels, which are then processed in parallel. During the encryption process of each channel, a block-wise parallel encryption mechanism is applied, ensuring simultaneous encryption of each block. This block-wise strategy effectively leverages parallel computing resources and balances the task load. To meet the demand for a large number of keystreams during encryption, the 2D-LRNM is introduced. It combines the simplicity and chaotic properties of the Logistic map with the multitimescale dynamics and neurodynamic behaviors of the Rulkov map. By overcoming the dimensional limitations inherent in the single Logistic map, this approach extends the system to a 2-D framework, significantly increasing the complexity of chaotic behavior and improving its unpredictability. Experimental results demonstrate that the proposed encryption algorithm achieves high security and reduces computation time by approximately 83.3%. © 2014 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Transmitter Creation by Consuming Free Energy in Molecular Communication

引用

IEEE Transactions on Molecular, Biological, and Multi-Scale Communications 2025年第2期11卷 292-303页

作者： Jing, Dongliang Li, Linjuan Cheng, Zhen Lin, Lin Eckford, Andrew W. Northwest A and F University College of Mechanical and Electronic Engineering Yangling China Ministry of Agriculture and Rural Affairs Key Laboratory of Agricultural Internet of Things Yangling China Zhejiang University of Technology School of Computer Science and Technology Hangzhou310023 China Tongji University College of Electronics and Information Engineering Shanghai China York University Department of Electrical Engineering and Computer Science TorontoON Canada

Information molecules play a crucial role in molecular communication (MC), acting as carriers for information transfer. A common approach to get information molecules in MC involves harvesting them from the environment;however, the harvested molecules are often a mixture of various environmental molecules, and the initial concentration ratios in the reservoirs are identical, which hampers high-fidelity transmission techniques such as molecular shift keying (MoSK). This paper presents a transmitter design that harvests molecules from the surrounding environment and stores them in two reservoirs. To separate the mixed molecules, energy is consumed to transfer them between reservoirs. Given limited energy resources, this work explores energy-efficient strategies to optimize transmitter performance. Through theoretical analysis and simulations, we investigate different methods for moving molecules between reservoirs. The results demonstrate that transferring higher initial concentration molecules enhances transmitter performance, while using fewer molecules per transfer further improves efficiency. These findings provide valuable insights for optimizing MC systems through energy-efficient molecule transfer techniques. © 2015 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

Finger Width Effects on Performance of GaN HEMTs 2

Finger Width Effects on Performance of GaN HEMTs

引用

2nd International Microwave and Antenna Symposium, IMAS 2024

作者： Nouri, Soheil Avval, Amirreza G. Darwish, Ali El-Ghazaly, Samir M. University of Arkansas Department of Electrical Engineering and Computer Science Fayetteville United States Army Research Laboratory AdelphiMD United States

ISBN: (纸本)9798350356359

In this study, we characterize GaN-HEMT devices and present both DC and AC measurement outcomes for the multi-finger configurations. Specifically, we introduce a new device featuring wide electrodes to assess and compare the performance of various multi-finger arrangements. This particular transistor comprises two fingers, each measuring 150 μm in width. We analyze and compare the s-parameters of structures with varying widths, extending our frequency range up to 67 GHz. This newly developed wide-finger configuration is integral to our ongoing efforts in developing optimized modeling approaches and improved transistor designs. The comparative analysis of different finger widths lays the groundwork for future explorations into high-frequency phenomena, including wave propagation effects and their impact on the performance of millimeter-wave transistors. © 2024 IEEE.

关键词： Gallium nitride

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：