检索结果-内蒙古大学图书馆

Dynamic Reinforcement Learning for Optimal Go ai Training: Adaptive Adjustment and Optimization

IEEE Transactions on Consumer Electronics 2024年

作者： Zhang, Chunjiong Shan, Gaoyang Lim, Junghyun Roh, Byeong-Hee Ajou University Department of AI Convergence Network Suwon16499 Korea Republic of Ajou University Department of Software and Computer Engineering Suwon16499 Korea Republic of

Go is a popular strategy game today, but due to its large search space and task complexity, ensuring stable ai implementation is challenging. Specifically, Go ai training requires setting a fixed optimal learning rate and schedule, which demands significant TPU and GPU resources. To facilitate Go-ai learning, this research explores adaptive adjustment and optimization techniques for dynamic reinforcement learning neural networks. First, we introduce a dynamic batch size technique that adjusts data volume at each training phase and incorporates dynamic network structure search, considering the number of network layers and residual blocks. Second, we propose a dynamic network topology that automatically modifies the learning rate based on the training batch size at various training phases. Our approach outperforms the baseline in terms of stability and model convergence speed. In 100 games, the Go-ai model achieved a 100% victory rate below the 7th rank and a 98% win rate at the 9th rank and higher. © 1975-2011 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Sum-Rate Maximization for RSMA-Enabled Energy Harvesting Aerial networks With Reinforcement Learning 14

Sum-Rate Maximization for RSMA-Enabled Energy Harvesting Aer...

引用

14th International Conference on Information and Communication Technology convergence, ICTC 2023

作者： Seong, Jaehyup Toka, Mesut Shin, Wonjae Ajou University Department of Artificial Intelligence Convergence Network Suwon Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon Korea Republic of Korea University School of Electrical Engineering Seoul Korea Republic of

ISBN: (纸本)9798350313277

In this paper, we propose a joint power and precoder design framework for energy-harvesting aerial networks, where an aerial base station serves multiple users via rate-splitting multiple access (RSMA) using harvested energy. To maximize the sum-rate from the long-term perspective, we utilize a deep reinforcement learning (DRL) approach to allocate optimal transmission power at each time based on the randomness property of the channel environment, harvested energy, and battery power information. Moreover, we employ sequential least squares programming (SLSQP) to design the RSMA precoder maximizing the sum-rate with the allocated power. Numerical results show the superiority of the proposed scheme over baseline methods in terms of the average sum-rate performance. © 2023 IEEE.

关键词： DRL Energy harvesting networks RSMA

来源：评论

学校读者我要写书评

暂无评论

Robust Rate-Matching Framework for Multibeam Satellite Communications with Phase Perturbations

Robust Rate-Matching Framework for Multibeam Satellite Commu...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Seong, Jaehyup Park, Juha Lee, Juhwan Lee, Jungwoo Shin, Wonjae Poor, H. Vincent Ajou University Department of Artificial Intelligence Convergence Network Suwon Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon Korea Republic of Seoul National University Department of Electrical and Computer Engineering Seoul Korea Republic of School of Electrical Engineering Korea University Seoul Korea Republic of Princeton University Department of Electrical and Computer Engineering PrincetonNJ United States

ISBN: (纸本)9798350370218

Multibeam satellite communications (SATCOM) is emerging as one of the key technologies to provide broadband services over a wide area with ubiquitous connectivity. Within the broad coverage for the multibeam SATCOM, the traffic demands of users are extremely heterogeneous due to various geological conditions and user distribution. Inspired by this, we propose a robust and powerful rate-matching (RM) framework to minimize the difference between traffic demands and offered rates based on rate-splitting multiple access (RSMA). Moreover, channel phase perturbations caused by both channel estimation and feedback errors are considered to capture realistic multibeam SATCOM scenarios. To tackle the non-convexity of the RSMA-based RM problem under phase perturbations, we convert the formulated problem into a tractable convex form via the successive convex approximation method and present an efficient algorithm to solve the RM problem. Numerical results show the superiority of the proposed RSMA-based scheme, compared with the various benchmark schemes, in terms of non-uniform traffic demand fulfillment and phase perturbation robustness. © 2023 IEEE.

关键词： heterogeneous traffic demand multibeam SATCOM phase perturbations Rate-matching RSMA

来源：评论

学校读者我要写书评

暂无评论

Authentication of Multi-agent System with Verifiable Computation and Distributed Aggregation 63

Authentication of Multi-agent System with Verifiable Computa...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Lee, Seungbeom Kim, Dongwoo Chung, Heewon Kim, Junsoo Shim, Hyungbo Seoul National University Asri Department of Electrical and Computer Engineering Korea Republic of Dongguk University Department of Ai · Sw Convergence Korea Republic of Desilo Inc Korea Republic of Seoul National University of Science and Technology Department of Electrical and Information Engineering Korea Republic of

ISBN: (纸本)9798350316339

We propose an authentication scheme for a multiagent system over integers, based on verifiable computation primitives. The naive approach, employing Freivalds' algorithm in centralized way, faces several challenges. Specifically, unreliability of the network introduces the risk of information tampering by other agents. To this end, it requires locally updating and merging the proofs of the individual states in a distributed manner. Our proposed method addresses these issues with assuming presence of a leader agent who is responsible for validating the correctness of all the states of the agents. This can be achieved by a distributed protocol that aggregates proofs from the individual agents, relying on the well-known knowledge-of-exponent assumption. By using this distributed protocol, computational complexity and communication cost are reduced compared to centralized verification. Furthermore, we incorporate a clustering technique to distribute storage requirements. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Intelligent Model to Predict Early Liver Disease using Machine Learning Technique

Intelligent Model to Predict Early Liver Disease using Machi...

引用

2022 International Conference on Business Analytics for Technology and Security, ICBATS 2022

作者： Ghazal, Taher M. Rehman, Aziz Ur Saleem, Muhammad Ahmad, Munir Ahmad, Shabir Mehmood, Faisal Faculty of Information Science and Technology Ukm Network and Communication Technology Lab Center for Cyber Security Malaysia School of Computer Science NCBAandE Lahore Pakistan Gachon University Department of Computer Engineering Korea Republic of Gachon University Department of It Convergence Engineering Korea Republic of

ISBN: (纸本)9781665409209

Liver Disease (LD) is the main cause of death worldwide, affecting a large number of people. A variety of factors affect the liver, resulting in this disease. The diagnosis of this condition is both expensive and time-consuming. Machine Learning offers a lot of potential in terms of automated disease diagnosis. As a result, the purpose of this research is to assess the efficacy of various Machine Learning (ML) algorithms to lower the high cost of liver disease diagnosis through prediction. With the current rise in numerous liver disorders, it's more important than ever to detect liver disease early on. This research proposed intelligent model to predict liver disease using machine learning technique. This proposed model is more effective and comprehensive in terms of performance of 0.884 accuracy, and 0.116 miss-rate. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Based Automatic Epileptic Seizure Detection Framework

引用

computers, Materials & Continua 2022年第3期70卷 5601-5630页

作者： Aayesha Muhammad Bilal Qureshi Muhammad Afzaal Muhammad Shuaib Qureshi Jeonghwan Gwak Shaheed Zulfikar Ali Bhutto Institute of Science and Technology IslamabadPakistan Department of Computer Science&IT University of Lakki MarwatKPKPakistan Stockholm University StockholmSweden Department of Computer Science School of Arts and SciencesUniversity of Central AsiaKyrgyz Republic Department of Software Korea National University of TransportationChungju27469Korea Department of Biomedical Engineering Korea National University of TransportationChungju27469Korea Department of AI Robotics Engineering Korea National University of TransportationChungju27469Korea Department of IT&Energy Convergence(BK21 FOUR) Korea National University of TransportationChungju27469Korea

Detection of epileptic seizures on the basis of Electroencephalogram(EEG)recordings is a challenging task due to the complex,non-stationary and non-linear nature of these biomedical *** the existing literature,a number of automatic epileptic seizure detection methods have been proposed that extract useful features from EEG segments and classify them using machine learning *** characterizing features of epileptic and non-epileptic EEG signals overlap;therefore,it requires that analysis of signals must be performed from diverse *** studies analyzed these signals in diverse domains to identify distinguishing characteristics of epileptic EEG *** pose the challenge mentioned above,in this paper,a fuzzy-based epileptic seizure detection model is proposed that incorporates a novel feature extraction and selection method along with fuzzy *** proposed work extracts pattern features along with time-domain,frequencydomain,and non-linear analysis of *** applies a feature selection strategy on extracted features to get more discriminating features that build fuzzy machine learning classifiers for the detection of epileptic *** empirical evaluation of the proposed model was conducted on the benchmark Bonn EEG *** shows significant accuracy of 98%to 100%for normal *** classification cases while for three class classification of normal ***-ictal *** accuracy reaches to above 97.5%.The obtained results for ten classification cases(including normal,seizure or ictal,and seizure-free or inter-ictal classes)prove the superior performance of proposed work as compared to other state-of-the-art counterparts.

关键词： Medical image processing electroencephalography machine learning fuzzy system models seizure detection epileptic seizure virtualization

来源：评论

学校读者我要写书评

暂无评论

Stress-ViT: In-Ear Plethysmography for Mental Stress Classification with Vision Transformer

Stress-ViT: In-Ear Plethysmography for Mental Stress Classif...

引用

2023 IEEE Biomedical Circuits and Systems Conference, BioCAS 2023

作者： Barki, Hika Chung, Sang Hoon Jafari, Roozbeh Chung, Wan-Young Pukyong National University Department of Ai Convergence Busan Korea Republic of Electrical and Computer Engineering College StationTX United States School of Engineering Medicine HoustonTX United States Pukyong National University Department of Electronic Engineering Busan Korea Republic of

ISBN: (纸本)9798350300260

Stressful situations have a significant impact on individuals' well-being, necessitating prompt stress diagnosis to mitigate potential long-term harm. This paper introduces an innovative in-ear photoplethysmography (PPG) device for detecting mental stress. The experiment was conducted to collect raw PPG and tri-axis acceleration signals from 15 participants through stress induction protocols, including the Stroop-color-word interference test and mental arithmetic calculations. Preprocessing techniques, such as bandpass filtering and motion artifact cancellation, were employed to address physiological and motion-related artifacts. The Short-Time Fourier Transform (STFT) was utilized to convert the filtered PPG signals into spectrograms, representing time-frequency images. Leveraging the Vision Transformer (ViT) model, renowned for image classification, the PPG signals were classified into distinct stress levels using fixed-size overlapping patches. Comprehensive experiments were conducted to compare the proposed ViT classifier with other pretrained CNN methods, demonstrating its superior performance with an average accuracy of 91.98%, recall of 91.97%, and precision of 92.02%. Integrating the in-ear PPG sensor with the ViT model proves to be a promising approach for diagnosing mental stress. The proposed in-ear PPG with high accuracy and a convenient design make it suitable for everyday stress assessment, thereby enhancing its potential as a valuable tool. © 2023 IEEE.

关键词： Classification Mental stress Photoplethysmography (PPG) Short-Time Fourier Transform (STFT) Spectrograms Vision transformer

来源：评论

学校读者我要写书评

暂无评论

Cluster Hopping in Multi-beam Satellite Communication Systems Using Deep Reinforcement Learning 14

Cluster Hopping in Multi-beam Satellite Communication System...

引用

14th International Conference on Information and Communication Technology convergence, ICTC 2023

作者： Sharma, Shruti Han, Sangmin Seong, Jaehyup Shin, Wonjae Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of Ajou University Department of Artificial Intelligence Convergence Network Suwon16499 Korea Republic of Korea University School of Electrical Engineering Seoul02841 Korea Republic of

ISBN: (纸本)9798350313277

Beam hopping method has become a promising and significant technology in the next generation of high throughput satellite (HTS) systems. Using deep reinforcement learning (DRL), this research suggests a unique method for improving precoded cluster hopping in multi-beam geostationary orbit (GEO) satellite communication systems. Choosing the optimum beam clusters for transmission based on the current channel circumstances, our goal is to increase the effectiveness and capacity of satellite communication systems. Our simulation results based on DRL yields better performance when compared to other techniques. © 2023 IEEE.

关键词： beam hopping deep reinforcement learning geostationary orbit precoding satellite networks

来源：评论

学校读者我要写书评

暂无评论

Evaluation for Elevation Angle-Dependent Beam Size in NR NTN Systems 14

Evaluation for Elevation Angle-Dependent Beam Size in NR NTN...

引用

14th International Conference on Information and Communication Technology convergence, ICTC 2023

作者： Han, Sangmin Shin, Wonjae Kim, Jae-Hyun Ajou University Department of Artificial Intelligence Convergence Network Suwon16499 Korea Republic of Korea University School of Electrical Engineering Seoul02841 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

ISBN: (纸本)9798350313277

Appropriate beam design plays a vital role in satellite-based Non-Terrestrial networks (NTN) towards beyond 5G. In this paper, we propose an evaluation for elevation angle-based major-semi axis beam radius. To deal with this, we calculate beam major semi-axis radius with elevation angle and differential delay in NTN, based on 3rd Generation Partnership Project (3GPP) New Radio (NR) standards. Using the evaluation method, within NR standards, the differential delay-based beam major semi-axis radius can be independent of the elevation angle in some elevation angle intervals. Furthermore, we compare the differential delay-based beam results with the 3dB beamwidth results. The comparison shows that the differential delay-based beam major semi-axis radius can be more critical according to the preamble structure, subcarrier spacing, and elevation angle. © 2023 IEEE.

关键词： beam size differential delay elevation angle-based beam Low Earth Orbit (LEO) satellite networks OFDM numerology preamble

来源：评论

学校读者我要写书评

暂无评论

Organizing aircraft navigation system as real time reference model architecture

Organizing aircraft navigation system as real time reference...

引用

Conference on Digital Avionics Systems (DASC)

作者： Khaled M Nabil Computer Engineering and Network Department AI Jouf University AI Jouf Saudia Arabia

This paper provides real-time reference model for the aircraft navigation system. The navigation function has been partitioned into goals and sub goals, each is assigned to a common structure process and executed on separate processing unit. That makes each process perform its specific calculations perfectly in a predictable execution time. The processes are linked in hierarchical architecture providing administration as a big organization. The implemented simulation prove that the proposed model are valid.

关键词： aircraft navigation Process control aircraft Aerospace electronics Real-time systems computer architecture Sensors

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：