检索结果-内蒙古大学图书馆

machine learning and Big data Analytics (Proceedings of international conference on machine learning and Big data Analytics (ICMLBDA) 2021) 1st ed. 2022

Machine Learning and Big Data Analytics (Proceedings of Int...

引用

丛书名： Lecture Notes in Networks and Systems

2022年

作者： Rajiv Misra Rudrapatna K. Shyamasundar Amrita Chaturvedi Rana Omer

来源：评论

学校读者我要写书评

暂无评论

RF Challenge: The data-Driven Radio Frequency Signal Separation Challenge

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2025年 6卷 4083-4100页

作者： Lancho, Alejandro Weiss, Amir Lee, Gary C. F. Jayashankar, Tejas Kurien, Binoy G. Polyanskiy, Yury Wornell, Gregory W. Universidad Carlos III de Madrid Signal Theory and Communications Leganés28911 Spain Gregorio Marañón Health Research Institute Madrid28007 Spain Bar-Ilan University Ramat Gan5290002 Israel Institute for Infocomm Research Communications and Networks Fusionopolis 138632 Singapore Massachusetts Institute of Technology Electrical Engineering and Computer Science Department CambridgeMA02139 United States MIT Lincoln Laboratory LexingtonMA02421 United States

We address the critical problem of interference rejection in radio-frequency (RF) signals using a data-driven approach that leverages deep-learning methods. A primary contribution of this paper is the introduction of the RF Challenge, which is a publicly available, diverse RF signal dataset for data-driven analyses of RF signal problems. Specifically, we adopt a simplified signal model for developing and analyzing interference rejection algorithms. For this signal model, we introduce a set of carefully chosen deep learning architectures, incorporating key domain-informed modifications alongside traditional benchmark solutions to establish baseline performance metrics for this intricate, ubiquitous problem. Through extensive simulations involving eight different signal mixture types, we demonstrate the superior performance (in some cases, by two orders of magnitude) of architectures such as UNet and WaveNet over traditional methods like matched filtering and linear minimum mean square error estimation. Our findings suggest that the data-driven approach can yield scalable solutions, in the sense that the same architectures may be similarly trained and deployed for different types of signals. Moreover, these findings further corroborate the promising potential of deep learning algorithms for enhancing communication systems, particularly via interference mitigation. This work also includes results from an open competition based on the RF Challenge, hosted at the 2024 IEEE international conference on Acoustics, Speech, and Signal Processing (ICASSP'24). © 2020 IEEE.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

Dynamic Dual-Strategy Update of Offline-to-Online Reinforcement learning for Optimal Energy System Scheduling 2nd

Dynamic Dual-Strategy Update of Offline-to-Online Reinforcem...

引用

2nd international conference on Smart Electrical Grid and Renewable Energy, SEGRE 2024

作者： Lin, Zhiyao Yang, AiHui Liu, Li Li, Lin Xiamen University of Technology Jimei District 600 Ligong Road Fujian Xiamen361024 China

ISBN: (纸本)9789819619641

In modern power systems, efficient energy scheduling is essential for ensuring system stability and optimizing resource allocation. At present, Deep Reinforcement learning (DRL) algorithms perform well in continuous action spaces, but they face challenges such as high online learning costs and poor offline learning performance. To address these challenges, this paper proposes a Dynamic Dual-Strategy Update (DDSU) DRL that combines Twin Delayed Deep Deterministic Policy Gradient (TD3) and Generative Adversarial Imitation learning (GAIL) technologies. By dynamically updating the agent’s strategy, DDSU enables parallel training of offline and online reinforcement learning, thereby enhancing the efficiency and accuracy of energy system scheduling. Experimental results show that DDSU significantly improves the convergence speed and final performance in the energy system scheduling task compared to the TD3 algorithm, in terms of reward acquisition, cost control, and system stability. These results demonstrate the potential of DDSU in enhancing the efficiency and accuracy of power system scheduling. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Onboard Detection Method of Metro Rail Corrugation Based on Unsupervised learning

Onboard Detection Method of Metro Rail Corrugation Based on ...

引用

international conference on Applied Nonlinear Dynamics, Vibration and Control, ICANDVC 2024

作者： Wang, Yang Xiao, Hong Zhang, Zhihai Chi, Yihao Zhao, Weize School of Civil Engineering Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Track Engineering Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789819633166

The onboard high-speed detection is a critical development direction for the operation and maintenance of railway networks. Rail corrugation is the most common track irregularity in metro systems, causing a series of environmental vibration and noise issues. Current onboard detection of rail corrugation primarily relies on axle box acceleration data and depends on data labeling and supervised learning frameworks. To facilitate data acquisition and reduce labeling costs, an unsupervised learning framework based on train body vertical vibration acceleration signals is proposed. First, the train body vertical vibration acceleration signals were transformed into time-frequency spectrogram datasets using Synchrosqueezed Wave Packet Transform (SSWPT). Then, an unsupervised learning framework was established based on momentum contrastive learning and trained on the unlabeled time-frequency spectrogram datasets. Finally, the pretrained model was fine-tuned for downstream tasks, including corrugation wavelength classification and amplitude assessment. Results indicate that the model achieved optimal performance after 430,000 iterations. For the binary classification of corrugation presence, the accuracy of the wavelength classification task ranged between 95% and 100%, while the amplitude assessment task achieved over 95% accuracy. Field application results demonstrate that the proposed model possesses strong generalization capabilities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Reward Generation via Large Vision-Language Model in Offline Reinforcement learning

Reward Generation via Large Vision-Language Model in Offline...

引用

2025 IEEE international conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Lee, Younghwan Luu, Tung M. Lee, Donghoon Yoo, Chang D. Electrical Engineering KAIST Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of

ISBN: (纸本)9798350368741

In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risky. However, designing dense reward signals for offline dataset requires significant human effort and domain expertise. Reinforcement learning with human feedback (RLHF) has emerged as an alternative, but it remains costly due to the human-in-the-loop process, prompting interest in automated reward generation models. To address this, we propose Reward Generation via Large Vision-Language Models (RG-VLM), which leverages the reasoning capabilities of LVLMs to generate rewards from offline data without human involvement. RG-VLM improves generalization in long-horizon tasks and can be seamlessly integrated with the sparse reward signals to enhance task performance, demonstrating its potential as an auxiliary reward signal. © 2025 IEEE.

关键词： Large Vision-Language Model Offline Reinforcement learning Reward Labeling

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Education and Training

Artificial Intelligence in Education and Training

引用

international conference on Innovative Approaches to the Application of Digital Technologies in Education and Research, SLET 2022

作者： Shashkova, Nina Chetyrbok, Petr Lukyanova, Yelena Kazak, Anatoliy Sidin, Maxim Kherson State Pedagogical University Kherson273003 Russia V.I. Vernadsky Crimean Federal University Simferopol295007 Russia North-Caucasian Federal University Stavropol355000 Russia

ISBN: (纸本)9783031787751

Artificial intelligence systems are becoming increasingly common and used in the educational industry. The paper examines the various possibilities of using artificial intelligence (AI) in education. Artificial intelligence systems are becoming more and more widespread and applied in the educational sector. This paper discusses various possibilities of using artificial intelligence (AI) in education. The paper discusses the use of adaptive learning with elements of artificial intelligence, allowing for an individual approach in training personnel in certain specialties. New methodologies, using AI in conjunction with information technology make it possible to effectively use tools such as virtual reality and Internet of things in the educational process. Practical research and recommendations for the application of AI in education are conducted on the Century Tech and Neuromation platforms. One of the problems in the development of deep neural networks remains the lack of labelled data. They are needed to train an artificial intelligence model. To solve this problem, the paper proposes the use of synthetic data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

FedDCT: A Dynamic Cross-Tier Federated learning Framework in Wireless Networks 18th

FedDCT: A Dynamic Cross-Tier Federated Learning Framework in...

引用

18th international conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Xian, Youquan Gan, Xiaoyun Yao, Chuanjian Li, Dongcheng Wang, Peng Liu, Peng Zhao, Ying Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin54104 China School of Computer Science and Engineering Guangxi Normal University Guilin54104 China School of Business Guilin University of Electronic Technology Guilin54104 China

ISBN: (纸本)9783031714634

Federated learning (FL), as a privacy-preserving machine learning paradigm, trains a global model across devices without exposing local data. However, resource heterogeneity and inevitable stragglers in wireless networks severely impact the efficiency and accuracy of FL training. In this paper, we propose a novel Dynamic Cross-Tier Federated learning framework (FedDCT). Firstly, we design a dynamic tiering strategy that dynamically partitions devices into different tiers based on their response times and assigns specific timeout thresholds to each tier to reduce single-round training time. Then, we propose a cross-tier device selection algorithm that selects devices that respond quickly and are conducive to model convergence to improve convergence efficiency and accuracy. Experimental results demonstrate that the proposed approach under wireless networks outperforms the baseline approach, with an average reduction of 54.7% in convergence time and an average improvement of 1.83% in convergence accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An LSTM-based detection model for breathing cracks with multiple damage positions and degrees of beam-like bridges under vehicle loads

引用

STRUCTURAL HEALTH MONITORING-AN international JOURNAL 2025年

作者： Wang, Cheng Yang, Zhen Gao, Kang Xia, Ye Li, Yi Ng, Ching-Tai Wu, Gang Southeast Univ Key Lab Concrete & Prestressed Concrete Struct Minist Educ 2 Dongnandaxue Rd Nanjing 211189 Peoples R China Natl & Local Joint Engn Res Ctr Intelligent Constr Nanjing Peoples R China Tongji Univ Dept Bridge Engn Shanghai Peoples R China State Key Lab Disaster Reduct Civil Engn Shanghai Peoples R China Univ Adelaide Sch Architecture & Civil Engn Adelaide SA Australia

The cracks of bridges are not always completely open during vibrations but undergo an open and closed cycle mode under moving vehicles. Therefore, this study proposes a long short-term memory (LSTM)-based detection model for breathing cracks with multiple damage positions and degrees of beam-like bridges for the first time. The contact point displacement variation (CPDV), serving as an evaluation indicator of the bridge damage, is calculated by analyzing the acceleration history data of the vehicle that has passed over a randomly damaged bridge. At the same time, CPDV is also used as the input variable of an LSTM neural network to monitor the damage location and degree of the bridge. By employing the finite element simulation of the bridge half-vehicle model, a dataset was created for the training and prediction of LSTM. The numerical results show that the proposed method can accurately identify complex breathing crack information at different vehicle speeds, and it is also robust to road roughness. In addition, a laboratory experiment was conducted to verify the proposed method. The experimental results show that CPDV is sensitive to bridge cracks and LSTM can realize higher damage prediction.

关键词： Breathing crack detection contact point displacement variation machine learning long short-term memory drive-by bridge damage inspection

来源：评论

学校读者我要写书评

暂无评论

machine learning Based Voltage Prediction with Various Levels of pH in IoT Environment 4th

Machine Learning Based Voltage Prediction with Various Level...

引用

4th international conference on Advanced Network Technologies and Intelligent Computing-ANTIC-Annual

作者： Kanagachidambaresan, G. R. Rohini, P. Jayasudha, V. Thipperudraswamy, S. P. Manickam, Pandiaraj Mathiyarasu, J. Kumararaja, P. Muralidhar, M. Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept Comp Sci & Engn Chennai Tamil Nadu India CSIR CECRI Cent Elect Chem Res Inst Electod & Electcatalysis Div Karaikkudi Tamil Nadu India Acad Sci & Innovat Res AcSIR Ghaziabad 201002 India Cent Inst Brackish Water Aquaculture Chennai Tamil Nadu India

ISBN: (纸本)9783031837821;9783031837838

For accurate pH measurement and voltage prediction, solution properties need to be converted into measurable electrical signals. Reliable and precise data from pH sensors are achieved by calibrating the sensors with known solutions, supporting effective monitoring and maintenance of water quality to safeguard organism health in aquaculture applications. In this study, fabricated pH strips are used for data measurement, and a dataset spanning various pH levels has been developed. Using machine learning algorithms, voltage is predicted across these pH values, with random forest regression yielding the best prediction accuracy for different pH ranges. This approach enhances sensor precision and reliability, minimizing the need for manual calibration. Additionally, it enables real-time pH monitoring and effectively captures complex parameter relationships, offering a more efficient and sustainable solution for optimal water quality management in aquaculture. The random forest model worked remarkably well, with a low RMSE of 0.01V and a R-2 value of 0.99, indicating great accuracy and minimum error in voltage predictions. The high R-2 score indicates that the model explains nearly all of the variance in the data.

关键词： Sensor Calibration machine learning Random Forest Regression pH Measurement Voltage Prediction

来源：评论

学校读者我要写书评

暂无评论

7th international Workshop on Advanced Analytics and learning on Temporal data, AALTD 2022 held at European conference on machine learning and Principles and Practice of Knowledge Discovery in databases, ECML PKDD 2022

7th International Workshop on Advanced Analytics and Learnin...

引用

7th international Workshop on Advanced Analytics and learning on Temporal data, AALTD 2022 held at European conference on machine learning and Principles and Practice of Knowledge Discovery in databases, ECML PKDD 2022

ISBN: (纸本)9783031243776

The proceedings contain 12 papers. The special focus in this conference is on Advanced Analytics and learning on Temporal data. The topics include: EDGAR: Embedded Detection of Gunshots by AI in Real-time;identification of the Best Accelerometer Features and Time-Scale to Detect Disturbances in Calves;ODIN AD: A Framework Supporting the Life-Cycle of Time Series Anomaly Detection Applications;clustering of Time Series Based on Forecasting Performance of Global Models;experimental Study of Time Series Forecasting Methods for Groundwater Level Prediction;fast Time Series Classification with Random Symbolic Subsequences;RESIST: Robust Transformer for Unsupervised Time Series Anomaly Detection;window Size Selection in Unsupervised Time Series Analytics: A Review and Benchmark;application of Attention Mechanism Combined with Long Short-Term Memory for Forecasting Dissolved Oxygen in Ganga River;data Augmentation for Time Series Classification with Deep learning Models;Dimension Selection Strategies for Multivariate Time Series Classification with HIVE-COTEv2.0.

关键词：

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：