检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Hu, Jiachen Zhong, Han Jin, Chi Wang, Liwei School of Computer Science Peking University China Center for Data Science Peking University China Department of Electrical and Computer Engineering Princeton University United States National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Center for Data Science Peking University Beijing Institute of Big Data Research China

Sim-to-real transfer, which trains RL agents in the simulated environments and then deploys them in the real world, has been widely used to overcome the limitations of gathering samples in the real world. Despite the empirical success of the sim-to-real transfer, its theoretical foundation is much less understood. In this paper, we study the sim-to-real transfer in continuous domain with partial observations, where the simulated environments and real-world environments are modeled by linear quadratic Gaussian (LQG) systems. We show that a popular robust adversarial training algorithm is capable of learning a policy from the simulated environment that is competitive to the optimal policy in the real-world environment. To achieve our results, we design a new algorithm for infinite-horizon average-cost LQGs and establish a regret bound that depends on the intrinsic complexity of the model class. Our algorithm crucially relies on a novel history clipping scheme, which might be of independent interest. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View Multi-Modal Head-Gaze Estimation for Advanced Indoor User Interaction

引用

computers, Materials & Continua 2022年第3期70卷 5107-5132页

作者： Jung-Hwa Kim Jin-Woo Jeong Department of Computer Engineering Kumoh National Institute of TechnologyGumi39177Korea Department of Data Science Seoul National University of Science and TechnologySeoul01811Kore

Gaze estimation is one of the most promising technologies for supporting indoor monitoring and interaction ***,previous gaze estimation techniques generally work only in a controlled laboratory environment because they require a number of high-resolution eye *** makes them unsuitable for welfare and healthcare facilities with the following challenging characteristics:1)users’continuous movements,2)various lighting conditions,and 3)a limited amount of available *** address these issues,we introduce a multi-view multi-modal head-gaze estimation system that translates the user’s head orientation into the gaze *** proposed system captures the user using multiple cameras with depth and infrared modalities to train more robust gaze estimators under the aforementioned *** this end,we implemented a deep learning pipeline that can handle different types and combinations of *** proposed system was evaluated using the data collected from 10 volunteer participants to analyze how the use of single/multiple cameras and modalities affect the performance of head-gaze *** various experiments,we found that 1)an infrared-modality provides more useful features than a depth-modality,2)multi-view multi-modal approaches provide better accuracy than singleview single-modal approaches,and 3)the proposed estimators achieve a high inference efficiency that can be used in real-time applications.

关键词： Human-computer interaction deep learning head-gaze estimation indoor monitoring

来源：评论

学校读者我要写书评

暂无评论

Temporal-Aware Deep Reinforcement Learning for Energy Storage Bidding in Energy and Contingency Reserve Markets

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第3期2卷 392-406页

作者： Li, Jinhao Wang, Changlong Zhang, Yanru Wang, Hao Monash University Department of Data Science and AI Faculty of IT and Monash Energy Institute MelbourneVIC3800 Australia Monash University Department of Civil Engineering MelbourneVIC3800 Australia University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China

The battery energy storage system (BESS) has immense potential for enhancing grid reliability and security through its participation in the electricity market. BESS often seeks various revenue streams by taking part in multiple markets to unlock its full potential, but effective algorithms for joint-market participation under price uncertainties are insufficiently explored in the existing research. To bridge this gap, we develop a novel BESS joint bidding strategy that utilizes deep reinforcement learning (DRL) to bid in the spot and contingency frequency control ancillary services (FCAS) markets. Our approach leverages a transformer-based temporal feature extractor to effectively respond to price fluctuations in seven markets simultaneously and helps DRL learn the best BESS bidding strategy in joint-market participation. Additionally, unlike conventional 'black-box' DRL model, our approach is more interpretable and provides valuable insights into the temporal bidding behavior of BESS in the dynamic electricity market. We validate our method using realistic market prices from the Australian National Electricity Market. The results show that our strategy outperforms benchmarks, including both optimization-based and other DRL-based strategies, by substantial margins. Our findings further suggest that effective temporal-aware bidding can significantly increase profits in the spot and contingency FCAS markets compared to individual market participation. © 2023 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Empowered Asynchronous Federated Reinforcement Learning for IoT-Based Traffic Trajectory Prediction

引用

IEEE Internet of Things Journal 2025年第11期12卷 17095-17109页

作者： Wang, Bin Tian, Zhao Tang, Fengxiao Pan, Heng She, Wei Liu, Wei Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450002 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou450002 China Central South University School of Computer Science and Engineering Changsha410083 China Zhongyuan University of Technology School of Cyber Space Security Zhengzhou450007 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou Key Laboratory of Blockchain and Data Intelligence Zhengzhou450002 China

Vehicle trajectory prediction plays a crucial role in IoT-based intelligent transportation systems, which can effectively address key issues, such as driving safety and multivehicle collaboration. However, the sensitivity of trajectory data and the reluctance of data holders to share it constrain the prediction model’s ability to capture vehicle behavior patterns in different scenarios. To address the above problems, we propose a blockchain-enabled asynchronous federated proximal policy optimization framework (BE-AFPPO) for the trajectory prediction of self-driving vehicles. First, we propose a curiosity proximal policy optimization (C-PPO) algorithm. The method utilizes a driven exploration strategy to actively motivate the intelligent agent to explore the unknown state space. The avoidance policy model reaches a local optimum when processing trajectory data. In addition, we design historical gated recurrent unit (GRU) and future GRU as input layers. The target’s historical motion features and future trajectory features are extracted, respectively. Then, various data is received through asynchronous federated learning. This model can fully learn the vehicle’s behavior patterns in different scenarios, which improves prediction accuracy. Based on this, we develop a blockchain-based dynamic group practical Byzantine fault tolerance (DG-PBFT) consensus algorithm. This enhances the credibility and integrity of the data while enriching the sources of trajectory data. Finally, we perform the experiments on the publicly available dataset nuScenes. The results demonstrate that the proposed method improves the robustness and accuracy of trajectory prediction. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Seer: Accelerating Block chain Transaction Execution by Fine-Grained Branch Prediction 51st

Seer: Accelerating Block chain Transaction Execution by Fine...

引用

51st International Conference on Very Large data Bases, VLDB 2025

作者： Zhang, Shijie Cheng, Ru Liu, Xinpeng Xiao, Jiang Jin, Hai Li, Bo National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Increasingly popular decentralized applications (dApps) with complex application logic incur significant overhead for executing smart contract transactions, which greatly limits public block chain performance. Pre-executing transactions off the critical path can mitigate substantial I/O and computation costs during execution. However, pre-execution does not yield any state transitions, rendering the system state inconsistent with actual execution. This inconsistency can lead to deviations in pre-execution paths when processing smart contracts with multiple state-related branches, thus diminishing pre-execution effectiveness. In this paper, we develop Seer, a novel public block chain execution engine that incorporates fine-grained branch prediction to fully exploit pre-execution effectiveness. Seerpredicts state-related branches using a two-level prediction approach, reducing inconsistent execution paths more efficiently than executing all possible branches. To enable effective reuse of pre execution results, Seer employs checkpoint-based fast-path execution, enhancing transaction execution for both successful and unsuccessful predictions. Evaluations with realistic block chain workloads demonstrate that Seer delivers an average of 27.7× transaction-level speedup and an overall 20.6× speedup in the execution phase over vanilla Ethereum, outperforming existing block chain execution acceleration solutions. © 2025, VLDB Endowment, All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An effective compressed image authentication scheme based on N-variant AMBTC

引用

Multimedia Tools and Applications 2024年第2期83卷 3801-3829页

作者： Su, Guo-Dong Chang, Chin-Chen Lin, Chia-Chen School of Big Data and Artificial Intelligence Fujian Polytechnic Normal University Fuzhou350300 China Department of Information Engineering and Computer Science Feng Chia University 100 Wenhwa Road Seatwen Taichung40724 Taiwan Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung41170 Taiwan

Image authentication is one technique that provides integrity protection for digital images, making them sensitive to any slight modification. Recently, the detectability of absolute moment block truncation coding (AMBTC) compressed images has been attracting more attention due to its integrity authentication concerns. Thus, this paper proposes an effective N-variant AMBTC based image authentication scheme for AMBTC compressed images. First, a novel AMBTC compression code is derived using a variant AMBTC technique that can provide a better quality of compressed images. Then, each AMBTC compression code is further eliminated into a version requiring fewer bits using the proposed N-variant AMBTC technique, and those vacated N-bits are used to conceal authentication codes, which is generated by hashing the AMBTC compression code and location information. Experimental results confirm that the proposed scheme has superior stability and accuracy in tampering detection while providing better visual quality of the watermarked image. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Analysis Based on Vision Transformer 2

Speech Emotion Analysis Based on Vision Transformer

引用

2022 2nd Conference on High Performance Computing and Communication Engineering, HPCCE 2022

作者： Huang, Xiaogang Zheng, Qifeng Zhang, Yuanyuan Cheng, Dong Liu, Yuting Dong, Chen College of Computer and Data Science College of Software Fuzhou University Fuzhou350108 China

ISBN: (纸本)9781510663374

Emotion is an essential aspect of human life, and effectively identifying corresponding emotions from different scenarios will help promote the development of human-computer interaction ***, emotion classification has gradually become a challenging and popular research field. Compared with text emotion analysis, emotion analysis of audio data is still relatively *** audio sentiment analysis research is based on feature information such as MFCC, MFSC, etc. while using time-memory models such as LSTM and RNN for emotion *** to the rapid development of transformers and attention mechanisms, many scholars have shifted their research from the RNN family to the transformer family or deep learning models with attention ***, this paper proposes a method to convert audio data into a spectrogram and use a vision transformer model based on transfer learning for emotion *** paper conducts experiments on the IEMOCAP dataset and the MELD dataset. The experimental results show that the emotion classification accuracy of the Vision transformer in the IEMOCAP and the MELD datasets reach 56.18% and 37.1%. © 2023 SPIE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Automated AI-Powered Fruit Identification Using Convolutional Neural Network

Automated AI-Powered Fruit Identification Using Convolutiona...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Sai Tejasree, K. Surendran, R. Rajakumar, B. Gomathi, R.M. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India J.N.N Institute of Engineering Department of Artificial Intelligence and Data Science Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

Clever system that can look at pictures of fruits and figure out what kind of fruit each picture shows. AI algorithms like deep learning, which is like giving the Machine learning model a crash course in fruit recognition. This method teaches the ML Model we clearly explained the Model using application's agent using PEAS and the application's task environment using the 6 dimensions by showing it tons of fruit images, so over time, it gets really good at spotting the differences and similarities between, say, a banana and a grape. We also used another technique called pattern recognition, which helps the computer pay attention to specific details like the fruit's color, shape, size and texture. Overcoming multiple obstacles in order to automatically identify the type of fruit from the picture. The variety of images is influencing the color, texture, and shape of many different types of fruits. When it came to fruit picture detection, Convolutional Neural Network (CNN) Algorithm outperformed standard support-vector-machine-based approaches using handcrafted features in terms of accuracy also, it is a lot faster to implement for new fruits. By integrating deep learning and pattern recognition techniques such as Convolutional Neural Network Algorithm we have got the accuracy of 84%, our system efficiently identified different fruit types from images, demonstrating the power and effectiveness of our methods. The goal of our project is to create a tool that can quickly and correctly identify many types of fruits in photos, which could be useful for things like sorting fruits in a grocery store or helping people learn about different fruits by using Convolutional Neural Network Algorithm. This is not just about teaching a computer to recognize fruits;it is about making technology that can understand and interact with the world in a way that is helpful to us. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Extremist Views Detection: Definition, Annotated Corpus, and Baseline Results 16th

Extremist Views Detection: Definition, Annotated Corpus, and...

引用

16th International Conference on Information Technology and Applications, ICITA 2022

作者： Hussain, Muhammad Anwar Shahzad, Khurram Sulaiman, Sarina Department of Computer Science University of Technology Malaysia Johor Bahru Malaysia Department of Data Science University of the Punjab Lahore Pakistan

ISBN: (纸本)9789811993305

Extremist view detection in social networks is an emerging area of research. Several attempts have been made to extremist views detection on social media. However, there is a scarcity of publicly available annotated corpora that can be used for learning and prediction. Also, there is no consensus on what should be recognized as an extremist view. In the absence of such a description, the accurate annotation of extremist views becomes a formidable task. To that end, this study has made three key contributions. Firstly, we have developed a clear understanding of extremist views by synthesizing their definitions and descriptions in the academic literature, as well as in practice. Secondly, a benchmark extremist view detection corpus (XtremeView-22) is developed. Finally, baseline experiments are performed using six machine learning techniques to evaluate their effectiveness for extremist view detection. The results show that bigrams are the most effective feature and Naive Bayes is the most effective technique to identify extremist views in social media text. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Structured Sampling for Robust Euclidean Distance Geometry 59

Structured Sampling for Robust Euclidean Distance Geometry

引用

59th Annual Conference on Information sciences and Systems, CISS 2025

作者： Kundu, Chandra Tasissa, Abiy Cai, HanQin University of Central Florida Department of Statistics and Data Science OrlandoFL32816 United States Tufts University Department of Mathematics MedfordMA02155 United States University of Central Florida Department of Statistics and Data Science Department of Computer Science OrlandoFL32816 United States

ISBN: (纸本)9798331513269

This paper addresses the problem of estimating the positions of points from distance measurements corrupted by sparse outliers. Specifically, we consider a setting with two types of nodes: anchor nodes, for which exact distances to each other are known, and target nodes, for which complete but corrupted distance measurements to the anchors are available. To tackle this problem, we propose a novel algorithm powered by Nystro m method and robust principal component analysis. Our method is computationally efficient as it processes only a localized subset of the distance matrix and does not require distance measurements between target nodes. Empirical evaluations on synthetic datasets, designed to mimic sensor localization, and on molecular experiments, demonstrate that our algorithm achieves accurate recovery with a modest number of anchors, even in the presence of high levels of sparse outliers. © 2025 IEEE.

关键词： Statistics

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：