检索结果-内蒙古大学图书馆

作者： Zhaotian Weng Jianbo Hong Lan Wang School of Software Tsinghua University Collage of Computer Science and Technology Jilin University College of Engineering Monash University

Conditional Generative Adversarial Nets(CGAN) is often used to improve conditional image generation ***,there is little research on Representation learning with CGAN for causal *** paper proposes a new method for finding representation learning functions by adopting the adversarial *** apply the pattern of CGAN and theoretically demonstrate the feasibility of finding a suitable representation function in the context of two distributions being *** theoretical result shows that when two distributions are balanced,the ideal representation function can be found and thus can be used to further research.

关键词： casual inference generative adversarial nets conditional generative adversarial nets representation learning

来源：评论

学校读者我要写书评

暂无评论

DULRTC-RME: A Deep Unrolled Low-rank Tensor Completion Network for Radio Map Estimation

DULRTC-RME: A Deep Unrolled Low-rank Tensor Completion Netwo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yao Wang Xin Wu Lianming Xu Na Liu Li Wang School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China School of Electronic Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Radio maps enrich radio propagation and spectrum occupancy information, which provides fundamental support for the operation and optimization of wireless communication systems. Traditional radio maps are mainly achieved by extensive manual channel measurements, which is time-consuming and inefficient. To reduce the complexity of channel measurements, radio map estimation (RME) through novel artificial intelligence techniques has emerged to attain higher resolution radio maps from sparse measurements or few observations. However, black box problems and strong dependency on training data make learning-based methods less explainable, while model-based methods offer strong theoretical grounding but perform inferior to the learning-based methods. In this paper, we develop a deep unrolled low-rank tensor completion network (DULRTC-RME) for radio map estimation, which integrates theoretical interpretability and learning ability by unrolling the tedious low-rank tensor completion optimization into a deep network. It is the first time that algorithm unrolling technology has been used in the RME field. Experimental results demonstrate that DULRTC-RME outperforms existing RME methods.

关键词： Learning systems Wireless communication Training Tensors Estimation Signal processing algorithms Training data Radio propagation Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Prediction Model for T20 and Test Match Outcomes Using Machine Learning

A Comprehensive Prediction Model for T20 and Test Match Outc...

引用

engineering & Computing Technologies (ICECT), International Conference on

作者： Zoha Ahsan Shahwaiz Ghumman Attique Ur Rehman Sabeen Javaid Tahir Muhammad Ali Azka Mir Department of Software Engineering University of Sialkot Sialkot Pakistan Department of Computer Science Gulf University for Sciences and Technology Mubarak Al-Abdullah Kuwait

ISBN: (数字)9798350349719

ISBN: (纸本)9798350349726

Cricket is a popular sport worldwide, played with a bat and balls. This paper used classification and regression to predict the T20 and Test matches results and scores because cricket fans and analysts always want to predict which team will win the match and how much score a team will make. We have used a supervised machine learning technique to predict the score and result for T20 and Test matches. Cricket match prediction dataset comprising of 13 features and 7827 instances utilized for training the model. For the prediction of winning and losing, we have used Naïve Bayes, Gradient Boosted Trees, Logistic Regression, Deep learning, Decision Tree, Random Forest, and Generalized Linear Model. For Score Prediction, we have used Decision Trees, Random Forests, Gradient Boosted Trees, Generalized Linear Models, and Deep Learning. We've shown the most accurate model after evaluating the accuracy percentages of the several classifiers listed above. Our introduced model has gained an accuracy rate of 96.15% using the Gradient Boosted Trees classifier for Match Score Prediction and 71.72% accuracy by using the Generalized Linear Model for match result prediction. The Rapid Miner tool has been used to perform machine learning techniques to train models. This paper discusses the effectiveness and use of machine learning methods to develop highly accurate models for Cricket match prediction dataset comprising of 13 features and 7827 instances utilized for training the model.

关键词： Training Deep learning Logistic regression Fans Accuracy Computational modeling Predictive models

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Multi-Objective Resource Allocation in Multi-Platoon Cooperative Vehicular Networks

Deep Reinforcement Learning for Multi-Objective Resource All...

引用

作者： Xu, Yuanyuan Zhu, Kun Xu, Hu Ji, Jiequ Hohai University College of Computer and Information Nanjing211100 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China University of Victoria Department of Electrical and Computer Engineering VictoriaV8P 5C2 Canada

Grouping vehicles into platoons is a promising cooperative driving scenario to enhance the traffic safety and capacity of future vehicular networks. However, fast changing channel conditions in multi-platoon vehicular networks cause tremendous uncertainty for resource allocation. In addition, the unprecedented proliferation of various emerging vehicle-to-infrastructure (V2I) applications may result in some service demands with conflicting quality of experience. In this paper, we formulate a multi-objective resource allocation problem, which maximizes the transmission success ratio of intra-platoon communications and the mean opinion score (MOS) of V2I communication links. To efficiently solve this multi-objective optimization problem, we resort to a deep reinforcement learning (DRL) framework. Specifically, we divide it into a set of scalar optimization subproblems based on the weighted sum approach and model each one as a partially observable stochastic game (P-OSG), where each platoon acts as an agent and the actions taken by all platoons correspond to the resource allocation solution. We further propose a contribution-based dual-clip proximal policy optimization (CD-PPO) algorithm to deal with each subproblem, which is a DRL algorithm based on the actor-critic framework. The network parameters of all subproblems are then optimized collaboratively by using the proposed training algorithm and the neighborhood parameter transfer strategy. The desired Pareto front is obtained when all subproblems are solved. Simulation results reveal that the proposed algorithm can outperform other algorithms in terms of the MOS and transmission success ratio. © 2002-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HIGH RESOLUTION IMAGE QUALITY DATABASE

arXiv

引用

arXiv 2024年

作者： Huang, Huang Wan, Qiang Korhonen, Jari Shenzhen University School of Computer Science and Software Engineering Shenzhen China University of Aberdeen School of Natural and Computing Sciences Aberdeen United Kingdom

With technology for digital photography and high resolution displays rapidly evolving and gaining popularity, there is a growing demand for blind image quality assessment (BIQA) models for high resolution images. Unfortunately, the publicly available large scale image quality databases used for training BIQA models contain mostly low or general resolution images. Since image resizing affects image quality, we assume that the accuracy of BIQA models trained on low resolution images would not be optimal for high resolution images. Therefore, we created a new high resolution image quality database (HRIQ), consisting of 1120 images with resolution of 2880 × 2160 pixels. We conducted a subjective study to collect the subjective quality ratings for HRIQ in a controlled laboratory setting, resulting in accurate MOS at high resolution. To demonstrate the importance of a high resolution image quality database for training BIQA models to predict mean opinion scores (MOS) of high resolution images accurately, we trained and tested several traditional and deep learning based BIQA methods on different resolution versions of our database. The database is publicly available in https://***/jarikorhonen/hriq. © 2024, CC BY.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Write-Optimized Persistent Hash Index for Non-Volatile Memory

Write-Optimized Persistent Hash Index for Non-Volatile Memor...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Renzhi Xiao Dan Feng Yuchong Hu Yucheng Zhang Lanlan Cui Lin Wang School of Software Engineering Jiangxi University of Science and Technology Nanchang China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute School of Computer Science and Engineering XI'AN University of Technology Xi'an China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

A hashing index provides rapid search performance by swiftly locating key-value items. Non-volatile memory (NVM) technologies have driven research into hashing indexes for NVM, combining hard disk persistence with DRAM-level performance. Nevertheless, current NVM-based hashing indexes must tackle data inconsistency challenges caused by NVM write reordering or partial writes, and mitigate rapid local wear due to frequent updates, considering NVM's limited endurance. The temporary allocation of buckets in NVM-based chained hashing to resolve hash collisions prolongs the critical path for writing, thus hampering write performance. This paper presents WOPHI, a write-optimized persistent hash index scheme for NVM. By utilizing log-free failure-atomic writes, WOPHI minimizes data consistency overhead and addresses hash conflicts with bucket pre-allocation. Experimental results underscore WOPHI's significant performance enhancements, with insertion latency slashed by up to 88.2% and deletion latency boosted by up to 82.6% compared to existing state-of-the-art schemes. Moreover, WOPHI substantially mitigates data consistency overhead, reducing cache line flushes by 59.3%, while maintaining robust write throughput for insert and delete operations.

关键词： Nonvolatile memory Europe Writing Throughput Hard disks Indexes Resource management

来源：评论

学校读者我要写书评

暂无评论

Response Time Analysis for Real-Time DAG Tasks Under Partitioned Scheduling

Response Time Analysis for Real-Time DAG Tasks Under Partiti...

引用

International Conference on computer and Communications (ICCC)

作者： Yumeng Chen Songlin Liu Jianhong Zhou Xiang Ling National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China China School of Computer and Software Engineering Xihua University China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Parallel task systems with real-time constraints are widely applied in various fields. Response time analysis is a necessary condition for online admission of applications in dynamic systems. This article focuses on the worst-case response time (WCRT) analysis of directed acyclic graph (DAG) tasks on multiprocessors under partitioned scheduling. We propose a new WCRT analysis algorithm, named the radiative-extended structure analysis (RESA) algorithm. We demonstrate that an-alyzing the radiative-extended structure (Res) helps to obtain more accurate analysis results. Compared with state-of-the-art algorithms, RESA achieves tighter upper bounds on self-interference and high-priority interference without increasing time and space complexity. RESA performs better by comparing the average response time observed in simulation experiments.

关键词： Directed acyclic graph Upper bound Interference cancellation Processor scheduling Heuristic algorithms Real-time systems Partitioning algorithms Complexity theory Time factors Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Forecasting the Stability of COVID-19 Vaccine Companies Stock Market using LSTM and Time-series Models

Forecasting the Stability of COVID-19 Vaccine Companies Stoc...

引用

International Conference on Communication, Computing and Digital Systems (C-CODE)

作者： Rahemeen Khan Safia Baloch Department of Software Engineering Bahria University Karachi Pakistan Department of Computer Science FAST University Karachi Pakistan

Stock price forecasting is challenging because stock markets are volatile and nonlinear in nature. With the impact of the Covid-19 outbreak in 2019, stock market forecasting has become more complicated. The goal of this study is to identify the top brands in the global covid-19 vaccination market and their impact on the stock market. By forecasting the next months stock exchange, traders will be able to select the most suitable company to invest in. In this paper, MSE, RMSE, and MAPE are used as evaluation matrices to compare timeseries and neural network models such as Arima, Prophet, and LSTM. According to the results of a comparative analysis, the LSTM model produced the most accurate predictions on majority stock prices dataset for the selected vaccination brands. Brand stability is achieved by predicting future stock exchange prices using an outperformed LSTM model. As a result, BioNTech has been identified as a high potential stable brand that the buyer can invest to gain enormous returns among the massive number of probabilistic events.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving and Research-Utilizable Trajectory Generator via Deep Generative Approach

A Privacy-Preserving and Research-Utilizable Trajectory Gene...

引用

International Conference on Electronics Technology (ICET)

作者： Xinyue Sun Tianyu Wo School of Computer Science and Engineering Beihang University Beijing China School of Software Beihang University Beijing China

Large-scale trajectory data is critical for a smart city to improve the efficiency of a transportation system. However, the release of original trajectory data violates privacy protection principles if no privacy-preserving approach is adopted, that’s why the public trajectory data for research is so limited. To enable extensive available trajectory data publishing, we propose a Privacy-Preserving and research-utilizable Trajectory Generator (PPTG), which uses a deep generative model to provide utilizable synthetic trajectories. Specifically, PPTG can not only extract the intrinsic and spatial features, but also get rid of possible privacy information from the real trajectories. In experiments, we show that the privacy-preserving trajectory data generated by PPTG can achieve superior performance in terms of privacy protection and data utility against the existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Practical Teaching Platform based on Data Mining

Intelligent Practical Teaching Platform based on Data Mining

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Qi Liu Xiao Chen Kun Niu Wanru Zhang Yiman Gao Jin Wei School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

In the era of rapid Internet expansion, the data generated has witnessed exponential growth, concealing valuable information within. Consequently, the field of data mining has flourished, finding extensive applications across diverse industries. However, its full potential remains untapped in the realm of higher education. In light of the "Big Data Analysis and Mining" course, this paper makes a detailed investigation on the problems existing in practical teaching. To address these problems, we propose an intelligent practical teaching platform based on data mining technology. This platform harnesses data mining and cloud storage techniques, adopting a blended approach that seamlessly integrates online and offline teaching methods. It offers a comprehensive solution for practical teaching, with the primary objective of enhancing the effectiveness of practical teaching and augmenting students’ hands-on capabilities. Finally, we present the outcomes and applications of this platform since its inception over one year ago, showcasing its tangible impact on higher education.

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：