检索结果-内蒙古大学图书馆

Joint User Scheduling and UAV Height Control for Smart Wearable Device Charging Network 19th

Joint User Scheduling and UAV Height Control for Smart Wea...

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Ji, Hongjing Wang, Xiaojie Ning, Zhaolong School of Software Engineering Dalian University of Technology Dalian China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9783031651229

This paper studies the user device time slot scheduling and Unmanned Aerial Vehicle (UAV) height control problem in the UAV-assisted smart wearable charging network. In contrast to traditional studies that only consider UAVs to serve user devices at a fixed height and ignore the flexibility and mobility of UAVs. We consider the UAV coverage and limited battery energy constraints as well as the charging demand of wearable devices;aiming to maximize network throughput. Specifically, first we formulate the problem as a Constrained Markov Decision Process (CMDP), and then propose a Proximal Policy Optimization (PPO)-CMDP algorithm for solving the formulated problem based on the Lagrangian original pairwise strategy optimization. Finally, the results from simulation evaluations show that our proposed algorithm can learn the mobility policy of UAV and the time slot scheduling policy of wearable devices to maximize the throughput of the achieved network while ensuring that the power of the UAV satisfies the constraint, and outperforms the baseline scheme. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

OSMF: A framework for OSS process measurement

OSMF: A framework for OSS process measurement

引用

International Conference on Information and Communication technology, ICT-EurAsia 2013

作者： Sunindyo, Wikan Danar Ekaputra, Fajar Juang Data and Software Engineering Research Group School of Electrical Engineering and Informatics Bandung Institute of Technology Ganesha Street 10 Bandung 40132 Indonesia

ISBN: (纸本)9783642368172

An Open Source software (OSS) project can be considered as a new type of business entity involving various roles and stakeholders, e.g., project managers, developers, and users, who apply individual methods. The project managers have the responsibility to manage the OSS development in a way that the OSS product can be delivered to the customers in time and with good quality. This responsibility is challenging, because the heterogeneity of the data collected and analyzed from different stakeholders leads to the complexity of efforts of the project managers to measure and manage OSS projects. In this paper, we propose a measurement framework (OSMF) to enable the project managers to collect and analyze process data from OSS projects efficiently. Initial results show that OSMF can help project managers to manage OSS business processes more efficient, hence improve the decision on OSS project quality. © 2013 Springer-Verlag.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Data-to-text Generation with Data Control and Multi-loss Fusion 2

Data-to-text Generation with Data Control and Multi-loss Fus...

引用

2nd International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2023

作者： Luo, Weier Yue, Xi Zhong, Chaotie Chengdu University of Information Technology Chengdu610225 China Sichuan Province Engineering Technology Research Center of Support Software of Informatization Application China

ISBN: (纸本)9798400707544

The goal of data-to-text generation is to generate fluent and fidelity natural language based on input data. At present, most models focus on data planning. Generating text according to the planning can effectively improve the fidelity to the generated text, but they lack attention to the fluency of the generated text, resulting in poor readability of the generated text. In order to address this issue, we propose a data-to-text generation model based on a pre-training language model. A control module is cleverly designed inside the language model to improve the fidelity to generated text. In training stage, multiple loss functions are cleverly designed to optimize the fluency and fidelity of generated text. Finally, the experimental results of RotoWire datasets show that the strong prior knowledge based on the Generative Pre-Training 2.0 (GPT2) can effectively improve the fluency of the generated text, and the proposed model in this paper can generate and control the fluency and fidelity of the generated text simultaneously. © 2023 Copyright held by the owner/author(s).

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Real-Time Resume Classification System Using LinkedIn Profile Descriptions 1

Real-Time Resume Classification System Using LinkedIn Profil...

引用

1st IEEE International Conference on Computational Intelligence for Smart Power System and Sustainable Energy, CISPSSE 2020

作者： Ramraj, S Sivakumar, V. Ramnath G, Kaushik Srm Institute of Science and Technology Department of Software Engineering Chennai India Srm Institute of Science and Technology Department of Computer Science Chennai India

ISBN: (纸本)9781728172743

In the domain of online job recruitment, accurate job and resume classification is vital for both the seeker and the recruiter. We have built an automatic text classification system that utilizes various techniques like Term frequency-inverse document frequency with Machine Learning and Convolution Neural network for training the model with texts and classifying them into labels and finally to compare their results. Using resume data of applicants, we have categorized them into different categories. Due to the sensitive nature of resume data, we have used domain adaptation. A classifier is trained on a large dataset of job description snippet, which is then used to classify resume data. Despite having a small dataset, consistent classification performance is seen. The primary filter for this type of work is the efficiency the system can provide. We aim to compare the results obtained by various algorithms that are generated using the same data so that the efficiency of each algorithm can be evaluated. From the result, it is evident that character-level CNN gives a better F1 score compared to other models. © 2020 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Modeling source code in bimodal for program comprehension

引用

Neural Computing and Applications 2024年第22期36卷 13815-13832页

作者： Wen, Dongzhen Zhang, Xiaokun Diao, Yufeng Zhao, Ziyun Jiang, He Lin, Hongfei School of Computer Science and Technology Dalian University of Technology 2rd Ling Gong Road Liaoning Dalian116024 China Department of Software Engineering School of Software Technology Dalian University of Technology No. 321 Tuqiang Street Dalian Economic and Technological Development Zone Liaoning Dalian116024 China School of Computer Science and Technology Inner Mongolia University for Nationalities 536 West Huolinhe Street Inner Mongolia Tongliao028000 China

Source code is an intermediary through which humans communicate with computer systems. It contains a large amount of domain knowledge which can be learned by statistical models. Furthermore, this knowledge can be used to build software engineering tools. We find that the functionality of the source code depends on the programming language-specific token which build the base structure, while identifiers provide natural language information. On this basis, we found that the knowledge in the source code can be sufficiently learned more when modeling the source code in bimodal. This paper presents the bimodal composition language model (BCLM) for source code modeling and representation. We analyze the effectiveness of bimodal modeling, and the results show that the bimodal approach has great potential for source code modeling and program comprehension. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

FedRec++: Lossless Federated Recommendation with Explicit Feedback 35

FedRec++: Lossless Federated Recommendation with Explicit Fe...

引用

35th AAAI Conference on Artificial Intelligence, AAAI 2021

作者： Liang, Feng Pan, Weike Ming, Zhong National Engineering Laboratory for Big Data System Computing Technology College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9781713835974

With the marriage of federated machine learning and recommender systems for privacy-aware preference modeling and personalization, there comes a new research branch called federated recommender systems aiming to build a recommendation model in a distributed way, i.e., each user is represented as a distributed client where his/her original rating data are not shared with the server or the other clients. Notice that, besides the sensitive information of a specific rating score assigned to a certain item by a user, the information of a user’s rated set of items shall also be well protected. Some very recent works propose to randomly sample some unrated items for each user and then assign some virtual ratings, so that the server can not identify the scores and the set of rated items easily during the server-client interactions. However, the virtual ratings assigned to the randomly sampled items will inevitably introduce some noise to the model training process, which will then cause loss in recommendation performance. In this paper, we propose a novel lossless federated recommendation method (FedRec++) by allocating some denoising clients (i.e., users) to eliminate the noise in a privacy-aware manner. We further analyse our FedRec++ in terms of security and losslessness, and discuss its generality in the context of existing works. Extensive empirical studies clearly show the effectiveness of our FedRec++ in providing accurate and privacy-aware recommendation without much additional communication cost. Copyright © 2021, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation and Machine Learning based Thermal Modeling of Tilted Active Tiles in Data Centers 2020

Performance Evaluation and Machine Learning based Thermal Mo...

引用

5th International Conference on Machine Learning Technologies, ICMLT 2020

作者： Rasheed, Zeeshan Xiong, Wei Cong, Gaoxiang Niu, Hongxun Wan, Jianxiong Wang, Yongsheng Li, Lixiao Inner Mongolia University of Technology and Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service China

ISBN: (纸本)9781450377645

Thermal management system of data center continuously face a lot of challenges, because data center industry has seen a boom growth in power density. In this paper we proposed the Tilted Active Tiles (TATs) to improve the local cold air supply and prevent the air flow blow over the rack. In traditional active tiles, fans are placed horizontally which cause the airflow blows over the rack, rather than into, the racks. To solve this issue, we adjusted the angle of the active tile to direct the airflow into the rack. We further introduced ANN based thermal models to predict the thermal performance of TATs. To train the ANN models, we adopted the data set obtained from a data center of Inner Mongolia Meteorology Information Center. The prediction accuracy of the model was extensively compared and analyzed, and the prediction accuracy and overhead of different neural network structures, i.e., BP and LSTM, were evaluated. Experimental results show that the rack with blanking panels has better thermal performance, and the temperature distribution at bottom, middle and top of the rack were same under smaller PWM. Thermal efficiency model was established by BP and LSTM, in this experiment single output model and multi output model were analyzed. The single output model can predict the temperature at different heights on the rack. In single output model the predicted effect of BP model is better than LSTM. The average prediction error is 0.57. The multi-output model can only predict the temperature at a fixed height of the rack. In multi output model LSTM model is better than BP. LSTM prediction error is less than BP. The average prediction error is 0.07. © 2020 ACM.

关键词： Thermoanalysis

来源：评论

学校读者我要写书评

暂无评论

Research on Service Model of Mobile Library Based on Context Awareness 10

Research on Service Model of Mobile Library Based on Context...

引用

10th International Conference on Orange technology, ICOT 2022

作者： Ye, Pin-Ju Hu, Yuan-Wang School of Software Changzhou College of Information Technology Changzhou China School of Electronic and Electrical Engineering Changzhou College of Information Technology Changzhou China

ISBN: (纸本)9781665454193

The mobile library perceives the user's situation and provides personalized information services as the goal. The paper starts with situational awareness as an entry point, starting from two perspectives of mobile phone user situational awareness middleware and service model level, researches and proposes the service model framework of library situational awareness, design context-aware adaptive middleware, construct a mobile library mobile service model based on context-awareness, design a personalized learning system incorporating context-awareness which can improve and enrich the theory of mobile library knowledge service research. It provides a new basis for the development and application of the theory of library situational awareness services. © 2022 IEEE.

关键词： Information services

来源：评论

学校读者我要写书评

暂无评论

Hierarchical software Design Methodology for High Concurrency and Fine-Grained Permission Control Scenarios 21

Hierarchical Software Design Methodology for High Concurrenc...

引用

2nd International Conference on Control, Robotics and Intelligent System, CCRIS 2021

作者： Han, Yuan Song, Qingqing Huang, Xinquan Yin, Jie School of Computer and Software Nanjing Vocational University of Industry Technology China School of Electronic and Information Engineering Suzhou University of Science and Technology China

ISBN: (纸本)9781450390453

Because complex software usually faces high concurrency and complex permission control scenarios, and there are problems with low code reuse rate and chaotic function module structure in the development process of its access control module, so providing software design methodology for such scenarios is helpful to improve software productivity and software quality play an important role. This paper proposes a hierarchical software design methodology for the development of complex software under high concurrency and fine-grained permission control scenarios. The software design methodology divides the hierarchical structure according to the characteristics of the access control process, and provides support for fine-grained control and multi-level control of permissions. For high concurrency scenarios, a cache management layer is added to improve the efficiency of the access control process. According to the actual needs of software development, the specific levels in the software design methodology are divided. By decoupling the user status detection, user status verification and permission authentication in the access control process, the support of this software design methodology in different framework environments is guaranteed and the security risks caused by the high coupling between frameworks are reduced. Through a series of 0-500K concurrent test experiments, the performance data of different frameworks in the same scenario is obtained, which provides users with a reference when implementing the software design methodology proposed in this article, enable it to choose a framework for better performance depending on the scenario it faces. © 2021 ACM.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Fast algorithms on primality testing for numbers 255 s 2n ± 1

Fast algorithms on primality testing for numbers 255 s 2n ±...

引用

2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019

作者： Huang, Dandan Zhang, Zheng Tang, Zhihao School of Software Engineering School of Cybersecurity Jinling Institute of Technology Nanjing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728140346

关键词： Cryptosystem Lucasian sequence Primality testing Quadratic reciprocity law

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：