检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wei, Tong Li, Hao-Tian Li, Chun-Shu Shi, Jiang-Xin Li, Yu-Feng Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT. © 2024, CC BY.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence Technology in Power System Stability Assessment

引用

Procedia computer science 2023年 228卷 79-88页

作者： Siyu Xiang Cao zhen Jian Peng Linghao Zhang Zhengguo Pu State Grid Sichuan Electric Power Research Institute Chengdu Sichuan 610095 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611700China College of Computer Science Sichuan University Chengdu 610065 China Anhui Jiyuan Software Co. Ltd. Hefei 230088 China

In order to realize power system stability assessment, the author studies a deep Convolutional neural network algorithm for power system operation stability assessment. Combining short-term simulation with neural network prediction to reduce the time required for transient stability analysis can be used in various simulation analysis scenarios. A deep Convolutional neural network algorithm is used to improve the performance of the security system. A deep Convolutional Neural Network (CNN) is used to construct a multi-layer and multi-column neural network to evaluate the stability of electrical networks. The system significantly improves the efficiency of evaluating specific faults, particularly enhancing the specificity of evaluation judgments, and reducing the additional maintenance workload caused by providing stability warnings for the operation status of faultless power grids. The experimental results indicate that, the system has shown certain advantages in terms of sensitivity to the judgment of various types of faults mentioned above, especially improving the sensitivity to other faults with unknown causes, which is 10.8 percentage points higher than the previous system. The smallest difference in the improvement of sensitivity indicators is the sensitivity to ground faults. The previous system reached 95.4%, while this system increased by 3.9 percentage points to 99.3%. It is proved that the deep CNN is applicable to the task of power system operation stability assessment.

关键词： Deep Convolutional neural network Power system operation Stability assessment Algorithm Innovation

来源：评论

学校读者我要写书评

暂无评论

A Revocable Fast and Lightweight Parallel Encryption Scheme for IIoT

引用

IEEE Internet of Things Journal 2025年

作者： Lu, Junze Hu, Chunqiang Chen, Jiajun Xia, Hui Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education China Chongqing University School of Big Data and Software Engineering Chongqing400030 China Ocean University of China College of Computer Science and Technology China

As the Industrial Internet of Things (IIoT) expands, the number of stakeholders increases. Many entities require significant amounts of data from industrial devices. These data streams improve information sharing and optimize the industrial chain. However, IIoT’s enormous data volumes pose challenges to traditional encryption methods, which are unable to meet efficiency and energy consumption requirements. Thus, a new, efficient encryption algorithm is essential for managing data flows among IIoT subscribers. In this paper, we propose a fast, low-energy, high-security encryption scheme to manage multi-entity data streams. First, we introduce a novel encryption scheme based on the Subset Sum Problem (SSP), which improves energy efficiency and speed. Second, to meet subscription requirements, we employ attribute-based encryption (ABE) for key forwarding. Finally, we handle subscription revocations with device key updates. The device owner utilizes their secret value to generate an identity proof with a key update request. © 2014 IEEE.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

MGC: Multiple-Gray-Code for 3D NAND Flash based High-Density SSDs

MGC: Multiple-Gray-Code for 3D NAND Flash based High-Density...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Yina Lv Liang Shi Qiao Li Congming Gao Yunpeng Song Longfei Luo Youtao Zhang School of Computer Science and Technology East China Normal University Shanghai China Ministry of Education Software/Hardware Co-Design Engineering Research Center School of Informatics Xiamen University Xiamen China Computer Science Department University of Pittsburgh Pittsburgh USA

QLC (4-bit-per-cell) and more-bit-per-cell 3D NAND flash memories are increasingly adopted in large storage systems. While achieving significant cost reduction, these memories face degraded performance and reliability issues. The industry has adopted two-step programming (TSP), rather than one-step programming, to perform fine-granularity program control and choose gray-code encoding, as well as LDPC (Low-Density Parity-Check Code) for error correction. Different flash manufacturers often integrate different gray-codes in their products, which exhibit different performance and reliability characteristics. Unfortunately, a fixed gray-code encoding design lacks the ability to meet the dynamic read and program performance requirements at both application and device *** this paper, we propose MGC, a multiple-gray-code encoding strategy, that adaptively chooses the best gray-code to meet the optimization goals at runtime. In particular, MGC first extracts the performance and reliability requirements based on application-level access patterns and detects the reliability degree of SSD. It then determines the appropriate gray-code to encode the data, either from host/user application or due to garbage collection, before writing the pages to the flash memory. MGC is integrated in FTL (flash translation layer) and enhances the flash controller to enable runtime gray-code arbitration. We evaluate the proposed MGC scheme. The results show that MGC achieves better performance and lifetime guarantee compared with state-of-the-arts and introduces little overhead.

关键词： Performance evaluation Three-dimensional displays Runtime Programming Writing Encoding Parity check codes

来源：评论

学校读者我要写书评

暂无评论

Power load prediction of smart grid based on deep learning

引用

Procedia computer science 2023年 228卷 762-773页

作者： Siyu Xiang Cao Zhen Jian Peng Linghao Zhang Zhengguo Pu State Grid Sichuan Electric Power Research Institute Chengdu Sichuan 610095 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611700 China College of Computer Science Sichuan University Chengdu 610065 China Anhui Jiyuan Software Co. Ltd. Hefei 230088 China

Real electricity costs, weather, and historical load data are added as new reference data when analyzing the characteristics of the load change policy to improve the forecasting model. A load forecasting model for smart grid based on convolutional neural network(CNN) is proposed. The model first analyzes the characteristics of the variable model and determines the forecast model inputs using two methods of correlation analysis to understand the impact of actual energy costs, weather and other factors on the changes. Second, since Feedforward neural network is deficient in processing the correlation information between loads, the prediction model developed by the author was studied as CNN. After completing the training, input two sets of real datasets for final data analysis and comparison, and the results show that, LSTM, BP, SVR[UNK]MAPE[UNK]RMSE respectively 0.49%, 0.57%, 0.83%, 1.44% and 106.08 MW, 113.82MW, 169.77 MW, 285.61 MW. It can be seen that the prediction model proposed by the author has the highest accuracy and the best fit with the trend of actual load changes. It is proved that the CNN model has certain advantages when dealing with load forecasting problems related to time series.

关键词： Real-time electricity price CNN Input features Power load forecasting

来源：评论

学校读者我要写书评

暂无评论

An exploratory study on automatic identification of assumptions in the development of deep learning frameworks

arXiv

引用

arXiv 2024年

作者： Yang, Chen Liang, Peng Ma, Zinan School of Artificial Intelligence Shenzhen Polytechnic University Shenzhen518055 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science Wuhan University Wuhan430072 China Department of Computer Science and Engineering Chalmers University of Technology GothenburgS-412 96 Sweden

Context: Stakeholders constantly make assumptions in the development of deep learning (DL) frameworks. These assumptions are related to various types of software artifacts (e.g., requirements, design decisions, and technical debt) and can turn out to be invalid, leading to system failures. Existing approaches and tools for assumption management usually depend on manual identification of assumptions. However, assumptions are scattered in various sources (e.g., code comments, commits, pull requests, and issues) of DL framework development, and manually identifying assumptions has high costs (e.g., time and resources). Objective: The objective of the study is to evaluate different classification models for the purpose of identification with respect to assumptions from the point of view of developers and users in the context of DL framework projects (i.e., issues, pull requests, and commits) on GitHub. Method: First, we constructed a new and largest dataset (i.e., the AssuEval dataset) of assumptions collected from the TensorFlow and Keras repositories on GitHub. Then we explored the performance of seven non-transformers based models (e.g., Support Vector Machine, Classification and Regression Trees), the ALBERT model, and three decoder-only models (i.e., ChatGPT, Claude, and Gemini) for identifying assumptions on the AssuEval dataset. Results: The study results show that ALBERT achieves the best performance (f1-score: 0.9584) for identifying assumptions on the AssuEval dataset, which is much better than the other models (the 2nd best f1-score is 0.8858, achieved by the Claude 3.5 Sonnet model). Though ChatGPT, Claude, and Gemini are popular models, we do not recommend using them to identify assumptions in DL framework development because of their low performance. Fine-tuning ChatGPT, Claude, Gemini, or other language models (e.g., Llama3, Falcon, and BLOOM) specifically for assumptions might improve their performance for assumption identification. Conclusions: This stu

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

UAV swarm regular geometric formation transformation and interactive control algorithm 5

UAV swarm regular geometric formation transformation and int...

引用

5th International Conference on Data science and Information Technology, DSIT 2022

作者： Wu, Pengnian Wang, Zihao Zhang, Zhiwei Hu, Guangpeng Dou, Wenying Zheng, Jiangbin School of Software Northwestern Polytechnical University Xi'an China School of Cyberspace Security University of Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Computer Science Northwestern Polytechnical University Xi'an China School of Electronic Information Engineering Beihang University Beijing China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

Compared with a single UAV, a UAV swarm has higher task execution efficiency, more robust system scalability, and better environmental adaptability when performing tasks. Different mission scenarios have additional requirements for the formation of a UAV swarm. In this context, the UAV swarm regular geometric formation transformation algorithm is proposed and implemented. The remote interactive control algorithm of the intelligent terminal based on Huawei SCM-W09 Pad and NOLO VR equipment is proposed and implemented. The deployment of the algorithm is mainly based on the Crazyflie miniature quadrotor, the Optitrack motion capture system, and the Crazyswarm software framework. Under limited communication resources, Crazyradio PA is used to expand the controllable UAV swarm scale from 17 to 20 under single-channel conditions. Through the actual flight experiment of the UAV swarm algorithm, the feasibility and practicability of the proposed algorithm are fully verified. Finally, we provide technical ideas and feasibility demonstrations to improve the proposed UAV swarm algorithm further. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Usability Evaluation of Kids’ Learning Apps

Usability Evaluation of Kids’ Learning Apps

引用

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Amer Ibrahim Murad Al-Rajab Khalid Hamid Muhamamd Aqeel Salman Muneer Mehvish Parveen Maryam Saleem College of Computer and Information Technology American University in the Emirates Dubai United Arab Emirates Assistant Professor Computer Scienc and IT College of Engineering Abu Dhabi University Department of Computer Science Superior University Lahore Pakistan Department of Software Engineering Superior University Lahore Pakistan School of Computer Science NCBA&E Lahore Pakistan Applied Science Research Center Applied Science Private University Amman Jordan School of Computer Science NCBAE Lahore Pakistan

The main objective of learning applications is to use modern electronic technologies to impart knowledge, communicate knowledge, and Direct learning models with their learning activities in a timely and effective manner. The preponderance of the apps were designed to up-skill the kids in the fundamentals of letters and numbers. Generally, they were grounded and practice skills in nature, based on a lack of abilities in critical thinking, favoring parrot-fashion skills, and contributing to a deep conceptual comprehension of more specific concepts are unable. By using appropriate evaluation methodologies, the purposed study observes essential characteristics and aspects that affect the usability of interfaces. An evaluation of the app's features will figure out to ensure user contentment. When a kid interacts with a learning interface, the ease of use provided by the interface is validated. Because a large number of the apps were designed to train kids’ fundamentals of alphabetic and numeric. The focus of this research is to see whether self-proclaimed learning apps for kids are built according to developmentally appropriate standards to help kids in formal and informal learning settings develop socially, emotionally, and academically.

关键词： Electronic learning User interfaces Security Usability Standards Business

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Algorithm for Container-based Microservice Scheduling in Hybrid Cloud

Ant Colony Algorithm for Container-based Microservice Schedu...

引用

2021 International Conference on Big Data and Intelligent Algorithms, BDIA 2021

作者： Lin, Miao Xi, Jianqing Bai, Weihua Wu, Jiayin School of Software Engineering South China University of Technology Guangzhou510006 China School of Computer Science Zhaoqing University Zhaoqing526061 China School of Computer Guangdong Vocational College of Post and Telecom Guangzhou510630 China

The microservice model divides the application into a group of loosely coupled and collaborative fine-grained services, which results in the workflow scheduling problem, especially in the complex environment of resource diversity such as hybrid cloud. To solve this problem, this paper establishes a workflow scheduling model of microservice based on multiple container instances and proposes an ant colony optimization (ACO) algorithm to optimize finish time and resource cost. The algorithm proposed optimizes update strategies of multi-objective heuristic information to improve the selection probability of the dominant path. The comparative experiments show that the proposed optimization algorithm achieves better results in scheduling objectives in the hybrid cloud. © Published under licence by IOP Publishing Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Efficient Evidence-Based Selection for Clinical Researchers in Traditional Chinese Medicine

SSRN

引用

SSRN 2023年

作者： Li, Yizhen Huang, Zhe Luan, Zhongzhi Zhao, Lei Xu, Shujing Zhang, Yunan Wu, Lin Liu, Yixing Han, Dongran School of Computer Science and Engineering Beihang University Beijing China School of Life and Science Beijing University of Chinese Medicine Beijing China School of Software Beihang University Beijing China School of Management Beijing University of Chinese Medicine Beijing China

Purpose Searching and selecting clinical evidence for systematic reviews (SRs) or clinical guidelines are vital for researchers in traditional Chinese medicine (TCM). The process can be time-consuming and resource-intensive, requiring significant effort from researchers. In this study, we introduce a new method for evidence-based selection that combines artificial intelligence (AI) and human efforts to achieve both swift and precise for TCM *** We use the knowledge engineer (KE) approach and a series of Boolean logic codes to select potential evidence automatically and accurately, with minimal human intervention. The selection details are recorded in real-time, enabling researchers to backtrack and verify the accuracy of the selection process. We apply the new approach in ten high-quality systematic reviews of randomly selected with TCM topics in the Chinese language. To evaluate the method's effectiveness, we compare the screen time and accuracy of the traditional selection method with the new *** The results show that the new method can accurately select potential literature under the same criteria while taking less time. Moreover, the new approach can identify more related evidence literature in some cases while tracking the selection progress for future reference. This study also identifies traditional screening methods are subjective and may lead to error inclusion of literature that does not meet the standards. The new method provides a more accurate and efficient way to select potential clinical evidence for TCM practitioners, outperforming traditional methods that rely solely on human *** We offer a novel approach to select clinical evidence for reviews and guidelines in TCM that can significantly reduce the workload for researchers. Our method holds promise for improving the efficiency and accuracy of evidence-based selection and may be used by editors to check the quality of manuscripts in the future. © 2023, The

关键词： Diagnosis

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：