检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Chen, Jingxue Deng, Liangjun Qiu, Yao Zhao, Pengbiao Lei, Hang Song, Jingcheng Wang, Xiaopei School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China Institute of Building Information Modeling Ningbo Polytechnic College Zhejiang Ningbo315800 China College of Information Science and Engineering Linyi University Shandong Linyi276000 China Department of Computer Science and Engineering University of California RiversideCA92521 United States

There are lots of sensitive information in medical consumer devices. Since Consumer electronics products in the healthcare mainly focus on health monitoring and personal health management, such as wearable ECG monitoring devices, smart weight scales and so on. It is paramount to ensure the security and reliability of software in healthcare delivery, especially for sensitive medical data of integration with artificial intelligence (AI). Therefore, it is necessitating strict security verification and continuous vigilance against potential software vulnerabilities. WebAssembly, known for its security, portability, and speed, has emerged as a crucial technology for medical device software, significantly impacting the healthcare electronics sector, particularly in AI-generated content. There is a novel machine learning-based approach to address the challenges of symbolic execution in WebAssembly by automatically modeling unknown functions using a fine-tuned large language model (LLM) with 20 billion parameters, enhancing the execution's integrity and efficiency. The method, applicable across multiple programming languages and extendable to WebAssembly-compiled programs, shows promising experimental results in model performance and efficiency. This ensures enhanced security and reliability of software for CE, setting the stage for more flexible WebAssembly standards in medical CE and AI-driven healthcare devices. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution reconstruction based on improved generative adversarial network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第2期6卷 155-163页

作者： Wang, Ying-Li Li, Xiao-Jing Ma, Hong-Bin Ding, Qun Pirouz, Matin Ma, Qi-Tao Department of Electronic Engineering Heilongjiang University No.74 Xuefu Road Harbin Heilongjiang China Faculty of Engineering The Hong Kong Polytechnic University 11 Yucai Road Hung Hom Kowloon Hong Kong Department of Computer Science California State University Fresno United States

This article introduces the super-resolution reconstruction of images based on an improved generative confrontation network, improves the network structure of the generator, and proposes a super-resolution reconstruction algorithm for the recursive residual generation confrontation network. Its discriminator uses PatchGAN as the discriminator. The network solves the bottleneck of low feature information utilization and slow convergence of the generation countermeasure network in the super-resolution algorithm based on convolutional neural network. The reconstruction algorithm is compared with mainstream super-resolution reconstruction algorithms on standard data sets such as Set5 and Set14. The data shows that the algorithm can effectively improve the use of feature information, restore the details of low-resolution images, and improve the quality of image reconstruction. © 2021, Taiwan Ubiquitous Information. All rights reserved.

关键词： Generative adversarial networks

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

SSRN

引用

SSRN 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 ***: We constructed a new and largest dataset (i.e., AssuEval) of assumptions collected from the TensorFlow and Keras repositories on GitHub;explored the performance of seven traditional machine learning models (e.g., Support Vector Machine, Classification and Regression Trees), a popular DL model (i.e., ALBERT), and a large language model (i.e., ChatGPT) of identifying assumptions on the ***: The experiment results show that ALBERT achieves the best performance (f1-score: 0.9584) of identifying assumptions on the AssuEval dataset, which is much better than the other models (the 2nd best f1-score is 0.6211, achieved by ChatGPT). Though ChatGPT is the most popular large language model, we do not recommend using it to identify assumptions in DL framework development because of its low performance on the task. Fine-tuning ChatGPT specifically for assumption identification could improve the ***: This study provides researchers with the largest dataset of assumptions for further research (e.g., assumption classification, evaluation, and

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Educating Project Stakeholders: A Preliminary Report 42

Educating Project Stakeholders: A Preliminary Report

引用

42nd IEEE/ACM International Conference on software engineering Workshops, ICSEW 2020

作者： Dekhtyar, Alex Da Silva, Bruno Slocum, Karson Department of Computer Science and Software Engineering California Polytechnic State University San Luis Obispo United States

ISBN: (纸本)9781450379632

In college coursework, we take care to educate future professional software engineers on how software development process works. computer science and software engineering students across the globe study software process models, gather requirements, design, implement and test their software, work on software maintenance, learn to submit bug reports, build project roadmaps, construct UML diagrams, and deploy software. Yet, ever since the emergence of consumer-facing software, software development often is a collaboration between professional software engineers and multiple stakeholders whose education, professional expertise, and general experience lie outside of computing. We teach future software engineers how to develop software. Why don't we do the same with other future stakeholders? This paper is a description of a pilot software engineering Without Programming course developed and taught at our university for the first time in 2020. In this early stage report (the course is ongoing as of the submisison deadline, but will have been completed by the time of the workshop) we outline the need for the course, its learning objectives, its organization, and the expected results. © 2020 Owner/Author.

关键词： Education computing

来源：评论

学校读者我要写书评

暂无评论

Joint Beamforming and Trajectory Optimization for UAV-Assisted Double IRS Secure Transmission System: A Deep Reinforcement Learning Approach

Joint Beamforming and Trajectory Optimization for UAV-Assist...

引用

Metaverse Computing, Networking and Applications (MetaCom), IEEE International Conference on

作者： Yihao Qi Zhou Su Qichao Xu Dongfeng Fang School of Mechatronic Engineering and Automation Shanghai University Shanghai China School of Cyber Science and Engineering Xi’an Jiaotong University Xi’an China Department of Computer Science California Polytechnic State University San Luis Obispo USA

Unmanned aerial vehicle (UAV) integrated with intelligent reflecting surface (IRS) has excellent potential to improve air-to-ground communication performance. However, the openness of the air-to-ground channel makes secure information transmission a challenging issue. In this paper, we first propose a UAV-assisted double IRS secure transmission system, where one IRS is carried by UAV, and the other is deployed near the base station. The collaborative beamforming gain provided by the cascaded reflection link overcomes the performance bottleneck of a single IRS in the air. Secondly, with the aim of maximizing the sum secrecy rate, a problem is formulated for jointly optimizing the trajectory of UAV and the phase shift of each IRS. As the formulated problem is a non-convex optimization problem and varies dynamically with the environment, a deep reinforcement learning-based secure transmission approach is presented to continuously achieve the optimal phase shift and trajectory of UAV in dynamic environments. Furthermore, we reduce the dimension of the action space by dividing the IRS into several sub-surfaces, each of which shares the same phase shift. The simulation results demonstrate that the secrecy rate of the UAV-assisted double IRS secure transmission system can be significantly improved by the proposed approach.

关键词：

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

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

MSFA-Net : Multiple Spatial-Channel Feature Aggregation Network for Change Detection and a UAV-CD Dataset

MSFA-Net : Multiple Spatial-Channel Feature Aggregation Netw...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jiahao Pan Yikui Zhai Haolin Lv Tingfeng Xian Zilu Ying Hao Quan Xudong Jia College of Electronics and Information Engineering Wuyi University Jiangmen China Future Aviation Science and Technology Co. Ltd Jiangmen China Department of Electronics Information and Bioengineering Polytechnic University of Milan Milan Italy College of Engineering and Computer Science California State University Northridge America

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Change detection in remote sensing images is pivotal for monitoring and comprehending dynamic environmental phenomena. Nonetheless, conventional change detection models have grappled with correlating information between channel and spatial dimensions due to inherent feature extraction limitations. Hence, this paper proposes an innovative change detection framework and a high resolution UAV change detection dataset named UAV-CD dataset. The introduced network embraces a Siamese network, amalgamating a feature extraction backbone network along with spatial and channel reconstruction convolution (ScConv) and Ghost modules. A primary contribution of this paper is the incorporation of ScConv into the change detection network, facilitating the reconstruction of information in both spatial and channel dimensions. Additionally, the Ghost module is employed to fortify information across distinct channel dimensions within the feature maps. Compared with current state-of-the-art methods, it is indicated that the proposed approach achieves superior performance on the LEVIR-CD, SYSU-CD, and our proposed dataset UAV-CD.

关键词： Convolution Feature extraction Autonomous aerial vehicles Robustness Sensors Task analysis Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Efficient COVID-19 detection using data mining algorithms: a comparison of basic and hybrid approaches

引用

Soft Computing 2025年第3期29卷 1437-1451页

作者： Saidi, Mohammad Gheibi, Mohammad Ghazikhani, Adel Lotfata, Aynaz Chahkandi, Benyamin Familsamavati, Sajad Behzadian, Kourosh Department of Computer Science Imam Reza International University Mashhad Iran MS of Software Engineering Information and Communication Technology Unit Mashhad Municipality Fire and Safety Services Organization Mashhad Iran Big Data Lab Imam Reza International University Mashhad Iran Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Liberec46117 Czech Republic Tallinn10615 Estonia Department of Pathology Microbiology and Immunology School of Veterinary Medicine University of California Davis95616 United States Department of Urban and Regional Planning San Jose State University San Jose95192 United States Faculty of Civil and Environmental Engineering Gdansk University of Technology Narutowicza Street 11/12 80-233 Gdansk Poland Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Monterrey Mexico School of Computing and Engineering University of West London London United Kingdom

Accurate and efficient diagnosis of COVID-19 remains a significant challenge due to the limitations of current detection methods, such as blood tests and chest scans, which can be time-consuming and error-prone. This study aims to compare the performance of basic and hybrid data mining algorithms in diagnosing COVID-19, using blood test results and clinical information to identify the most effective approach. A dataset of 200 records from suspected and infected COVID-19 patients, with 23 characteristics and one diagnostic class, was analysed. Nine data mining algorithms were tested: four basic algorithms (Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor) and five hybrid algorithms (Random Forest, AdaBoost, Majority Voting, XGBoost, Bagging). The study also integrated Response Surface Methodology (RSM) and Adaptive-Network-based Fuzzy Inference System (ANFIS) to enhance model performance. The Bagging algorithm demonstrated superior performance with an accuracy of 88%, sensitivity of 74%, and F-criterion of 78%. The integration of RSM and ANFIS further showed that a smart model could be developed for efficient pandemic crisis management, achieving up to 100% accuracy when considering key factors like AST, Albumin, and CRP. The findings suggest that Bagging and hybrid data mining algorithms can significantly improve COVID-19 detection, reducing time and errors in identifying exposed individuals. The study highlights the potential of combining machine learning techniques with RSM-ANFIS models for effective pandemic management and decision-making in medical settings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Scale-Temporal Interaction Network For Remote Sensing Image Change Detection And A UAV-CD Dataset

A Scale-Temporal Interaction Network For Remote Sensing Imag...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Tingfeng Xian Zilu Ying Haolin Lv Jiahao Pan Yikui Zhai Hao Quan Xudong Jia College of Electronics and Information Engineering Wuyi University Jiangmen China Future Aviation Science and Technology Co. Ltd Jiangmen China Department of Electronics Information and Bioengineering Polytechnic University of Milan Milan Italy College of Engineering and Computer Science California State University Northridge America

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Remote sensing (RS) image change detection (CD) is a challenging visual task due to its rich and complex image information. Nowadays, CD has yielded fruitful results. However, insufficient feature interaction hinders further improvement of CD performance. In this paper, we introduce a scale-temporal interaction network (STI-Net). It extracts multi-scale bitemporal features using a depth-separable convolution-based Siamese encoder, followed by both Cross-Scale Feature Interaction (CSFI) and Cross-Temporal Feature Interaction (CTFI). Finally, we employ a straightforward decoder to generate the change map. Additionally, to enrich the CD data, we introduced a new dataset based on UAV optical image, named UAV-CD. This dataset comprises 2660 pairs of images sized at 768×768 pixels, focusing primarily on building and land changes. Experiments demonstrate that our method outperforms existing state-of-the-art methods on two public CD datasets as well as UAV-CD, showcasing excellent performance.

关键词： Visualization Buildings Focusing Feature extraction Autonomous aerial vehicles Optical imaging Decoding

来源：评论

学校读者我要写书评

暂无评论

Short-term power load forecasting based on multi-step probability distribution deep learning network 6

Short-term power load forecasting based on multi-step probab...

引用

6th International Conference on computer Information science and Application Technology, CISAT 2023

作者： Chen, Ming Gao, Huaijin Chen, Kun Du, Chong Yang, Zhijie Computer Technology and Software Engineering Wuhan Polytechnic Wuhan430074 China Biomedical Engineering and Instrument Science Zhejiang University Hangzhou310027 China Electric Power Research Institute State Grid Hubei Electric Power Co. Ltd Wuhan430077 China Huanggang Power Supply Company State Grid Hubei Electric Power Co. Ltd Huanggang438021 China Wuhan Marine College Wuhan430062 China

ISBN: (纸本)9781510668546

With the improvement of renewable energy utilization rate, its proportion in power generation continues to increase. However, the uncertainty of renewable energy power generation has always been an urgent problem. Accurate forecast of short-term power load can assist modern power systems in accurately allocating the proportion of traditional and renewable energy generation. This is crucial for the safety and economic operation of the power grid. Power load forecasting can be seen as a multivariate time series forecasting problem. Most of existing studies have focused on predicting the next moment power load. However, a great number of decisions in power planning scenarios require predictive models that can provide a complete conditional distribution with richer information, namely probability distribution prediction. To address this limitation, we applied a multi-step probability prediction model based on recurrent neural networks on short-term power load forecasting. Experiments conducted on the annual power load of multiple regions in the United states and comparison with some classic models verify the superiority of the applied model. The results indicate that the model applied in the article has a promising predictive performance. © 2023 SPIE.

关键词： Forecasting

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：