检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Software Quality, Reliability, and Security Companion, QRS-C 2023

作者： Liu, Jinrun Tang, Xinyu Li, Linlin Chen, Panpan Liu, Yepang Southern University of Science and Technology Shenzhen Guangdong China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering China

ISBN: (纸本)9798350359398

Programmers often seek help from Q&A websites to resolve issues they encounter during programming. Stack Overflow has been a widely used platform for this purpose for over a decade. Recently, revolutionary AI-powered platforms like ChatGPT have quickly gained popularity among programmers for their efficient and personalized programming assistance via natural language interactions. Both platforms can offer valuable assistance to programmers, but it's unclear which is more effective at enhancing programmer productivity. In our paper, we conducted an exploratory user study to compare the performance of Stack Overflow and ChatGPT in enhancing programmer productivity. Two groups of students with similar programming abilities were instructed to use the two platforms to solve three different types of programming tasks: Algorithmic challenges, library usage, and debugging. During the experiments, we measured and compared the quality of code produced and the time taken to complete tasks for the two groups. The results show that, concerning code quality, ChatGPT outperforms Stack Overflow significantly in helping complete algorithmic and library-related tasks, while Stack Overflow is better for debugging tasks. Regarding task completion speed, the ChatGPT group is obviously faster than the Stack Overflow group in the algorithmic challenge, but the two groups have a similar performance in the other two tasks. Additionally, we conducted a post-experiment survey with the participants to understand how the platforms have helped them complete the programming tasks. We analyzed the questionnaires to summarize ChatGPT and Stack Overflow's strengths and weaknesses pointed out by the participants. By comparing these, we identified the reasons behind the two platforms' divergent performances in programming assistance. © 2023 IEEE.

关键词： ChatGPT programming Stack Overflow user study

来源：评论

学校读者我要写书评

暂无评论

Feature Recognition for Fecal Occult Blood Using Convolutional Neural Networks

Feature Recognition for Fecal Occult Blood Using Convolution...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Lee, Yi-Chuan Wu, Tin-Yu Lu, Ying-Ting Tey, Fu-Jie Liu, Deng-Ying Lin, Yu-Xiu Department of Biotechnology and Animal Science National Ilan University Yilan Taiwan Department of Management Information Systems National Pingtung University of Science and Technology Pingtung Taiwan Department of Computer Science and Information Engineering National Ilan University Yilan Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan

ISBN: (纸本)9798331521165

The incidence of colorectal cancer has been ranked number one in Taiwan for 10 consecutive years and the number of new cases continue to increase every year. According to health insurance data, the medical care costs attributable to colorectal cancer is estimated to be over NT$11 billion per year. However, early colorectal cancer may have no symptoms until it is detected by regular screening. All cancers start when damage to genes in healthy cells cause gene mutations. If damaged DNA cannot be repaired, abnormal cells grow and multiply quickly. Common colorectal cancer screening methods include the chemical fecal occult blood test (guaiac-based fecal occult blood test, known as g-FOBT) and the colonoscopy. The procedure for colonoscopy, however, is always considered unacceptable and intolerable, making early detection and treatment of colorectal cancer even more difficult. With the rapid advancement in genome sequencing technologies and the cross application of bioinformatics and big data science, the medical model of precision medicine, or personalized medicine, has emerged recently. This paper uses the Convolutional Neural Networks (CNN) to integrate spectral technology with blood feature recognition, and presents a home testing kit for quick and effective detection of fecal occult blood in complex environments. © 2025 IEEE.

关键词： Theranostics

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Pneumothorax Diagnosis and Segmentation Using Deep Convolution Neural Network

A Novel Method for Pneumothorax Diagnosis and Segmentation U...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Shanthi, S. Nirmaladevi, K. Mathiarasi, N. Tharani, As. Krithika Monisha, A. Kuppuchamy, R. Krishnamoorthy, N. Kongu Engineering College Department of Computer Science & Engineering Perundurai India PSNA College of Engineering and Technology Department of Computer Applications Tamilnadu Dindigul India Vellore Institute of Technology Department of Software Systems and Engineering Vellore Campus India

ISBN: (纸本)9798350348217

A pneumothorax is the accumulation of air in the pleural space between the chest and lungs. Air that is in the lungs during breathing can leak out of the lungs and become trapped between the chest and lungs in the thoracic cavity, causing chest pain, difficulty breathing, and ultimately the complete collapse of the taut lungs. pneumothorax. Therefore, early diagnosis and treatment should be started. Neural networks have proven effective in image classification tasks, and many researchers believe that training neural network models can detect radiologist-diagnosed chest abnormalities such as pneumonia and pneumothorax. is proving. Moreover, we utilize various techniques, including Stochastic Weight Averaging (SWA), aggressive data augmentation, and learning rate schedule. We use the chest x-ray dataset provided by the 2019 SIIM-ACR In this study, a ResNet-34 neural network is trained on a data set of chest x-rays containing over 10,675 images to create a model that predicts the presence of pneumothorax from chest *** suggested system receives a Dice Similarity Coefficient (DSC) of 0.8410 © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Optimum Estimation of Coastal Currents Using Moving Vehicles

引用

Journal of Atmospheric and Oceanic Technology 2023年第12期40卷 1431-1441页

作者： Chen, Kuanyu Huang, Chen-Fen Zheng, Zhe-Wen Lin, Sheng-Fong Liu, Jin-Yuan Guo, Jenhwa Institute of Oceanography National Taiwan University Taipei Taiwan Department of Power Vehicle and Systems Engineering National Defense University Taoyuan Taiwan Department of Earth Science National Taiwan Normal University Taipei Taiwan Department of Marine Environmental Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electrical and Computer Engineering Tamkang University New Taipei City Taiwan Department of Engineering Science and Ocean Engineering National Taiwan University Taipei Taiwan

Ocean acoustic tomography (OAT) deploys most moored stations on the periphery of the tomographic region to sense the solenoidal current field. Moving vehicle tomography (MVT), an advancement of OAT, not only samples the region from various angles for improving the resolution of mapped currents but also acquires information about the ir-rotational flow due to the sampling points inside the region. To reconstruct a complete two-dimensional current field, the spatial modes derived from the open-boundary modal analysis (OMA) are preferable to the conventional truncated Fourier series since the OMA technique describes the solenoidal and irrotational flows efficiently in which all modes satisfy the coastline and open boundary conditions. Comparisons of the reconstructions are presented using three different representations of currents. The first two representations explain only the solenoidal flow: the truncated Fourier series and the OMA Dirichlet modes. The third representation, accounting for the solenoidal and irrotational flows, uses all the OMA modes. For reconstructing the solenoidal flow, the OMA representation with the Dirichlet modes performs better than the Fourier series. A large difference appears near the bay mouth, where the OMA-Dirichlet reconstruction shows a better fit to the uniform currents. However, considerable uncertainty exists outside the bay mouth where the irrotational currents dominate. This can be improved by the third representation with the inclusion of the Neumann and boundary modes. The reconstruction results using field data were validated against the acoustic Doppler current profiler (ADCP) measurements. Additionally, incorporating constraints from ADCP measurements enhances the accuracy of the reconstruction. © 2023 American Meteorological Society.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

A Retrospective Study on Obesity to Evaluate Omnipotence of Physical Condition Feature Set

A Retrospective Study on Obesity to Evaluate Omnipotence of ...

引用

2022 IEEE International Conference on Data science and Information System, ICDSIS 2022

作者： Sengupta, Diganta Mondal, Subhash Banerjee, Susanta Navin, Harsh Meghnad Saha Institute of Technology Department of Computer Science & Engineering Department of Computer Science & Business Systems Kolkata India

ISBN: (数字)9781665498012

ISBN: (纸本)9781665498012

One of the growing medical concerns globally is obesity. The age old popular notion for the disease lies in physical conditions (PC), and eating habits (EH), leading to much observed debate for the root cause of obesity. This study establishes the omnipotence of PC over EH as a leading cause of obesity. The dataset used for the study comprised of 16 features which were divided into two feature subsets (FSS);one FSS containing 9 PC features, and the other FSS containing features related to EH. Initially obesity was classified using the complete feature dataset, followed by classification using the PC and EH FSSs respectively. Eight Machine Learning (ML) algorithms were used for the study. Regular performance metrics were used to evaluate the results. It was observed that the PC features unanimously contributed to obesity in contrast to EH features. Moreover, boosting was done using six algorithms, and results reflected that all the boosting algorithms enhanced the results. Of all the boosting algorithms, Hist-Gradient Boost generated the best results. The prime focus of the study is to analyze the major features for obesity using ML algorithms including boosting. This study computationally concludes that physical conditions have a greater impact on obesity with respect to eating habit conditions. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Network-Agnostic Voltage-to-Power Sensitivities of a Real-Time Reduced Active Distribution Network

Network-Agnostic Voltage-to-Power Sensitivities of a Real-Ti...

引用

2023 IEEE PES Innovative Smart Grid Technologies - Asia, ISGT Asia 2023

作者： Prasad, Manorath Rather, Zakir Hussain Razzaghi, Reza Doolla, Suryanarayana Indian Institute of Technology Bombay Department of Energy Science and Engineering Mumbai India Monash University Department of Electrical and Computer Systems Engineering Melbourne Australia

ISBN: (纸本)9798350327748

The advent of distribution-level phasor measurement units (D-PMUs) has enhanced the observability of active distribution networks (ADNs) and improved their energy management and control. Recently, various ADN control strategies that require detailed network parameter information have been proposed based on the voltage-to-power sensitivities of the ADN nodes. This paper proposes a new realistic approach to determining nodal voltage-to-power sensitivities of a synchrophasor measurement-based reduced ADN model. The real-time synchrophasor data dynamically updates the parameters of the reduced equivalent model to follow the time-varying operating conditions of the ADN accurately. The voltage-to-power sensitivities of the retained observable nodes are derived from the power flow Jacobian matrix using reduced equivalent model parameters. Thus, the proposed approach is agnostic about detailed line impedance data of the complex ADN. Further, the computational complexity is significantly decreased with the reduced number of nodes in the equivalent ADN model. The proposed approach has been tested on modified IEEE-33 bus benchmark system with high penetration of photovoltaic inverters using a DIgSILENT PowerFactory MATLAB co-simulation platform. © 2023 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks 39

Improving Pareto Set Learning for Expensive Multi-objective ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Nguyen, Minh-Duc Dinh, Phuong Mai Nguyen, Quang-Huy Hoang, Long P. Le, Dung D. College of Engineering and Computer Science VinUniversity Viet Nam VinUni-Illinois Smart Health Center VinUniversity Viet Nam Department of Computer Science and Engineering The Ohio State University United States Information Systems Technology and Design Singapore University of Technology and Design Singapore

ISBN: (纸本)157735897X

Expensive multi-objective optimization problems (EMOPs) are common in real-world scenarios where evaluating objective functions is costly and involves extensive computations or physical experiments. Current Pareto set learning methods for such problems often rely on surrogate models like Gaussian processes to approximate the objective functions. These surrogate models can become fragmented, resulting in numerous small uncertain regions between explored solutions. When using acquisition functions such as the Lower Confidence Bound (LCB), these uncertain regions can turn into pseudo-local optima, complicating the search for globally optimal solutions. To address these challenges, we propose a novel approach called SVH-PSL, which integrates Stein Variational Gradient Descent (SVGD) with Hypernetworks for efficient Pareto set learning. Our method addresses the issues of fragmented surrogate models and pseudo-local optima by collectively moving particles in a manner that smooths out the solution space. The particles interact with each other through a kernel function, which helps maintain diversity and encourages the exploration of underexplored regions. This kernel-based interaction prevents particles from clustering around pseudo-local optima and promotes convergence towards globally optimal solutions. Our approach aims to establish robust relationships between trade-off reference vectors and their corresponding true Pareto solutions, overcoming the limitations of existing methods. Through extensive experiments across both synthetic and real-world MOO benchmarks, we demonstrate that SVH-PSL significantly improves the quality of the learned Pareto set, offering a promising solution for expensive multi-objective optimization problems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

IoT-based Efficient Waste Management on University Campus: Enhancing Monitoring and Optimization through Machine Learning 3

IoT-based Efficient Waste Management on University Campus: E...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Sumathi, M. Hanumanthappa, J. Santhosh Kumar, K.S. Shiva Prakash, S.P. Meghana, J. Department of Studies in Computer Science University of Mysore Manasagangothri Campus Mysuru Karnataka570006 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering University of Mysore Manasagangothri Campus Mysuru Karnataka570006 India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru Karnataka570006 India Department of Computer Science Mahajana Post Graduate Center Mysuru Karnataka570016 India

The introduction of an IoT-based smart waste management system is proposed to optimize various aspects of university campus waste recycle management processes, such as garbage collection scheduling, waste type identification, and collection routes. This system utilizes advanced data analytics algorithms, wireless communication protocols, and sensors to measure and document variations in trash levels, enabling real-time monitoring of waste accumulation. Through this IoT-based infrastructure, university administrators and waste management staff gain fine-grained visibility and control over garbage collection processes. The implications for sustainability advocacy and environmental stewardship in academic environments are significant. By fostering a culture of environmental awareness and accountability, universities can instill ideals of conservation and resourcefulness in their student populations and staff. The proposed IoT-enabled waste bin system exemplifies the synergy between technological innovation and environmental responsibility, serving as a model for institutions worldwide. Collaboration among universities can leverage IoT technology to drive positive change, mitigate environmental degradation, and promote sustainable practices beyond campus boundaries. Efficient waste management is crucial for nurturing sustainability on college and university campuses, as evidenced by the urgent need for the collection and recycling of compost, general waste, and recyclables. Our models consistently achieve high performance, with perfect scores (1.000) across all split ratios, indicating flawless classification of waste types. Although the Artificial Neural Network (ANN) demonstrates slightly lower accuracy, ranging from 0.973 to 0.997 depending on data splits, it still performs well. As a result, Naive Bayes produces less accurate results, typically surpassing 0.93 but falling short of Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM)'s flawless

关键词： Electronic Waste

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Cardiovascular Disease Risk Evaluation 6

A Hybrid Approach for Cardiovascular Disease Risk Evaluation

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Sesadri, U. Jumlesha, Shaik Raju, S. Hrushikesava Adinarayna, S. Choudhury, Nabanita Jadala, Vijaya Chandra Department of CSE Vardhaman College of Engineering Telangana Hyderabad India AP Tirupati517501 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Guntur522502 India Department of Computer Science and Systems Engineering College of Engineering Andhra University Visakhapatnam531162 India Faculty of Computer Technology Assam down town University Assam Guwahati India School of Computer Science and Artificial Intelligence SR University Ananthasagar Hasanparthy Hanumakonda Telangana Warangal506371 India

ISBN: (纸本)9798331522667

Nowadays, the risk estimators are to be applied based on the population characteristics of their country, which is termed as race attribute. There were specific tools to determine the risk of cardiovascular disease. Among many diseases, the mortality rate of the people is increasing due to a lack of quality lifestyle. In order to provide a guide to the individual based on their specific characteristics and lifestyle, would classify the risk into specific categories like severe (High), Moderate, and normal(Low) with pre-defined threshold constraints. The risk assessment estimators alert the individual to control certain modifiable attributes irrespective of their non-modifiable elements. The integration of random forests and intelligent rule mining would generate the CVD risk prediction. Efficiency as well as interpretability are important in this competitive hybrid model. The ultimate benefits assured are extending the lives of the patients by knowing the importance of daily work, habits, and their control food, presenting a powerful opportunity by practicing better personalization monitoring and improved patient care, and improved informed decisions for immediate action. The early prevention initiation by identifying the risk severity optimizes follow-up of better practices and treatment styles, resulting in improved decision making for better health care of the individual. © 2025 IEEE.

关键词： Accuracy Cardio-vascular disease Efficiency Hybridization Modifiable attributes Prediction Risk estimator

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection and Classification using Emperor Penguin Optimizer (EPO) based Region Convolutional Neural Network (RCNN) 2

Plant Disease Detection and Classification using Emperor Pen...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Shanbhog, Manjula Bhatia, Neha Singh, A Swathi Pavithra, M. School of Sciences Department of Computer Science Delhi NCR India Panipat Institute of Engineering and Technology Department of Information Technology Haryana Panipat India MIT-ADT School of Computing Department of Information and Technology Maharashtra Pune India Panimalar Engineering College Department of Computer Science and Business Systems Chennai India

ISBN: (纸本)9798350384277

Agriculture stands as India's most crucial industry, despite grappling with a 35% annual loss in crop yield attributed to plant diseases. Traditionally, the detection of plant diseases has been a laborious process, hampered by insufficient laboratory infrastructure and expert knowledge. Plant disease detection methods that are automated provide a useful way to expedite the labor-intensive process of keeping an eye on large-scale agricultural fields and recognizing disease symptoms as soon as they appear on plant leaves. Current developments in deep learning (DL) and computer vision have highlighted the benefits of creating autonomous models for plant disease identification based on visible symptoms on leaves. In this study, we propose a novel method for detecting and classifying plant diseases by combining the Emperor Penguin Optimizer (EPO) with a Region Convolutional Neural Network (RCNN). The suggested methodology uses EPO to improve the discriminative power of features extracted from plant pictures, allowing for a more robust and accurate classification procedure. The Classification Region Convolutional Neural Network (RCNN) is used to leverage spatial correlations within the image, allowing for exact disease region localization. The goal of this integration is to increase the overall efficiency and dependability of plant disease detection systems. The investigations made use of the well-known PlantVillage dataset, which comprises 54,305 data of different plant disease types in 38 categories. Furthermore, an analysis was carried out in comparison with similar advanced investigations. According to the experiment results, RCNN-EPO outperformed in terms of classification accuracy, achieving 94.552%. © 2024 IEEE.

关键词： Convolutional neural networks

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：