检索结果-内蒙古大学图书馆

Conference on Software engineering Education & Training (CSEE&T)

作者： Muhammet Mustafa Olmez Edward Gehringer Dept. of Electrical and Computer Engineering North Carolina State University Raleigh NC USA Dept. of Computer Science North Carolina State University Raleigh NC USA

ISBN: (数字)9798350378979

ISBN: (纸本)9798350378986

In addressing the need for test case generation in software projects and the validation and repair processes, various algorithms and AI models are increasingly being applied with novel approaches. On the other hand, despite the established effectiveness of the Test-Driven Development (TDD) approach in testing and development, there is still a lack of research examining the impact of human-machine interaction on software validation and coding. This paper introduces a tool, the test-skeleton generator, which utilizes an OpenAI model to generate test skeletons. These skele-tons include test names, signatures, and scenario descriptions, omitting the actual test bodies. To explore the implications of this tool, an empirical experiment involving student participation was conducted to assess the conversion of test skeletons into functional tests with human-machine interaction. The study reveals significant insights, indicating that human-machine interaction plays a crucial role in shaping both the testing and programming phases, encouraging students to prioritize writing tests before modifying source code. Teams adopting this approach demonstrate a tendency to produce more tests, leading to higher code coverage. Additionally, our research underscores the growing potential of AI language models to generate tests that closely resemble those written by human developers. Notably, human-machine interaction has proven its significant positive impact on the validation and repair process of AI -generated tests.

关键词： Human computer interaction Source coding Human-machine systems Software algorithms Maintenance engineering Writing Programming

来源：评论

学校读者我要写书评

暂无评论

Machine-Learning Object Detection and Recognition for Surveillance System using YoloV3 1

Machine-Learning Object Detection and Recognition for Survei...

引用

1st International Conference on electrical, Electronics, Information and Communication Technologies, ICEEICT 2022

作者： Soma, Shridevi Waddenkery, Nischita Poojaya Dodappa Appa College of Engineering Dept. of Computer Science and Engineering Karnataka Kalburagi India

ISBN: (纸本)9781665436472

Intelligent Video surveillance is one of the most emerging technologies in computer vision, used for object detection and locating within the video or image. Majority of the research are carried on the Yolo algorithm on vehicle tracking, monitoring vehicles, and medical science. The main objective of this paper is to develop an optimal solution to detect, locate multiple objects such as person and vehicles in a single frame using Kitti dataset. Usually the kitti data set focuses on foreground vehicle detection;in the proposed algorithm it detects person, vehicle and also the background objects. The output obtained for every image includes the information of object such as probability, classification of the object, bonding box, object center (x, y coordinates), height, width using Non-Maximum Suppression (NMS) algorithm. The Kitti dataset of 350 images is used and it is observed that classification rate is 80% at 0.3 confidence threshold value over bounding boxes pixel area for vehicle and person detection. This work can be further carried out in detecting and tracking of objects at different weather conditions like rainy, winter and also during night. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Parkinson's Disease 4

Automated Detection of Parkinson's Disease

引用

4th International Conference on Recent Trends in computer science and Technology, ICRTCST 2021

作者： Sharma, Shivani Singh, Pratima Ajay Kumar Garg Engineering College Dept. Of Computer Science & Engineering Uttar Pradesh India

ISBN: (纸本)9781665466332

The prognosis of Parkinson's disease is one of the maximum critical hassles that must be investigated in the early levels of the graduation of the disorder to be able to lessen the disorder development rate of the various individuals. Tracking Parkinson's disease (PD) symptom development frequently makes use of UPDRS ratings, which calls for the affected person's presence in the clinic, and time-ingesting bodily examinations via way of means of the skilled medical team of workers. Thus, symptom tracking is high-priced and logistically inconvenient for the affected person. Here, for the primary time, we have made a system that could detect PD in few minutes rapidly with clinical accuracy by conducting speech tests, tremor tests and handwriting tests and hence further predict stage of the disease. This model will make a foundation in telemonitoring frameworks converting wide-ranging medical trials into rapid PD treatments. Thus, our study will focus on finding the best model to provide an automated method to extract the necessary biomarkers which will help in the prediction and classification of Parkinson's disease into stages. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT Based Weather Station Prototype with CRHUDA Algorithm and Regression for Rain Prediction 11

IoT Based Weather Station Prototype with CRHUDA Algorithm an...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Ramelan, Agus Sulistyo, Meiyanto Eko Kiswanto Rohmani, Rahmat Sukriyandoko, Ivan Abdhira Muharman, Arya Zifa Latifah, Ayu Universitas Sebelas Maret Dept. of Electrical Engineering Surakarta Indonesia Infrastructure and Research Assurance Telkom Indonesia Bandung Indonesia Institut Teknologi Garut Departement of Computer Sciences Garut Indonesia

ISBN: (纸本)9798350389654

Fast and accurate rainfall predictions are needed to improve preparedness for climate change. This work applies Internet of Things (IoT) technology in real-time weather monitoring prototype through the development of an Automatic Weather System (AWS). This system utilizes Arduino Uno, ESP8266, DHT-22, and BMP180 to measure temperature, humidity, and air pressure, and integrates IoT infrastructure for more accurate data collection. The collected data is used in the CRHUDA (Crossing Humidity, Dewpoint, and Atmospheric pressure) model to determine the starting point for rain formation based on the intersection of humidity and air pressure. This model is strengthened by a multiple linear regression algorithm which is refined with the Kalman Filter for more accurate rainfall estimates. The results show that the CRHUDA model and linear regression technique are able to predict rainfall patterns effectively, although the accuracy of the regression model is lower in mild weather conditions. © 2024 IEEE.

关键词： Atmospheric pressure

来源：评论

学校读者我要写书评

暂无评论

Implementation of Multiple Discriminant Analysis (MDA) for Clustering Smart Village in West Java Based Podes (Potensi Desa) Database 4

Implementation of Multiple Discriminant Analysis (MDA) for C...

引用

4th International Conference on Informatics, Multimedia, Cyber and Information System, ICIMCIS 2022

作者： Tosida, Eneng Tita Solihin, Indra Permana Jayawinangun, Roni Ardiansyah, Deden Pakuan Univeristy Computer Science Dept. Bogor Indonesia Upn Veteran Informatic Dept. Jakarta Indonesia Pakuan University Communication Science Dept. Bogor Indonesia Pakuan University Computer Engineering Dept. Bogor Indonesia

ISBN: (纸本)9781665473279

Village development is accelerated through the smart village program. Village development in Indonesia, including West Java Province, is measured using the Developing Village Index (IDM). The 50 villages that are the locus of smart villages in West Java Province consist of three statuses, namely underdeveloped, developing and advanced. By using clustering using Multiple Dicriminant Analysis (MDA), this study try to identify smart village locus indicators based on the Village Building Index (IDM) based on Village Potential Data and classify them based on their status. The results of the smart village clustering in West Java province show that the smart village program can be adopted by villages with a lagging village index (IDM) level of 12%. Nine predictors were found to distinguish intelligent villages with lagging, developing and independent status, namely Public places, hospitals, pharmacies, community activities, security posts, banks & financial institutions, agricultural stores and Sewerage Treatment. This condition is a very interesting finding because it breaks the assumption that smart villages can only be adopted by villages with a minimally developed IDM level. The results of smart village clustering based on village potential data also show that smart village clusters are dominated by developing IDM-level villages. The multiple discriminant-based clustering model was carried out through two alternative models, and one of the models was able to show a canonical correlation of 0.906. © 2022 IEEE.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Medical Image Classification Based on Feature Ensembling using DeepNets 9

Multi-Class Medical Image Classification Based on Feature En...

引用

9th International Conference on Computing for Sustainable Global Development, INDIACom 2022

作者： Asharani Kagolanu, Venkata Srilakshmi Thimmareddy, Lakshmi Kanala, Kavitha Lakshmi Sirisha, B. Maturi Venkata Subba Rao Engineering College Dept. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9789380544441

Medical image classification plays a key role in computer-aided detection and diagnosis systems. Conventional machine learning, neural network-based approaches strongly depends on the type of features i.e. texture, edge, shape, and/or blob along with their amalgamations, extracted from the medical image. Since most of the feature extraction algorithms are specific to the modalities and problem. The machine learning or neural network-based model built using these features lack- of generalization and high-level problem representation ability. Deep Learning (DL) methods based on deep features deliver an active way to build an edge-to-edge model which has the ability to reckon the classification labels with the input raw pixels of medical domain images. Due to the unavailability of massive medical data, high noise rate, and resolution of medical images, DL approaches grieve in terms of classification rate. To improve the classification rate, we propose to fuse the contemporary features (high-level features) extracted from a deep convolution neural network (DCNN) and conventional texture features. The building of the planned model comprises the subsequent steps. Firstly, DCNNs (MobileNet, GoogelNet, and Resnet.) are trained as feature extractors, and the feature vectors are extracted. Second, we extract the traditional texture features of medical images. Lastly, we fuse the deep features and texture features which represent robust high-level features for medical image classification. We assess the proposed method on standard medical image benchmark datasets: MEDMNIST We attain classification accuracy of 99.1%, experimental results confirm that fusing texture features and deep learning features results in the increase of accuracy of medical image classification. © 2022 Bharati Vidyapeeth, New Delhi.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Real-time Human Movement Recognition and Interaction in Virtual Fitness using Image Recognition and Motion Analysis 12

Real-time Human Movement Recognition and Interaction in Virt...

引用

12th International Conference on Awareness science and Technology, iCAST 2023

作者： Yeh, ChunHsiu Shen, Wei-Cheng Ma, Chi-Wei Yeh, Qiu-Tong Kuo, Chung-Wei Chen, Jong-Shin Dept. of Information Engineering Computer Science Feng Chia University Taichung Taiwan CollegeofComputerScience Jimei University Xiamen China Dept. of Information Communication Engineering ChaoYang University of Technology Taichung Taiwan

ISBN: (纸本)9798350324693

This research focuses on the application of image recognition, motion detection, and artificial intelligence techniques to achieve real-time identification and analysis of human movements in a dynamic manner. The primary goal is to establish a seamless association between captured human movements and corresponding actions performed by virtual avatars. The implementation involves the utilization of image processing methodologies from python's OpenCV and pygame libraries. MediaPipe technology is employed to capture users' images and facilitate accurate detection of specific movement patterns. By calculating the angles between users' limbs and torso, the correctness of certain movements can be assessed. The research is practically developed and applied to a simulated fitness system, where an interactive exercise game platform is devised. The system is characterized by its engaging user interface, enhancing the ease and enjoyment of fitness activities. The seamless integration of interactive virtual avatars and real users within physical activities serves to stimulate greater participation, particularly among the elderly. The amalgamation of image recognition and motion detection technologies presents opportunities for combining fitness and entertainment in diverse life scenarios, offering an enhanced experience of physical exercise and enjoyment. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

STABILIZING THE KUMARASWAMY DISTRIBUTION

arXiv

引用

arXiv 2024年

作者： Wasserman, Max Mateos, Gonzalo Dept. of Computer Science University of Rochester RochesterNY14620 United States Dept. of Electrical and Computer Engineering University of Rochester RochesterNY14620 United States

Large-scale latent variable models require expressive continuous distributions that support efficient sampling and low-variance differentiation, achievable through the reparameterization trick. The Kumaraswamy (KS) distribution is both expressive and supports the reparameterization trick with a simple closed-form inverse CDF. Yet, its adoption remains limited. We identify and resolve numerical instabilities in the inverse CDF and log-pdf, exposing issues in libraries like PyTorch and TensorFlow. We then introduce simple and scalable latent variable models based on the KS, improving exploration-exploitation trade-offs in contextual multi-armed bandits and enhancing uncertainty quantification for link prediction with graph neural networks. Our results support the stabilized KS distribution as a core component in scalable variational models for bounded latent variables. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling of Weight Perception Based on Subjectivity by Considering Individual Differences

Modeling of Weight Perception Based on Subjectivity by Consi...

引用

International Symposium on Soft Computing and Intelligent Systems (SCIS)

作者： Daisuke Kushida Kei Nakajima Dept. Electrical Engineering and Computer Science Faculty of Engineering Tottori University Tottori Japan Dept. Engineering Graduate School of Sustainability Science Tottori University Tottori Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

The minimum amount of perception that humans can perceive is called the stimulus threshold. This study aims to clarify the stimulus threshold of weight perception for the biceps brachii muscle based on a method of constant stimuli. In general, the stimulus threshold depends on the individual. The authors consider that physical characteristics are related to individual differences, construct a model of the relationship between physical characteristics and stimulus thresholds, and attempt to estimate stimulus thresholds from physical characteristics. The constructed model is evaluated via cross-validation and found to be able to estimate stimulus thresholds from physical characteristics with an 85% accuracy.

关键词： Accuracy Predictive models Muscles Load modeling

来源：评论

学校读者我要写书评

暂无评论

The Integration of 6G and Blockchain into an Efficient AIoT-Based Smart Education Model 6

The Integration of 6G and Blockchain into an Efficient AIoT-...

引用

6th World Symposium on Communication engineering, WSCE 2023

作者： Lioupa, Anna Memos, Vasileios A. Stergiou, Christos L. Ishibashi, Yutaka Psannis, Konstantinos E. School of Information Sciences University of Macedonia Dept. of Applied Informatics Thessaloniki Greece Graduate School of Engineering Nagoya Institute of Technology Dept. of Computer Science Nagoya Japan

ISBN: (纸本)9798350339505

The technological advances impact the future classrooms and the whole education system. The evolution of 6G promises faster speeds based on terahertz, wireless communication, the leverage of artificial intelligence (AL), virtually reality (VR) and generally a fully connected world. The use of applications of IoT and AIoT improves the education environment, but the intelligent network services undoubtedly gather, store and analyze big data which are vulnerable to attackers. As a solution we may consider the technology of blockchain. The trust and security of next generation intelligent networks are essential part of their design. In this article we suggest a data security system based on blockchain for AL applications in 6G networks. First, we present two Al-enabled applications, indoor positioning and mobile payment within the framework of 6G in the university area. We present the efficiency of blockchain in data security for Al-enabled systems using two case studies of indoor positioning system and mobile payment. The 6G system which is fully supported by Al and the integration of this in technology of blockchain, is ensured the security in future wireless communication. © 2023 IEEE.

关键词： Blockchain

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：