检索结果-内蒙古大学图书馆

20th International conference on Intelligent Computing (ICIC)

作者： Zhang, Mengxiang Zhao, Qing Li, Jiaqi Liu, Tao Tianjin Univ Sci & Technol Coll Artificial Intelligence Tianjin 300457 Peoples R China

ISBN: (纸本)9789819755936;9789819755943

To enhance students' self-management skills and improve the effectiveness of online learning, and to help teachers understand each student's learning behavior, this paper proposes and designs an attention detection algorithm based on the temporal analysis of gaze direction. The algorithm aims to detect hidden distraction phenomena during online classes. The algorithm utilizes the FaceSSD face detection model and the Dlib-based facial landmark detection model to achieve the detection of students' gaze direction. It extracts real-time time-series data regarding students' gaze direction during class and applies a compressed and improved dynamic time warping algorithm for distraction detection. Furthermore, to enhance the real-time feedback capability of the system, a top student strategy is proposed to reduce the computational workload. Experimental results demonstrate that the proposed algorithm can quickly and effectively detect students' distraction phenomena, including daydreaming, distraction, and hidden activities like using mobile phones in blind spots of the camera's visual capture. This research is significant for helping teachers evaluate students' performance in online classrooms and enable intelligent monitoring of teaching quality.

关键词： classroom Hidden mind-wandering Face detection Top student strategy

来源：评论

学校读者我要写书评

暂无评论

Boosting-Based Machine Learning Approaches for Diabetes Prediction using Indian Demographic and Health Survey data 3

Boosting-Based Machine Learning Approaches for Diabetes Pred...

引用

3rd IEEE North Karnataka Subsection Flagship International conference, NKCon 2024

作者： Kallur, Shanta Yaligar, Suman Thotad, Puneeth N. Kle Institute of Technology Affiliated to Visvesvaraya Technological University Dept. of Computer Science & Engineering Hubballi580027 India Kle Institute of Technology Affiliated to Visvesvaraya Technological University Dept. of Master of Computer Applications Hubballi580027 India

ISBN: (纸本)9798350364569

Traditional diagnostic techniques are time-consuming and prone to error. Performance is added however time and cost are reduced by using computer-aided diagnostic methods. This study aims to calculate how healthy boosting-based machine learning classifiers perform in automatically identifying diabetes in the Indian context. For this experiment, Indian demographic and health survey 2021 data on women aged 19 to 79 are considered. This data includes clinical, anthropometric, and biochemical components. 12,103 of the 706,504 responders who tested positive for diabetic testing were considered. The predictive exploration-based boosting machine learning models are adopted, such as adaptive boosting, categorical boosting, extreme gradient boosting, gradient boosting, and light gradient boosting models. Kernel Principal Component analysis is employed for feature extraction. The Extreme Gradient Boosting model demonstrated strong performance on the diabetes dataset both before and after applying Kernel PCA. The metrics including accuracy, F1-score, precision, and recall for the XGBoost model showed improvements: accuracy increased from 81% to 83%, F1-score from 81% to 82%, precision from 81% to 88%, and recall from 81% to 76%.In contrast, Adaptive Boosting performed poorly, while Categorical Boosting, Gradient Boosting, and Light Gradient Boosting models achieved moderate performance levels. Overall, the model attained optimal performance across metrics such as accuracy, precision, Area Under the Curve (AUC), and recall. © 2024 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Beyond traditional sleep scoring: Massive feature extraction and data-driven clustering of sleep time series

引用

SLEEP MEDICINE 2022年 98卷 39-52页

作者： Decat, Nicolas Walter, Jasmine Koh, Zhao H. Sribanditmongkol, Piengkwan Fulcher, Ben D. Windt, Jennifer M. Andrillon, Thomas Tsuchiya, Naotsugu Monash Univ Turner Inst Brain & Mental Hlth Sch Psychol Sci Melbourne Vic Australia Monash Univ Monash Ctr Consciousness & Contemplat Studies Philosophy Dept Melbourne Vic Australia Monash Univ Monash Ctr Consciousness & Contemplat Studies Melbourne Vic Australia Univ Sydney Sch Phys Sydney NSW Australia Sorbonne Univ Paris Brain Inst CNRS Inserm F-75013 Paris France Natl Inst Informat & Commun Technol NICT Ctr Informat & Neural Networks CiNet Osaka Suita 5650871 Japan Adv Telecommun Res Computat Neurosci Labs 2-2-2 Hikaridai Seika Kyoto 6190288 Japan

The widely used guidelines for sleep staging were developed for the visual inspection of electrophysi-ological recordings by the human eye. As such, these rules reflect a limited range of features in these data and are therefore restricted in accurately capturing the physiological changes associated with sleep. Here we present a novel analysis framework that extensively characterizes sleep dynamics using over 7700 time-series features from the hctsa software. We used clustering to categorize sleep epochs based on the similarity of their time-series features, without relying on established scoring conventions. The resulting sleep structure overlapped substantially with that defined by visual scoring. However, we also observed discrepancies between our approach and traditional scoring. This divergence principally stemmed from the extensive characterization by hctsa features, which captured distinctive time-series properties within the traditionally defined sleep stages that are overlooked with visual scoring. Lastly, we report time -series features that are highly discriminative of stages. Our framework lays the groundwork for a data-driven exploration of sleep sub-stages and has significant potential to identify new signatures of sleep disorders and conscious sleep states. (c) 2022 Elsevier B.v. All rights reserved.

关键词： Sleep scoring Massive feature extraction Time -series analysis Clustering Polysomnography (PSG) Sleep physiology Electroencephalography (EEG)

来源：评论

学校读者我要写书评

暂无评论

Reproducibility Companion Paper: MeTILDA - Platform for Melodic Transcription in Language Documentation and Application 23

Reproducibility Companion Paper: MeTILDA - Platform for Melo...

引用

ACM International conference on Multimedia Retrieval (ICMR)

作者： Lee, Mitchell Lee, Chris Penmetsa, Sanjay v. Chen, Min Miyashita, Mizuki Fish, Naatosi Wu, Bo Khan, Omar Univ Washington Bothell Comp & Software Syst Bothell WA 98011 USA Univ Montana Dept Anthropol Missoula MT USA Blackfeet Community Coll Browning MT USA MIT IBM Watson AI Lab Cambridge MA USA Reykjavik Univ Reykjavik Iceland

ISBN: (纸本)9798400701788

This companion paper supports the replication of the development and evaluation of "MeTILDA - Platform for Melodic Transcription in Language Documentation and Application" that we presented in the ICMR 2021. MeTILDA aims to help document and analyze pitch patterns of endangered languages including Blackfoot, whose prosodic system is characterized by pitch movements. It develops a new form of audio analysis (termed MeT scale which is a perceptual scale) and automates the process of creating visual aids (Pitch Art) to provide more effective visuals of perceived changes in pitch movement. In this paper, we explain the file structure of the source code and publish the details of our data as well as system operations. Moreover, we provide a link to the demo video for facilitating the use of our platform.

关键词： Endangered language MeTILDA Perceptual scale Pitch Art

来源：评论

学校读者我要写书评

暂无评论

Development and Application of data analysis and visualization Software in Oil Testing Process

Development and Application of Data Analysis and Visualizati...

引用

Telecommunications and Power Electronics (TELEPE), International conference on

作者： Liqiang Wu Wanxue Jiang Zhi Chen Downhole Services Company CNPC Bohai Drilling Engineering Company Limited Renqiu Hebei China

ISBN: (数字)9798350369212

ISBN: (纸本)9798350380002

This study is devoted to the development and application of data analysis and visualization software in the process of oil testing, aiming at improving the understanding of underground reservoirs and the accuracy of reservoir development decisions. Through in-depth investigation and analysis of the requirements of geological data analysis and visualization, a powerful Oilanalysis software platform is designed and implemented, which can effectively process and analyze various types of geological data and provide intuitive and interactive visual display. The software developed in this study has flexible data import and processing functions, and can handle various geological data types including logging data, seismic data and core analysis data. At the same time, the software also integrates various data analysis and visualization algorithms, including stratigraphic modeling, porosity analysis, seismic exploration profile display and other functions, providing users with comprehensive data analysis and display tools. Through the analysis of practical application cases, the practical utility of the software in the process of oil testing is verified, which proves that it has important application value and popularization prospect.

关键词： visualization data analysis Accuracy Geology Oils data visualization Reservoirs Software Telecommunications Testing

来源：评论

学校读者我要写书评

暂无评论

User-Attention Based Product Aesthetics Evaluation with Image and Eye-Tracking Fusion data analysis 15

User-Attention Based Product Aesthetics Evaluation with Imag...

引用

15th International conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2023

作者： Xing, Baixi Song, Xinjie Chen, Qimeng Shi, Lei Pan, Yanhong Wang, Kaiqi Tang, Mengyue Industrial Design Institute Zhejiang University of Technology Hangzhou China School of Design and Architecture Zhejiang University of Technology Hangzhou China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Newcastle University Newcastle upon Tyne United Kingdom

ISBN: (纸本)9798350326178

Users' viewing behavior could affect their perception and evaluation of design works. Taking into account users' visual attention as a subjective cognition cue, we used eye-tracking evidence to identify users' focus areas for further analysis. We conducted experiments to extract the image features of design images and the reviewers' eye-tracking data, aiming to predict the product design ranking in the competition through fusion data analysis. In particular, we collected 1,504 product design images from a design competition. Four deep convolutional neural networks were selected to explore the best aesthetics computation model. The experimental results show that using design images and eye-tracking data fusion can improve the model prediction performance. Finally, MobileNet-v3 achieves the highest classification accuracy of 74.75%. This suggests the proposed method can provide useful insights into personalized aesthetics evaluation and user-centered design perception. © 2023 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

analysis of the thermal control system for the 3U CubeSat nanosatellite - "iXAYA

Analysis of the thermal control system for the 3U CubeSat na...

引用

International conference on AeroSpace Science and Technology 2023, ICASST 2023

作者： Zuñiga-Contreras, F.D. Farah-Simón, A. Ferrer-Perez, J.A. Gaviria-Arcila, D. valdés-Galicia, J.F. Sänchez-Guzmán, J.A. Romo-Fuentes, C. Ramírez-Aguilar, J.A. Chavez-Moreno, R.G. Mexico Instituto de Astronomia UNAM Mexico Centro de Alta Tecnologia Facultad de Ingenieria UNAM Campus Juriquilla Programa Espacial Universitario Mexico

In recent years, space exploration has become increasingly accessible to a diverse array of countries, facilitated in part by CubeSat nanosatellites. These versatile nanosatellites find applications in a wide spectrum of fields, from forest fire detection and meteorological observation to communication systems, particle analysis, and hot spot identification. This article delves into the outcomes of a comprehensive thermal analysis conducted on the IXAYA nanosatellite. The primary mission of this nanosatellite is to identify hot spots in the vicinity of Mexico City. The thermal analysis process entails a meticulous review of each subsystem along with the associated boundary conditions. This study commences with the definition of an optical payload and a thorough assessment of subsystem requirements. Subsequently, we calculate both external and internal thermal loads. With these foundational data points, we progress to ascertain the temperature distribution across the entirety of the satellite, ensuring that all constituent elements remain within their designated operational temperature ranges. In the closing section, we present our findings and conclusions. © Published under licence by IOP Publishing Ltd.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Building Management Systems with Distributed Intelligence 13

Enhancing Building Management Systems with Distributed Intel...

引用

13th IEEE International conference on Communication Systems and Network Technologies, CSNT 2024

作者： Rajalakshmi, B. Reddy, v venkat Malviya, Bhupendra Thethi, H Pal Praveen Adnan, Myasar Mundher New Horizon College of Engineering Department of Computer Science Bangalore India Institute of Aeronautical Engineering Hyderabad India Ies College of Technology Department of Computer Science & Engineering M. P. Bhopal India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Uttar Pradesh Greater Noida201306 India The Islamic University Najaf Iraq

ISBN: (纸本)9798350305463

There has been a significant change in the management and operation of buildings as a result of the incorporation of Distributed Intelligence into Building Management Systems. This paper analyzes the revolutionary potential of this integration, concentrating on the suggested technique, which amalgamates Decentralized Sensor Networks, Federated Learning, and Predictive Maintenance algorithms. The approach uses real-time data, machine learning, and decentralized decision-making to improve building operations. The new technique is shown to perform better on all of the most important performance criteria when compared to the six original approaches. The suggested technique greatly improves upon conventional methods with regards to energy efficiency, occupant comfort, system responsiveness, maintenance cost reduction, security effectiveness, and flexibility. It is much easier to understand the comparative analysis and how the suggested solution outperforms the separate methods by using visual representations. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions 24

Detecting Multimodal Situations with Insufficient Context an...

引用

32nd ACM International conference on Multimedia, MM 2024

作者： Liu, Junzhang Wang, Zhecan Ayyubi, Hammad You, Haoxuan Thomas, Chris Sun, Rui Chang, Shih-Fu Chang, Kai-Wei Columbia University New York United States Virginia Tech Virginia United States University of California Los Angeles Los Angeles United States

ISBN: (纸本)9798400706868

Despite the widespread adoption of vision-Language Understanding (vLU) benchmarks such as vQA v2, OKvQA, A-OKvQA, GQA, vCR, SWAG, and visualCOMET, our analysis reveals a pervasive issue affecting their integrity: these benchmarks contain samples where answers rely on assumptions unsupported by the provided context. Training models on such data fosters biased learning and hallucinations as models tend to make similar unwarranted assumptions. To address this issue, we collect contextual data for each sample whenever available and train a context selection module to facilitate evidence-based model predictions. Strong improvements across multiple benchmarks demonstrate the effectiveness of our approach. Further, we develop a general-purpose Context-AwaRe Abstention (CARA) detector to identify samples lacking sufficient context and enhance model accuracy by abstaining from responding if the required context is absent. CARA exhibits generalization to new benchmarks it wasn't trained on, underscoring its utility for future vLU benchmarks in detecting or cleaning samples with inadequate context. Finally, we curate a Context Ambiguity and Sufficiency Evaluation (CASE) set to benchmark the performance of insufficient context detectors. Overall, our work represents a significant advancement in ensuring that vision-language models generate trustworthy and evidence-based outputs in complex real-world scenarios. GitHub link: https://***/JunzhangLiu/CARA © 2024 ACM.

关键词： visual languages

来源：评论

学校读者我要写书评

暂无评论

Comprehensive and Comparative analysis between Transfer Learning and Custom Built vGG and CNN-SvM Models for Wildfire Detection 6

Comprehensive and Comparative Analysis between Transfer Lear...

引用

6th International conference on Intelligent Computing in data Sciences, ICDS 2024

作者： Jonnalagadda, Aditya v. Hashim, Hashim A. Harris, Andrew Carleton University Department of Mechanical and Aerospace Engineering OttawaONKIS-5B6 Canada

ISBN: (纸本)9798350351200

Contemporary Artificial Intelligence (AI) and Machine Learning (ML) research places a significant emphasis on transfer learning, showcasing its transformative potential in enhancing model performance across diverse domains. This paper examines the efficiency and effectiveness of transfer learning in the context of wildfire detection. Three purpose-built models-visual Geometry Group (vGG)-7, vGG-10, and Convolutional Neural Network (CNN)-Support vector Machine(SvM) CNN-SvM-Are rigorously compared with three pretrained models-vGG-16, vGG-19, and Residual Neural Network (ResNet) ResNet101. We trained and evaluated these models using a dataset that captures the complexities of wildfires, incorporating variables such as varying lighting conditions, time of day, and diverse terrains. The objective is to discern how transfer learning performs against models trained from scratch in addressing the intricacies of the wildfire detection problem. By assessing the performance metrics, including accuracy, precision, recall, and F1 score, a comprehensive understanding of the advantages and disadvantages of transfer learning in this specific domain is obtained. This study contributes valuable insights to the ongoing discourse, guiding future directions in AI and ML research. © 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：