检索结果-内蒙古大学图书馆

Deep Learning Approaches for Stress Detection: A Survey

IEEE Transactions on Affective Computing 2024年第02期16卷 499-517页

作者： Kyrou, Maria Kompatsiaris, IoannisSenior Petrantonakis, Panagiotis C. Aristotle University of Thessaloniki Artificial Intelligence and Information Analysis Laboratory Dept. of Informatics GR 54124 Greece Information Technologies Institute Centre for Research and Technology Hellas GR 57001 Greece Aristotle University of Thessaloniki Dept. of Electrical and Computer Engineering GR 54124 Greece

Stress has a severe impact on individuals irrespective of age, sex, work, or background. The reliable development of stress detection techniques enhances the social, educational, physical, economic, and professional quality of life, preventing chronic stress and proposing alleviation strategies. Research studies examine psychological, cognitive, behavioral, and physiological reactions to identify stress adequately. Deep Learning (DL) has received significant attention in recent years as it deals with high-dimensional, heterogeneous data and automatically learns representative features. This paper presents a survey on stress detection with recent DL approaches, leveraging data from all possible sources (physiological, speech, facial expressions, gestures, and social media content). The methodological outlines, the best results, and the main contributions of each study are discussed. We also describe publicly available datasets used by several of the presented works. Finally, we emphasize various open issues within the field of research and highlight key directions for future work © 2024 IEEE.

关键词： Social psychology

来源：评论

学校读者我要写书评

暂无评论

Implementing a Robust and Scalable Detect-and-Avoid Algorithm for UAV Navigation in ROS 15

Implementing a Robust and Scalable Detect-and-Avoid Algorith...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Meimetis, Dimitrios Daramouskas, Ioannis Lappas, Vaios Perikos, Isidoros Kapoulas, Vaggelis Paraskevas, Michael Nkua Department of Aerospace Science & Technology Athens Greece Computer Technology Institute and Press 'Diophantus' Patras Greece UoP Applied Mechanics Lab Patras Greece UoP Computer Engineering and Informatics Department Patras Greece Computer Technology Institute and Press 'Diophantus' University of Peloponnese Electrical and Computer Engineering Dept. Patras Greece

ISBN: (纸本)9798350368833

Unmanned aerial vehicles (UAVs) have garnered significant attention from the research community during the last decade, due to their diverse capabilities and potential applications. One of the most critical functions that drones must execute efficiently is navigation in real-world environments. This paper presents a decentralized approach for enabling unmanned aerial vehicles (UAVs) to navigate safely in unknown environments and avoid obstacles. Leveraging the Optimal Reciprocal Collision Avoidance (ORCA) algorithm, implemented in the Robot Operating System (ROS), our method facilitates conflict detection and resolution in 2D environments. Through simulations using ROS, Gazebo, and Iris drones, we validate the effectiveness of our approach in scenarios with initial trajectory conflicts. Our work addresses the pressing need for UAVs to autonomously plan and execute safe flights, laying the groundwork for enhanced UAV capabilities in various real-world applications. The simulation results demonstrate the efficiency and robustness of our approach. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

CRISP - DM Process in Smart Building Management 11

CRISP - DM Process in Smart Building Management

引用

11th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Dursun, Mahir Sabyrzhan, Moldir Gazi University Faculty of Technology Dept. of Electrical and Electronics Engineering Ankara Turkey Graduate School of Informatics Gazi University Department of Computer Science Ankara Turkey

ISBN: (纸本)9798350362541

Smart Buildings are buildings that integrate and combine intelligence, management, control, materials, and construction as a single system to meet all the needs of the building, such as comfort, energy efficiency, and durability. In universities, laboratories are used less frequently than other facilities and classrooms. Courses and students may change in the same classroom, and the period of use of such classrooms is much more extended than in laboratories. However, classrooms may only be used for classes during long breaks or for short periods of non-use between exams. In addition, there is no provision for when the heating system will start to heat up before classes or when it will be turned off after classes. By planning heating and lightning, energy and costs will be saved. This paper presents data acquisition methods for preparing a dataset to create a machine learning (ML) model to save energy loss in university laboratories. The developed model will predict energy consumption in classrooms and laboratories based on weather conditions. The study is being conducted in two stages. The first stage describes how to collect data using electronic devices such as Internet of Things (IoT) controllers of Smart Building Management Systems. The second stage gave possibilities for data analysis and preparation using the phases of the Cross-Industry Standard Process for Data Mining (CRISP-DM). © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Precision Localization: An Experimental Study on BLE Fingerprinting and Trilateration with ESP32 1

Precision Localization: An Experimental Study on BLE Fingerp...

引用

1st IEEE International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems, ICAECIS 2023

作者： Elhusseiny, Ahmed H. Zamzam, Marwa Zaghloul, Yasmine The German International University Dept. of Electrical Engineering Cairo Egypt The German International University Dept. of Informatics and Computer Science Cairo Egypt

ISBN: (纸本)9798350348057

This paper presents a method for indoor localization using two complementary techniques: Fingerprinting (FP) and Trilateration. The system is based on Bluetooth Low Energy (BLE) technology and a network of wireless anchors to determine the location of a mobile device. The FP approach collects Received Signal Strength Indicator (RSSI) data from BLE anchors in various indoor locations and creates a map of the environment in an offline stage. During the online stage, the device's location is determined by comparing its current RSSI measurements to the map. The FP technique showed an accuracy of 79.31% without positions on the other side of a separating concrete wall and 71.88% including those positions. In contrast, trilateration calculates the position of the device using distance measurements from multiple anchors, achieving an accuracy of 44.44%. Both techniques were tested in various environments and layouts, and the results indicate that FP is more suitable for indoor localization, particularly in large buildings with many rooms. This paper highlights the potential of these two techniques for practical indoor localization applications. Moreover, one of the experimental setups for the fingerprinting technique was tested in multiple rooms separated by a concrete wall to provide information about the potential scalability of the technique. © 2023 IEEE.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Velocity-aided Channel Estimation for Spatially Selective mmWave Massive MIMO Communications 31

Velocity-aided Channel Estimation for Spatially Selective mm...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Vlachos, Evangelos Mavrokefalidis, Christos Berberidis, Kostas Industrial Systems Institute ATHENA Research Center Patras Greece Dept. of Computer Engineering and Informatics University of Patras Patras Greece

ISBN: (纸本)9789464593600

This paper focuses on addressing the challenge of estimating multiple-input multiple-output (MIMO) channels for wireless communication between a ground base-station and a moving vehicle. One recently recognised model for time-varying channels incorporates spatial selectivity, which is referred to as beam squint, and is particularly relevant in the millimeter-wave (mmWave) range. In such scenarios, it is essential to account for the beam squint when attempting to recover channel parameters using a training sequence. However, the use of a training sequence alone may be insufficient for this purpose. To overcome this issue, in this work, we propose a channel estimation approach that exploits information provided by the control module of the vehicle, namely its velocity. The estimation problem that is designed, regards the channel both in a parametric and a non-parametric form and the alternating direction method of multipliers is utilised to efficiently solve it. It is demonstrated via simulations that considerable gains can be achieved if information from the control unit of the vehicle can be appropriately introduced and exploited. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Cooperative Five Degrees of Freedom Motion Estimation for A Swarm of Autonomous Vehicles 48

Cooperative Five Degrees of Freedom Motion Estimation for A ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Piperigkos, Nikos Lalos, Aris S. Berberidis, Kostas Anagnostopoulos, Christos University of Patras Computer Engineering and Informatics Dept Rion Patras Greece Industrial Systems Institute Athena Research Center Patras Greece

ISBN: (纸本)9781728163277

In this paper, we propose a novel cooperative-based system that facilitates each autonomous vehicle of the swarm to be fully aware of its 5 degrees of freedom (DOF) motion, i.e., 3D translation and 2D rotation, a very important task for autonomous navigation, known also as simultaneous localization and mapping (SLAM). The novelty is that the interconnected vehicles of the swarm share a common collective task: simultaneously estimating self and neighboring vehicles' 5 DOF by perceiving, transmitting, associating and fusing heterogeneous data, e.g., visual, mechanical, satellite based, etc., relying on different sensor modalities and vehicular communication. The proposed sensor fusion framework is based on the Extended Kalman Filter algorithm, which is reformulated in order to capture cooperative 3D translation and 2D rotation estimation in an alternating fashion. Numerical results using the driving parameters of many cars from CARLA simulator, indicate very promising accuracy in terms of absolute trajectory error. © 2023 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cabbage Plant Protection: CNN Algorithm for Insect Identification

Enhancing Cabbage Plant Protection: CNN Algorithm for Insect...

引用

2024 International Conference on Information Technology Research and Innovation, ICITRI 2024

作者： Senjaya, Remi Musa, Purnawarman Sularsih, Puji Novrina, Novrina Aryunani, Witari Suhartini, Suhartini Gunadarma University dept. of Informatics Engineering Depok Indonesia Gunadarma University dept. of Electrical Engineering Depok Indonesia Gunadarma University dept. of Information Technology Depok Indonesia Gunadarma University dept. of Computer Science Depok Indonesia

ISBN: (纸本)9798350376210

People frequently find it straightforward to identify insects that feed on cabbage plants based on the insects' characteristics. However, challenges arise when employing a computer for precise bug categorization and identification. The implementation of Deep Learning (DL) utilizes the Convolutional Neural Network (CNN) technique, renowned for its effectiveness in categorizing and recognizing objects in digital photo data. The CNN algorithm delivers notable results in photo identification, simulating the human visual brain's image recognition through artificial neural networks in the Python programming language. To enrich the user experience, frameworks like Keras and TensorFlow are employed in neural network development. Our research will use the CNN algorithm to determine insect species in cabbage images. Achieving high accuracy involves coupling the CNN algorithm with the VGGNet architectural model. Notably, utilizing an epoch value of 150 resulted in a 97.75% accuracy rate during the training model technique;however, the validation accuracy was slightly lower at 94.25%. The corresponding loss and validation rates were 0.0613% and 0.2945%, respectively. Moreover, based on the model (150 epochs), the testing outcomes in the study, involving 48 images beyond the dataset and incorporating additional information, resulted in an accuracy rate of 91.66%. © 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

Breast Cancer Prediction Using Random Forest and Gaussian Naïve Bayes Algorithms 1

Breast Cancer Prediction Using Random Forest and Gaussian Na...

引用

1st International Conference on Information System and Information Technology, ICISIT 2022

作者： Sulistiani, Ita Wulandari, Windu Astuti, Fathia Dwi Widodo State University of Jakarta Dept. of Informatics and Computer Engineering Education Jakarta Indonesia

ISBN: (数字)9781665402002

ISBN: (纸本)9781665402002

Breast cancer is the second deadliest cancer after lung cancer. In 2021, ASCO-American Society of Clinical Oncology states that female invasive breast cancer increased by half a percent from 2008 to 2017. Breast cancer is induced by a misspelling of a cell, which causes the cell to become uncontrollable. If the problem is not treated soon within a few months, a large number of cells containing the wrong instructions can be detected as cancer. Machine learning has been widely used for developing breast cancer prediction models. Unfortunately, the problem of imbalanced datasets tends to have little to no attention in previous research using machine learning. This research aimed to develop breast cancer prediction models using Random Forest and Gaussian Naïve Bayes Classifier. Borderline Synthetic Minority Oversampling Technique (BSM) is applied to handle the imbalanced dataset problem;meanwhile, machine learning algorithms such as Random Forest and Gaussian Naïve Bayes algorithms were used to build the prediction models. Using UCI Machine Learning Wisconsin Breast Cancer Dataset (WBCD), the combination of BSM and Random Forest algorithm showed the highest recall score, approximately around 99.8%. Meanwhile, the BSM and Gaussian Naïve Bayes Classifier combination provided the lowest recall score among generated models, 78.2%. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Human Gender Detection from Facial Image using Global and Local Feature

Human Gender Detection from Facial Image using Global and Lo...

引用

2022 International Conference on Electrical and Information Technology, IEIT 2022

作者： Ningrum, Lusiana Diyan Dewantara, Bima Sena Bayu Sari, Dewi Mutiara Politeknik Elektronika Negeri Surabaya Dept. of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665453035

ISBN: (纸本)9781665453035

Identifying gender is frequently difficult when physical characteristics show different facts, which can lead to public controversy. This paper describes a method for determining a person's gender solely based on physical characteristics, particularly facial shape and features. The method used combines global and local facial features. Face landmark detection is a global feature that displays a face's shape or contour in 2D. While the Histogram of Oriented Gradient (HOG) is a local feature that shows the detailed shape of facial components like eyebrows, eyes, nose, and mouth. The combined information from global and local features is fed into the Support Vector Machine (SVM) and classified as male or female. Based on the experimental results, our system was able to identify gender with an accuracy of 80% with an average F-measure is 0.8. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation for Fitness Exercise Movement Correction 24

Human Pose Estimation for Fitness Exercise Movement Correcti...

引用

24th International Electronics Symposium, IES 2022

作者： Rahmadani, Atharian Dewantara, Bima Sena Bayu Sari, Dewi Mutiara Politeknik Elektronika Negeri Surabaya Dept. of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

Based on computer vision technology, this research suggests an application to identify and assess a fitness practitioner's movements. Several fitness movements such as lifting weights, squat jumps, and pull-ups that are very beneficial for health and body fitness become the main movement for body building. However, those kinds of activities may be very dangerous if done incorrectly. Based on the problem, we developed an application based on computer vision to recognize and correct the pose accuracy of fitness practitioners by using input in the form of videos that record the movements of fitness practitioners continuously. To categorize the many forms of fitness sport movements, this system uses the support vector machine (SVM) method. On the monitor screen, the classification results will be visible. The result shows that the accuracy of the system is 96.87% by using SVM with the Radial Basis Function (RBF) kernel type and can make corrections to four types of fitness movements with a testing accuracy of 90.62%. © 2022 IEEE.

关键词： Sports

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：