检索结果-内蒙古大学图书馆

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Tsuchiya, Yoshihiko Suga, Norisato Uruma, Kazunori Fujisawa, Masaya Tokyo University of Science Dept. of Information and Computer Technology Tokyo Japan Shibaura Institute of Technology Dept. of Information and Communication Engineering Tokyo Japan Kogakuin University Dept. of Computer Science Tokyo Japan

ISBN: (纸本)9798350355079

Intelligent Reflecting Surfaces (IRS) is attracting attention for wireless communications at high-frequency band. IRS can control radio propagation by reflecting radio waves and shifting their phase. As one of the methods to control IRS, location-based methods have been proposed. However, to achieve highly accurate IRS control by the methods, the assumed propagation model must match the actual propagation environment. This study proposes a method to control the IRS from location information adapted to the propagation environment by using machine learning. Numerical experiments confirm that the proposed method can appropriately control IRS regardless of the propagation environment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning Algorithms in Edge Intelligence for Ultra-Reliable and Low-Latency Communications in the Industrial Metaverse 29

Using Machine Learning Algorithms in Edge Intelligence for U...

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Mohammadvand, Reza Mozayani, Naser Dept. Computer Engineering Iran University of Science and Technology Tehran Iran

ISBN: (纸本)9798331523114

Given the rapid advancements in technologies such as the metaverse and digital twins, the need for effective integration of communication, computation, and storage in complex systems and edge computing environments is becoming increasingly apparent. This paper proposes an architecture to support an industrial metaverse based on digital twins that optimizes resources by leveraging mobile edge computing and ultra-reliable low-latency communication. This architecture reduces latency by employing task offloading and storage methods on nearby edge servers, meeting the precise requirements of future metaverses in terms of reliability and latency minimization. The proposed model, utilizing reinforcement learning algorithms such as Deep Q-Network (DQN), Double Deep Q-Network (DDQN), and Dueling Double Deep Q-Network (Dueling DDQN), is capable of achieving adaptability in dynamic conditions and making intelligent decisions. The simulation results demonstrate that the proposed method reduces by more than 10% on average compared to the best method available in the literature and improves resource utilization efficiency. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Ensembled Obstructive Sleep Apnea Detection Using Extra Tree Ensemble Technique 2

Ensembled Obstructive Sleep Apnea Detection Using Extra Tree...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Khan, Atiya Biswas, Saroj Kr. Chunka, Chukhu Barman, Subhas National Institute of Technolgy Silchar Dept. of Computer Science & Engg. Silchar India Jalpaiguri Government Engineering Collage Dept. of Computer Science & Engg West Bengal India

ISBN: (纸本)9798350371314

Obstructive Sleep Apnea (OSA) is a sleep-related disorder with repetitive episodes of complete or partial upper airway obstruction during sleep. These episodes result in disrupted breathing patterns and reduced oxygen levels in the blood. Electroencephalogram is a valuable tool in detecting and diagnosing sleep apnea as it provides insights into the disruptions of sleep caused by repeated apnea events. This paper proposes an efficient model to detect OSA named Ensembled Expert System for Obstructive Sleep Apnea Detection (EESOSAD) using EEG physiological sensors and an Extra Tree ensemble classifier. The proposed model incorporates Discrete Wavelet Transform with Daubechies order-8 for decomposing EEG signal into multiple sub-bands and extracting statistical features like - Maximum, Minimum, Mean, Standard Deviation, Kurtosis, Power, Energy, Root Mean Square, and Variance. A state-of-the-art data preprocessing pipeline is also designed and developed for treating corrupted, missing, duplicates, and outliers, as medical data are prone to noise, anomalies, and inconsistencies that can distort patterns and compromise analysis validity. Finally, for the classification task, the Extra Tree ensemble classifier is used for OSA detection to comprehensively evaluate the performance of the developed data pre-processing and feature fusion pipeline. Multiple evaluation metrics, including Precision, Recall, Accuracy, F1-score, and AUC-ROC curve, have been employed to compare and assess the model's effectiveness. Furthermore, diverse state-of-the-art ensemble learning models have been incorporated for benchmark comparison and discussion. The proposed EESOSAD model achieved an average accuracy of 59% and outperformed multiple benchmark models with an optimal performance margin. © 2024 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Explainable AI-based Detection and Interpretation of Abnormalities in Chest X-rays 3

Explainable AI-based Detection and Interpretation of Abnorma...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Muthukumar, Sai Smrithi Gandham, Bhavika Vijayekkumaran, Trisha Jyotsna, C. Aiswariya Milan, K. Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331523893

Chest X-ray images are widely used in diagnosing medical conditions, however, due to radiologist fatigue and shortage of resources the possibility of spotting peculiarities increases. This work proposes an explainable AI system to identify, quantify, and explain the pathology found in chest x-ray images. It builds credibility, enhances medical judgment, and reflects efficient utilization of radiology assets. This study used ResNet for the chest X-ray image classification and compared it with other related models like EfficientNetB0, DenseNet, VGGNet, and MobileNet. ResNet had the best AUC value of 0.826 thereby garnering it the best classification accuracy hence validating its selection as the main model. Moreover, ResNet adapted explainability to provide visual and textual interpretations and to classify diseases where such actionable insights could improve the reliability of diagnosis and patient outcomes. © 2025 IEEE.

关键词： CheXpert Explainable AI Grad-CAM ResNet X-ray masks X-rays

来源：评论

学校读者我要写书评

暂无评论

Enhancing Solar Energy Efficiency: A Deep Learning Approach for Dust Detection

Enhancing Solar Energy Efficiency: A Deep Learning Approach ...

引用

2024 International Conference on Smart Electronics and Communication Systems, ISENSE 2024

作者： Vigna Harish, R. Ramya, A. Siva, S. Santhi, S. Kalaiselvi, S. Anitha, V. National Engineering College Dept. of Information Technology Tuticorin India National Engineering College Dept. of Computer Science and Engineering Tuticorin India

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528126

In recent decades, power generation from PV systems has become increasingly popular. However, several environmental variables, such as dust deposition on PV panels, have significantly reduced PV energy production. Several approaches are under investigation to identify dust and decrease power loss. These include thermal imaging, image processing, sensors, and IoT devices, machine learning, and deep learning. The orientation of a solar panel and the angular inclination relative to the horizontal plane affect one of the environmental factors that impact its performance: since they have an impact on how much solar energy that enters into the photovoltaic panel's surface. Dust, for one, is another example of environmental factors: the quantity of energy output can be influenced by coming into contact with dust. Dust particles lying on the panel's surface have the potential to reduce light from reaching the solar modules, which would drastically reduces the energy output. Cleaning or reducing modules is critical, but these procedures must be continuously monitored and assessed for their effects. Image processing algorithms can be used to detect dust to optimize solar panels. In this paper, a novel dataset from Kaggle comprising images of dusty and clean solar panels is presented, aiming to facilitate the research on automated dust detection algorithms. The dataset is utilized to evaluate the performance of existing state-of-the-art (SOTA) image classification methods. Subsequently, a new Convolutional Neural Network (CNN) architecture, ResNet-50 with an additional attention mechanism, is proposed, specifically designed for solar panel dust detection. The experimental results shows that the proposed method outperforms other SOTA algorithms, achieving an accuracy level of 96.2%. © 2024 IEEE.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Remote-Controlled Raft for Enhanced Water Quality Assessment 20

IoT-Enabled Remote-Controlled Raft for Enhanced Water Qualit...

引用

20th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2024

作者： Surasak, Thattapon Kitchat, Kotcharat Jiteurtragool, Nattagit King Mongkut's University Of Technology North Bangkok Faculty Of Applied Science Dept. Of Computer And Information Science Bangkok Thailand National Central University Dept. Of Computer Science And Information Engineering Taoyuan Taiwan

ISBN: (纸本)9798350382310

Water is vital for all life, serving as the foundation for plants and aquatic creatures and promoting abundance among all living beings. This study introduces an innovative approach by combining the Internet of Things (IoT) with advanced sensing techniques to assess water quality. The IoT-powered water quality testing raft has been developed to significantly enhance the monitoring capabilities. Equipped with sensors measuring key parameters such as turbidity, pH, and temperature, the raft provides a comprehensive understanding of water quality. Its GPS module enables real-time tracking and maintains location history, ensuring precise sampling. The collected data undergoes robust processing by a Raspberry Pi, ensuring integrity before being showcased on the Thingsboard. The system's uniqueness lies in its capacity to promptly issue alerts via LINE Notify upon detecting water quality abnormalities, ensuring timely intervention. This IoT-powered raft represents a paradigm shift in water quality assessment, characterised by its precision, remote capabilities, and user-focused approach. Practical applications have been demonstrated through real-world testing in a private lake in Cha-choengsao province, Thailand. The seamless integration of IoT into environmental monitoring marks a significant advancement in ensuring water quality and ecosystem health. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Suitable and Style-Consistent Multi-Texture Recommendation for Cartoon Illustrations

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2024年第7期20卷 1-26页

作者： Wu, Huisi Wang, Zhaoze Li, Yifan Liu, Xueting Lee, Tong-Yee College of Computer Science and Software Engineering Shenzhen University No. 3688 Nanhai Road Nanshan District Guangdong Shenzhen518060 China Dept. of Computer Science and Information Engineering National Cheng-Kung University No. 1 University Road Tainan70101 Taiwan

Texture plays an important role in cartoon illustrations to display object materials and enrich visual experiences. Unfortunately, manually designing and drawing an appropriate texture is not easy even for proficient artists, let alone novice or amateur people. While there exist tons of textures on the Internet, it is not easy to pick an appropriate one using traditional text-based search engines. Although several texture pickers have been proposed, they still require the users to browse the textures by themselves, which is still labor-intensive and time-consuming. In this article, an automatic texture recommendation system is proposed for recommending multiple textures to replace a set of user-specified regions in a cartoon illustration with visually pleasant look. Two measurements, the suitability measurement and the style-consistency measurement, are proposed to make sure that the recommended textures are suitable for cartoon illustration and at the same time mutually consistent in style. The suitability is measured based on the synthesizability, cartoonity, and region fitness of textures. The style-consistency is predicted using a learning-based solution since it is subjective to judge whether two textures are consistent in style. An optimization problem is formulated and solved via the genetic algorithm. Our method is validated on various cartoon illustrations, and convincing results are obtained. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Cardiomegaly Detection Using Deep Learning 4

Cardiomegaly Detection Using Deep Learning

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Suganthi, S.U. Sivabalan, A. Akash, M.V. Barath, B. Goushik, G. Anto Akash, P. Sri Sairam Institute of Technology Dept. of Artificial Intelligence And Data Science Tamil Nadu Chennai India Sri Sairam Engineering College Dept. of Artificial Intelligence And Data Science Tamil Nadu Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

This research introduces an innovative method for forecasting cardiomegaly, a common heart condition marked by an enlarged heart, by combining deep learning and machine learning methods. Using the ResNet50 architecture, we examine chest X-ray images to identify cardiomegaly indications. At the same time, a Random Forest algorithm analyses clinical data in a table format, such as age, gender, and different cardiac indicators, to improve prediction accuracy. Our approach combines these models to use unstructured images and structured health data, resulting in a comprehensive diagnostic tool. The data, collected from public health databases, was carefully labelled to guarantee accurate training and validation. Preliminary results showed the promising accuracy of the hybrid model, surpassing individual approaches, and demonstrating the potential of integrated models to improve diagnostic capabilities in cardiology. This study helps improve medical imaging and predictive analytics in healthcare, providing a productive solution for early detection and management of cardiomegaly. The results highlight the promise of combining AI models to change diagnostic methods and enhance patient results. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Secured Release through an Agile Security Growth Framework 29

Secured Release through an Agile Security Growth Framework

引用

29th ISSAT International Conference on Reliability and Quality in Design, RQD 2024

作者： Bhattacharya, Saikath Williams, Laurie Singh, Munindar P. Electrical Engineering and Computer Science Milwaukee School of Engineering Milwaukee United States Dept. of Computer Science North Carolina State University Raleigh United States

ISBN: (纸本)9798986576138

Software development teams need to produce and assess secure software products so that they can perform critical functionality. Because no software product can ever be "perfectly secure, " development teams need to decide when a software product is "secure enough" to be released, that is, to make a decision on the product’s release readiness. The goal of this paper is to aid software practitioners in predicting whether a software product is "secure enough" to be released through the evolution and evaluation of software security growth models (SSGM). In this paper, we adapt and evolve software reliability growth models (SSGMs) for the purpose of SSGM using empirical software vulnerability analysis. We quantitatively compare the quality of agile software versions by comparing the security correction and detection process over testing time and software testing cost. The framework is generic to incorporate software vulnerability data into different time frames and multiple agile software versions. We evaluated our SSGM using data from Google Chromium, which uses an agile process with releases every 50 days. © Conference Proceedings of the 29th ISSAT International Conference on Reliability and Quality in Design, RQD 2024.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Factors Affecting Mental Health of High School Students due to COVID-19: An Exploratory Study

Factors Affecting Mental Health of High School Students due ...

引用

2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023

作者： Reza, Md. Rokonuzzaman Islam, Muhammad Nazrul Islam, Mohian Mumu, Afnan Alauddin Faisal, Faiz Al The International University of Scholars Dept. of Computer Science and Engineering Dhaka Bangladesh Military Institute of Science and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh LTIMindtree Ltd. Washington United States Green University of Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350316001

Mental health is one of the most significant factors in the human life span. It also influences how we interact with people, manage stress, and make good decisions. From childhood and youth through maturity, mental health is crucial at every stage of life. In the era of the COVID-19 pandemic, it becomes more vulnerable and affects teenagers as others. In this study, high school students' (10-19 years old) mental health states and the most contributing factors that affect their mental health were assessed through a statistical and machine learning-based approach. The study data were collected through an online survey and received responses from 158 respondents. The data were analyzed statistically with a chi-square test and path analysis considering all the possible factors of anxiety and depression to determine the most contributing factors. Besides, a few Machine Learning (ML) algorithms have been developed such as Logistic Regression(LR), Support Vector Machine(SVM), Naive Bayes(NB), AdaBoost(AB), and Random Forest(RF) for the prediction of anxiety and depression and found that AdaBoost achieved the highest score (86%). As outcomes, the overall analysis revealed that academic concerns such as poor understanding of online classes, daily activities like sleep pattern disruption, and extended uses of electronic devices are the major causes of the deterioration of high school students' mental health. © 2023 IEEE.

关键词： COVID-19

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：