检索结果-内蒙古大学图书馆

4th IEEE Global Conference for Advancement in Technology, GCAT 2023

作者： Thotad, Puneeth N. Kallur, Shanta Mundaragi, Laxmi Kadam, Swati H. Dept. of Master of Computer Applications K.L.E. Institute of Technology Hubballi580 027 India Dept. of Computer Science and Engineering K.L.E. Institute of Technology Hubballi580 027 India

ISBN: (纸本)9798350305258

Mental illness is a common condition in the 21st century. Despite the significant number of people who experience mental illness, many continue to experience stress without comprehending its damaging effects on their brain. Python and machine learning tools are adopted to create the mental health tracker system. According to the experimentation, the work focuses on developing a psychological well-being tracker. The prediction uses various models such as logistic regression, random forest, decision tree, and k-nearest neighbor. In the proposed system, the patient must answer the questions to predict their mental illness condition. Based on the responses given by the patient, the system will predict whether they need treatment or not. The system will attempt to gain an understanding of a user's mental state, determine whether they are suffering, and then suggest steps they can take to improve their mental health situation. Mental health prediction might benefit psychological departments looking to enhance their counseling and diagnosis abilities. The model was developed by collecting the question-answer set as options related to mental health by consulting specialized doctors in the hospital. The model is trained using different ML algorithms, finding their accuracy and predicting the results. The analysis was made by considering the raw data and normalized data. Models performance was improved with normalization with the following accuracies. 71.4%, 73.5%, 80.6%, and 81.2% accuracies are obtained for Logistic regression, K-Nearest Neighbor, Decision Tree, and Random Forest, respectively. © 2023 IEEE.

关键词： Decision Tree Digital Mental Health K-Nearest Neighbor Logistic Regression Machine Learning Random Forests

来源：评论

学校读者我要写书评

暂无评论

A Study on the Efficient ESS Charging/Discharging Operation Algorithm in LVDC Microgrid Environment

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第6期73卷 1063-1073页

作者： Jung, Sang-Woo An, Yoon-Young Kim, Ki-Il Dept. of Computer Science and Engineering Chungnam National University Korea Republic of ICT Convergence Standards Research Division Electronics and Telecommunications Research Institute Korea Republic of

Modern power systems are developing in a sustainable and energy-efficient direction, and research on intelligent power grids that accommodate new and renewable energy is being actively conducted. Since new and renewable energy-based distributed power generation systems and ESS are output as DC power, the DC microgrid reduces the power conversion step and improves the stability and efficienc of the power distribution network. The core of this study is to compare and analyze the performance of the three charge/discharge operation algorithms based on AI prediction in the LVDC microgrid environment. The AI server learns real-time data through interworking with the EMS to predict future load usage and solar power generation, and performs the charge/discharge operation algorithm of ESS based on the collected ESS state data. This paper presents the configuration of the LVDC microgrid testbed, the integration method between EMS and electrical facilities, and analyzes the performance of the developed ESS charge/discharge operation algorithm. It also evaluates the effectiveness of each operation algorithm through actual operation data and simulation, analyzes how these strategies contribute to system load reduction and energy efficiency improvement, and provides guidelines for selecting the optimal ESS charge/discharge operation algorithm under specific conditions. © The Korean Institute of Electrical Engineers.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Novel Hybrid One-Class RNN Model Using Adversarial Data Augmentation for Anomaly Detection in Systems Operations 10

Novel Hybrid One-Class RNN Model Using Adversarial Data Augm...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Jaisharma, K. Devi, T. Deepa, N. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384369

The industries are expanding their infrastructure landscape with advanced processors and supercomputers. It is also important to maintain the systems operations robustly and efficiently to handle the service with zero interrupts. But the illegal contractors will be tampering the system's ability by using augmented data dynamically. This research is to detect the anomaly presence through system operations data. The proposed Novel Hybrid One Class RNN model utilizes the advertiser augmented data to compare with the actual system operations data such as processor utilization, data read/write, network utilizations, request/response count, systems temperature and latency measure over the time period. The result shows the Novel Hybrid One Class RNN model achieves the accuracy of 98.4%, precision of 98.1%, recall of 97.8% and F1-score of 97.3% and performed better than the existing models such as K-mean, Gaussian, Markov Chain, Isolation Forest and One Class SVM models for the considered real world AWS EC2 operations dataset collected under various work load conditions. © 2024 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Selfish Users in Listen-Before-Talk Co-existence of Cellular-Wi-Fi Networks: Counteraction Methods 21

Selfish Users in Listen-Before-Talk Co-existence of Cellular...

引用

21st International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, WiOpt 2023

作者： Saibharath, S. Mishra, Sudeepta Arora, Gazal Sharma, Anamika Hota, Chittaranjan Dept. of Computer Science and Information systems BITS Pilani Hyderabad Campus India Dept. of Computer Science and Engineering IIT Ropar Punjab India

ISBN: (纸本)9783903176553

5G operates in the unlicensed spectrum to expand its capacity. This spectrum provides more uplink and downlink frequency bands in 5G to satisfy ultra-dense and scalability requirements. Wi-Fi is a prominent wireless technology that operates in unlicensed bands. Due to the proximity of cellular and Wi-Fi channels, utilization of both Wi-Fi and 5G New Radio (NR) can cause interference. The co-existence of 5G NR and Wi-Fi devices lacks the means of communication for negotiation and coordination among them. Listen-Before-Talk and Duty-cycling are standard Medium Access Control (MAC) mechanisms to enable co-existence. Due to a lack of coordination, network utilization becomes unfair with the existence of selfish devices. The selfish users could maximize throughput and affect other Wi-Fi and NR users. Here, we investigate the effects of selfish nodes on this Wi-Fi Co-existence with 5G. These nodes disobey exponential backoff to boost their channel acquisition. We study the effect of misbehavior through the Order Gain metric. Through standard CSMA/CA settings with overall channel occupancy of 99.75%, we demonstrate that selfish users profoundly impact fair co-existence. We study the side effects through throughput, channel sensing, and acquisition for various backoff window access patterns. Finally, we go through counteraction methods to overcome the selfish user impact. © 2023 IFIP.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

MAD-TI: Meta-Path Aggregated-Graph Attention Network for Drug Target Interaction Prediction 31

MAD-TI: Meta-Path Aggregated-Graph Attention Network for Dru...

引用

31st International Conference on Electrical engineering, ICEE 2023

作者： Shami Tanha, Reza Sadighian, Maryam Zabihian, Arash Hooshmand, Mohsen Afsharchi, Mohsen Dept. Computer Science and It Zanjan Iran Tehran Iran University of Zanjan Dept. Electrical and Computer Engineering Zanjan Iran

ISBN: (纸本)9798350312560

Computational identification of unknown drug-target interactions (DTI) is crucial in locating new drug treat-ments for proteins, viruses, and diseases. This work proposes MAD-TI a meta-path-based, GAT-oriented method to predict DTIs. Our proposed method uses a heterogeneous graph of drugs, targets, diseases, and side effects as the input graph. Then, it applies two graph attention networks to generate the embeddings of drugs and targets. Using the embeddings, it predicts the unknown DTIs. The results show that MAD-TI outperforms the state-of-the-art methods. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Integrating Temporal Analysis with Hybrid Machine Learning and Deep Learning Models for Enhanced Air Quality Prediction 19

Integrating Temporal Analysis with Hybrid Machine Learning a...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Omer, Muhammad Ali, Sardar Jaffar Raza, Syed M. Le, Duc-Tai Choo, Hyunseung Dept. of Computer Science and Engineering Sungkyunkwan University Suwon Korea Republic of Dept. of AI Systems Engineering Sungkyunkwan University Suwon Korea Republic of James Watt School of Engineering University of Glasgow Glasgow United Kingdom Dept. of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798331507817

Air pollution remains a critical issue, adversely affecting public health and the environment. In this study, we utilize the Air Quality index dataset from Kaggle to analyze temporal and seasonal variations of key pollutants, specifically Carbon Monoxide (CO), Nitrogen Oxides (NOx), and Benzene (C6H6 ). Building upon this analysis, we predict Absolute Humidity (AH), a vital meteorological factor influencing pollutant dispersion, using Machine Learning (ML) and Deep Learning (DL) techniques. Three ML techniques, Linear Regression (LR), Random Forest (RF), and Support Vector Regression (SVR), and three DL techniques, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are employed for predicting AH. The results indicate that while the RF model achieved the lowest Mean Absolute Error (MAE) among ML methods (0.02), the CNN model, despite having an MAE of 0.04, demonstrated statistical superiority through paired t-tests and Wilcoxon signed-rank tests (p © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of COVID-19 Tweets 1

Sentiment Analysis of COVID-19 Tweets

引用

1st International Conference on Informatics, ICI 2022

作者： Gupta, Isha Chatterjee, Indranath Gupta, Neha Mriirs Faculty of Computer Applications Faridabad India Tomsyong University Dept. of Computer Science Engineering Busan Korea Republic of

ISBN: (纸本)9781665437219

Sentiment analysis is the field of computer science that studies people's behaviour or attitude towards objects, events, organizations, and products. Organizations make use of this to improve their products. This paper aims to study people's behaviour towards COVID 19. We have taken data from Twitter to analyse the sentiments. The results show that people don't have positive sentiments towards this coronavirus. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Security Aware Lighting Control System for Public Open Spaces: An IoT Powered Approach

A Security Aware Lighting Control System for Public Open Spa...

引用

2023 International Conference on Computational Intelligence, Networks and Security, ICCINS 2023

作者： Firdhous, Mohamed Fazil Mohamed Elbreiki, Walid Abdullahi, Ibrahim Briki, Wesam Arlimatti, Shivaleela University of Moratuwa Dept. of Information Technology Moratuwa Sri Lanka College of Computer Technology Dept. of Computer Science Benghazi Libya Ibrahim Badamasi Babangida University Dept. of Computer Science Niger State Lapai Nigeria Higher Institute of Engineering Technologies Dept. of Computer Science Benghazi Libya Dr. D y Patil Prathisthan's College of Engineering Dept. of Computer Science and Engineering Maharashtra Kolhapur India

ISBN: (纸本)9798350313796

Cities world over are becoming more congested as people moving into them for better living conditions. Such fast migration towards cities puts heavy demands on city resources. One of the resources that suffers an impact almost immediately is the open spaces in cities. Open spaces are the public spaces that are accessed by people freely for different purposes. Open spaces help citizens maintain a healthy life by relieving stresses. The open spaces visited by people at night must provide adequate lighting for them to engage in their activities. It is seen that many open spaces waste energy as the lights have been on throughout the nights irrespective of usage of the space. In this paper, the authors propose a security aware lighting control system that helps minimize the energy waste without compromising on security. A prototype implementation was tested and the results were positive promising real field implementations. © 2023 IEEE.

关键词： Control systems

来源：评论

学校读者我要写书评

暂无评论

An Advanced MIMO Multicarrier Framework for NTN-Based 5G Broadcast/Multicast Transmissions 11

An Advanced MIMO Multicarrier Framework for NTN-Based 5G Bro...

引用

11th IEEE International Workshop on Metrology for AeroSpace, MetroAeroSpace 2024

作者： Rahman, Talha Faizur Marojevic, Vuk Sacchi, Claudio Mississippi State University Dept. of Electrical and Computer Engineering Mississippi StateMS United States University of Trento Dept. of Information Engineering and Computer Science Trento Italy The University of New Mexico Dept. of Electrical Engineering AlbuquerqueNM United States

ISBN: (纸本)9798350385045

Satellites are teaming up with 5G, forming a non-terrestrial network (NTN), to support broadband applications over wide coverage areas. However, low latency and high reliability are the challenges in NTN which is addressed through the use of low-earth orbit (LEO) satellites. High transmission efficiency can be accomplished by employing multiple-input multiple-output (MIMO) antenna systems and multicarrier wave-forms. Conventional multicarrier techniques, such as Orthogonal Frequency Division Multiplexing (OFDM) and its variants, are sensitive to the nonlinear distortion of high power amplifiers (HPAs) and high Doppler environments. Therefore, we consider Constant Envelope OFDM (CE-OFDM) assisted with Space-Time Shift Keying (STSK) and Low-Density Parity Check (LDPC) encoding for 5G broadcast/multicast systems based on LEO satellites working in the L-band. We propose a low complexity receiver based on A Posteriori Probability (APP) STSK decoding integrated with LDPC decoding, in which we derive the APP of LDPC coded bits for the STSK-CE-OFDM transmission. We analyze the computational complexity of the proposed receiver scheme and conclude that it is effective in counteracting HPA nonlinearity and high Doppler effects inherent to LEO satellites. Numerical results show that the proposed framework outper-forms conventional multicarrier techniques with a gain as high as 16 dB in the presence of amplifier nonlinearity. © 2024 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of VGG19 and ResNet50 V2 for Enhanced Brain Tumor Detection 3

Comparative Analysis of VGG19 and ResNet50 V2 for Enhanced B...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Fulara, Saurabh Upadhyay, Deepak Sharma, Kunj Bihari Rawat, Ramesh Singh Graphic Era Hill University Department of PDP Dehradun India Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to be University Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350372120

This paper compares the performance of two most common deep learning models ResNet50 V2 and VGG19 when using medical imaging for brain tumour detection. Even though early and accurate diagnosis is crucial to improving the treatment and survival of patients, traditional diagnostic methods are ineffective. The purposes of this paper are, first, to evaluate the performance and capabilities of VGG19 and ResNet50 V2 with regard to current achievements in convolutional neural networks using those for brain tumour detection, and second, to compare the accuracy of the results of both models. Based on the accuracy, precision, recall, and F1-scores of both models, the study obtained a general accuracy of 60%. The obtained results demonstrate marked trade-offs between the accuracy and recall of the two models, showing their major advantages and drawbacks. The conclusion of the paper deals with the possible implications of the study for practice and further research aimed to increase the efficiency and applicability of AI in medical diagnostics. Such studies may explore hybrid models, expansion of data augmentation, and the role of interpretability in the support for medical experts. © 2024 IEEE.

关键词： computerized tomography

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：