检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Integrated Intelligence and communication Systems, ICIICS 2024

作者： Manjunatha, D.V. Maindola, Meenakshi Jose, Reny Kaliappan, S. Patel, Mitul Maranan, Ramya Department of Electronics & Communication Engineering Alvas Institute of Engineering & Technology Moodabidri India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Idukki India Division of Research and Development Lovely Professional University Phagwara India Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Vadodara India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai India

ISBN: (纸本)9798331504960

In order to improve the visual quality of low-resolution video frames, this study introduces a new superresolution method for real-time video processing that is powered by artificial intelligence. With little computational overhead, the suggested approach uses a hybrid deep learning model to reconstruct high-resolution frames. This model mixes Convolutional Neural Networks (CNNs) with Generative Adversarial Networks (GANs). The suggested method outperforms state-of-the-art methods by 12.3% in PSNR and 8.7% in SSIM, according to experimental results on benchmark video datasets. The PSNR is 34.56 dB and the SSIM is 0.94. Also, running on a GTX 1080Ti GPU, the system shows an average processing speed of 30 fps, which is great for real-time apps. The suggested strategy is effective in eliminating artifacts, improving visual clarity, and retaining fine details in various real-time video processing contexts, according to both quantitative and qualitative results. © 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

Towards Real Time Traffic Analysis with Reduced Image Quality

Towards Real Time Traffic Analysis with Reduced Image Qualit...

引用

IEEE India Conference (INDICON)

作者： Rohit Mohanraj Erunika Oshani Dayaratna Department of Electronics and Communication Engineering National Institute of Technology Warangal Warangal India Department of Statistics and Computer Science Faculty or science University of peradeniya SriLanka

ISBN: (数字)9798350391282

ISBN: (纸本)9798350391299

This paper presents a detailed study of two computationally efficient object recognition models-YOLOv5 and Fast R-CNN with a MobileNet backbone-focusing on their performance under different degrees of image / video qualities. Blurring is a common problem in autonomous driving due to motion, weather conditions, and other factors, which can greatly reduce picture quality and, consequently, the accuracy of object recognition. Also, the low-quality images produced by on-car devices suffer when trying to utilize them for advanced detection applications. Utilizing the Zenseact Open Dataset (ZOD), images are generated by varying kernel sizes of Gaussian blur to examine how each model's recognition accuracy is affected by picture degradation. Our study shows key differences in the stability of these models, showing the trade-offs between processing speed and recognition confidence in poor visual settings. The results provide helpful guidance for choosing object recognition systems that keep performance in difficult situations, crucial for the safety and efficiency of driverless cars.

关键词： YOLO Performance evaluation Degradation Training Adaptation models Visualization Accuracy Real-time systems Object recognition Video recording

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Overview of Multi-agent Systems for Controlling Smart Grids

引用

CSEE Journal of Power and Energy Systems 2022年第1期8卷 115-131页

作者： Om Prakash Mahela Mahdi Khosravy Neeraj Gupta Baseem Khan Hassan Haes Alhelou Rajendra Mahla Nilesh Patel Pierluigi Siano Power System Planning Division Rajasthan Rajya Vidyut Prasaran Nigam Ltd.Jaipur-302005India Media Integrated Communication Laboratory Graduate School of EngineeringOsaka UniversityOsakaJapan Computer Science and Engineering Department Oakland UniversityRochesterUSA Department of Electrical and Computer Engineering Hawassa UniversityHawassa 1530Ethiopia Faculty of Mechanical and Electrical Engineering Tishreen UniversityLattakiaSyria Department of Electrical Engineering National Institute of Technology Kurukshetra Department of Management&Innovation Systems University of Salerno84084 SalernoItaly

Agents are intelligent entities that act flexibly and autonomously and make wise decisions based on their intelligence and experience.A multi-agent system(MAS)contains multiple,intelligent,and interconnected collaborating agents for solving a problem beyond the ability of a single agent.A smart grid(SG)combines advanced intelligent systems,control techniques,and sensing methods with an existing utility power *** controlling smart grids,various control systems with different architectures have already been ***-based control of power system operations has been shown to overcome the limitations of time required for analysis,relaying,and protection;transmission switching;communication protocols;and management of plant *** systems provide an alternative for fast and accurate power network *** paper provides a comprehensive overview of MASs used for the control of smart *** paper provides a wide-spectrum view of the status of smart grids,MAS-based control techniques and their implementation for the control of smart *** of MASs in the control of various aspects of smart grids-including the management of energy,marketing energy,pricing,scheduling energy,reliability,network security,fault handling capability,communication between agents,SG-electrical vehicles,SG-building energy systems,and soft grids—have been critically *** than a hundred publications on the topic of MAS-based control of smart grids have been critically examined,classified,and arranged for fast reference.

关键词： Coordinated control multi-agent systems renewable energy sources smart energy infrastructure smart grid

来源：评论

学校读者我要写书评

暂无评论

A Novel Optimized Resource Allocation Algorithm using GWO Optimization Technique for WBAN 23

A Novel Optimized Resource Allocation Algorithm using GWO Op...

引用

Proceedings of the 2023 12th International Conference on Software and Information engineering

作者： Amira Olayan Albashir Adel Youssef Mohamed Samir Abou El-Seoud Faculty of Informatics and Computer Science The British University (BUE) Egypt Department of Electronics and Communication Engineering Arab Academy for Science Technology and Maritime Transport Egypt

ISBN: (纸本)9798400708107

Wireless Body Area Networks have severe challenges in energy management to enhance the longevity of the system. Specifically, for a WBAN system that operates by ambient energy sources. The system combines energy scavenging modules integrated into the sensors carried by patients, enabling data transmission to a personal device. Our approach does not rely on previous information as the characteristics of the scavenged and consumed energy are stochastic. To optimize user utility, a formulation of an optimization problem by employing the Grey Wolf Optimization technique (GWO) compared to previous works that used different optimization techniques, to decompose it into three sub-problems: battery management, collecting rate control, and transmission power allocation. To achieve our goals, we apply the GWO to the introduced online resource allocation algorithm that serves two primary purposes: (1) balancing energy scavenging and consumption of network nodes to ensure system stability, and (2) maximizing user utility. Through simulation results, we validate the effectiveness and optimization capabilities of the algorithm while applying a different optimization technique from the previous works maintained.

关键词： Energy management GWO WBAN

来源：评论

学校读者我要写书评

暂无评论

Exploring the Benefits of Deep Learning for Forecasting Time Series Data 3

Exploring the Benefits of Deep Learning for Forecasting Time...

引用

3rd International Conference on Smart Generation Computing, communication and Networking, SMART GENCON 2023

作者： Daivagna, Umesh.M. Vinay Kumar, S.B. Agarwal, Ankita Jha, Gaurav Sharmila, P. Dodia, Shubham J. Atlas SkillTech University Department of UGDX Maharastra Mumbai India Faculty of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350319125

Deep present day is swiftly emerging as an effective device for forecasting time series records. Current advances in deep mastering fashions permit computerized characteristic extraction and trendy contemporary complex nonlinear dynamic relationships among inputs and outputs. The ability to symbolize high-level temporal and temporal-spatial systems of modern-day multivariate time collection facts gives extended accuracy and reliability in forecasting. Moreover, recent strategies skip entering facts via temporal convolutional neural networks to forecast destiny values in present-day time-collection statistics. This article delves into the use of deep learning for forecasting time series data. Deep learning methods, specifically recurrent neural networks, are found to outperform traditional forecasting techniques in accuracy and efficiency. The ability of deep learning to automatically extract patterns and relationships from large amounts of data makes it a valuable tool for forecasting in various industries such as finance, healthcare, and energy. Additionally, the integration of deep learning with other techniques, such as feature selection and data preprocessing, can further improve its forecasting capabilities. Overall, the benefits of using deep learning for time series forecasting make it a promising approach for decision-making and strategic planning in a rapidly changing world. It has enabled the improvement of brand-new state-of-the-art deep ultra-modern models that could seize the dynamics of contemporary statistics sequences without counting on any prior expertise, resulting in correct forecasts. This paper evaluation the modern deep, brand-new techniques for time collection forecasting and discusses the recent traits in the field. Capability-demanding situations and opportunities within the application of modern deep modern day for time series forecasting are addressed in detail in the paper. © 2023 IEEE.

关键词： convolutional developments forecasting learning techniques

来源：评论

学校读者我要写书评

暂无评论

Classification Models and Variable Selection for SME Credit Risk Assessment in Balance the Data Set 10

Classification Models and Variable Selection for SME Credit ...

引用

10th International Conference on Digital Arts, Media and Technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Intharasompong, Sornthun Jitpattanakul, Anuchit Mekruksavanich, Sakorn Wongwiwat, Piyada Phaphan, Wikanda King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok10800 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Thailand University of Phayao School of Information and Communication Department of Computer Engineering 56000 Thailand Suansunandha Rajabhat University Faculty of Science and Technology Bangkok10800 Thailand Research Group in Statistical Learning and Inference Thailand

ISBN: (纸本)9798331543273

Small and medium-sized enterprises (SMEs) are frequently considered high credit risk, making it difficult to obtain loans from banks. A viable substitute for assessing borrower creditworthiness more impartially is using machine learning-based credit risk assessment (CRA) algorithms. This study evaluated the performance of five machine learning techniques: decision tree, support vector machine, gradient boosting, K-nearest neighbor, and Naïve Bayes. We evaluated each model with K-fold cross-validation and utilized the Stepwise selection method for the variable selection. To address the underlying data imbalance, we balanced the dataset with the SMOTE technique, which showed that normal loans were more widespread than Non-Performing Loans (NPLs). After balancing the data, the Gradient Boosting model displayed the best accuracy, F-measure, and robustness without variable selection, making it the most effective model for predicting SME loans. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Significance of deep learning for Covid-19: state-of-the-art review

引用

Research on Biomedical engineering 2022年第1期38卷 243-266页

作者： Nayak, Janmenjoy Naik, Bighnaraj Dinesh, Paidi Vakula, Kanithi Dash, Pandit Byomakesha Pelusi, Danilo K Kotturu AP Tekkali532201 India Department of Computer Application Veer Surendra Sai University of Technology Odisha Burla768018 India Department of Computer Science and Engineering Sri Sivani College of Engineering AP Srikakulam532402 India Faculty of Communication Sciences University of Teramo Coste Sant&#39 Agostino Campus Teramo Italy

Purpose: The appearance of the 2019 novel coronavirus (Covid-19), for which there is no treatment or a vaccine, formed a sense of necessity for new drug discovery advances. The pandemic of NCOV-19 (novel coronavirus-19) has been engaged as a public health disaster of overall distress by the World Health Organization. Different pandemic models for NCOV-19 are being exploited by researchers all over the world to acquire experienced assessments and impose major control measures. Among the standard techniques for NCOV-19 global outbreak prediction, epidemiological and simple statistical techniques have attained more concern by researchers. Insufficiency and deficiency of health tests for identifying a solution became a major difficulty in controlling the spread of NCOV-19. To solve this problem, deep learning has emerged as a novel solution over a dozen of machine learning techniques. Deep learning has attained advanced performance in medical applications. Deep learning has the capacity of recognizing patterns in large complex datasets. They are identified as an appropriate method for analyzing affected patients of NCOV-19. Conversely, these techniques for disease recognition focus entirely on enhancing the accurateness of forecasts or classifications without the ambiguity measure in a decision. Knowing how much assurance present in a computer-based health analysis is necessary for gaining clinicians’ expectations in the technology and progress treatment consequently. Today, NCOV-19 diseases are the main healthcare confront throughout the world. Detecting NCOV-19 in X-ray images is vital for diagnosis, treatment, and evaluation. Still, analytical ambiguity in a report is a difficult yet predictable task for radiologists. Method: In this paper, an in-depth analysis has been performed on the significance of deep learning for Covid-19 and as per the standard search database, this is the first review research work ever made concentrating particularly on Deep Learning for NC

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Semiconductor Laboratory: Usability Testing to Improve User Experience (UX) in Virtual Environments 3

Virtual Reality Semiconductor Laboratory: Usability Testing ...

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2023

作者： Ahmed Alnagrat, Ahmed Jamah Ismail Alkhallas, Muhannad Imhmed Mohamed, Abdalslam S Che Ismail, Rizalafande Syed Idrus, Syed Zulkarnain Salem Saed, Halifah Department of Computer Science and Information Technology Wadi al-Shati Fezzan Libya Perlis Kangar01000 Malaysia Faculty of Engineering Technology in Zuwarah Department of Software Engineering Zuwarah Libya Aljufra University Faculty of Information Technology Aljufra Libya Arau02600 Malaysia Department of Communication Perlis Kangar01000 Malaysia Higher Institute of Science and Technology Wadi Al-Shati Department of Computer Science and Information Technology Wadi al-Shati Fezzan Libya

ISBN: (纸本)9798350319897

The Virtual Reality (VR) Semiconductor Laboratory, a computer-based virtual lab designed for training engineering students in semiconductor concepts, was evaluated to enhance user experience (UX) in virtual environments. A sample of 97 participants, including undergraduate, Master's, and PhD students, participated in the study. The User Experience Questionnaire (UEQ) was developed to collect data from users to evaluate their experience with the VR lab. The results of the study showed that the participants had a positive experience with the VR learning environment. They found the experience to be enjoyable, easy to understand, and helpful in completing learning tasks. The majority of participants rated the experience as very easy or easy in terms of learning and understanding the material, enjoyment, ease of using the interface, comfort with body movement during learning, and assistance with tasks. Additionally, most participants rated the experience as very easy in terms of task completion and comfort with the VR experiment. The study found high reliability in terms of usability, indicating that the UEQ is a valid and reliable tool for assessing virtual laboratory usability. These findings suggest that virtual laboratories can be effective learning and training tools in various fields, such as science and engineering. This research highlights the potential of VR technology in improving the training and learning experience for students. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection Based on Unified Code Property Graph 1

引用

Proceedings of the 20th Web Information Systems and Applications Conference, WISA 2023

作者： Li, Wei Li, Xiang Feng, Wanzheng Jin, Guanglu Liu, Zhihan Jia, Jing College of Computer Science and Technology Harbin Engineering University Harbin150001 China College of Communication Engineering Jilin University Jilin130012 China Faculty of Arts Design and Architecture School of Built Environment The University of New South Wales SydneyNSW2052 Australia

ISBN: (数字)9789819962228

ISBN: (纸本)9789819962211

As the number of source codes grows rapidly, detecting source code vulnerabilities in current software has become an important study. Most current deep learning-based vulnerability detection technologies treat source code as a sequence, which loses the source code’s structural information, leading to many false positives in the detection results. We propose a novel source code vulnerability detection model, named UCPGVul, based on the Unified Code Property Graph (UCPG). A new graph representation, UCPG, is proposed to extract semantic features from the source code. By extracting features from UCPG, our proposed UCPGVul model can capture more vulnerability features. Experimental results on a publicly available dataset show that UCPGVul can achieve more accurate and stable detection results compared to five state-of-the-art methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis and Assessment of Wind Energy Potential of Al-Hodeidah in Yemen

引用

computers, Materials & Continua 2021年第11期69卷 1995-2011页

作者： Fahd N.Al-Wesabi Murad A.Almekhlafi Mohammed Abdullah Al-Hagery Mohammad Alamgeer Khalid Mahmood Majdy M.Eltahir Ali M.Al-Sharafi Amin M.El-Kustaban Department of Computer Science King Khalid UniversityMuhayel AseerKingdom of Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Electrical Engineering–Communication Engineering Sana’a UniversityYemen Department of Computer Science College of ComputerQassim UniversitySaudi Arabia Department of Information Systems King Khalid UniversityMayahel AseerKSA Department of Computer Science College of Computers and Information TechnologyUniversity of BishaKSA Department of Electronic Faculty of EngineeringUSTSana’aYemen

Renewable energy is one of the essential elements of the social and economic development in any civilized *** use of fossil fuels and the non-renewable form of energy has many adverse effects on the most of *** the high potential of renewable energy sources in Yemen and the absence of similar studies in the region,this study aimed to examine the wind energy potential of Hodeidah-Yemen Republic by analyzing wind characteristics and assessment,determining the available power density,and calculate the wind energy extracted at different *** average wind speed of Hodeidah was obtained only for the data currently available for the five years 2005–2009(due to the current economic and the political situation in Yemen).The results show that the average wind speed in the five years is(25.2 W/m2 at 10 m,93.9 W/m2 at 30 m,and 173.5 W/m2 at 50 m).The average yearly wind power density(25.2 W/m2 at 10 m,93.9 W/m2 at 30 m and 173.5 W/m2 at 50m),and the average yearly energy density(220.8 KWh/m2/year at 10 m,822.6 KWh/m2/year at 30 m and 1519.9 KWh/m2/year at 50 m).This research is a preliminary assessment of the potential of wind energy in Hodeidah,which provides useful information for developing wind energy and an efficient wind *** to the International Wind Energy Rating criteria,the region of Hodeidah falls under‘Class 2’and is classified as‘Marginal’for most of the year.

关键词： Energy potential wind speed weibull distribution wind power density

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：