检索结果-内蒙古大学图书馆

Automatic classification of normal/AD brain MRI slices using whale-algorithm optimized hybrid image features

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14237-14248页

作者： Kadry, Seifedine Jessy, V. Elizabeth Rajinikanth, Venkatesan Crespo, Rubén González Department of Applied Data Science Noroff University College Kristiansand4612 Norway College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Division of Research and Innovation Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Tamil Nadu Chennai602105 India Department of Computer Science and Technology Universidad Internacional de La Rioja La Rioja Logroño Spain

In recent years, the prevalence of Age-Related Illnesses (ARL) has been increasing among older individuals, and early recognition and treatment will result in better living conditions. It is well known that Alzheimer's Disease (AD) is among the ARD, and severe cases may result in dementia as well. It is the purpose of this study to propose a technique for distinguishing normal/AD brain MRI slices with improved accuracy utilizing the T2-modality. This scheme consists following phases: (i) Brain MRI collection and preprocessing, (ii) Deep feature extraction with the chosen scheme, (iii) Handcrafted feature extraction, (iv) Whale Algorithm (WA) based feature reduction and serial integration, and (v) binary classification using five-fold cross-validation. A total of 2000 MRI slices (1000 normal and 1000 AD class) are examined during this task using images collected from Alzheimer’s Disease Neuroimaging Initiative (ADNI). This study confirms that the proposed scheme provides a classification accuracy of > 98% when applied with the K-Nearest Classifier. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Urban Waste Management: Cutting-Edge Image Processing for Precise Solid Waste Classification 5

Revolutionizing Urban Waste Management: Cutting-Edge Image P...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Rama Krishna, S. Patan, Muzeeb Khan Sudarsan, J.S. Padmapriya, R. Bhagavathiperumal, S. Balaram, Allam Department of Computer Science & Engineering Hyderabad502329 India College of Engineering and Technology University of Technology and Applied Sciences Department of EEE Muscat Oman India Sathyabama Institute of Science and Technology Department of Civil Engineering Chennai India Sri Krishna College of Engineering and Technology Coimbatore India MLR Institute of Technology Department of Computer Science and Engineering Hyderabad500043 India

ISBN: (纸本)9798331530013

Due to rapid urbanization and population growth, urban waste management has become one of the major challenges faced by cities around the world. Solid waste classification and sorting are necessary for intensifying recycling, safeguarding environment and manage additional landfilling of materials that are reusable or recyclable, and are getting in landfill of solid waste in certain extent. In this study, an original ensemble model using the VGG19 and EfficientNet architectures is proposed to classify solid waste in urban area. This proposed model was applied on a dataset consists of 2,527 number of images in to six classes to increase the accuracy of classification as well as to maximize the efficiency of waste. It preprocesses the incoming data using various techniques such as image resizing, normalization and augmentation to make the dataset more diverse and robust. The ensemble mechanism performed better combining the detailed feature extraction skills of VGG19 and versatile and scalable architecture of EfficientNet. On test set, it outperformed individual models and the accuracy for the proposed model was 98.75% which closely followed, previously obtain the best result. © 2024 IEEE.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Traffic-oriented reconfigurable NoC with augmented inter-port buffer sharing

引用

Frontiers of Information technology & Electronic Engineering 2024年第10期25卷 1322-1336页

作者： Chenglong SUN Yiming OUYANG Huaguo LIANG School of Computer and Information Engineering Fuyang Normal UniversityFuyang 236041China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230601China School of Electronic Science and Applied Physics Hefei University of TechnologyHefei 230601China

As the number of cores in a multicore system increases,the communication pressure on the interconnection network also *** network-on-chip(NoC)architecture is expected to take on the ever-expanding communication demands triggered by the ever-increasing number of *** communication behavior of the NoC architecture exhibits significant spatial–temporal variation,posing a considerable challenge for NoC *** this paper,we propose a traffic-oriented reconfigurable NoC with augmented inter-port buffer sharing to adapt to the varying traffic flows with a high ***,a modified input port is introduced to support buffer sharing between adjacent ***,the modified input port can be dynamically reconfigured to react to on-demand ***,it is ascertained that a centralized output-oriented buffer management works well with the reconfigurable input ***,this reconfiguration method can be implemented with a low overhead hardware design without imposing a great burden on the system *** experimental results show that compared to other proposals,the proposed NoC architecture can greatly reduce the packet latency and improve the saturation throughput,without incurring significant area and power overhead.

关键词： Network-on-chip Reconfigurable Traffic-oriented Buffer sharing

来源：评论

学校读者我要写书评

暂无评论

Typhoon Track Image Prediction Using a Comprehensive LSTM Attention Model in Deep Learning 4

Typhoon Track Image Prediction Using a Comprehensive LSTM At...

引用

4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

作者： Jiang, Yiping Yu, Yi Ma, Yuelong Zhuang, Jiahao Ye, Xianze Yuan, Yifeng Su, Guanpeng Guangdong University of Science and Technology School of Computer Science Guangdong Dongguan China University of Macau Faculty of Science and Technology Fst China South China Normal University School of Information and Optoelectronic Science and Engineering Guangdong Guangzhou China Macao Polytechnic University Faculty of Applied Sciences China Zhuhai College of Science and Technology School of Computer Guangdong Zhuhai China

ISBN: (纸本)9798350394375

Typhoons are exceptionally destructive tropical cyclones that possess the capacity to inflict significant harm upon society. For institutions engaged in risk assessment and disaster mitigation, accurately forecasting typhoon paths and trajectories is of paramount importance. In this study, we propose a Typhoon Track Image Prediction model based on a Comprehensive Long Short-Term Memory (LSTM) Attention Model in the field of Deep Learning. This model significantly improves the accuracy of typhoon track prediction. To assess its performance, we utilize typhoon data from the China Typhoon Network spanning from 1949 to 2022. The Comprehensive LSTM Attention Model is compared against other popular models such as Temporal Convolutional Networks (TCN), traditional LSTM, and Seq2Seq models for forecasting the typhoon track over a 12-hour period. The results demonstrate the superiority of our proposed model, showcasing its effectiveness in terms of superior accuracy in typhoon track prediction. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Improving Oil Spill Detection in Marine Environments Through Deep Learning Approaches 4

Improving Oil Spill Detection in Marine Environments Through...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Shanmukh, M. Phani Priya, S. Baghavathi Madeswaran, Tamilselvi Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India University of Technology and Applied Sciences Department of Information Technology Nizwa Oman

ISBN: (纸本)9798350343670

Oil spills represent a major environmental threat, particularly in marine ecosystems. Timely detection and segmentation of oil spills from satellite imagery is crucial for directing rapid response and remediation *** research concludes with an insights by developing a deep learning approach for automated detection and segmentation of oil spills from synthetic aperture radar (SAR) *** research implements and compares three algorithms PSPNET,DeepLapV3 and fully convolutional networks (FCN) with U-Net for semantic segmentation of SAR *** the networks are trained on a dataset of SAR images with pixel-wise labels indicating oil spill regions. This research also evaluates the segmentation performance using common metrics like intersection-over-union (IoU) and pixel-wise accuracy. Our results indicate that both FCN and U-Net can effectively detect and delineate oil spill regions, with U-Net demonstrating slightly higher IoU scores and with and accuracy of 95%. The deep learning models generalize well to unseen SAR images. Overall, this work demonstrates the feasibility of deep convolutional neural networks for automated analysis of SAR imagery to enable rapid oil spill response at marine environment. © 2024 IEEE.

关键词： Deep Learning Algorithms Oil Spill Detection Rapid Oil Spill Response Semantic Segmentation Synthetic Aperture Radar (SAR) Imagery

来源：评论

学校读者我要写书评

暂无评论

E-Medical Administration: An Automated Healthcare Management System 4th

E-Medical Administration: An Automated Healthcare Management...

引用

4th International Conference on Data, Engineering, and Applications, IDEA 2022

作者： Awotunde, Joseph Bamidele Misra, Sanjay Abdullahi, Thairu Olanrewaju Agrawal, Akshat Department of Computer Science University of Ilorin Ilorin Nigeria Department of Applied Data Science Institute for Energy Technology Halden Norway Amity University Haryana Manesar India

ISBN: (纸本)9789819724505

Almost any service may now be found on the Internet, thanks to advances in web technology. Every major industry is converting and building a digital face for all of its core activities to get closer to the rising digital market. A person or company using redundancy tactics in today's society will not gain from it. All well-run and well-managed businesses today need Internet access. Information digitization is critical in healthcare because of the need to move swiftly and effectively. It lays the groundwork for the creation of software that makes it easier to go from paper documents to electronic ones. Therefore, this paper proposes an automated hospital management system. E-Medical Administration is a web-based platform that removes the need for paper prescriptions in hospitals and offers E-Medical Management, which would enhance patient management, doctor scheduling, and universal access to patient data anywhere in the hospital. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Assistive Tools with Hand Skeleton Analysis in Online Arts Education 6

AI-Enhanced Assistive Tools with Hand Skeleton Analysis in O...

引用

6th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Kao, Chiao-Wen Wu, Wen-Hsuan Huang, Chi-Sheng Ming Chuan University Department of Applied Artificial Intelligence Taipei Taiwan National Taichung University of Science and Technology Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350396133

The global COVID-19 pandemic has significantly impacted education worldwide, leading to a transition from traditional in-person teaching to asynchronous online learning. Thanks to the valuable contributions of numerous high-quality educational content creators, online audiovisual materials have opened up boundless opportunities for cross-border, crossdisciplinary online learning. This removes geographical and temporal barriers and broadens the spectrum of learning resources available to individuals with diverse needs. Particularly for individuals with disabilities, mobility impairments, or social anxiety, online learning offers an inclusive and accessible environment, fostering the democratization and equity of education and ensuring highquality education regardless of physical conditions or locations. However, unlike foundational subjects, the learning process for arts heavily relies on live demonstrations by teachers and imitation by students, presenting a challenge in the online learning setting especially true for beginners as learning arts often necessitates personalized guidance and real-time feedback. To address this challenge, Mediapipe technology was used to capture the hand movements of both teachers and students in this study. Aeep learning model was used to analyze the similarity of pen-holding postures between students and teachers, thereby providing real-time feedback to supplement the lack of interactivity in online drawing learning and enhance learning outcomes. The developed learning method simulates the role of teachers in traditional classrooms and widens the scope of arts education, providing AI-powered tools for those interested in cultivating aesthetics and lifelong learning opportunities. For the care of the elderly, in addition to enhancing emotional and psychological well-being through aesthetics, the method can be utilized for rehabilitation or the assessment of degenerative conditions. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Application of Edge Detection technology Based on YOLOv8 in Smart Mobility Aids 6

Application of Edge Detection Technology Based on YOLOv8 in ...

引用

6th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Kao, Chiao-Wen Wang, Shih-Tung Huang, Chi-Sheng Ming Chuan University Department of Applied Artificial Intelligence Taipei Taiwan National Taichung University of Science and Technology Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350396133

Global aging presents profound challenges, especially concerning the well-being and mobility of the elderly. Fortunately, technological progress offers means for those with mobility limitations. With the aging population, the significance of the safety and accessibility of passive mobility methods becomes increasingly apparent. In this context, many individuals are using wheelchairs or other assistive devices to maintain their independence for daily mobility. Outdoor environments pose numerous challenges for wheelchair users, such as curbs, uneven road surfaces, and unexpected obstacles. These challenges elevate the risk of accidents and limit freedom of movement. To address these challenges and enhance the adaptability of assistive devices outdoors, we proposed a method by combining YOLOv8 for semantic segmentation with real-time edge detection of road scenes to accurately estimate curb positions. By leveraging the proposed method, various elements of the environment are accurately identified in real-time, including curbs and road conditions. Moreover, by calculating the distance between the wheelchair and the curbs, the system provides timely alerts and guidance to users regarding potential hazards or obstacles, empowering them to swiftly respond to their surroundings and avoid collisions for safety. For the elderly with visual impairments or declining reaction capabilities, the benefits of the system are significant. By enhancing safety, accessibility, and adaptability, the system revolutionizes mobility assistance and empowers individuals to lead more fulfilling and independent lives as they age. © 2024 IEEE.

关键词： Wheelchairs

来源：评论

学校读者我要写书评

暂无评论

Optimizing Healthcare Accessibility and Effectiveness through the Implementation of AI Solutions for Remote Patient Monitoring 3

Optimizing Healthcare Accessibility and Effectiveness throug...

引用

3rd IEEE World Conference on applied Intelligence and Computing, AIC 2024

作者： Singh, Jagendra Sahu, Dinesh Prasad Kumar, Ashwini Ahmad, Salman Khursheed Majumder, Jayeeta Gangopadhyay, Sourav Bennett University School of Computer Science Engineering & Technology Greater Noida India Camellia Institute of Technology & Management Department of Computer Science & Engineering Jaipur India Gl Bajaj Institute of Technology & Management Dept. of Applied Computational Science and Engineering Greater Noida India Brainware University Department of Hospital Management Kolkata India

ISBN: (纸本)9798350384598

This study investigates the optimization of healthcare accessibility and effectiveness by integrating artificial intelligence (AI) solutions within Internet of Things (IoT) systems for remote patient monitoring. Embracing a holistic approach, we deploy medical sensors, including temperature, pressure, heart rate, and oxygen sensors, to collect patients' continuous health metrics (vital signs). These sensed data are then transmitted to an Arduino controller, responsible for managing data communication with the cloud infrastructure using a Wi-Fi module that facilitates data storage and analysis. Stored data are accessed by authorized healthcare professionals, who exploit machine learning models, including Artificial Neural Networks (ANN), Logistic Regression (LR) and Decision Tree (DT), to forecast patients' health outcome in advance using the sensed data. A rigorous evaluation demonstrated the IoT system's effectiveness, based on testing with sensed data from ten patients over a month, where 70% of the data were used for training the models, and the rest for testing. The proposed IoT system demonstrates the success;ANN exhibited the highest accuracy at 97.88%, followed by LR at 93.43%, and DT at 91.20%. Precision, recall, and F1 scores further validated the models' ability to predict health outcome accurately. Evaluation of the accuracy and loss curves showed the convergence of the models towards optimal performance. This study contributes to remote healthcare monitoring and provides a promising IoT paradigm for realizing ubiquitous remote monitoring, optimized healthcare effectiveness, and patient outcome through AI-enabled IoT systems. © 2024 IEEE.

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

Impact of Gamification on Student Learning: An Empirical Evidence 5th

Impact of Gamification on Student Learning: An Empirical Evi...

引用

5th International Conference on Entrepreneurship, Innovation, and Leadership, ICEIL 2023

作者： Garg, Anchal Madhulika Centre for Applied Computer Science School of Creative Technologies University of Bolton BoltonBL3 5AB United Kingdom Department of Computer Science and Engineering Amity School of Engineering and Technology Uttar Pradesh Noida India

ISBN: (纸本)9789819716814

Learner diversity is a matter for universities enrolling international students. Hence, learner engagement then becomes a major concern for instructors. This study uses gamification techniques to determine its impact on engagement and learning when it comes to diverse cohort of learners. A survey questionnaire method was used to identify the effect of gamification on engagement, motivation, performance, and learning. This empirical study revealed that quizzes supported by gamification enhanced engagement, performance, and learning but did not motivate learners to study outside the lecture theatre. This paper also summarizes the issues while using gamified quizzes in the classroom settings and provides potential solutions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

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：