检索结果-内蒙古大学图书馆

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Hemanth, S.V. Kirubha, D. Reddy, Sheri Ramchandra Chelladurai, T. Soundari, A. Gnana Amirthayogam, G. Hyderabad Institute of Technology and Management Department of Computer Science and Engineering Telangana Hyderabad501401 India Rajarajeswari College of Engineering Department of Computer Science and Engineering Karnataka Bangalore560074 India Telangana Hyderabad501401 India Psna College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Dindigul624622 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Thandalam600124 India Department of Information Technology Tamilnadu Chennai603103 India

ISBN: (纸本)9798350375190

Cloud Computing (CC) is a powerful paradigm for accessing IT services over the internet, allowing multiple consumers to share resources. Therefore, it requires task scheduling, allocating, and gradually releasing resources. Hence, efficient Task Scheduling (TS) and Resource Allocation (RA) in cloud systems is crucial to optimize resource usage and ensure timely completion. Assigning computing tasks in a cloud environment is a multifaceted process affected by numerous factors, including network bandwidth availability, completion time, and cost considerations. Traditional scheduling models based on heuristic algorithms have limitations in complex in cloud environments. To tackle these issues, we introduce Multi objective Ant Colony Optimization (MACO) and Adaptive Sequence Dynamic Allocation (ASDA) techniques for TS and RA in the cloud environment. Initially, the tasks submitted globally are divided into long and short queues. After that, the MACO algorithm schedules the task based on queues. Subsequently, the proposed ASDA algorithm efficiently allocates the most appropriate Virtual Machine (VM). If a VM is already occupied, the proposed method promptly chooses the next available VM based on the progress of the work completion process. According to the experimental results, the proposed algorithm achieves significant cost savings compared to other algorithms. © 2024 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Divide-and-train: A new approach to improve the predictive tasks of bike-sharing systems

引用

Mathematical Biosciences and engineering 2024年第7期21卷 6471-6492页

作者： Ali, Ahmed Salah, Ahmad Bekhit, Mahmoud Fathalla, Ahmed Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Higher Future Institute for Specialized Technological Studies Cairo3044 Egypt College of Computing and Information Sciences University of Technology and Applied Sciences Ad-Dhahirah Ibri Oman Zagazig University Department of Computer Science Faculty of Computers and Informatics Sharkeya Zagazig Egypt Sydney Australia Kaplan Business School Sydney Australia Department of Mathematics Faculty of Science Suez Canal University Ismailia Egypt

Bike-sharing systems (BSSs) have become commonplace in most cities worldwide as an important part of many smart cities. These systems generate a continuous amount of large data volumes. The effectiveness of these BSS systems depends on making decisions at the proper time. Thus, there is a vital need to build predictive models on the BSS data for the sake of improving the process of decision-making. The overwhelming majority of BSS users register before utilizing the service. Thus, several BSSs have prior knowledge of the user’s data, such as age, gender, and other relevant details. Several machine learning and deep learning models, for instance, are used to predict urban flows, trip duration, and other factors. The standard practice for these models is to train on the entire dataset to build a predictive model, whereas the biking patterns of various users are intuitively distinct. For instance, the user’s age influences the duration of a trip. This endeavor was motivated by the existence of distinct user patterns. In this work, we proposed divide-and-train, a new method for training predictive models on station-based BSS datasets by dividing the original datasets on the values of a given dataset attribute. Then, the proposed method was validated on different machine learning and deep learning models. All employed models were trained on both the complete and split datasets. The enhancements made to the evaluation metric were then reported. Results demonstrated that the proposed method outperformed the conventional training approach. Specifically, the root mean squared error (RMSE) and mean absolute error (MAE) metrics have shown improvements in both trip duration and distance prediction, with an average accuracy of 85% across the divided sub-datasets for the best performing model, i.e., random forest. © 2024 the Author(s).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Water Distribution Pump Scheduling with SVM-Based Machine Learning Using IoT Sensor Data 2

Optimizing Water Distribution Pump Scheduling with SVM-Based...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Basavaraddi, Chethan Chandra S. Jegan Amarnath, J. Muthukannan, K. Choudri, Subramani Roy Malathi, N. Department of Computer Science and Engineering Kalpataru Institute of Technology Tiptur Karnataka Tumkur India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Chennai India Department of Information Technology Sri Shanmugha College of Engineering and Technology Tamil Nadu Salem India Department of Computer Science and Engineering Vsardhaman College of Engineering Telangana Hyderabad India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350305418

Water distribution is essential to urban infrastructure, and pump scheduling is crucial to water reliability. Traditional pump scheduling uses preset or manual modifications, wasting resources and water. This paper introduces a unique strategy that uses Machine Learning (ML) techniques, notably Support Vector Machines (SVM) and Internet of Things (IoT) data for dynamic pump scheduling in water distribution systems to overcome these difficulties. The proposed method uses IoT sensors throughout the water distribution network to gather real-time water flow, pressure, and demand data. After processing, an SVM-based ML model predicts water demand and system behavior using this data. SVM, which can handle non-linear and high-dimensional data, captures complicated IoT variable interactions. The system provides optimum pump schedules in real time using SVM for prediction. These schedules adapt to changing circumstances to maximize energy efficiency and reduce pipeline breakdowns. SVM integration also detects abnormalities and leaks, improving system dependability and decreasing water loss. It advances IoT and ML in water distribution management. The SVM-based strategy improves water distribution network operating efficiency, saving money, reducing environmental impact, and enhancing service quality. The suggested method improves water supply system sustainability and resilience in smart cities and urban areas by being scalable and adaptive. © 2023 IEEE.

关键词： Operational Efficiency Real-time Data Water Distribution Water Loss Reduction

来源：评论

学校读者我要写书评

暂无评论

Advancing Brain-computer Interaction: EEG-based Eye Movement Recognition with AI 7

Advancing Brain-Computer Interaction: EEG-based Eye Movement...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Saidala, Ravi Kumar Ramnath, M. Komala, C.R. Vidhya, N.G. Taqui, Syed Noeman Rajendiran, M. Alliance University Department of Computer Science And Engineering Karnataka Bangalore560076 India Ramco Institute of Technology Department of Artificial Intelligence And Data Science Tamil Nadu Rajapalayam626117 India Hkbk College of Engineering Department of Information Science And Engineering Bengaluru560 045 India St. Joseph's Institute of Technology Omr Department of Information Technology Tamil Nadu Chennai600119 India Saveetha Institute of Medical And Technical Sciences Saveetha School of Engineering Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India Panimalar Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai600123 India

ISBN: (纸本)9798350359299

The integration of Electroencephalography (EEG) and Brain-computer Interface (BCI) technologies is causing an evolution in healthcare, accessibility, and neuroscience. This multidisciplinary method offers a non-invasive means to communicate and control through intentional eye movements, which is particularly promising for patients suffering from neurological illnesses. In this study, eye movements are identified using EEG data from the EPOC Flex wireless EEG brain device. Using advanced Deep Learning models such as the Deep Belief Network (DBN) and the Deep Residual Network (Deep ResNet), and attempted to distinguish four distinct eye movements: open, close, right, and left. Some of the primary metrics utilized for assessing these models were accuracy, precision, recall, and F1 score. The Deep ResNet model gives better results with an accuracy of 96.25%, recall of 95.85%, precision of 96.66%, and an F1 score of 96.24%. The findings suggest that BCI frameworks can leverage EEG-based eye movement detection to improve rehabilitation procedures and make computers and devices easier to operate. This study's findings open a path for future research into neurotechnological applications and human-computer interaction. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Personalized Health Monitoring Platform with Privacy Preservation in IoT Cloud Networks using Deep Learning 8

Personalized Health Monitoring Platform with Privacy Preserv...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Bhat, Devidas Kansal, Vipashi Kumar, B.N. Mohan Patil, Harshal Vekariya, Daxa Kannan, Sathish Department of Information Science and Engineering Karkala Udupi District Karnataka Nitte India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248 002 India R R Institute of Technology Department of Electronics and Communication Engineering Karnataka Bangalore560090 India Iilm University School of Computer Science & Engineering Greater Noida201306 India Parul Institute of Engineering and Technology Parul University Department of Computer Science & Engineering Post Limda Gujarat 391760 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350376425

Deep learning-based models have demonstrated the potential for personalized health monitoring, creating revolutionary opportunities in healthcare delivery and patient outcomes. In the present study, different deep learning algorithms like LSTM, GRU, CNN and Autoencoders are compared on health data. There are various performance measures for each model such as accuracy, precision, recall and F1-score to see how well it can deal with different types of health data. As a result, LSTM achieved remarkable performance metrics including an accuracy of 0.92, a precision of 0.88, recall of 0.94 and F1 score of 0.91 although it required long training time of about 12 hours. GRU had an accuracy value of 0.89, precision was at 0.85;recall stood at 0.91 and f-1 score was at 0.88 while still having a shorter training time which was ten hours unlike CNN that performed well in image processing with an accuracy level of o'95% and preciseness that amounted to o'92%. Besides this CNN took longer to train since the time was twenty-four hours but not like Autoencoders whose anomaly detection efficiency resulted in low reconstruction errors amounting to only five (5%) percent or less even though the training time is just eight (8) hours with relatively lower accuracies and precisions reaching eighty-seven (87%) percent or eighty-two (82%) percent respectively These findings highlight the multifaceted approach and promise that deep learning models bring to transforming individualized health monitoring, allowing accurate extraction of actionable information from personal biometrics and enabling proactive healthcare. These models, which employ advanced computational tools, offer exciting opportunities for improving the speed and precision of diagnoses, refining treatment strategies, and advancing personalized medicine globally. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

In Situ Monitoring and Assessment of Ischemic Skin Flap by High-Frequency Ultrasound and Quantitative Parameters

引用

Sensors 2024年第2期24卷 363页

作者： Huang, Da-Ming Wang, Shyh-Hau Department of Computer Science and Information Engineering National Cheng Kung University Tainan70101 Taiwan Institute of Medical Informatics National Cheng Kung University Tainan70101 Taiwan

Skin flap surgery is a critical procedure for treating severe skin injury in which post-surgery lesions must well monitored and cared for noninvasively. In the present study, attempts using high-frequency ultrasound imaging, quantitative parameters, and statistical analysis were made to extensively assess variations in the skin flap. Experiments were arranged by incising the dorsal skin of rats to create a skin flap using the chamber model. Measurements, including photographs, 30 MHz ultrasound B-mode images, skin thickness, echogenicity, Nakagami statistics, and histological analysis of post-surgery skin flap, were performed. Photograph results showed that color variations in different parts of the skin flap may readily correspond to ischemic states of local tissues. Compared to post-surgery skin flap on day 7, both integrated backscatter (IB) and Nakagami parameter (m) of the distal part of tissues were increased, and those of the skin thickness were decreased. Overall, relative skin thickness, IB, and m of the distal part of post-surgery skin flap varied from 100 to 67%, −66 to −61 dB, and 0.48 to 0.36, respectively. These results demonstrate that this modality and quantitative parameters can be feasibly applied for long-term and in situ assessment of skin flap tissues. © 2024 by the authors.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Interdisciplinary perspectives on privacy awareness in lifelogging technology development

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2291-2312页

作者： Wilkowska, Wiktoria Offermann, Julia Colonna, Liane Florez-Revuelta, Francisco Climent-Pérez, Pau Mihailidis, Alex Poli, Angelica Spinsante, Susanna Ziefle, Martina Human-Computer Interaction Center RWTH Aachen University Aachen Germany Swedish Law and Informatics Research Institute Stockholm University Stockholm Sweden Department of Computer Technology University of Alicante Alicante Spain Department of Occupational Science and Occupational Therapy University of Toronto Toronto Canada Department of Information Engineering Marche Polytechnic University Ancona Italy

Population aging resulting from demographic changes requires some challenging decisions and necessary steps to be taken by different stakeholders to manage current and future demand for assistance and support. The consequences of population aging can be mitigated to some extent by assisting technologies that can support the autonomous living of older individuals and persons in need of care in their private environments as long as possible. A variety of technical solutions are already available on the market, but privacy protection is a serious, often neglected, issue when using such (assisting) technology. Thus, privacy needs to be thoroughly taken under consideration in this context. In a three-year project PAAL (‘Privacy-Aware and Acceptable Lifelogging Services for Older and Frail People’), researchers from different disciplines, such as law, rehabilitation, human-computer interaction, and computer science, investigated the phenomenon of privacy when using assistive lifelogging technologies. In concrete terms, the concept of Privacy by Design was realized using two exemplary lifelogging applications in private and professional environments. A user-centered empirical approach was applied to the lifelogging technologies, investigating the perceptions and attitudes of (older) users with different health-related and biographical profiles. The knowledge gained through the interdisciplinary collaboration can improve the implementation and optimization of assistive applications. In this paper, partners of the PAAL project present insights gained from their cross-national, interdisciplinary work regarding privacy-aware and acceptable lifelogging technologies. © 2022, The Author(s).

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Human Action Recognition Using Difference of Gaussian and Difference of Wavelet

引用

Big Data Mining and Analytics 2023年第3期6卷 336-346页

作者： Gopampallikar Vinoda Reddy Kongara Deepika Lakshmanan Malliga Duraivelu Hemanand Chinnadurai Senthilkumar Subburayalu Gopalakrishnan Yousef Farhaoui Department of Computer Science and Engineering(AI&ML) CMR Technical CampusHyderabad 501401India. Department of Information Technology Kakatiya Institute of Technology and ScienceWarangal 506015India. Department of Electronics and Communication Engineering Malla Reddy Engineering College for Women(Autonomous)Hyderabad 500100India. Department of Computer Science and Engineering S.A.Engineering College(Autonomous)Thiruverkadu 600077India. Department of Electronics and Communication Engineering Saveetha Institute of Medical and Technical Sciences(SIMATS)Chennai 602105India. Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai 600062India. IDMS Team STI LaboratoryFaculty of Sciences and TechniquesMoulay Ismail University of MeknèsErrachidia 25003Morocco.

Human Action Recognition(HAR)attempts to recognize the human action from images and *** major challenge in HAR is the design of an action descriptor that makes the HAR system robust for different environments.A novel action descriptor is proposed in this study,based on two independent spatial and spectral *** proposed descriptor uses a Difference of Gaussian(DoG)filter to extract scale-invariant features and a Difference of Wavelet(DoW)filter to extract spectral *** create a composite feature vector for a particular test action picture,the Discriminant of Guassian(DoG)and Difference of Wavelet(DoW)features are *** Discriminant Analysis(LDA),a widely used dimensionality reduction technique,is also used to eliminate duplicate ***,a closest neighbor method is used to classify the *** and UCF 11 datasets were used to run extensive simulations of the suggested strategy,and the accuracy assessed after the simulations were run on Weizmann datasets for five-fold cross validation is shown to perform *** average accuracy of DoG+DoW is observed as 83.6635%while the average accuracy of Discrinanat of Guassian(DoG)and Difference of Wavelet(DoW)is observed as 80.2312%and 77.4215%,*** average accuracy measured after the simulation of proposed methods over UCF 11 action dataset for five-fold cross validation DoG+DoW is observed as 62.5231%while the average accuracy of Difference of Guassian(DoG)and Difference of Wavelet(DoW)is observed as 60.3214%and 58.1247%,*** the above accuracy observations,the accuracy of Weizmann is high compared to the accuracy of UCF 11,hence verifying the effectiveness in the improvisation of recognition accuracy.

关键词： human action recognition difference of Gaussian difference of wavelet linear discriminant analysis Weizmann UCF 11 accuracy

来源：评论

学校读者我要写书评

暂无评论

PET Myocardial Flow Reserve Estimation from 4D-Coronary-CT using Deep Neural Network 46

PET Myocardial Flow Reserve Estimation from 4D-Coronary-CT u...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Shen, Chenxi Iwaguchi, Takafumi You, Shaodi Kawakubo, Masateru Nagao, Michinobu Kawasaki, Hiroshi Kyushu University Graduate School of Information Science and Electrical Engineering Fukuoka Japan Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka Japan University of Amsterdam Informatics Institute Amsterdam Netherlands Kyushu University Faculty of Medical Sciences Department of Health Sciences Fukuoka Japan Tokyo Women's Medical University Department of Diagnostic Imaging & Nuclear Medicine Tokyo Japan

ISBN: (纸本)9798350371499

The myocardial flow reserve (MFR) index proves to be a highly effective means of assessing the severity of myocardial ischemic disease. An MFR value below two commonly indicates impaired coronary artery perfusion function. Nevertheless, the measurement of MFR using the NH3-positron emission tomography (NH3-PET) method is both invasive and time-consuming. In order to alleviate the burden on both patients and doctors, we aim to achieve accurate estimation of MFR through a coronary computed tomography angiography image processing method. In this paper, we propose 2 methods: one is estimation method of MFR using i) coronary flow index (CFI) with multiple linear regression (MLR) and the other one is ii) vertical-time (VT) image with fully connected network (FCN) and convolutional neural network (CNN). We evaluate the performance between the observed and estimated MFR values with the Pearson correlation coefficient. The results show that LAD = 0.31, LCX = 0.19, and RCA = -0.21 in MLR method;LAD = 0.19, LCX =-0.37, and RCA = 0.23 in FCN and LAD = 0.34, LCX = 0.44 and RCA = 0.37 in CNN. The results exhibit superior performance based on VT images-based method compared to the CFI-based method, which show that VT images method is *** relevance- MFR is a crucial indicator in the clinical field of cardiovascular diseases, aiding in the early diagnosis, risk assessment, treatment monitoring, and prognosis evaluation of cardiac conditions. Nevertheless, the measurement of MFR using the NH3-PET method is both invasive and time-consuming. Our results show that estimating the MFR through VT images is a promising method. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Resource Allocation for Smart Grids using Deep Reinforcement Learning in IoT Cloud Systems 8

Energy-Efficient Resource Allocation for Smart Grids using D...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Patil, Harshal Kansal, Vipashi Balasubramani, R. Manohar, Talari Vekariya, Daxa Kannan, Sathish Iilm University School of Computer Science & Engineering Uttar Pradesh Greater Noida201 306 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248 002 India Department of Information Science and Engineering Karnataka Nitte574110 India Anantha Lakshmi Institute of Technology and Sciences Department of Electrical and Electronics Engineering Andhra Pradesh Ananthapuramu515721 India Parul Institute of Engineering and Technology Parul University Department of Computer Science & Engineering Post Limda Gujarat 391760 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350376425

This study describes the use of deep reinforcement learning (DRL) models to fine-tune resource allocation for smart grids in order to reduce energy waste and operational costs. The research experiment evaluates four different DRL algorithms, which include SAC, DDPG, PPO, and A3C. It demonstrates performance through various evaluation metrics, which include impeccable energy efficiency, perfect resource utilization, load balancing ratio, average response time, and computational overhead. SAC is proven to achieve 92.5% energy efficiency, 88.7% resource utilization, 90% load balancing ratio, and response time of 120ms. The computational overhead assessed supplements to 15 GFLOPS. DDPG showcased 90.1% energy efficiency and 85.4% resource utilization, 88.9% load balancing, a response time of 110 ms, and a computational overhead of 14.8 GFLOPS. On the other hand, PPO and A3C also proved to work well and have a promising future to be implemented in a dynamic grid. This analysis demonstrates that practical applications from DRL, including real-time decision-making and adaptive control approaches, can prove vital while assigning and working on energy tasks and renewable conduct. These models prove important and beneficial in enhancing the operational efficiency of the smart grid, understanding and learning continuously from real-time data. It will be a vital concept and idea that would be helpful in ensuring that smart grids work perfectly to help in a reduction in carbon footprints and effective energy resource management to ensure end-use service provider satisfactions. © 2024 IEEE.

关键词： Deep reinforcement learning

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：