检索结果-内蒙古大学图书馆

3rd International Conference on Advanced Computing and Applications, ICACA 2024

作者： Sutradhar, Shrabani Bose, Rajesh Majumder, Sudipta Mondal, Haraprasad Dibrugarh University Institute of Engineering and Technology Dibrugarh University Assam Dibrugarh786001 India Department of Computational Science Brainware University West Bengal Kolkata India Department of Computer Science & Engineering JIS University West Bengal Kolkata India

ISBN: (纸本)9789819747986

In response to the escalating demands for advanced processing capabilities in healthcare applications, we introduce a ground-breaking solution, the Hybrid Fog-Cloud Offloading (HFCO) approach, for Internet of Medical Things (IoMT) devices. This method optimally offloads complex tasks to cloud servers or nearby fog nodes, mitigating the inherent limitations of IoMT devices. The offloading decision is intelligently made by IoMT devices, considering task requirements and collaborating with nearby fog nodes. The challenge of selecting the most suitable fog node is addressed through an autonomous decision-making mechanism employing a Markov Decision Process (MDP) and the Actor-Critic algorithm. Our proposed strategy surpasses current state-of-the-art approaches, evident in numerical simulations showcasing reduced latency, heightened efficiency, load balancing, and improved scalability, resilience, and security. By seamlessly integrating cloud resources, the HFCO approach empowers IoMT applications, ensuring minimal latency, efficient task execution, and a robust, secure healthcare infrastructure. This research pioneers a dynamic solution to enhance the operational efficacy of IoMT devices in healthcare settings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Classification using CNN, Inception V3 and Transfer Learning

COVID-19 Classification using CNN, Inception V3 and Transfer...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Mohammed Iqbal, M. Tamilmani, G. Tej Pavan, Caserker Hema Sri Pranav, Pendyala VIT-AP University School of Computer Science and Engineering Amaravati India SRM Institute of Science and Technology Department of Computational Intelligence Kattankulathur Chennai India

ISBN: (纸本)9798350319200

The outbreak of the COVID-19 pandemic has posed unprecedented challenges for global healthcare systems, neces-sitating accurate and rapid diagnostic solutions. The suggested method utilizes the capabilities of Convolutional Neural Networks (CNN) and the Inception V3 module to provide a novel deep learning strategy for COVID-19 identification. The capacity of the Inception V3 architecture to extract nuanced features from challenging medical imaging data is famous. This work evaluates the performance of the CNN-Inception V3 model in differentiating COVID-19 instances from other respiratory illnesses, such as pneumonia, fibrosis, tuberculosis, and normal lung scans, through a thorough examination employing a broad dataset of chest X-ray and CT images. Important parameters like accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC) are used to assess the model's performance. The study also explores the interpretability of CNN-Inception V3 model predictions, providing information on possible clinical uses. The results of this study add to the corpus of research on deep learning-based COVID-19 diagnostics and show the value of cutting-edge technology in the fight against infectious diseases. © 2023 IEEE.

关键词： CNN classification COVID-19 deep learning fibrosis Inception V3 pneumo-nia tuberculosis X-ray

来源：评论

学校读者我要写书评

暂无评论

Time Series Analysis and Forecasting of Air Quality Index of Dhaka City of Bangladesh

Time Series Analysis and Forecasting of Air Quality Index of...

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Sakib, Sheikh Rahmatulla Sara, Kamarun Nahar Hossain Rasel, Md. Tahmid Asif, Md. Masudul Islam Nahid, Md. Aynul Hasan Rahman, Md. Saifur Mridha, M.F. Islam, Ashraful Bangladesh University of Business and Technology Department of Computer Science and Engineering Dhaka Bangladesh Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh American International University-Bangladesh Department of Computer Science Dhaka Bangladesh Independent University Bangladesh Center for Computational and Data Sciences Dhaka Bangladesh

ISBN: (纸本)9798350337617

In Dhaka, the capital city of Bangladesh, various sources including vehicle emissions, industrial activities, brick kilns, building sites, and open rubbish burning contribute to the air pollution problem. To assess the air quality, the Air Quality Index (AQI) is utilized, which categorizes air quality based on pollutant concentration. In this study, we have built ARIMA, Auto-ARIMA, SARIMAX, and VAR models to predict the air quality of Dhaka. Unlike previous studies, we have utilized hourly air pollutants factors such as PM2.5, PM10, SO2, CO, NO2, and O3 to forecast air quality. Our novel approach enables us to predict the monthly and weekly air quality of Dhaka city. Our analysis reveals that the SARIMAX model, which takes into account seasonal patterns, trends, and external factors, is the most accurate in predicting Dhaka city's air quality. The model's prediction performance is assessed using statistical indicators such as mean absolute percentage error and root mean square error. The study highlights that the SARIMAX model could aid policymakers in evaluating the efficacy of air pollution control measures. © 2023 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

computer-Aided Design for Skin Disease Identification and Categorization Using Deep Learning 7

Computer-Aided Design for Skin Disease Identification and Ca...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Varalakshmi, K. Revathi, A. Srm Institute of Science And Technology Department of Computer Science And Engineering Chennai Tamilnadu Kattangulathur India Srm Institute of Science And Technology Department of Computational Intelligence Chennai Tamilnadu Kattangulathur India

ISBN: (纸本)9798350371406

Slin diseases are disorders that affect the tissues of the human skin. The common skin disease includes eczema, psoriasis, acne, moles and various fungal infections. Skin disorders contribute 1.79% of the global burden of disease across the world. The identification and categorization of skin diseases are done through advanced methodologies which include deep learning techniques with computer-aided designs. This helps the medical professional to accurately diagnose and categorize skin diseases. The initial step of skin disease identification involves image processing and feature extraction through the Convolutional Neural Network (CNN).This helps in analyzing the skin images and classifying the distinct patterns and anomalies which forms the essential for the identification of particular skin conditions. This helps in accurately recognizing various skin diseases like melanoma, psoriasis and eczema through the evaluation of large amounts of datasets. The categorization of skin disease is obtained through RNN and LSTM. This is done by analyzing the temporal characteristics and symptom progression. These skin disease exhibits unique patterns and minute changes in appearance over time. The accurate identification of skin disease progression is obtained through modelling sequential data using LSTM and RNN. This provides an accurate solution for disease progression with personalized treatment recommendations. They help the dermatologist by providing automatic decision-making techniques. Thus the integration of CNN, RNN and LSTM helps to achieve higher efficiency and accuracy in skin disease diagnosis and monitoring. This helps to obtain improved potential to reduce diagnostic errors and enhance patient outcomes. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

UAV -Based Object Tracking Using Siamese Networks and Kalman Filtering

UAV -Based Object Tracking Using Siamese Networks and Kalman...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramanan, S.V. Rajasekar, M. Shanmugapriya, G. Sujitha, R. Akshya, J. Choudhry, Mani Deepak P Pg Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Vsb college of Engineering Department of Computer Science and Engineering Technical Campus Coimbatore India Dr.N G.P Institute of Technology Department of Computer Science and Business Systems Coimbatore India Christ The King Engineering College Department of Information Technology Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

The ability to match features and keep track of objects in changing dynamic environments is still an important problem, particularly due to varying noise levels, diverse datasets, and high dimensional feature spaces. Euclidean Distance and Cosine Similarity based matching are existing methods that commonly do not generalize well, particularly in the case of cross domain scenarios, where noise and motion dynamics are powerful factors to limit the accuracy of tracking. However, Deep Metric Learning approaches can extract robust features at the cost of computational efficiency and are unsuitable for real-time applications. This research proposes a Siamese Network framework to solve these problems by using robust feature matching and multi-object tracking. Based on that, the proposed framework uses a dual-branch network architecture in which feature embeddings extracted from paired inputs are mapped through the same shared latent space. Furthermore, the adaptive learning rate leads to efficient convergence during the training. Experimental results show that the Siamese Network not only achieves better accuracy than the existing methods and the more such as Deep Metric Learning but also performs significantly more efficient computation. With an accuracy of 90.2 % at a precision of 88.5%, the framework's inference time is much faster than that of Deep Metric Learning at 2.0ms. Furthermore, the proposed method performs well on the generalization over datasets with a 15% improvement of cross-domain matching accuracy on Euclidean Distance. By striking this balance between accuracy, efficiency and adaptability, it shows its suitability for dynamic and noisy environments for real-time tracking. The proposed method fills existing gaps and achieves a new state of the art for feature matching and tracking performance. © 2025 IEEE.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Diverse Classification Algorithms of Machine Learning by Using Various Quality Metrics 5

Comparative Analysis of Diverse Classification Algorithms of...

引用

5th IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2023

作者： Kathiresan, V. Dinesh, G. Sarveshwaran, Velliangiri Jayakanth, J.J. Kiruthika, M. Remu, Yuvaraj GITAM University Dept. of Computer Science and Engineering Bengaluru Karnataka India SRM Institute of Science and Technology Department of Computational Intelligence Kattankulathur India

ISBN: (纸本)9798350338287

Machine learning classification algorithms and their applications are becoming increasingly popular in today's era of information science. Choosing an algorithm that is appropriate for the problem and application is a challenging task. The quality of the prediction model is significantly influenced by selecting the right algorithm. The purpose of the study and comparative analysis highlights the benefits and drawbacks of various classification algorithms from all perspectives. The Machine Learning (ML) based classification algorithms such as Logistic Regression (LR), K-Nearest Neighbour(KNN), DT (Decision Tree), SVM (Support Vector Machine), and Naïve Bayes (NB) are assessed for comparative analysis. These algorithms were tested and analysed using various datasets acquired and used from the UCIML repository. Algorithms are evaluated using well-established effective measures for accuracy, recall, and precision. A variety of datasets are used to monitor, measure, and compare each algorithm's performance in terms of metrics. Each algorithm's effectiveness and efficacy are analysed and compared from all aspects. Based on overall performance, the algorithms are ranked in the following order: logistic regression, decision tree, SVM, KNN, and Nave Bayes. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Analysis of Heat Transfer of the Nanofluid Al2O3/H2O Flow Across a Stretching Sheet under the Effects of Thermal Radiation

Analysis of Heat Transfer of the Nanofluid Al2O3/H2O Flow Ac...

引用

2024 International Conference on Thermofluids and Manufacturing science, ICTMS 2024

作者： Krishnendu, S. Nagaraja, K.V. Shali, S. Department of Computer Science Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Computational Science Lab Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Mechanical Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

Efficient heat transfer is very crucial for the various industries in electrical, nuclear power, aerospace and automobile fields. By exhibiting improved thermal conductivity, nanofluids have emerged as an alternative for enhanced thermal and energy efficiency applications. The present study examines the movement of nano fluid across a surface that extend when heat radiation and magnetic fields are present. Using appropriate similarity variables, governing partial differential equations are converted to nonlinear ordinary differential equations. engineering factors which are discussed include Nusselt number and skin friction coefficient. Numerical analysis is optimized using the response surface methodology. The Response Surface Methodology (RSM) with face-centred Central Composite Design is utilized to calculate heat flux transfer at the stretched sheet. The interaction of heat radiation, magnetic field parameter, and solid volume fraction are investigated in the present work. It is worth noting that the local Nusselt number responds positively to the magnetic field parameter and the solid volume fraction, whereas the skin friction coefficient responds negatively. © Published under licence by IOP Publishing Ltd.

关键词： Skin friction

来源：评论

学校读者我要写书评

暂无评论

WiMA:Towards a Multi-Criterion Association in Software Defined Wi-Fi Networks

引用

computers, Materials & Continua 2023年第5期75卷 2347-2363页

作者： Sohaib Manzoor Hira Manzoor Saddaf Rubab Muhammad Attique Khan Majed Alhaisoni Abdullah Alqahtani Ye Jin Kim Byoungchol Chang Department of Electrical Engineering Mirpur University of Science and Technology(MUST)Mirpur-10250(AJK)Pakistan Faculty of Electronics Telecommunications and InformaticsGdansk University of Technology80-233 GdanskPoland Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates National University of Sciences and Technology(NUST) Islamabad44000Pakistan Department of Computer Science HITEC UniversityTaxilaPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Korea Center for Computational Social Science Hanyang UniversitySeoul04763Korea

Despite the planned installation and operations of the traditional IEEE 802.11 networks,they still experience degraded performance due to the number of *** of the main reasons is the received signal strength indicator(RSSI)association problem,in which the user remains connected to the access point(AP)unless the RSSI becomes too *** this paper,we propose a multi-criterion association(WiMA)scheme based on software defined networking(SDN)in Wi-Fi *** association solution based on multi-criterion such as AP load,RSSI,and channel occupancy is proposed to satisfy the quality of service(QoS).SDNhaving an overall view of the network takes the association and reassociation decisions making the handoffs smooth in throughput *** implementWiMA extensive simulations runs are carried out on Mininet-NS3-Wi-Fi network *** performance evaluation shows that the WiMA significantly reduces the average number of retransmissions by 5%–30%and enhances the throughput by 20%–50%,hence maintaining user fairness and accommodating more wireless devices and traffic load in the network,when compared to traditional client-driven(CD)approach and state of the art Wi-Balance approach.

关键词： Association multi-criterion SDN Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Second-Year University Student Retirement Prediction Model Using Machine Learning 16

Second-Year University Student Retirement Prediction Model U...

引用

16th International Conference on Knowledge and Smart Technology, KST 2024

作者： Saelim, Prapatsorn Chochiang, Kitsiri Vasupongayya, Sangsuree College of Digital Science Prince of Songkla University Songkhla Thailand Prince of Songkla University Division of Computational Science Songkhla Thailand Prince of Songkla University Department of Computer Engineering Songkhla Thailand

ISBN: (纸本)9798350370737

Student retirement is an important issue in all higher education institutions, affecting the income of each faculty and the university. In this research, a model for predicting student retirement is created and the factors affecting the student retirement are also analyzed. The information of the second-year Faculty of science undergraduate students, Prince of Songkla University, from the academic year 2018-2022-totally 3,092 students-are used as the workload. The researcher performed the analysis using classification machine learning techniques namely the support vector machine algorithm to compare between the traditional data import method and data enhancement using the synthetic minority over-sampling technique (SMOTE). The kernel functions in the experiments include linear, polynomial, radial basis function kernel (RBF), and sigmoid. 10-fold cross-validation is used. The results show that 9 significant factors that affect the model predicting retirement of the student status include academic performance of 4 basic science subjects, field of study, student loans, hometown, and parent's income. The model with the best efficiency and time efficiency is the one with the SMOTE technique and the RBF kernel support vector machine algorithm. The performance accuracy is at 89.64%. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Morpho-contour exponential estimation algorithm for predicting breast tumor growth from MRI imagery

引用

International Journal of Information Technology (Singapore) 2024年 1-16页

作者： Kaladevi, P. Kanimozhi, N. Nirmala, B. Sivasankari, R. Department of Computer Science and Engineering K. S. Rangasamy College of Technology (Autonomous) Tamil Nadu Tiruchengode 637215 India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai 603203 India Computer Science and Engineering Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Porur Chennai 600116 India Department of Computer Science Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Vandalur Tamil Nadu Chennai 600 048 India

Breast tumor grows rapidly have an elevated risk of progressing to a metastatic state, leading to the spread of tumor tissues to other regions of the body. Early detection of such metastatic sites can be facilitated by predicting these tumors' growth rate. In this context, we introduce a novel Morpho-Contour Exponential Estimation (MoCEE) method to estimate the potential growth rate of identified breast tumors using magnetic resonance imaging (MRI) datasets. This methodology not only effectively captures morphological traces but also pinpoints regions indicative of infectious spread. This precision is achieved by enhancing the Mask R-CNN with an active contour function, ensuring the accurate segmentation of the breast tumor. Once segmented, the tumor's growth rate is computed using the exponential growth model, which accurately determines the rate by analyzing the distance between two distinct random points on the tumor's segmented region. Subsequently, this derived information, processed through a gradient boosting approach, predicts the likelihood of tumor growth across two different breast tumor categories. In our study, we assessed the proposed MoCEE method from two crucial angles. Firstly, we rigorously evaluated its ability to accurately segment both benign and malignant breast tumors. Our analysis involved comparing MoCEE's performance to that of various deep learning networks, yielding impressive segmentation accuracy percentages, such as 93.12% and 92.22% for benign and malignant tumors in BUSnet, and even higher values for other networks. Secondly, we explored MoCEE's capability to estimate tumor size, considering different probability growth rates (k^=0.2, 0.3, 0.4, and 0.5). Notably, proposed MoCEE proved highly accurate in predicting tumor growth rates across this range of probabilities. These findings highlight MoCEE's versatility and robustness, making it a valuable tool for precise breast tumor analysis and prediction. © The Author(s), under exclusiv

关键词： And gradient boosting approach Breast tumors Exponential growth model Mask R-CNN Morpho-contour exponential estimation (MoCEE)

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：