检索结果-内蒙古大学图书馆

IEEE International Conference on Biomedical engineering, computer and Information Technology for Health

作者： Abdullah Al Masum Zishad Hossain Limon Md Ariful Islam Md Shahidur Rahman Mahbub Khan Sheikh Shemanto Afridi Md. Redwan Ahmed Shafiur Rahman Dept. of Information Technology Westcliff University CA USA Dept. of Computer Science Westcliff University CA USA Dept. of Business Administration International American University CA USA Dept. of Engineering management Westcliff University CA USA Dept. of Management Information System Pacific State University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798331534356

ISBN: (纸本)9798331534363

An essential part of the digestive system, the esophagus permits food and liquids to move easily from the throat to the stomach. Traditional diagnostic techniques, such as endoscopy and biopsy, are invasive and resource-intensive, making them less practical in resource-constrained environments. To address these challenges, we proposed utilizing a hybrid Deep Learning (DL) model called GAN-EfficientNet, which combines the power of Generative Adversarial Networks (GAN) and EfficientNet to effectively classify esophageal diseases. Our approach employs advanced image preprocessing techniques and data augmentation methods to enhance the diversity and balance of the dataset. Feature extraction using the Spatial Gray Level Dependence Method (SGLDM) and Principal Component Analysis (PCA) significantly reduces computational complexity without compromising accuracy. We explored both binary and multiclass classification methods, recognizing their crucial roles in various diagnostic scenarios. Binary classification distinguishes between normal and diseased states, essential for initial screening, while multiclass classification identifies specific esophageal diseases, aiding in personalized treatment plans. The GAN-EfficientNet model demonstrated exceptional performance, achieving an impressive F1 score of 99.44% for binary classification and 99.64% for multiclass classification. Additionally, we developed a web application that facilitates quick and precise disease diagnosis, particularly advantageous in areas with limited resources. This tool significantly improves patient outcomes through early detection, leading to reduced healthcare costs and less burden from advanced esophageal diseases.

关键词： Deep learning Accuracy Computational modeling Generative adversarial networks Feature extraction Data augmentation Data models Medical diagnosis Diseases Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Hyper-IIoT: A Smart Contract-inspired Access Control Scheme for Resource-constrained Industrial Internet of Things

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Li, Dun Li, Hongzhi Crespi, Noel Minerva, Roberto Li, Ming Liang, Wei Li, Kuan-Ching Tsinghua University Department of Industrial Engineering China Institut Polytechnique de Paris Samovar Telecom SudParis Palaiseau91120 France Chizhou University College of Big Data and Artificial Intelligence Chizhou247100 China The Hong Kong Polytechnic University Research Institute for Advanced Manufacturing Hung Hom Hong Kong Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Sanya Research Institute Hunan Key Laboratory for Service Computing and Novel Software Technology China Providence University Dept. of Computer Science and Information Engineering Taiwan

In recent years, the refinements in industrial processes and the increasing complexity of managing privacy-sensitive data in Industrial Internet of Things (IIoT) devices have highlighted the need for secure, robust, and adaptive data management solutions. In this work, we propose a smart contract-assisted access control scheme for IIoT, which employs the Attribute-Based Access Control (ABAC) model to set access permissions for different industrial components. Besides, we defined a storage model and data format for private data by designing and deploying smart contracts to manage system operations and access policies. In addition, the bloom filter component is deployed to optimize the efficiency of contract management and system performance. Experimental results show that in real-world simulations, Hyper-IIoT demonstrates excellent contract execution time control, stable system throughput, and rapid consensus processes that are capable of handling high throughput and efficient consensus in distributed systems, even in large-scale request scenarios. © 2016 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Developing mapping and allotment in volunteer cloud systems using reliability profile algorithms in a virtual machine 2

Developing mapping and allotment in volunteer cloud systems ...

引用

2nd International Conference on Computation, Automation and Knowledge Management, ICCAKM 2021

作者： Jeyalaksshmi, S. Nidhya, M.S. Suseendran, G. Pal, Souvik Akila, D. Information Technology Vels Institute of Science Technology Advanced Studies Chennai India Periyar Maniammai Institute of Science Technology Dept of Software Engineering Vallam Thanjavur India Global Institute of Management and Technology Department of Computer Science and Engineering India

ISBN: (纸本)9781728194912

While the placement of the Virtual computer was It remains an open challenge for Volunteer Cloud Computing, which reveals many divergent gaps in conventional cloud computing contexts, and has been thoroughly studied. Features, including sporadic usability of nodes and Infrastructure that's inefficient. In this article, we are modeling the Virtual In Volunteer Cloud Computing, computer positioning dilemma As a multi-dimensional, constrained 0-1 knapsack issue and Built algorithms to satisfy the basic aims and shortcomings of Volunteer Cloud Computing. The proof of a dedicated Cloud Computing Volunteer, The competitive success outcomes of these test beds are illustrated With algorithm. © 2021 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Aerial Vehicle Detection and Classification Through Fusion of Multi-Domain Features of Acoustic Signals

Aerial Vehicle Detection and Classification Through Fusion o...

引用

engineering & Computing Technologies (ICECT), International Conference on

作者： Malaika Sumble Sumair Aziz Muhammad Umar Khan Khushbakht Iqtidar Raul Fernandez-Rojas Department of Electronics Engineering University of Engg. & Tech. Taxila Taxila Pakistan Faculty of Science and Technology University of Canberra Canberra ACT Australia Dept. of Computer & Software Engineering National University of Sciences & Tech. Islamabad Pakistan

ISBN: (数字)9798350349719

ISBN: (纸本)9798350349726

Detection of aerial vehicles is a challenging task. Over time, the significance of developing such vehicles has increased rapidly. However, an utmost concern arises from the potential misuse of these small-sized vehicles in illicit activities such as unauthorized surveillance, smuggling contraband, or disrupting critical infrastructure significant security threats. Recognizing the gravity of this issue, we have opted to introduce an innovative approach to automate the detection processes for aerial vehicles. This initiative aims to deploy effective drone detection systems to mitigate risks and safeguard against illegal activities. We put use to two datasets from GitHub depot. Cepstral, spectral, and time domain features were extracted from the data, followed by classification. We conducted two experiments, with the first (Drone, No-Drone) yielding 98.6% accuracy, using the Ensemble (Bagged Trees) classifier. The second set of experimentation addressed five classes: Background Noises, Bebop Drone, Drone, Helicopter, and Mambo Drone. Ensemble (Bagged trees) again outperformed all other classifiers and achieved 98.3% accuracy. The results highlight that our proposed framework gives effective results based on audio signals of different aerial vehicles.

关键词： Machine learning algorithms Accuracy Cepstral analysis Surveillance Signal processing algorithms Feature extraction Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Clustering Algorithms to Analyze the Road Traffic Crashes

Clustering Algorithms to Analyze the Road Traffic Crashes

引用

2021 International Conference on science and Contemporary Technologies, ICSCT 2021

作者： Islam, Mahnaz Rafia Jenny, Israt Jahan Nayon, Moniruzzaman Islam, Md. Rajibul Amiruzzaman, Md Abdullah-Al-Wadud, M. University of Asia Pacific Dept. Computer Science and Engineering Dhaka1205 Bangladesh West Chester University Department of Computer Science West ChesterPA19383 United States King Saud University Department of Software Engineering Riyadh11543 Saudi Arabia

ISBN: (纸本)9781665421324

Selecting an appropriate clustering method as well as an optimal number of clusters in road accident data is at times confusing and difficult. This paper analyzes shortcomings of different existing techniques applied to cluster accident-prone areas and recommends using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Ordering Points To Identify the Clustering Structure (OPTICS) to overcome them. Comparative performance analysis based on real-life data on the recorded cases of road accidents in North Carolina also show more effectiveness and efficiency achieved by these algorithms. © 2021 IEEE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Accelerating Real-Time Imaging for Radiotherapy: Leveraging Multi-GPU Training with PyTorch 22

Accelerating Real-Time Imaging for Radiotherapy: Leveraging ...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Obe, Ruth Kaufmann, Brandt Baird, Kaelen Kadel, Sam Soltani, Yasmin Cham, Mostafa Gobbert, Matthias K. Barajas, Carlos A. Jiang, Zhuoran Sharma, Vijay R. Ren, Lei Peterson, Stephen W. Poif, Jerimy C. U. of Houston-Clear Lake Dept. of Computer Science and of Software Engineering United States U. of San Francisco Dept. of Mathematics and Statistics United States Skidmore College Dept. of Computer Science and of Mathematics United States Mount Holyoke College Dept. of Computer Science and of Psychology United States U. of Houston Dept. of Biomedical Engineering United States U. of Maryland Dept. of Information Systems Baltimore County United States U. of Maryland Dept. of Mathematics and Statistics Baltimore County United States Medical Physics Graduate Program Duke University United States U. of Maryland School of Medicine Dept. of Radiation Oncology United States U. of Maryland School of Medicine Department of Radiation Oncology United States U. of Cape Town Dept. of Physics South Africa H3D Inc. United States

ISBN: (纸本)9798350345346

Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy tissues. Real-time imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera's non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera's image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch's flexibility, powerful capabilities in handling sequential data, and enhanced G PU usage. This accelerates the model's computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7 % to over 60 %. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple G PU s, which significantly reduced the training time with a minor impact on model accuracy. © 2023 IEEE.

关键词： Clas-sification Compton camera Distributed Data Parallelism Proton beam therapy PyTorch Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Exploring Relationships among Bitcoin’s Market Price, Energy Consumption and Carbon Dioxide Emissions: A Machine Learning Approach

Exploring Relationships among Bitcoin’s Market Price, Energ...

引用

Humanitarian Technology Conference (KHI-HTC), IEEE Karachi Section

作者： Aadil Jamali Najma Imtiaz Ali Imtiaz Ali Brohi Nadeem Ahmed Kanasro Muhammad Umar Murad Asad Ali Jamali IMCS University of Sindh Jamshoro Pakistan Dept. of Computer Science Government College University Hyderabad Pakistan Dept. of Software Engineering Istanbul Aydin University Istanbul Turkey Dept. of Economics University of Essex Colchester United Kingdom

The cryptocurrency boom has resulted in a substantial rise in energy usage and carbon emissions. The mining process of Bitcoin is notorious for its energy intensive process because it requires huge computational power. The carbon footprint of Bitcoin mining is a growing concern that’s why we have to analyze the number of CO2 emissions resulting from the mining procedure. In this study, we have utilized machine learning techniques to examine the number of CO2 emissions generated by Bitcoin mining, analyzed the correlations between Bitcoin price, electricity consumption, and CO2 emissions, and pinpoint the factors during the process of Bitcoin mining that leads to CO2 emissions. We gathered global data set on Bitcoin electricity consumption, prices, and CO2 emissions. We trained supervised machine learning model (Regression) in Python to analyze and investigate the data. Our research findings have great implications for policymakers and researchers worried about the impact of the latest technologies on the environment, and in future Bitcoin policies and practices; they should prioritize sustainability and reduce the carbon footprint of mining operations. In the end, our research will provide valuable insights into the environmental impact of Bitcoin mining, highlight the factors that cause CO2 emissions and underscored the need for further research and action to reduce the carbon footprint of cryptocurrencies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Breast Cancer: A Machine Learning Approach 3

Performance Analysis of Breast Cancer: A Machine Learning Ap...

引用

3rd International Conference on Inventive Research in Computing Applications, ICIRCA 2021

作者： Khatun, Tania Utsho, Md. Mahfuzur Rahman Islam, Md. Ashiqul Zohura, Mst. Fatematuz Hossen, Md. Sagar Rimi, Robaiya Akter Anni, Sabiha Jannat Daffodil International University Dept. of Computer Science and Engineering Dhaka Bangladesh Daffodil International University Dept. of Software Engineering Dhaka Bangladesh Shahabuddin Medical College Gulshan-2 Dhaka Bangladesh

ISBN: (纸本)9780738146270

Nowadays, breast cancer is the most emerging diseaseamong women both in developed as well as developing countries. Due to increased life prospects, increased urbanization, and therelinquishment of western societies, the rareness of breast cancer is supersizing in the developing world. Even it became a second popular cause of cancer that has already been announced. It's very hard to identify the early symptom of this type of cancer for reducing numerous death. Different methods of machine learning and data mining techniques are using for medical diagnosis. In this study, four machine-learning algorithms are applying to analyze breast cancer in the inflammation stage and dig up the most cabbalistic and non-cabbalistic risk factors. To analyze breast cancer data from the Coimbra dataset from the UCI machine learning repository to create accurate prediction models for breast cancer. For getting better performance and to get higher accuracy Naïve Bayes (NB), Random Forest (RF), Multilayer Perceptron (MLP), Simple Logistic Regression (SLR) are using to find out some higher accuracy sequentially 70%, 68%, 85%, and 75%. Among all the above algorithms a better accuracy was achieved using Multi-layer Perceptron. Linear Regression (LiR) models are applying to dig up the most cabbalistic and non-cabbalistic risk factors of breast cancer. These results will help the doctor to detect breast cancer easily in the early stage and take the necessary steps. © 2021 IEEE.

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

VR REAL RUN: An immersive Oculus Quest 2-Based Virtual Reality Exergaming 4

VR REAL RUN: An immersive Oculus Quest 2-Based Virtual Reali...

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Mambu, Joe Y. Rismayani Sihotang, Jay Idoan Rantung, Vivi Peggy Computer Science Faculty Universitas Klabat Airmadidi Indonesia Dipa Makassar University Dept. of Software Engineering Makassar Indonesia Faculty of Information Technology Universitas Advent Indonesia Bandung Indonesia Faculty of Information System Universitas Negeri Manado Tondano Indonesia

ISBN: (纸本)9781665453950

There are many different types of exergaming, but one of the most engaging one is the one with virtual reality. This type of gaming allows you to immerse yourself in a completely different world, and it can be a lot of fun. Due to Covid-19 pandemic many people resort to their usual exercise activities and opt to do it at home yet only to find a monotonous and boring fitness routine. VR Real Run is aimed to give a solution on how to have fun and to get fit at the same time. By using the latest and front runner in the VR headsets products, the Oculus Quest 2, we developed an exergame that require user to run in place and jump to play. It also features high score to motivate users in perform better in the next session. A black box test has been well performed and a usability test was came out with a 79 SUS score which translate the application as 'good' therefore its usability is acceptable. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Combined Attack Scenario to Exploit the Join Procedure of LoRaWAN 13

A Combined Attack Scenario to Exploit the Join Procedure of ...

引用

13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2021

作者： Le, Duc Tran Dinh, Truong Duy Pham, Van Dai Kirichek, Ruslan Filin, Egor Shestakov, Alexander University of Science and Technology The University of Danang Danang Viet Nam Bonch-Bruevich Saint Petersburg State University of Telecommunications Dept. of Software Engineering and Computer Science Saint-Petersburg Russia

ISBN: (纸本)9781665402194

In the LoRaWAN network, end devices must initiate the join operation by sending packets to the Network Server. This process contains several flaws that attackers can use to disrupt network functioning. We will study, analyze, and compare several techniques for exploiting vulnerabilities that are typically conducted during the join procedure in LoRaWAN. Additionally, we propose considering a possible attack scenario, which may occur when the attacker combines some attack techniques to exploit the join procedure. and copy;2021 IEEE. © 2021 IEEE computer Society. All rights reserved.

关键词： Jamming

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：