检索结果-内蒙古大学图书馆

3rd International Conference on Smart Generation computing, Communication and Networking, SMART GENCON 2023

作者： Rengarajan, A. Kumar, Rohit Sakhare, Nitin N. Thangarasu, N. Mahalakshmi, V. Bhimanpallewar, Ratnmala N. Department of Computer Science and Information Technology Karnataka Bangalore India Vivekananda Global University Department of Civil Engineering Jaipur India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Pune India

ISBN: (纸本)9798350319125

Machine studying is unexpectedly revolutionizing the manner facts is analyzed and utilized in actual-time selections. with the aid of utilising effective algorithms, gadget gaining knowledge of can unlock effective insights from actual-time input statistics greater speedy and as it should be than traditional strategies. however, to make sure its fulfillment and effectiveness, there have to be a quantitative size procedure to assess how device studying algorithms are impacting the effectiveness of actual-time information evaluation. This paper pursuits to provide a comprehensive evaluation of the cutting-edge nation of device learning and its effect on actual-time facts analysis, as well as unique techniques to degree the effectiveness of device learning algorithms. specifically, the paper will observe the use of supervised studying fashions, unsupervised learning fashions, and reinforcement mastering strategies to create efficient and correct fashions that could quickly analyze and produce beneficial insights from real-time statistics. Additionally, this paper will talk various techniques that can be used to quantify the effectiveness of device gaining knowledge of fashions which includes predictive accuracy, records and function selection, and model interpretability. finally, the paper can even discuss challenges and destiny issues for measuring the authentic effect of machine studying on actual-time records analysis. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Fractal Minkowski-shaped resonator for noninvasive biomedical measurements: Blood glucose test

引用

Progress In Electromagnetics Research C 2021年 107卷 143-156页

作者： Obaid, Sarah M. Elwi, Taha A. Ilyas, Muhammad Electrical and Computer Engineering Altinbas University Turkey Department of Communication Engineering Al-Ma’moon University College Baghdad Iraq

This work presents a noninvasive measurement technique to detect the blood glucose level for diabetic individuals using a fractal microwave resonator printed on an FR-4 substrate. The proposed fractal is based on the 1st order of Minkowski open loops (MOL) coupled with an open-stub transmission line (OSTL) to increase the resonator selectivity at 2.45 GHz. Moreover, an air gap in the middle path of the OSTL is filled with multi wall carbon nanotubes patch (CNT) to increase the field fringing at a specific region. The proposed resonator is designed numerically with CST Microwave Studio. The size limitations for biomedical devices are considered to account for wearable applications. Later, an analytical study is presented on the proposed resonator sensitivity. The detection technique is based on the resonant frequency tuning, bandwidth variation, impedance matching change, and phase displacement for the S-parameters in the S11 and S12 spectra. The sample under test is mounted on a CNT patch of the OSTL which employs the characterization of the specimen. The proposed design idea could be generalized for a wide variety of biomedical detection liquids. © 2021, Electromagnetics Academy. All rights reserved.

关键词： Scattering parameters

来源：评论

学校读者我要写书评

暂无评论

Enhancing Mild Cognitive Impairment Detection through Efficient Magnetic Resonance Image Analysis

引用

computers, Materials & Continua 2024年第8期80卷 2081-2098页

作者： Atif Mehmood Zhonglong Zheng Rizwan Khan Ahmad Al Smadi Farah Shahid Shahid Iqbal Mutasem K.Alsmadi Yazeed Yasin Ghadi Syed Aziz Shah Mostafa M.Ibrahim Department of Computer Science and Technology Zhejiang Normal UniversityJinhua321002China Zhejiang Institute of Photoelectronics&Zhejiang Institute for Advanced Light Source Zhejiang Normal UniversityJinhua321004China Department of Data Science and Artificial Intelligence Zarqa UniversityZarqa13100Jordan School of Chemical and Environmental Engineering College of ChemistryChemical Engineering andMaterials ScienceSoochow UniversitySuzhou215123China Department of Management Information Systems College of Applied Studies and Community ServiceImam Abdulrahman Bin Faisal UniversityDammam32244Saudi Arabia Department of Computer Science Al Ain UniversityAbu Dhabi999041United Arab Emirates Department of Electrical Engineering Faculty of EngineeringMinia UniversityMinia61519Egypt Healthcare Technology and Innovation Theme Faculty Research Centre for Intelligent HealthcareCoventry UniversityCoventryCV48BWUK

Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer’s disease(AD).Mild cognitive impairment(MCI)is a condition that falls between the spectrum of normal cognitive function and ***,previous studies have mainly used handcrafted features to classify MCI,AD,and normal control(NC)*** paper focuses on using gray matter(GM)scans obtained through magnetic resonance imaging(MRI)for the diagnosis of individuals with MCI,AD,and *** improve classification performance,we developed two transfer learning strategies with data augmentation(i.e.,shear range,rotation,zoom range,channel shift).The first approach is a deep Siamese network(DSN),and the second approach involves using a cross-domain strategy with customized *** performed experiments on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset to evaluate the performance of our proposed *** experimental results demonstrate superior performance in classifying the three binary classification tasks:NC ***,NC ***,and MCI ***,we achieved a classification accuracy of 97.68%,94.25%,and 92.18%for the three cases,*** study proposes two transfer learning strategies with data augmentation to accurately diagnose MCI,AD,and normal control individuals using GM *** findings provide promising results for future research and clinical applications in the early detection and diagnosis of AD.

关键词： Alzheimer’s disease mild cognitive impairment normal control transfer learning classification augmentation

来源：评论

学校读者我要写书评

暂无评论

A Unique Method of Detection of Edges and Circles of Multiple Objects in Imaging Scenarios Using Line Descriptor Concepts 1

引用

International Conference on Advances in IoT, Security with AI, ICAISA 2023

作者： Patil, Rajesh Maharudra Nagaraja, B.G. Prasad, M.R. Manjunath, T.C. Rayappa, Ravi Electrical Engineering Department SKNS College of Engineering Korti Affiliated to Solapur University Maharashtra Pandharpur India Electronics and Communication Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Computer Science and Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Electronics and Communication Engineering Deparment Dayananda Sagar College of Engineering Bengaluru India Electronics and Communication Engineering Jain Institute of Technology Karnataka Davanagere India

ISBN: (数字)9789819950881

ISBN: (纸本)9789819950874

This paper proposes a novel method for detecting the edges and circles of multiple objects in imaging scenarios using line descriptor concepts. The method involves analyzing the intensity gradient and the orientation of the pixels in the image, and using this information to identify lines and circles that are likely to correspond to object boundaries. The proposed approach is compared with existing methods and is shown to provide superior performance in terms of accuracy and computational efficiency. The method is particularly useful for applications such as object recognition and tracking, where accurate detection of object boundaries is essential. The experimental results demonstrate the effectiveness of the proposed method in detecting edges and circles of multiple objects in different imaging scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Spiking-Transformer Optimization on FPGA for Image Classification and Captioning

Spiking-Transformer Optimization on FPGA for Image Classific...

引用

IEEE Southeastcon

作者： Uchechukwu Leo Udeji Martin Margala Electrical and Computer Engineering department University of Massachusetts Lowell Lowell USA Computing and Informatics department University of Louisiana at Lafayette Lafayette USA

This paper presents an FPGA (Field Programmable Gate Arrays) architecture specifically crafted to optimize spiking transformers on FPGA. The initial phase involved designing transformer networks and conducting training for image classification and captioning tasks using the MNIST and COCO (Microsoft Common Objects In Context) datasets, respectively. Following this, an architecture was developed to replace artificial neurons in the transformer network with spiking neurons. Mixed precision was employed in the design, and the implementation was carried out on both CPU and GPU platforms. Profiling of the program was conducted to identify resource-intensive areas, leading to the proposal of an FPGA model designed to accelerate both training and inference processes. The results showcase significant performance improvements in throughput and a modest enhancement in prediction accuracy compared to certain existing benchmarks. Specifically, the image captioning task achieved approximately 80% accuracy, while the image classification task reached around 93% accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Building Safety Through Machine Learning-Based Smoke Detection

Enhancing Building Safety Through Machine Learning-Based Smo...

引用

Advances in electrical, computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Sulaiman Syed Mohamed Judeson Antony Kovilpillai J Pragya Mahmood Hussain Mir Golda Brunet R Tawseef Ahmad Mir Alliance School of Advanced Computing Alliance University Bangalore India Department of Computer Science & Engineering Government College of Engineering Thanjavur India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

Smoke detection in surveillance systems plays a crucial role in ensuring the safety and security of various environments, including buildings, forests, and industrial sites. In this paper, a comprehensive analysis of machine learning algorithms applied to smoke detection is presented. The proposed technique is validated using the Smoke Detection Dataset from Kaggle. The dataset comprises a diverse collection of images captured in different scenarios, including both smoke and non-smoke instances. The performance of various machine learning classifiers was evaluated. This included ensemble methods Random Forest (RF), Gradient Boosting (GB), AdaBoost (AB), linear models Logistic Regression (LR), kernel methods Support Vector Machine (SVM), decision-based methods Decision Tree (DT), and nearest neighbor methods K-Nearest Neighbors (KNN). Their precision, recall, AUC-ROC score, and Intersection over Union (IoU) are measured to assess their effectiveness in smoke detection. The results highlight that classifiers such as RF, DT, KNN, GB and AdaBoost achieve outstanding performance, with perfect scores in multiple metrics.

关键词： Support vector machines Radio frequency Smart buildings Surveillance Buildings Urban areas Nearest neighbor methods Feature extraction Safety Smoke detectors

来源：评论

学校读者我要写书评

暂无评论

Deciphering the impact of diversity in CNN-based ensembles on overcoming data imbalance and scarcity in medical datasets: A case study on diabetic retinopathy

引用

Informatics in Medicine Unlocked 2024年 49卷

作者： Inamullah Hassan, Saima Belhaouari, Samir Brahim Amin, Ibrar Institute of Computing Kohat University of Science and Technology Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Department of Electrical Engineering and Computer Science Khalifa University

Early detection of diabetic retinopathy (DR) is critical in preventing vision loss. However, building accurate Artificial intelligence (AI) models for multiple classes, including early-stage (Class-1) detection, is challenging due to limited and imbalanced medical datasets. The availability of such datasets is restricted due to ethical and privacy concerns. Traditional ensemble models also struggle with raw medical images, further complicating the issue as they require structured data. This study presents a novel deep learning-based ensemble model (EM) designed for multiple and specifically for precise early stage (Class 1) DR classification. The EM uses eight diverse Convolutional Neural Networks (CNNs) with carefully crafted strategies to enhance diversity. Data augmentation and generation techniques address imbalanced data through data diversity, while parameter and architectural diver-sity within CNNs-based EM maximize predictive performance. Evaluation on the publicly available Kaggle APTOS DR dataset demonstrates significant improvement over individual models and existing approaches. The proposed EM achieves multi-class accuracy (93.00 %), precision (93.00 %), sensitivity (98.00 %), and specificity (99.00 %). This research highlights the effectiveness of diversified CNNs ensembles in overcoming challenges posed by imbalanced and scarce data for multiple-class DR classification. This approach paves the way for developing robust and accurate AI-powered diagnostic tools for improved diabetic retinopathy screening. © 2024 The Authors

关键词： Convolutional neural networks Deep learning Diabetic retinopathy Ensemble diversity Ensemble model Machine learning Medical image analysis Retinal images

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Grover's Quantum Algorithm Simulation: Cloud-Based Parallel computing Enhancements 4

A Novel Approach to Grover's Quantum Algorithm Simulation: C...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Gejea, Adugna Mekonnen Mayakannan, S. Palacios, Rosana Marianela Hamad, Abdulsattar Abdullah Sundaram, Barani Alghamdi, Wajdi Bule Hora University Department of Computer Science Ethiopia Vidyaa Vikas College of Engineering and Technology Department of Mechanical Engineering Tamilnadu Namakkal India Department of Marketing Engineering Riobamba060155 Ecuador Dijlah University College Department of Medical Laboratory Techniques Baghdad Iraq King Abdulaziz University Faculty of Computing and Information Technology Department of Information Technology Jeddah21589 Saudi Arabia

ISBN: (纸本)9798350300888

A truly universal quantum computer is still on the small scale at the present. There has been no transition from the laboratory use of quantum computers to more widespread use of the technology. As a result, quantum simulation has emerged as the accepted norm for supporting the validation of quantum algorithms. Many conventional algorithms benefit from grover's quantum search method because it accelerates their usage of search heuristics. For better multi-core load balancing, memory utilization, and simulation efficiency, this research presented a high-performance grover method simulation that combines the benefits of grover's technique with the parallel of cloud computing. This study also suggests and experimentally compares five distinct cloud-based computing architectures that are well-suited to quantum simulation. Through research and testing, this study also verifies the optimization's efficiency. Depending on the size of the current configuration, the experimental results reveal that the simulation can reach 31 bits. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

AsT: An Asymmetric-Sensitive Transformer for Osteonecrosis of the Femoral Head Detection 37

AsT: An Asymmetric-Sensitive Transformer for Osteonecrosis o...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Chen, Haoyang Liu, Shuai Lu, Feng Li, Wei Sheng, Bin Li, Mi Jin, Hai Zomaya, Albert Y. National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Centre for Distributed and High Performance Computing School of Computer Science The University of Sydney Australia Department of Computer Science and Engineering Shanghai Jiao Tong University China Tongji Hospital Tongji Medical College Huazhong University of Science and Technology China

ISBN: (纸本)9781577358800

Early diagnosis of osteonecrosis of the femoral head (ONFH) can inhibit the progression and improve femoral head preservation. The radiograph difference between early ONFH and healthy ones is not apparent to the naked eye. It is also hard to produce a large dataset to train the classification model. In this paper, we propose Asymmetric-Sensitive Transformer (AsT) to capture the uneven development of the bilateral femoral head to enable robust ONFH detection. Our ONFH detection is realized using the self-attention mechanism to femoral head regions while conferring sensitivity to the uneven development by the attention-shared transformer. The real-world experiment studies show that AsT achieves the best performance of AUC 0.9313 in the early diagnosis of ONFH and can find out misdiagnosis cases firmly. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Synthesizing Supervisors with a Minimum Control Base for Discrete-Event Systems

Synthesizing Supervisors with a Minimum Control Base for Dis...

引用

2022 American Control Conference, ACC 2022

作者： Hugh Moulton, Richard Scott, Stephen H. Rudie, Karen Queen's University Department of Electrical and Computer Engineering Kingston Canada Queen's University Department of Biomedical and Molecular Science The Centre for Neuroscience Studies and the Department of Medicine Kingston Canada Queen's University Department of Electrical and Computer Engineering The School of Computing and the Ingenuity Labs Research Institute Kingston Canada

ISBN: (数字)9781665451963

ISBN: (纸本)9781665451963

Controlling a discrete-event system commonly entails synthesizing a supervisor to ensure that the plant's closed-loop behaviour respects a certain specification. In the traditional approach to this problem, if the desired behaviour is not controllable then the specification's supremal controllable sublanguage is enforced instead. Here we invert the problem and formulate the Minimum Control Base Problem, with the goal of finding the minimum set of controllable events that guarantees controllability for the desired behaviour. We show that the sets of controllable events that maintain controllability for the desired behaviour form a complete lattice with respect to subset inclusion and that there is therefore a minimum capability supervisor for any desired sublanguage of the plant's behaviour. We apply our techniques to the Small Factory problem and discuss further applications including systems design, dynamic discrete-event systems, and biological systems. © 2022 American Automatic Control Council.

关键词： Supervisory personnel

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：