检索结果-内蒙古大学图书馆

Revolutionizing Medical Diagnostics: Exploring Creativity in AI for Biomedical Image Analysis

Revolutionizing Medical Diagnostics: Exploring Creativity in...

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Krishnamoorthy, P. Swetha, Devulapally Geetha, Pamidimukkala Sai Karunambiga, K. Ayyasamy, Ramesh Kumar Kiran, Ajmeera Thiruthangal Nadar College PG Department of Computer Science Tamil Nadu Chennai India Vaagdevi Engineering College Department of Computer Science and Engineering Telangana Bolli Kunta India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram India Karpagam Institute of Technology Department of CSE Tamil Nadu Coimbatore India Faculty of Information and Communication Technology Kampar Malaysia MLR Institute of Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798331540685

Biomedical image analysis plays a crucial role in the early and accurate diagnosis of diseases, significantly impacting patient outcomes. This study presents an innovative approach to biomedical image analysis by integrating machine learning techniques with a user-friendly web interface. The system takes input images uploaded through the web interface and processes them using advanced machine learning algorithms implemented in Python. The goal is to automate the detection of diseases from these images, enhancing the efficiency and precision of diagnosis. Convolutional Neural Networks (CNNs), a specialized class of deep learning models designed for image analysis, are employed to learn and characterize disease-specific patterns. The proposed approach is evaluated using diverse biomedical images encompassing various diseases and conditions. Extensive experiments demonstrate the system's effectiveness, achieving high accuracy, sensitivity, and specificity in disease detection. Integrating machine learning with a web interface simplifies the diagnostic process and enables remote consultations, making healthcare services more accessible and timelier. In conclusion, this study presents a robust framework for automated biomedical image analysis, demonstrating the potential of machine learning and web technologies in revolutionizing healthcare diagnostics. The system's accuracy and user-friendly interface make it a valuable tool for healthcare professionals, contributing to early disease detection and improved patient care. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Pre-Impact and Impact Fall Detection Based on a Multimodal Sensor Using a Deep Residual Network

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3371-3385页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Image Information and Intelligence Laboratory Department of Computer EngineeringFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayaoThailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok 10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research Institute King Mongkut’s University of Technology North BangkokBangkok 10800Thailand

Falls are the contributing factor to both fatal and nonfatal injuries in the ***,pre-impact fall detection,which identifies a fall before the body collides with the floor,would be ***,researchers have turned their attention from post-impact fall detection to pre-impact fall ***-impact fall detection solutions typically use either a threshold-based or machine learning-based approach,although the threshold value would be difficult to accu-rately determine in threshold-based ***,while additional features could sometimes assist in categorizing falls and non-falls more precisely,the esti-mated determination of the significant features would be too time-intensive,thus using a significant portion of the algorithm’s operating *** this work,we developed a deep residual network with aggregation transformation called FDSNeXt for a pre-impact fall detection approach employing wearable inertial *** proposed network was introduced to address the limitations of fea-ture extraction,threshold definition,and algorithm *** training on a large-scale motion dataset,the KFall dataset,and straightforward evaluation with standard metrics,the proposed approach identified pre-impact and impact falls with high accuracy of 91.87 and 92.52%,*** addition,we have inves-tigated fall detection’s performances of three state-of-the-art deep learning models such as a convolutional neural network(CNN),a long short-term memory neural network(LSTM),and a hybrid model(CNN-LSTM).The experimental results showed that the proposed FDSNeXt model outperformed these deep learning models(CNN,LSTM,and CNN-LSTM)with significant improvements.

关键词： Pre-impact fall detection deep learning wearable sensor deep residual network

来源：评论

学校读者我要写书评

暂无评论

Deployment of neural networks for WLAN thumbprint indoor positioning system

引用

International Journal of Information Technology (Singapore) 2025年 1-7页

作者： Kushwaha, Ajay Agarwal, Trapty Singh, Manpreet MP, Sunil Sharma, Amit Jain, Romil Bhuvaneswari, P. Computer Science and Engineering Rungta College of Engineering and Technology Chhatisgarh Bhilai India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Centre of Research Impact and Outcome Chitkara University Punjab India Department of Electronics and Communication Engineering Faculty of Engineering and Technology Jain (Deemed-to-be University) Karnataka Bangalore India School of Computer Applications Lovely Professional University Punjab India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh Chandigarh India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science and Technology Chennai India

With the application and development of related technologies based on user location information, location-based services have become essential for daily lives. Despite this fact, Wireless Local area networks (WLAN’s) often face time complexities in streamlining and collection of data. Thus, the given paper introduces a deep-learning model based on convolutional neural network (CNN) to predict user’s indoor location from the received wireless signal strength fingerprint maps. The aim is to enhance WLAN indoor localization by streamlining the data collection process. The proposed indoor positioning model leverages a region of interest (ROI) extraction technique to simulate the wireless received signal strength intensity in WLAN’s. By incorporating this advanced technique, the model aims to improve the accuracy and efficiency of WLAN localization. To optimize and evaluate the model’s performance in real-world scenarios, experiments are conducted using simulated datasets obtained from the publicly available database such as UCI repository. The results show that the proposed model attains the highest validation accuracy (97.11%) and training accuracy (97.34%) as compared to the existing deep learning algorithms used for indoor localization. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： CNN Deep learning Indoor localization Region of interest (ROI) Signal strength WLAN

来源：评论

学校读者我要写书评

暂无评论

Innovative methods of signal processing for hydrogen-filled proportional counters

引用

IEEE Sensors Journal 2025年第11期25卷 19159-19167页

作者： Horna, Aleš Kolář, Ondřej Kubíček, Michal Czakoj, Tomáš Košťál, Michal Mazánková, Věra Petr, Jiří Cvachovec, František Ančář, Aleš Král, Jan Přenosil, Václav Matěj, Zdeněk Masaryk University Faculty of Informatics Department of Computer Systems and Communications Brno602 00 Czech Republic Brno University of Technology Faculty of Electrical Engineering and Communication Department of Radioelectronics Brno616 00 Czech Republic Research Centre Řež Husinec-Řež250 68 Czech Republic University of Defence Faculty of Military Technology Department of Mathematics and Physics Brno602 00 Czech Republic VF a.s. Černá Hora 679 21 Czech Republic

Proportional counters filled with hydrogen are suitable for fast neutron detection and spectrometry. As their sensitivity is not limited only to this type of ionizing radiation as desired, an approach suitable for event discrimination was investigated. Several counters of the given construction were subjected to various radiation fields and the effort was directed to the examination of pulse-shape discrimination method intended to distinguish neutrons from gamma rays and parasitic events (microdischarges) if these also occurred. Rising edge duration of the output pulses and their amplitudes were mapped into diagrams enabling visual discrimination while the criteria for further computational processes are to be determined. Pulse waveforms from charge-sensitive preamplifier with the proportional counters connected were recorded using an FPGA-based custom-build acquisition unit and then post-processed. Moreover, the possibility of operation verification and energy calibration based on the introduction of helium-3 admixture into the gas filling was studied, as well as the energy resolution abilities. Also, the theoretical basis for particle discrimination is presented in the form of description of events and principles involved. © 2001-2012 IEEE.

关键词： Gamma rays

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of CNN and SVM Machine Learning Techniques for Plant Disease Detection 4th

Comparative Analysis of CNN and SVM Machine Learning Techniq...

引用

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

作者： Adeniyi, Abidemi Emmanuel Madamidola, Olugbenga Ayomide Awotunde, Joseph Bamidele Misra, Sanjay Agrawal, Akshat Department of Computer Science College of Computing and Communication Studies Bowen University Iwo Nigeria Department of Information Technology Federal University of Technology Akure Nigeria Department of Computer Science Faculty of Communication and Information Sciences University of Ilorin Ilorin Nigeria Department of Applied Data Science Institute for Energy Technology Halden Norway Department of Computer Science & Engineering Amity University Haryana Gurugram122412 India

ISBN: (纸本)9789819700363

The growing advancement of different jobs, skills and businesses has stimulated the spread of diseases. Most of the time, these diseases can cross countries’ borders and spread at a very rapid rate. Avoiding and detecting these infections have proved to be a major problem for our public health and one that must be treated with great importance. Crop disease has haunted, farmers have been victimized for several decades, and a remedy must be offered to halt this damage. As a result, a system should be developed to detect plant disease. Untreated plant diseases ultimately result in a loss to the farmer. Traditional methods of detecting plant disease have become less efficient and inaccurate;thus there is need to improve on the techniques of plant disease detection, as a reliable detection of plant diseases will greatly improve the quality of food crops produced and decrease the threat plant diseases pose to food security. Therefore, this study is aimed at analyzing comparatively, two machine learning language techniques convolutional neural network (CNN) and support vector machine (SVM) in terms of their respective accuracy in detecting plant diseases through their leaves in which both algorithms are used for the automatic diagnosis of plant disease. From the experimental test conducted on various plants using CNN and SVM algorithms, CNN had an accuracy of 98%, while SVM had an accuracy of 62% on various plant leaves used. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Utilizing Cutting-Edge Machine Vision Techniques for Swift Anomaly Detection in Suboptimal Surveillance Environments 3

Utilizing Cutting-Edge Machine Vision Techniques for Swift A...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Yadav, Rakesh Kumar Veena, C.S. Sudhamsu, Gadug Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350343274

In the realm of surveillance and anomaly detection, the proposed Adaptive Multimodal Anomaly Detection (AMAD) method stands as an innovative and potent approach. The objective of this method is to detect anomalies swiftly and accurately in suboptimal surveillance environments by amalgamating state-of-the-art machine vision techniques with multimodal data fusion. The core idea revolves around leveraging advanced deep learning architectures and statistical models, thereby enhancing the performance of anomaly detection systems. The AMAD method initiates with Algorithm 1: Multimodal Data Fusion, a process that involves integrating multimodal data streams, such as visual, thermal, and infrared information, into a unified feature space. This integration is accomplished using a weighted sum approach, allowing varying importance levels to be assigned to each modality based on weights (α, β, γ). This fusion strategy proves pivotal in capturing a holistic representation of the environment. Convolutional Neural Network (CNN) for Feature Learning follows, where a CNN architecture is employed to learn robust and discriminative features from the fused data. This study showcases that AMAD, with its multimodal integration, deep learning-based feature extraction, and efficient scoring mechanism, triumphs over traditional anomaly detection techniques. It significantly contributes to enhanced anomaly detection capabilities, emphasizing its potential for bolstering public safety and security in dynamic and challenging technological landscapes. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MIMO-NOMA with OSTBC for B5G Cellular Networks with Enhanced Quality of Service 10

MIMO-NOMA with OSTBC for B5G Cellular Networks with Enhanced...

引用

10th International Conference on Wireless Networks and Mobile communications, WINCOM 2023

作者： Sadia, Haleema Iqbal, Hafsa Ahmed, Ridha Alaa Ghulam Ishaq Khan Institute of Engineering and Technology Faculty of Electrical Engineering Topi Pakistan National University of Sciences and Technology School of Electrical Engineering and Computer Science Islamabad Pakistan University of Kufa Department of Electronics and Communication Engineering Najaf Iraq

ISBN: (纸本)9798350329674

Non-orthogonal multiple access (NOMA) scheme has proved a potential candidate to meet the design challenges of orthogonal multiple access (OMA) schemes. High spectrum efficiency and higher data rates are further achieved by integrating NOMA with multiple input multiple output (MIMO) technology. In this article, we have explored orthogonal space-time block coding (OSTBC) to improve the quality of service (QoS) for the proposed MIMO-NOMA framework. We specifically employed the Alamouti STBC scheme, which provides full diversity for the proposed network. At the transmitter side, OSTBC and power domain multiplexing with superposition coding are utilized, while at the reception side, a low complexity maximum likelihood (ML) detector is used, followed by successive interference cancellation (SIC). Based on bit error rate (BER) evaluations, Monte Carlo simulations are performed to analyze the performance of OSTBC MIMO-NOMA system under various fading channels. The proposed framework is further investigated with a higher modulation scheme and different channel code rates. The investigated Alamouti scheme provides a maximum diversity gain of 2M (M shows the number of receiving antennas) without any need for channel state information at the transmitter end and a less complex ML detector at the receiver end. This research lays the groundwork for designing adaptive modulation and coding methods for future MIMO-NOMA based B5G wireless communication systems. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Automatic Cardiovascular Disease Prediction Employing ECG Signals

引用

computer Modeling in engineering & Sciences 2023年第11期137卷 1677-1694页

作者： Muhammad Tayyeb Muhammad Umer Khaled Alnowaiser Saima Sadiq Ala’Abdulmajid Eshmawi Rizwan Majeed Abdullah Mohamed Houbing Song Imran Ashraf Department of Computer Science&Information Technology The Islamia University of BahawalpurBahawalpur63100Pakistan Department of Computer Engineering College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Science Khwaja Fareed University of Engineering and Information TechnologyRahim Yar KhanPakistan Department of Cybersecurity College of Computer Science and EngineeringUniversity of JeddahJeddah21959Saudi Arabia Faculty of Computer Science and Information Technology Universiti Tun Husein OnnMalaysia(UTHM)Bahru80536Malaysia Research Centre Future University in EgyptNew Cairo11745Egypt Department of Information Systems University of MarylandBaltimore CountyBaltimoreMD 21250USA Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-si38541Korea

Cardiovascular problems have become the predominant cause of death worldwide and a rise in the number of patients has been observed ***,electrocardiogram(ECG)data is analyzed by medical experts to determine the cardiac abnormality,which is *** addition,the diagnosis requires experienced medical experts and is ***,automated identification of cardiovascular disease using ECGs is a challenging problem and state-of-the-art performance has been attained by complex deep learning *** study proposes a simple multilayer perceptron(MLP)model for heart disease prediction to reduce computational *** dataset containing averaged signals with window size 10 is used as an *** competing deep learning and machine learning models are used for comparison.K-fold cross-validation is used to validate the *** outcomes reveal that the MLP-based architecture can produce better outcomes than existing approaches with a 94.40%accuracy *** findings of this study show that the proposed system achieves high performance indicating that it has the potential for deployment in a real-world,practical medical environment.

关键词： Cardiovascular disease prediction electrocardiograms deep learning multilayer perceptron

来源：评论

学校读者我要写书评

暂无评论

PTS-LIC: Pruning Threshold Searching for Lightweight Learned Image Compression

PTS-LIC: Pruning Threshold Searching for Lightweight Learned...

引用

2023 IEEE International Conference on Visual communications and Image Processing, VCIP 2023

作者： Luo, Ao Sun, Heming Liu, Jinming Lin, Fangzheng Katto, Jiro Yokohama National University Faculty of Engineering Kanagawa Japan Shanghai Jiao Tong University China Waseda University Department of Computer Science and Communication Engineering Tokyo Japan Waseda Research Institute for Science and Engineering Tokyo Japan

ISBN: (纸本)9798350359855

Learned Image Compression (LIC), which uses neural networks to compress images, has experienced significant growth in recent years. The hyperprior-module-based LIC model has achieved higher performance than classical codecs. However, the LIC models are too heavy (in calculation and parameter amounts) to apply to edge devices. To solve this problem, some former papers focus on structural pruning for LIC models. However, they either cause noticeable performance decrement or neglect the appropriate pruning threshold for each LIC model. These problems keep their pruning results sub-optimal. This paper proposes a Pruning Threshold Searching on the hyperprior module for different-quality LIC models. Our method removes most parameters and calculations while keeping the performance the same as the models before pruning. We removed at least 49.8% of parameters and 28.5% of calculations for the Channel-Wise-Context-Model-based models and 29.1% of parameters for the Cheng-2020 models. © 2023 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Static Video Summarization Using Transfer Learning and Clustering 2nd

Static Video Summarization Using Transfer Learning and Clus...

引用

2nd International Conference on Artificial Intelligence: Towards Sustainable Intelligence, AI4S 2024

作者： Kashid, Shamal Awasthi, Lalit K. Berwal, Krishan Saini, Parul Computer Science and Engineering NIT Uttarakhand Srinagar India Faculty of Communication Engineering Military College of Telecommunication Engineering Indore India

ISBN: (纸本)9783031813689

This research presents a novel approach to video summarization (VS) for efficiently extracting keyframes, reducing video redundancy while preserving essential content. The method combines deep learning and clustering techniques to generate concise video summaries by analyzing videos frame by frame. Using a dual convolutional neural network (CNN), we extract deep-level features. K-means clustering is then applied to group the feature descriptors of the video frames into keyframes and non-keyframes. This K-means clustering-based VS (KVS) method effectively selects the most relevant frames from the extracted features. Our proposed KVS approach outperforms existing VS techniques, achieving an average F-score of 73.1 and 76.3 on two benchmark datasets, Open Video and YouTube, respectively, demonstrating its superior ability to produce informative video summaries. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Video analysis

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：