检索结果-内蒙古大学图书馆

Arithmetic Optimization with Ensemble Deep Transfer Learning Based Melanoma Classification

computers, Materials & Continua 2023年第4期75卷 149-164页

作者： K.Kalyani Sara A Althubiti Mohammed Altaf Ahmed ELaxmi Lydia Seifedine Kadry Neunggyu Han Yunyoung Nam Department of Computer Science Dr.Nalli Kuppusamy Arts College(Affiliated to Bharathidasan UniversityTiruchirappalli)Thanjavur613003India Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Lepartment of Computer Engineering College of Computer Engineering&SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansandNorway Department of ICT Convergence Soonchunhyang UniversityKorea

Melanoma is a skin disease with high mortality rate while earlydiagnoses of the disease can increase the survival chances of patients. Itis challenging to automatically diagnose melanoma from dermoscopic skinsamples. computer-Aided Diagnostic (CAD) tool saves time and effort indiagnosing melanoma compared to existing medical approaches. In this background,there is a need exists to design an automated classification modelfor melanoma that can utilize deep and rich feature datasets of an imagefor disease classification. The current study develops an Intelligent ArithmeticOptimization with Ensemble Deep Transfer Learning Based MelanomaClassification (IAOEDTT-MC) model. The proposed IAOEDTT-MC modelfocuses on identification and classification of melanoma from dermoscopicimages. To accomplish this, IAOEDTT-MC model applies image preprocessingat the initial stage in which Gabor Filtering (GF) technique is *** addition, U-Net segmentation approach is employed to segment the lesionregions in dermoscopic images. Besides, an ensemble of DL models includingResNet50 and ElasticNet models is applied in this study. Moreover, AOalgorithm with Gated Recurrent Unit (GRU) method is utilized for identificationand classification of melanoma. The proposed IAOEDTT-MC methodwas experimentally validated with the help of benchmark datasets and theproposed model attained maximum accuracy of 92.09% on ISIC 2017 dataset.

关键词： Skin cancer deep learning melanoma classification dermoscopy computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Analysis of Data Extraction Techniques on Medical Health Records 1

Analysis of Data Extraction Techniques on Medical Health Rec...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Ruwali, Abhishek Bisht, Lavanya Narang, Harshit Das, Purushottam Dhanalakshmi, R. Yadav, Satya Prakash Graphic Era Hill University Computer Science and Engineering Dehradun India Indian Institute of Information Technology Department of Computer Science and Engineering Tamil Nadu Tiruchirappalli India Department of Computer Science and Engineering Greater Noida201306 India

ISBN: (纸本)9798350371802

Extracting cancer-related information from unstructured text presents challenges that require accurate identification and extraction techniques. This study compares three methods: keyword-based matching, regular expression pattern matching, and deep learning-based approaches. The study proposes evaluation metrics including file comparison, cosine similarity, and k-means clustering with Jaccard similarities. The findings demonstrate that the deep learning- based approach achieves the highest accuracy of 99.06%, outperforming the keyword-based (34.27%) and regular expression methods (93.58%). © 2024 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Detecting Misinformation in COVID-19 Content: A Machine Learning and Deep Learning Approach with Word Embeddings

引用

SN computer science 2025年第1期6卷 1-18页

作者： Chabukswar, Arati Shenoy, P. Deepa Venugopal, K.R. Department of Computer Science & Engineering University Visvesvaraya College of Engineering Bangalore University Karnataka Bengaluru 560001 India

Inaccurate information that is purposefully spread for a certain goal known as fake news related to COVID-19 tweets posing threats to public health, harm to the society. But creating a reliable method to identify news of this kind is difficult, particularly when the news is released combining factual and fictitious material. The identification of fake news with COVID-19 is challenging task in Natural Language Processing (NLP). This study uses Machine Learning (ML) models such as Support Vector Machine (SVM), Random Forest (RF), Gaussian Naıve Bayes (NB), Logistic Regression (LR) and Deep Learning (DL) models with several architectures such as Long-short Term memory (LSTM), Bidirectional LSTM with one-hot encoding representation and pre-trained word embeddings such as Word2Vec, GloVe and FastText, trained using 14,571 records on DataCOVID19 dataset obtained by combining datasets from three different sources available in Kaggle and GitHub repository. The tests on a real-world COVID-19 news dataset show that Bi-LSTM model improves performance when built over various embedding techniques such as Word2Vec, GloVe, FastText and One-hot encoding representation achieving highest accuracy score. The findings emphasise the potential of deep learning methods for identifying false news and have important ramifications for curbing the dissemination of false information about COVID-19 tweets known as Fake News Detection (FND). © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19 Deep learning Fake news Machine learning Natural language processing One-hot encoding Social media Word embeddings (Word2Vec, GloVe, FastText)

来源：评论

学校读者我要写书评

暂无评论

A Paradigm Shift in Ethereum Network Analysis Through Google BigQuery,Portation, and Visualization 6

A Paradigm Shift in Ethereum Network Analysis Through Google...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Suresh Kumar, N. Mirdula, S. Singh, Pushpa Gayathri, T. Jayanthi, S. Anandraj, M. School of Computer Science and Engineering Jain Deemed-to-be University Ramanagara India SRM TRP Engineering College Department of Electronic and Communication Engineering Trichy India IILM University Department of Computer Science and Engineering Greater Noida India MVJ College of Engineering Department of Computer Science and Engineering Bangalore India Guru Nanak Institute of Technology Department of Information Technology Ibrahimpatnam India Mahendra College of Engineering Department of Computer Science and Engineering Salem India

ISBN: (纸本)9798350306613

The primary objective of this research is to comprehensively explore and analyze the dynamics of the Ethereum network using innovative methodologies and system architectures. The study aims to extract meaningful statistics from the Ethereum blockchain, focusing on account activity, popularity trends, and the distribution of transactions. Through rigorous data collection, robust query construction, and advanced analytical techniques, the research seeks to provide valuable insights into how the Ethereum network has evolved, particularly in the aftermath of the 'crypto bubble explosion.' The overarching goal is to contribute to the understanding of Ethereum's structural patterns, user behaviors, and the impact of external factors on the network. The research has yielded significant results, unveiling key insights into Ethereum network dynamics. The data collection phase, facilitated by Google BigQuery, successfully captured and filtered relevant information from a specific block range post the 'crypto bubble explosion.' The SQL queries, strategically designed for active account identification and popularity assessment, demonstrated efficiency and accuracy in handling the vast Ethereum dataset. The proposed system, introducing the novel methodology of 'portation,' showcased its efficiency in extracting and interpreting Ethereum blockchain data using Google BigQuery. The system architecture, as illustrated in the diagram, proved to be a well-coordinated and dynamic framework, emphasizing the seamless flow of data and processes. © 2024 IEEE.

关键词： Crypto Bubble Explosion Decentralized Data Transactions Ethereum Blockchain Google BigQuery Power-law Analysis

来源：评论

学校读者我要写书评

暂无评论

3D CNN with Attention Modules for Enhanced COVID-19 and Pneumonia Screening from CT Scans 2

3D CNN with Attention Modules for Enhanced COVID-19 and Pneu...

引用

2nd International Conference on Power, electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Rahman, Taifur Faruk, Md. Farukuzzaman Khansur, Md. Nasif Srizon, Azmain Yakin Hasan, S. M. Mahedy Al Mamun, Md. Hossain, Md. Faruk Rajshahi University of Engineering & Technology Department of Computer Science & Engineering Rajshahi6204 Bangladesh Rajshahi University of Engineering & Technology Department of Electrical & Electronic Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798331517984

During the COVID-19 outbreak, deep-learning techniques have been extensively studied for computer-assisted diagnosis. However, distinguishing COVID-19 from other types of pneumonia remains challenging. This research describes an automated chest CT imaging technique for COVID-19 pneumonia screening. CT scans provide valuable three-dimensional information, aiding in detecting COVID-19 symptoms. The limited availability of comprehensive 3D datasets has slowed the use of attention-based models in this field. To address this, we propose a novel 3D Convolutional Neural Network (CNN) with a residual block incorporating self-attention and spatial attention modules. Our primary goal is accurately classifying COVID-19 and pneumonia cases based on CT scans. Integrating attention modules enhances spatial correlation analysis across CT slices, enabling dynamic re-calibration of the CNN output to identify complex patterns. Training our 3D CNN on CT scan images from the CC-CCII dataset achieved an impressive accuracy rate of 99.42%. Subsequently, we used the CNN's prediction probabilities to construct feature vectors for each sample. By training various machine learning classifiers independently and combining them through soft voting, we achieved a remarkable 98.66% accuracy. This study highlights how our approach can improve pulmonary patient care and diagnostic processes, leveraging state-of-the-art deep learning techniques for accurate and efficient COVID-19 pneumonia screening. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Efficient Smart Public Transit System Using RFID and IoT integration with MERN web applications

Efficient Smart Public Transit System Using RFID and IoT int...

引用

2025 International Conference on computer, electrical and Communication engineering, ICCECE 2025

作者： Madasanal, Kartik Gudnavar, Anand Nagarmunoli, Sreedevi Madagouda, Basavaraj Naregal, Keerti Visvesaraya Technological University Jain College of Engineering and Research Department of Computer Science and Engineering Belagavi India Graphic Era University Department of Computer Science and Engineering Dehradun India S.G.Balekundri Institute of Technology Visvesaraya Technological University Department of Computer Science and Engineering Belagavi India

ISBN: (纸本)9798331513894

This paper develops a Smart Public Transportation System using RFID technology, IoT integration, and a MERN-based web application for increasing the efficiency, accessibility, and user experience of urban transit systems. It addresses problems such as unreliable bus tracking, lack of support for multilingualism, and ineffective communication between operators and passengers. The key hardware components include RFID tags for bus identification, and IoT-enabled bus stations with RFID scanners, speakers, GSM modules for data transmission, and LCD displays. These ensure accurate real-time updates about the bus locations. On the software side, it is supported by a MERN stack, including MongoDB, ***, ***, and ***, providing a responsive web interface that's complemented by *** for dynamic route visualization and WebSockets for live updates. Multilingual support through i18next makes it inclusive for various user groups. The system is efficient in that it only updates when RFID scanners capture bus tags at certain checkpoints, thereby reducing server load much more than GPS-based systems. Additional features include route tracking, interactive maps, ticket pricing, and anonymous passenger chats. Crowd-sourced feedback mechanisms and an admin panel for bus management ensure the reliability and scalability of the system. This work shows the feasibility of cost-effective, scalable, and user-centric modernization of public transportation systems, paving the way for further enhancements such as integrated payment systems and AI-based route optimization. © 2025 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Towards Better Accuracy-Efficiency Trade-Offs: Dynamic Activity Inference via Collaborative Learning From Various Width-Resolution Configurations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6723-6738页

作者： Qin, Lutong Zhang, Lei Li, Chengrun Song, Chaoda Cheng, Dongzhou Wang, Shuoyuan Wu, Hao Song, Aiguo Nanjing Normal University School of Electrical and Automation Engineering Nanjing210023 China Shanghai200240 China Case Western Reserve University Department of Computer and Data Sciences ClevelandOH44106 United States University of Macau Department of Computer and Information Science Taipa999078 China Yunnan University School of Information Science and Engineering Kunming650500 China Southeast University Department of Instrument Science and Engineering Nanjing210096 China

Recently, deep neural networks have triumphed over a large variety of human activity recognition (HAR) applications on resource-constrained mobile devices. However, most existing works are static and ignore the fact that the computational budget usually changes drastically across various devices, which prevent real-world HAR deployment. It still remains a major challenge: how to adaptively and instantly tradeoff accuracy and latency at runtime for on-device activity inference using time series sensor data? To address this issue, this article introduces a new collaborative learning scheme by training a set of subnetworks executed at varying network widths when fueled with different sensor input resolutions as data augmentation, which can instantly switch on-the-fly at different width-resolution configurations for flexible and dynamic activity inference under varying resource budgets. Particularly, it offers a promising performance-boosting solution by utilizing self-distillation to transfer the unique knowledge among multiple width-resolution configuration, which can capture stronger feature representations for activity recognition. Extensive experiments and ablation studies on three public HAR benchmark datasets validate the effectiveness and efficiency of our approach. A real implementation is evaluated on a mobile device. This discovery opens up the possibility to directly access accuracy-latency spectrum of deep learning models in versatile real-world HAR deployments. © 2020 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches to Securing IoT Networks: A Comprehensive Review of Recent Advances 2

Machine Learning Approaches to Securing IoT Networks: A Comp...

引用

2nd IEEE International Conference on Advancements and Key Challenges in Green Energy and Computing, AKGEC 2024

作者： Saini, Harnit Prasad, Sanjeev Kumar Galgotias University School of Computer Science and Engineering Greater Noida India Ajay Kumar Garg Engineering College Computer Science and Engineering Department Ghaziabad India

ISBN: (纸本)9798350390179

The IoT is a network of physical objects embedded with sensors and software, connecting and exchanging data over the internet. With over 7 billion connected devices, experts predict growth to 10 billion by 2020 and 22 billion by 2025. Machine learning ML technologies are advancing quickly, with new algorithms and approaches emerging regularly. In this paper, a review is carried out that helps provide insights into their effectiveness in the current landscape. Different ML techniques are categorized and evaluated based on how they address diverse challenges. Reviewing current ML techniques helps in understanding their strengths and limitations in combating novel attack vectors. Later on, a comparative analysis of these techniques is conducted based on performance metrics. A comprehensive review identifies gaps in current research and practice, highlighting areas where ML techniques might need further development or improvement. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Cyber Attack in IoT Based Model Using ANN Model with Genetic Algorithm 5

Detection of Cyber Attack in IoT Based Model Using ANN Model...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Srivastava, Animesh Sharma, Hemendra Shanker Rawat, Rishikesh Garg, Navin Graphic Era Hill University Department of Computer Science & Engineering Dehradun India Coer University Department of Computer Science & Application Roorkee India Bansal College of Engineering Bhopal India Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350383522

Thanks to the IoT, our everyday lives are now more accessible, connected, and convenient than ever before. Because it facilitates the effortless transfer of massive amounts of data between interconnected devices, it leaves the network vulnerable to various forms of intrusion and attack. As the number of interconnected devices grows, the need for reliable attack detection systems to forestall malicious actions becomes paramount. This paper introduces a strategy for detecting attacks on the Internet of Things (IoT) that integrates Genetic Algorithms (GA) and Artificial Neural Networks (ANN) models. This paper introduces a model for an artificial neural network that uses genetic algorithms to detect attacks on the Internet of Things. While the GA adjusts the hyperparameters of the ANN model, the ANN model is responsible for determining whether network traffic is malicious or not. To evaluate the proposed system, an Internet of Things network traffic dataset was utilized. As demonstrated by the outcomes, the system has a commendable rate of detection. The system can spot DoS attacks. The results show that our method is great at finding attacks on the Internet of Things. we achieved a 99.3 percent accuracy rate with our suggested ANN with GA. © 2024 IEEE.

关键词： artificial neural networks attack detection deep learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Layer Perceptron for Fetal Health Classification Using Cardiotocography Data

引用

computers, Materials & Continua 2024年第8期80卷 2301-2330页

作者： Uddagiri Sirisha Parvathaneni Naga Srinivasu Panguluri Padmavathi Seongki Kim Aruna Pavate Jana Shafi Muhammad Fazal Ijaz Department of Computer Science and Engineering Prasad V Potluri Siddhartha Institute of TechnologyVijayawada520007India Amrita School of Computing Amrita Vishwa VidyapeethamAmaravatiAndhra Pradesh522503India Department of Tele informatics Engineering Federal University of CearáFortaleza60455-970Brazil Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramGunturAndhra Pradesh522302India Department of Computer Engineering Chosun UniversityGwangju61452Republic of Korea School of CSIT Symbiosis Skills and Professional UniversityPune412101India Department of Computer Engineering and Information College of Engineering inWadi AlddawasirPrince Sattam bin Abdulaziz UniversityWadi Alddawasir11991Saudi Arabia School of IT and Engineering Melbourne Institute of TechnologyMelbourne3000Australia

Fetal health care is vital in ensuring the health of pregnant women and the *** check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential *** know the status of the fetus,doctors monitor blood reports,Ultrasounds,cardiotocography(CTG)data,***,in this research,we have considered CTG data,which provides information on heart rate and uterine contractions during *** researchers have proposed various methods for classifying the status of fetus *** processing of CTG data is time-consuming and ***,automated tools should be used to classify fetal *** study proposes a novel neural network-based architecture,the Dynamic Multi-Layer Perceptron model,evaluated from a single layer to several layers to classify fetal *** strategies were applied,including pre-processing data using techniques like Balancing,Scaling,Normalization hyperparameter tuning,batch normalization,early stopping,etc.,to enhance the model’s performance.A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy(97%).An ablation study without any pre-processing techniques is also *** study easily provides valuable interpretations for healthcare professionals in the decision-making process.

关键词： Fetal health cardiotocography data deep learning dynamic multi-layer perceptron feature engineering

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：