检索结果-内蒙古大学图书馆

CNN-Based Deep Learning Model for Early Identification and Categorization of Melanoma Skin Cancer Using Medical Imaging

引用

SN computer science 2024年第7期5卷 911页

作者： Pandimurugan, V. Ahmad, Sultan Prabu, A.V. Rahmani, Mohammad Khalid Imam Abdeljaber, Hikmat A. M. Eswaran, Malathi Nazeer, Jabeen Computer Science and Engineering Acharya Institute of Technology Bangalore India Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia University Center for Research and Development (UCRD) Department of Computer Science and Engineering Chandigarh University Gharuan Punjab Mohali 140413 India Department of Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP Guntur 522502 India College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Department of Computer Science Faculty of Information Technology Applied Science Private University Amman Jordan MEU Research Unit Middle East University Amman 11831 Jordan Department of Computer Technology Kongu Engineering College Perundurai Tamil Nadu Erode India

In human life, skin cancer is a curse. If not appropriately diagnosed, it spreads around all body parts in the earlier stage. The melanoma skin cancer death rate is 75% all over the world. There is an urgent need for a cure to be in place. Swarm and evolutionary computation for healthcare deals with real-world healthcare applications. One of the best ways to do this is to find the genes that need to be turned off such that only cancer cells can die. The current therapies used to cure cancer focus on turning off cancer cells but, at times, affect healthy tissues. Using the power of Artificial Intelligence, one can easily mark out the cancer-affected area and provide treatment accordingly. Segmentation techniques can be used to mark cancer lesions, and advanced deep learning algorithms in computer vision can help classify which class of cancer lesions. Automatic detection of melanoma by using a dermoscopic sample is tricky to find the stage and percentage of lesions affected by using deep convolutional neural networks with the help of machine vision tools. To predict skin lesions, we developed a model with three layers, each having output channels of 16, 32, and 64, respectively. For this research, different samples were collected from the international skin imaging collaboration database (ISIC2019, ISIC2020, ISIC2021). The study computed the most important parameters for classifying and identifying the lesion with accuracy, precision, recall, and specificity values. The proposed DCNN model classifier attained an accuracy of 88.82%, 93.45%, and 95.15% with the respective datasets of ISIC2019, ISIC2020, and ISIC2021, indicating high performance compared with the other state-of-the-art networks. The proposed model is a better framework for automating early detection and classification of melanoma skin cancer to protect many lives and avoid mishaps. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Classification Convolution neural network Deep learning Medical imaging Melanoma Skin cancer Swarm and evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Machine Learning for Early Detection of Stroke and Haemorrhage

引用

computers, Materials & Continua 2022年第7期72卷 775-796页

作者： Zeyad Ghaleb Al-Mekhlafi Ebrahim Mohammed Senan Taha H.Rassem Badiea Abdulkarem Mohammed Nasrin M.Makbol Adwan Alownie Alanazi Tariq S.Almurayziq Fuad A.Ghaleb Department of Information and Computer Science College of Computer Science and EngineeringUniversity of Ha’ilHa’il81481Saudi Arabia Department of Computer Science&Information Technology Dr.Babasaheb Ambedkar Marathwada UniversityAurangabad431004India Faculty of Science and Technology Bournemouth UniversityPooleBH125BBUK Department of Computer Engineering College of Computer Science and EngineeringUniversity of Ha’ilHa’il81481Saudi Arabia College of Computer Science and Engineering Hodeidah UniversityHodeidah966Yemen School of Computing Faculty of EngineeringUniversiti Teknologi MalaysiaJohor BahruJohor81310Malaysia

Stroke and cerebral haemorrhage are the second leading causes of death in the world after ischaemic heart *** this work,a dataset containing medical,physiological and environmental tests for stroke was used to evaluate the efficacy of machine learning,deep learning and a hybrid technique between deep learning and machine learning on theMagnetic Resonance Imaging(MRI)dataset for cerebral *** the first dataset(medical records),two features,namely,diabetes and obesity,were created on the basis of the values of the corresponding *** t-Distributed Stochastic Neighbour Embedding algorithm was applied to represent the high-dimensional dataset in a low-dimensional data ***,the Recursive Feature Elimination algorithm(RFE)was applied to rank the features according to priority and their correlation to the target feature and to remove the unimportant *** features are fed into the various classification algorithms,namely,Support Vector Machine(SVM),K Nearest Neighbours(KNN),Decision Tree,Random Forest,and Multilayer *** algorithms achieved superior *** Random Forest algorithm achieved the best performance amongst the algorithms;it reached an overall accuracy of 99%.This algorithm classified stroke cases with Precision,Recall and F1 score of 98%,100%and 99%,*** the second dataset,the MRI image dataset was evaluated by using the AlexNet model and AlexNet+SVM hybrid *** hybrid model AlexNet+SVM performed is better than the AlexNet model;it reached accuracy,sensitivity,specificity and Area Under the Curve(AUC)of 99.9%,100%,99.80%and 99.86%,respectively.

关键词： Stroke cerebral haemorrhage deep learning machine learning t-SNE and RFE algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Movie Category Prediction with Hybrid Models for Enhanced Interpretability

Enhancing Movie Category Prediction with Hybrid Models for E...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Namitha, Seelam Prathibha, J. Reddy, Thokala Karthik Hariharan, Shanmugasundaram Kekreja, Vinay Prasad, Andraju Bhanu Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350348460

The paper presents an advanced method for predicting movie genres using a hybrid model that combines textual, visual, and numerical variables in a smooth manner. Our model achieves a remarkable accuracy of 84.73% by fusing feature-rich data, such as verbal descriptions, movie posters, and numerical metadata, with the strengths of deep learning approaches, such as recurrent neural networks (RNN) and long short-term memory (LSTM) networks. This extensive blending of modalities results in a genre classification scheme that is more complex and comprehensible. While the addition of textual data allows for a greater grasp of story the intricate details, the introduction of movie posters makes it easier to derive visual patterns. Furthermore, the numerical metadata offers insightful quantitative information. The model's superiority in managing diverse and multimodal data is demonstrated through a number of experiments and comparisons with traditional algorithms, substantiating its performance. Along with to making significant contributions to the field of movie genre prediction, this study highlights the effectiveness of hybrid models in deriving insightful patterns from intricate, multimodal datasets. © 2024 IEEE.

关键词： Deep Learning Hybrid Models Interpretability Long Short-Term Memory Movie Genre Prediction Multimodal Learning Numerical Features Recurrent Neural Networks Textual Features Visual Features

来源：评论

学校读者我要写书评

暂无评论

Biometric Aided Intelligent Security System Built using Internet of Things 2

Biometric Aided Intelligent Security System Built using Inte...

引用

2nd International Conference on Electronics and Renewable Systems, ICEARS 2023

作者： Josphineleela, R. Lekha, D. Natrayan, L. Purohit, Kamlesh Chandra Panimalar Engineering College Department of Computer Science Engineering Poonamallee600123 India R.M.K College of Engineering and Technology Department of Computer Science and Engineering Puduvoyal601206 India Saveetha School of Engineering Simats Department of Mechanical Engineering 602107 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun248002 India

ISBN: (纸本)9798350346640

Protection is critical for information, property, and even living beings. The usage of IoT and biometrics for security is becoming increasingly common as technology progresses. Facial recognition is widely accepted as a universally applicable, aggregated, and easily accessible biometric technology. Facial biometrics employ the same indicators that humans use to differentiate between persons. This study has investigated the face recognition technology in order to create a dependable door lock system. The biometric face recognition system developed using ESP32-CAM. When a face comes in front of the camera, the system instantly detects and recognizes it. A prototype was created and tested to evaluate the security functionality, effectiveness, and dependability. The findings indicate the result may be utilized effectively improve person's existence and safety, as well as for industrial and residential applications. © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Real-time Stream Processing in IoT Environments 9

Real-time Stream Processing in IoT Environments

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Rajasekar, P. Bhosale, Rupali Shekar Indhumathi, C. Sandeep, K.V. Prasanthi Kumari, N. Rajendiran, M. School of Computing Srm Institute of Science And Technology Department of Data Science And Business Systems Tamil Nadu Kattankulathur603203 India Bharati Vidyapeeth Institute of Technology Department of Electronics And Telecommunication Engineering Maharashtra Navi Mumbai400614 India Rmk College of Engineering And Technology Department of Computer Science And Business Systems Tamil Nadu Puduvoyal601206 India Dayananda Sagar College of Engineering Department of Electronics & Telecommunication Engineering Karnataka Bengaluru560111 India School of Computer Sciences University of Petroleum And Energy Studies Uttarakhand 248007 Dehradun India Panimalar Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai600123 India

ISBN: (纸本)9798350365092

New IoT devices generate massive real-time data. Fast, real-time stream processing is needed for IoT data insight extraction. There are pros and downsides to real-time stream processing for the Internet of Things (IoT). This article analyzes present methods and technologies. The inquiry begins with large-scale, real-time IoT data analysis. Real-time analytics and bulk processing limits are important for IoT decision-making. We then investigate IoT stream processing frameworks, methodologies, and systems' complexity. We explore Internet of Things technology selection and tradeoffs between scalability, accuracy, latency, and real-time processing system scalability. It covers real-time stream processing system design and deployment and risk mitigation. Case studies and use cases highlight real-time IoT stream processing. Healthcare, smart city, and industrial IoT operational efficiency and proactive decision-making improve with real-time data. Finally, the report suggests the Internet of Things real-time stream processing research. New IoT data analytics protocols, methods, and technologies are highlighted. We teach real-time stream processing to IoT academics, practitioners, and decision-makers. They could then develop more efficient and scalable IoT data stream optimization solutions. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Network-Based Rail Running Band Anomaly Recognition via Recurrent Attention Graphs

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 15381-15395页

作者： Ni, Xuefeng Fieguth, Paul W. Ma, Ziji Shi, Bo Liu, Hongli Hunan University College of Electrical and Information Engineering Changsha410012 China University of Waterloo Department of Systems Design Engineering WaterlooONN2L 3G1 Canada The Hong Kong University of Science and Technology Department of Computer Science and Engineering Sai Kung Hong Kong

Anomaly detection for rail running bands, the pattern of wheel-rail contact area, is crucial to analyze composite rail irregularities. This paper presents an all-weather vision-based solution for running-band inspection. However, two major algorithmic challenges restrict inspection effectiveness: 1) the identification of high-quality features for diversified and imbalanced data subject to noise and outliers, and 2) inferring implicit anomaly co-occurrence patterns. We regard overall running-band anomaly detection as a multi-label classification problem and develop a novel deep multi-anomaly recognition network via recurrent attention graphs (RAGRN). © 2004-2012 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Analysis of Apt Attack for Source Tracing in Industrial Internet Environment 7

Analysis of Apt Attack for Source Tracing in Industrial Inte...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Shrivastava, Anurag Mittal, Tanusha Almusawi, Muntather Kumar, Yogendra Anandhi, R.J. Bhavana, Munugapati Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Gla University Department of Electrical Engineering Mathura India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

As businesses become more dependent on networked digital devices, advanced persistent threats (APT) attacks are progressively becoming a component of the threat landscape. These types of attacks target essential pieces of infrastructure. This research paper presents an in-depth examination of source tracing in an industrial internet context, often known as an internet environment in the workplace. The purpose of this analysis is to reinforce the security posture against APT attacks. We are able to investigate a variety of strategies and procedures for tracing the origin of these assaults if we look closely at the fundamental aspects of advanced persistent threats (APT) attacks, such as entrance techniques, the spread of malware, and the removal of data. As a result of this, we investigate the essential aspects that comprise APT attacks. In addition, we discuss the challenges and limitations that are inherent to source tracing in industrial settings and provide workable solutions to these issues and limitations. Industrial companies will have the expertise and resources necessary to protect key infrastructure if advanced persistent threats can be effectively tracked down and neutralised. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Lung Tumor Volumetric Estimation and Segmentation using Adaptive Multiple Resolution Contour Model

Lung Tumor Volumetric Estimation and Segmentation using Adap...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： SenthilPandi, S. Kalpana, B. Kumar, Vinodh S. Kumar, P. Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Information Technology RMD Engineering College Chennai India

ISBN: (纸本)9798350305708

The need to identify pathology is strongly felt in image guided analysis. Tumor localization is essential for targeting the tumor. Tumor boundaries are often hard to delineate due to high variation in shape and size of the tumor. The tumor boundary is usually defined using the thresholding technique which may have high FP rate due to partial volume effects. Hence, this AMRC technique has to be repeated several times in order to get a more accurate result. The multiple thresholding technique often leads to an undesirable situation where the segmentation boundary contains holes which are hard to fill. The AMRC is a dynamic contour model that is able to adaptively adjust the contour to better fit the contour of the tumor. Segmentation of SVT involves two steps viz. identification of peak intensity pixels with the HECS model and definition of an adaptive contour with AMRC. © 2023 IEEE.

关键词： AMRC Segmentation Tumor Localization

来源：评论

学校读者我要写书评

暂无评论

Fraud Detection in Financial Transactions: A Machine Learning Approach 9

Fraud Detection in Financial Transactions: A Machine Learnin...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Patel, Shashank Pandey, Mudita Rajeswari, D. School of Computing College of Engineering And Technology Srm Institute of Science And Technology Department of Data Science And Business Systems Chennai Kattankulathur603203 India

ISBN: (纸本)9798350365092

Financial fraud presents substantial risks to individuals and financial institutions globally, necessitating efficient detection mechanisms to mitigate probable fatalities. In this study, the development and evaluation of machine learning (ML) models for detecting fraudulent activities in mobile money transactions are investigated. Using a synthetic dataset, realworld transaction scenarios involving a variety of transaction kinds and features are simulated. The effectiveness of many machine learning (ML) methods, such as LGBM, random forests, XGBoost, and logistic regression, in spotting fraudulent transactions is investigated through data preparation, feature engineering, and model-building procedures. Employing techniques such as SMOTE-Tomek resampling and hyperparameter tuning enhances the performance and robustness of our models. Our results reveal that the XGBoost classifier emerges as the top-performing model, exhibiting a remarkable accuracy of 99.95%. The findings underscore the potential of MLbased approaches to bolster security and trust in mobile financial services, contributing to the ongoing advancement of fraud detection methodologies in the financial sector. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification using CNN and Transfer Learning (TL) 7

Skin Cancer Classification using CNN and Transfer Learning (...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Patel, Shashank Pandey, Mudita Rajeswari, D. Srm Institute of Science And Technology School of Computing College of Engineering And Technology Department of Data Science And Business Systems Chennai Kattankulathur603203 India

ISBN: (纸本)9798350359299

Skin cancer is a predominant and possibly lethal condition that distresses people across the world. Primary detection and precise finding are crucial for leveraging efficacious treatment and enhanced patient consequences. This research study explores the application off Artificial Intelligence (AI) resolutions for the primary finding and analysis of skin cancer. The study leverages a dataset of dermatological images and employs various ML methods, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and decision trees, to analyse the existence of skin cancer with a higher degree of accuracy. By utilizing a combination of image processing and feature extraction, the AI model demonstrates higher performance in classifying skin lesions into malignant or benign categories. The proposed model has achieved an accuracy rate of 98.52%, making the AI-based system a promising tool for dermatologists and healthcare professionals. © 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

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：