检索结果-内蒙古大学图书馆

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Ghodeswar, Ujwala Puri, Chetan Shingade, Sharvari Waware, Teena Ladhe, Ajinkya Durge, Tejas Department of Electronics Engineering Yeshwantrao chavan College of Engineering Nagpur India Department of Computer Science & Design Faculty of Engineeering & Technology Wardha India

ISBN: (纸本)9798350361155

The research investigates how machine learning algorithms and Internet of Things (IoT) technologies might be combined to solve the crucial problem of separating fresh fruits from damaged apple fruits. Using Internet of Things (IoT) devices with sensors, the system collects extensive data on important characteristics, such as real-time apple picture analysis and available apple database. Convolutional neural networks (CNNs) and YOLO are two examples of sophisticated machine learning models that are used with this data to accurately classify the apples into different groups according to their quality. This initiative fosters enhanced efficiency, production, and profitability in the agricultural supply chain while providing a sustainable solution to the problems connected with fruit sorting. It represents a synergistic convergence of IoT, machine learning, and agriculture. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Innovative Skin Melanoma Diagnosis using Deep Learning and African Gorilla Troops Optimizer 1

Innovative Skin Melanoma Diagnosis using Deep Learning and A...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Parthasarathi, P. Nivedha, S. Balamurugan, M. Yuvaraj, D. Siamala Devi, S. Sangeethaa, S.N. Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Bannari Amman Institute of Technology Department of Information Technology Sathyamangalam India Sona College of Technology Dpartment of Computer Science and Engineering Salem India Kongu Engineering College Department of Computer Science and Design Perundurai India Sri Eshwar College of Engineering Kuniamuthur Department of Information Technology Coimbatore India Bannari Amman Institute of Technology Sathyamangalam Department of Computer Science and Engineering Erode India

ISBN: (纸本)9798350352931

Skin melanoma, a dangerous kind of skin cancer, necessitates accurate identification and diagnosis to improve patient outcomes. The use of deep learning algorithms into medical imaging promises significant advancements in skin disease analysis, particularly melanoma diagnosis. This study looks at the usage of a novel optimisation technique, the African Gorilla Troops Optimizer (AGTO), to enhance deep learning models in the segmentation and analysis of skin images. The AGTO, which is based on African gorilla groups' social and hunting activities, is an effective approach of improving convolutional neural networks (CNNs) for accurate and reliable skin image segmentation. The proposed approach uses AGTO to distinguish melanoma lesions from benign skin disorders, which increases their identification. Extensive research on benchmark skin image datasets has confirmed the AGTO-enhanced deep learning model's durability and performance, emphasising its clinical use in dermatology and the proposed model shows 98 %accuracy. This work not only underlines the need of advanced optimisation techniques in medical image processing, but it also paves the way for more effective diagnostic tools for skin problems. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Breast Cancer Diagnosis through Multi-Class Segmentation using Attention UNet Model 2

Improving Breast Cancer Diagnosis through Multi-Class Segmen...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Ghantasala, G.S. Pradeep Unhelkar, Bhuvan Chakrabarti, Prasun Vidyullatha, Pellakuri Pyla, Meghana Department of Information Systems and Decision Sciences Muma College of Business University of South Florida South Florida United States Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India

ISBN: (纸本)9798350383867

One of the prominent causes of death for women universally is breast cancer. The number of early deaths is reduced with early detection. Using an ultrasound scan, the data examine the ultrasound images of breast cancer. Three categories, including normal, benign, and malignant images, comprise the Breast Ultrasound Dataset. Incorporating machine learning with breast ultrasound images might yield significant outcomes for the identification, classification, and segmentation of breast cancer. Through a mediocre image size of 500 500 pixels, the collection comprises 750 images. Attention U-Net/UNet is the best-known model for Multi-Class Segmentation to create an attention U-Net Model. The Model will consist of a Decoder Block Encoder Block and an Attention Gate. The attention gate layers have neurons with sizes of 256, 128, and 64, which typically correspond to the number of channels in the feature maps. The output layer in the U-Net model characteristically consists of a single convolutional layer through a kernel size of 1 1. The activation function used in the output layer was sigmoid;whichever is collective for binary classification tasks like image segmentation. The sigmoid activation function outputs values between 0 and 1, representing the possibility of each pixel fitting to the target class. The loss function stated is "binary_crossentropy," which is appropriate in binary classification tasks. The optimizer specified has Adam, which is well-liked for neural network training because of its adaptable learning rate characteristics. In contrast to conventional gradient descent techniques, the Adam optimizer adjusts the learning rate during training, which might result in faster convergence and improved results with 98% accuracy at epoch 17 with a validation loss of 0.05. ©2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Ensemble Classifier using Wisconsin Dataset For Breast Cancer Prediction

Machine Learning Based Ensemble Classifier using Wisconsin D...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Ghantasala, G. S. Pradeep Kunchala, Anjaneyulu Sathiyaraj, R. Venkateswarulu Naik, B. Raparthi, Yaswanth Vidyullatha, P. Alliance University Faculty of Science & Technology Alliance College of Engineering and Design Bengaluru India Gitam University Gitam School of Technology Department of Computer Science and Engineering Karnataka Bangalore India Computer Science Engineering Narasimha Reddy Engineering College Hyderabad India Computer Science Engineering Vellore Institute of Technology TN Vellore India Computer Science Engineering Koneru Lakshmaiah Education Foundation A.P Guntur India

ISBN: (纸本)9798350315455

Subclass of Artificial Intelligence, machine learning integrates several optimizations, probabilistic, and statistical methodologies to help computers learn from prior occurrences and find it challenging to spot patterns in intricate datasets, noised and large datasets. As a result, machine learning in cancer diagnosis and detection has increased. In women, breast cancer is the utmost common malignancy. The study aims to predict breast cancer by comparing widely used machine learning algorithms and methodologies, neural networks, Random Forest, and Boosting, upon Wisconsin Diagnosis Breast Cancer data set to inspect the performance of critical characteristics such as precision and accuracy. This study's accurate, competitive results can be used for detection and treatment. © 2023 IEEE.

关键词： Artificial intelligence Boosting Cancer prediction Neural network Random Forest

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Object Detection Neural Network Models Based on Accuracy and Latency 2

Performance Comparison of Object Detection Neural Network Mo...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Gomathy, B. Sengottaiyan, N. Aarthi, K. Thirumoorthy, P. Tamizharasu, K. Kalyanasundaram, P. Dr.NGP Institute of Technology Dept of Computer Science and Business Systems Tamilnadu Coimbatore India Alliance College of Engineering and Design Alliance University Faculty of Science and Technology Karnataka Anekal562106 India Kongu Engineering College Department of ECE Erode Tamilnadu Perundurai638 060 India Nandha Engineering College Department of CSE Erode Perundurai638 052 India KSR Institute for Engineering and Technology Tiruchengode Department of CSE 637215 India

ISBN: (纸本)9798350327533

Aim: The purpose of this study is to compare the object detection performance of You Only Look Once V4 (YOLOv4) and Single Shot Multibox Detector (SSD) algorithms with respect to metrics like accuracy and latency. Materials and method: Twenty sample photos in all, from different classifications and labels, were gathered. These samples were divided into training dataset (60 %) and test dataset (40 %). To measure the performance, values for accuracy and latency were computed for YOLOv4 and SSD with G power 0.8. Result: The accuracy in prediction of the object in the image was higher in the YOLOv4 algorithm (97 %) compared to the SSD algorithm (84 %). After running a t-test on an independent sample of the two groups under consideration. It is observed that YOLOv4 reported greater preference than the SSD algorithm having p value 0.166 (p>0.05). It was proven that the YOLOv4 reported greater preference than SSD in terms of accuracy. © 2024 IEEE.

关键词： Convolutional neural networks Machine Learning Novel Custom Dataset Object Detection Single Shot Multibox Detector You Only Look Once V4

来源：评论

学校读者我要写书评

暂无评论

Exploring Local Governance and Sustainability Challenges in Community Reserves: A Data Science Perspective with Global Insights 3

Exploring Local Governance and Sustainability Challenges in ...

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing technology, ODICON 2024

作者： Sachin Pavithran, A.P. Banerjee, Anurima Pradeep Ghantasala, G.S. Rajesh Sharma, R. Ananthanagu, U. Natarajan, Suresh Kumar Vidyullatha, Pellakuri Department of Humanities and Social Sciences Ramanagara India Department of Humanities and Social Sciences India Alliance College of Engineering and Design Alliance University Department of Computer Science and Engineering Bengaluru India Alliance University Center of Excellence in Immersive Technologies Bengaluru India Ramanagara India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Guntur Vaddeswaram India

ISBN: (纸本)9798350354379

As one of the furthermost noticeable industries, tourism strives for to magnify the situation in numerous forms, effectually addressing the dissimilar matters and concerns into the world nowadays. Frequently, these issues disturb the ecologically momentous areas and the local communities on a higher note. It's the need of the hour to check the forecasts of sustainable and community-based coastal tourism, whichever targets to promote the area's tourism potential over vigorous involvement by the local community although preservative the aboriginal ecological balance. Kerala, a classic tourism destination in India, provides significant opportunities for livelihood options to the local community who depend on natural resources. The contemporaneous research paper was centered on a case study of Kadalundi- Vallikkunnu Community Reserve in Kerala, the local authority and several influences it could need onto the local community then the recommendations whichever could be measured to discourse a interrelated issues. A vast portion of the respondents, having tourism activities as their primary source of income, have identified the problem of environmental degradation as prevalent in the area. In contrast, the rest are unaware of the harmful effects happening to the natural ecosystem, primarily because of waste disposal and water pollution. The paper is an endeavor to shed graceful on the local governance system of community reserve and socio-economic aspects of the local communities on the development of tourism initiatives in Kerala. © 2024 IEEE.

关键词： Community Based Coastal Tourism Community Reserve Environmental Degradation Rural Tourism Sustainability

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Identify Pituitary Tumor Using an Optimal CNN Model with Deep Learning

A Novel Approach to Identify Pituitary Tumor Using an Optima...

引用

2023 International Conference on Computational Intelligence, Networks and Security, ICCINS 2023

作者： Ebin, P.M. Thomas, Roja Ismail, Safad Kavitha Nair, R. Alliance School of Advance Computing Alliance University Banglore India Mangalam College of Engineering Department of Computer Science and Engineering Ettumanoor India College of Engineering Chengannur Department of Computer Engineering Chengannur India Acharya Institute of Technology Department of Ai &ml Banglore India

ISBN: (纸本)9798350313796

The technical paper introduces a novel approach to identifying pituitary tumors using an Optimized Convolutional Neural Network (OCNN) model with deep learning. Pituitary tumors rank among the most prevalent variety of brain tumors, and accurate identification is critical for proper diagnosis and treatment. The suggested method makes use of a deep learning framework that combines an ideal feature extraction method with a pre-trained CNN model. The pulled out features are then used to train the CNN model to classify pituitary tumors accurately. The effectiveness of the suggested method is assessed using a publicly accessible dataset, revealing that it surpasses the performance of current leading techniques. The suggested method possesses the capacity to act as a valuable asset for making clinical decisions in the field of neuroimaging, particularly for the accurate identification of pituitary tumors. The results of the experiment indicate that our suggested model successfully detects and classifies tumors with high accuracy, sensitivity, and specificity. Our model specifically achieves a 99.55% overall accuracy, 99% sensitivity, 99% specificity and 99% F1 score. These outcomes show that our suggested CNN design for brain tumor identification and classification performs better than several state-of-the-art techniques. © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Synergistic CNN-Random Forest Model for Signature Recognition and Classification 2

Synergistic CNN-Random Forest Model for Signature Recognitio...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Jain, Anuj Kumar Ghantasala, G. S. Pradeep Sharma, Vikrant Kaur, Gaganpreet Rajesh Sharma, R. Sungheetha, Akey Chandigarh University Department of Cse Punjab Mohali India Alliance University Alliance College of Engineering and Design Department of Computer Science and Engineering Bengaluru India Graphic Era Hill University India Graphic Era Deemed to be University Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350388916

The abstract performance characteristics of a signature classifying hypothesis, including precision, recall, F1-Score, encouragement, support percentage, and accuracy for two different signature classification levels. To take a Signature Classification stage one, the proposed approach achieves remarkable accuracy, recall, and F1-Score ratings of 99.87%, 99.50%, & 99.68%, accordingly. These metrics show how amazingly well the algorithm can classify situations in this category. The robustness of the model is demonstrated by the support column, which has 4020 instances classified as Signature Classification Stage 1. With a significant value of 0.47, the support percentage indicates the class's contribution to the entire dataset. In a similar vein, Signature Classification Stage 2 exhibits excellent performance characteristics, with 99.77 percent accuracy, recall, and F1-Score. There is a greater support rate in this class since 4510 instances give 0.52 to the total dataset. The model demonstrates its ability to identify signals with a stunning 99.64% Small Average accuracy, which is the average precision over all cases. Both signature levels performed in balance, as indicated by the weighted average & macro average metrics, which are predicted to be 99.73% for F1-Score, 99.82% for accuracy, & 99.64% for recall. This demonstrates how the model succeeds in maintaining a high level of accuracy throughout the entire dataset in addition to predicting specific classes. With a 99.6483% overall accuracy, it is shown that the notion of signature classification helps classify signatures at different levels. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Overcoming Spatial Constraints in VR:A Survey of Redirected Walking Techniques

引用

Journal of computer Science & technology 2024年第4期39卷 841-870页

作者： Jia-Hong Liu Yang-Fu Ren Qi Wen Gan Kui Huang Fiona Xiao Yu Chen Er-Xia Luo Khang Yeu Tang Yue-Yao Fu Cheng-Wei Fan Sen-Zhe Xu Song-Hai Zhang Academy of Arts and Design Tsinghua UniversityBeijing 100084China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China College of Computer Technology and Application Qinghai UniversityXining 810016China Zhili College Tsinghua UniversityBeijing 100084China School of Computer Beijing Information Science and Technology UniversityBeijing 100192China Department of Physics Tsinghua UniversityBeijing 100084China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

As the virtual reality(VR)technology strives to provide immersive and natural user experiences,the challenge of aligning vast virtual environments with limited physical spaces remains *** survey comprehensively explores the advancements in redirected walking(RDW)techniques aimed at overcoming spatial constraints in *** addresses this by subtly manipulating users’physical movements to allow for seamless navigation within constrained *** survey delves into gain perception mechanisms,detailing how slight discrepancies between virtual and real-world movements can be utilized without user awareness,thus extending the effective navigable *** RDW control algorithms for gain-based RDW are analyzed,highlighting their implementation and effectiveness in maintaining immersion and minimizing perceptual ***,novel methods extending beyond traditional gain-based techniques are discussed,showcasing innovative approaches that further refine VR *** practical implications of RDW in enhancing safety and reducing physical collisions in VR environments are underscored,alongside its potential to improve user experience by aligning virtual exploration more closely with natural human behavior *** a thorough review of existing literature and recent advancements,this survey provides a systematic understanding for researchers,developers,and industry *** underscores the importance of RDW in the future of VR,emphasizing RDW's role in making VR more accessible and practical across various applications,from education and training to therapy and *** paper concludes with a forward-looking perspective on the continued evolution and potential of RDW in revolutionizing virtual reality experiences.

关键词： virtual reality(VR) redirected walking(RDW) redirection gain perception

来源：评论

学校读者我要写书评

暂无评论

Real-Time Facial Recognition System for Secure college Bus Transport using Deep Learning Techniques 3

Real-Time Facial Recognition System for Secure College Bus T...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kavitha, M.N. Saranya, S.S. Pragatheeswari, E. Priya, N. Kaviya Ranjith, S.R. Vanchivel, N. Rahul Kongu Engineering College Department of Computer Science and Design Tamil Nadu India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Tamil Nadu Erode India Kongu Engineering College Department of Csd Tamil Nadu India

ISBN: (纸本)9798331509675

The proposed system aims to enhance student transportation security through real-time face detection and recognition. Leveraging the MTCNN framework for accurate face detection and the FaceNet model for reliable face recognition, the system ensures only authorized students can board designated buses by comparing captured faces with a pre-registered database. In case of mismatches, alerts are triggered to notify drivers and authorities. Additionally, parallel implementation of Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers improves authentication accuracy. The system's deep learning-based architecture ensures robust performance under varying environmental conditions and supports continuous learning for long-term reliability. © 2025 IEEE.

关键词： Students

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：