检索结果-内蒙古大学图书馆

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Bhandari, Sonam Chaudhary, Sumit Malhotra, Sonal Joshi, Kapil Kirola, Madhu Rajkumar Uttaranchal Institute Of Technology Uttaranchal University Dept. of Computer Science and Engineering Dehradun India Graphic Era Hill University Graphic Era Deemed to be University Dept. of Computer Science and Engineering Dehradun India Dev Bhoomi Uttarakhand University Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350367171

With the widespread use of digital media, amount of visual content on the internet and the incidence of image plagiarism has also increased. In various domains including academia, journalism and creative industries, unauthorized use or reproduction of images without proper attribution has become significant concern. Scaling, rotation, cropping, filtering due to these diverse range of transformations detecting image plagiarism is a challenging task now. This study investigates the use of deep learning approach to image plagiarism detection that combines methods for similarity measurement, clustering and feature extraction. A comprehensive solution is being proposed by combining Scale Invariant Feature Transform (SIFT) for extracting features, Bag of Visual Words (BoVW) model and Convolutional Neural Networks (CNNs) for image analysis. The effectiveness of the proposed approach through extensive experiments is demonstrated, outperforming the baseline methods and showcasing superior performance metrics. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Study on Optimization and Augmentation Techniques for Improving the Performance of CADx System for Cat Skin Disease

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第1期74卷 135-141页

作者： Won, Hyeong-Sik Park, Jae-Beom Cho, Hyun-Chong Dept. of Electronics Engineering Interdisciplinary Graduate Program for BIT Medical Convergence Dept. of Data Science Kangwon National University Korea Republic of Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

In modern society, the number of households raising pets is increasing. As pet ownership increases, the cost of treating companion cats is also rising, with a significant portion of these costs going toward the treatment of skin diseases. Skin diseases are among the common ailments in pets, and swift action is required if they occur in cats. However, early lesions lack distinctive characteristics, making accurate diagnosis difficult. Therefore, this study proposes a CADx(computer-Aided Diagnosis) system that classifies images of cat skin conditions into inflammatory lesions, non-inflammatory lesions, and normal images using a dataset of cat skin diseases. We selected the ConvNeXt model, based on CNN, which can learn regional information and features. To learn various patterns of skin lesions, we applied Mixup, an image augmentation technique. When Mixup was applied, the model accuracy was 0.8679, showing a 3.35% improvement compared to the original dataset. Additionally, Lookahead Optimizer was applied to ensure stable learning of Mixup. When both Mixup and Lookahead Optimizer were applied, the model accuracy was 0.8741, showing a high improvement of 3.97% compared to the original dataset. Therefore, the Lookahead Optimizer helps with the stable training of mixup, which can improve the performance of the model. Copyright © The Korean Institute of Electrical Engineers.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Development of a Deep Learning-Based System for Cat Skin Disease Classification and Grad-CAM Visualization

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第2期74卷 339-344页

作者： Won, Hyeong-Sik Cho, Hyun-Chong Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of Dept. of Electronics Engineering and Interdisciplinary Graduate Program for BIT Medical Convergence Dept. of Data Science Kangwon National University Korea Republic of

Skin diseases in companion cats can worsen if not treated promptly, and this can increase the financial burden on pet owners. To prevent this, early and accurate diagnosis is essential. This study introduces a deep learning-based computer-Aided Diagnosis (CADx) system designed to classify cat skin diseases into non-inflammatory and inflammatory lesions by comparing them with normal images. The system employs the EfficientNetV2 model and incorporates image augmentation techniques like AutoAugment and AugMix to enhance classification performance. The study results indicate that the developed model achieved an 84.68% accuracy for non-inflammatory lesions, reflecting a 10.06% improvement, and a 97.19% accuracy for inflammatory lesions, reflecting a 2.45% improvement. Furthermore, we applied Grad-CAM to visualize the regions of interest in the images, offering veterinarians critical insights into the location and characteristics of the lesions. This system has the potential to significantly improve the precision of diagnosing skin diseases in companion cats, thereby supporting better veterinary care. Copyright © The Korean Institute of Electrical Engineers.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimized Techniques Based on Dense Neural Networks

Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimize...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Aly, Salah A. Bakhiet, Ali Balat, Mazen Badya University Faculty of Computing & Data Science Giza Egypt Fayoum University Faculty of Science Computer Science Dept. Fayoum Egypt Computer Science Dept. October 6th City Giza Egypt E-Japanese University of Science & Tech. Cs & It Dept. Alexandria Egypt

ISBN: (纸本)9798350367560

Lymphoma diagnosis, particularly distinguishing between subtypes, is critical for effective treatment but remains challenging due to the subtle morphological differences in histopathological images. This study presents a novel hybrid deep learning framework that combines DenseNet201 for feature extraction with a Dense Neural Network (DNN) for classification, optimized using the Harris Hawks Optimization (HHO) algorithm. The model was trained on a dataset of 15,000 biopsy images, spanning three lymphoma subtypes: Chronic Lymphocytic Leukemia (CLL), Follicular Lymphoma (FL), and Mantle Cell Lymphoma (MCL). Our approach achieved a testing accuracy of 99.33%, demonstrating significant improvements in both accuracy and model interpretability. Comprehensive evaluation using precision, recall, F1-score, and ROC-AUC underscores the model's robustness and potential for clinical adoption. This framework offers a scalable solution for improving diagnostic accuracy and efficiency in oncology. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Internet of Things IoMT data Aggregation Using Machine Learning 2

Internet of Things IoMT Data Aggregation Using Machine Learn...

引用

2nd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2024

作者： Pulabaigari, Lakshmi Sagar Sivakumar, C. School of Computing Mohan Babu University Dept. of Computer Science and Engineering Andhra Pradesh Tirupati India School of Computing Mohan Babu University Dept. of Data Science Andhra Pradesh Tirupati India

ISBN: (纸本)9798350372847

The Internet of Things (IoT) has revolutionized the way data is handled and collected, allowing for large amounts of information to be revolutionized quickly and efficiently. This has paved the way for Machine Learning (ML) applications to be used on IoT datasets, such as 10MT data aggregation. This paper discusses the use of a ML approach for aggregation 10MT data in order to better understand trends and classify patterns in various sectors that would otherwise go undetected. It discusses the benefits and challenges of such a system, and how it could be used to improve the efficiency of industrial operations. It stresses the importance of data integrity in this process, as wrong or incomplete datasets can significantly reduce the accuracy and reliability of the results obtained. Furthermore, it discusses the need for suitable ML algorithms and models, such as clustering and random forest, to be applied to the collected data in order to produce robust and meaningful output. It observes the security and privacy challenges associated with such ML-based 10MT data aggregation systems, and the potential solutions available. © 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

Detecting Helmets Of The Bike Riders Using Deep Learning Algorithms 14

Detecting Helmets Of The Bike Riders Using Deep Learning Alg...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Mia, Yousuf Rahman, Md. Solaimanur Basak, Animesh Hossain, Sheikh Mufrad Zulfiker, Md. Sabab Sumaia, Merina Akter Daffodil International University Dept. of Computer Science & Engineering Dhaka Bangladesh Model Institute of Science & Technology Dept. of Computer Science & Engineering Gazipur Bangladesh

ISBN: (纸本)9798350335095

We propose real-time bike helmet detection in our study. A lot of people ride bikes in our nation. Motorbikes are more popular than vehicles because they are cheaper to maintain, take up less parking space, and provide more mobility and adaptability in urban situations. Bike riding is entertaining yet risky. Bicyclist safety is the planned system's main purpose. Many drivers don't wear helmets even though they're mandated by law. In emerging countries, mortality has been growing steadily. A helmet detection technology that identifies drivers without helmets is needed to safeguard the public. We employ a real-time 3202 dataset for this approach. We gather wearing helmet 1911 and no helmet 1291 data and utilize algorithms like VGG16, Resnet50, MobileNet v.02, Inception V3, EfficientNet, and CNN. The EfficientNet achieved 98% accuracy. Each person's comparison statement techniques are in the implementation section. To construct the optimum model for the conditions, this inquiry uses model validation approaches. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FBG Sensor Design and Analysis for Early Detection of Cancer 18

FBG Sensor Design and Analysis for Early Detection of Cancer

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Sharan, S.C. Dhruva, H.K. Mary Anitha, T. Roy, Neil Sharan, Preeta Madhwesha Moudgalya, R. The Oxford College of Engineering Dept. of Computer Science and Engineering Bangalore India The Oxford College of Engineering Dept. of Mca Bangalore India Delhi Technological University Dept. of Computer Science and Engineering New Delhi India The Oxford College of Engineering Dept. of Electronics and Communication Engineering Bangalore India The Oxford College of Engineering Dept. of Science and Humanities Bangalore India

ISBN: (纸本)9789380544519

Several of the current procedures for detecting cancer, such as mammography, ultrasound, MRI, and biopsy, are either expensive, painful, intrusive, or have limitations in accuracy and sensitivity. As a result, there is a need for a simple, noninvasive, and cost-effective tool for detecting cancer at an early stage. Fiber Bragg grating (FBG) sensors offer a wide range of uses in primary care and biomedical applications for intelligent sensing. Furthermore, fiber-optic FBGs have several benefits that set them apart. The most noteworthy of these applications, of course, are incredibly valuable human health indicators such as blood pressure, heart rate, and body temperature. Temperature and blood pressure vary depending on a person's physical, involuntary, nervous, and mental state. Therefore, measuring vital parameters, especially temperature can help in the early identification of symptoms of a disease. Research suggests that temperature variation is observed in cancerous cells (breast, cervix, and blood vessels). FBGs can be utilized as thermal sensors to measure temperature changes with great sensitivity and precision. FBG sensors also face some challenges, such as low signal-to-noise ratio, cross-sensitivity, and environmental interference. Therefore, optimizing the Q factor of FBG sensors is crucial for improving their performance and reliability for cancer identification. In the current study, an optimized FBG sensor was designed and simulated. The average Q-factor obtained in 244.26. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Blood cancer FBG Fiberoptic Hela cells MCF-7 cells modulation OptiGrating SMF

来源：评论

学校读者我要写书评

暂无评论

Frequency Response Deterioration due to Surface Ridge Abrasion of Tactile Sensors 13

Frequency Response Deterioration due to Surface Ridge Abrasi...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Yanwari, Muhammad Irwan Okamoto, Shogo Polines Dept. Computer Engineering Technology Japan Tokyo Metropolitan University Dept. Computer Science Tokyo Japan

ISBN: (纸本)9798350355079

Epidermal ridges are crucial for tactile sensing in both human fingers and synthetic sensors. These ridges are made of compliant materials and susceptible to abrasion damage after iterative use. This study focuses on examining the impact of sensor ridge damage on the acquired signal, which encompasses a broad range of frequency components. We compared the frequency responses of a tactile sensor scanning sandpaper with both intact and damaged sensors. The degradation of signal levels was evident across the 0-1,000 Hz range, with particularly prominent suppression of the peak frequency component. This study demonstrates the frequency-dependent influence of ridge abrasion. © 2024 IEEE.

关键词： Friction

来源：评论

学校读者我要写书评

暂无评论

Investigating the Efficacy of Diverse Machine Learning Classifiers for Parkinson's Disease Detection 15

Investigating the Efficacy of Diverse Machine Learning Class...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Roy, Sourabarna Debbarma, Tina Pal, Tannistha Duraisamy, Prakash National Institute of Technology Agartala Dept. of Computer Science and Engineering Agartala India University of Wisconsin- Green Bay Dept. of Computer Science and Engineering WI54311 United States

ISBN: (纸本)9798350370249

To detect Parkinson's disease, we compare the effectiveness of K-Nearest Neighbors (KNN), Logistic Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) algorithms. Utilizing a dataset with clinical and biomedical features, we preprocess the data to handle missing values and standardize the features. Subsequently, we train each algorithm with the preprocessed data and evaluate their performance using metrics like accuracy, precision, recall, and F1-score. Our results indicate that all four algorithms achieve excellent accuracy in diagnosing Parkinson's disease, with KNN slightly outperforming the others. However, the selection of the algorithm may depend on specific needs such as interpretability and computational efficiency. Additionally, we conduct a feature importance analysis to identify the most relevant features for Parkinson's disease identification, offering insights that can aid in early diagnosis and disease management. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Sentimental Analysis of Various TV Serials in Society 15

Sentimental Analysis of Various TV Serials in Society

引用

15th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2023

作者： Sarkar, Ripa Sarkar, Ratna R. BRAC University Dept. of Computer Science and Engineering Dhaka Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Savar Bangladesh

ISBN: (纸本)9798350324433

Sentiment analysis which involves identifying emotions in the text is a widely studied topic of natural language processing. Many researchers focus on social media content like posts, tweets and reviews for their studies. In this paper, a large number of data from comments about serials on social media and internet forums in Banglish is collected and analyzed. We use NLP techniques to do the sentiment analysis of the comments. This study explores how different kinds of serials have impacted society and concentrates on how they have influenced the creation of Banglish comments. This study aims to conduct a sentiment analysis of Banglish comments generated in response to different genres of serials and to analyze their potential societal implications. Along with Long Short-Term Memory (LSTM), we use several machine-learning algorithms such as Logistic Regression (LR), Multinomial Naive Bayes (MNB), Gaussian Naive Bayes, Decision Tree (DT), AdaBoost, Random Forest (RF) and Support Vector Machine (SVM) to create this model. The SVM gives the highest accuracy among all of the machine learning algorithms. © 2023 IEEE.

关键词： Sentiment 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：