检索结果-内蒙古大学图书馆

5th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2023

作者： Karmakar, Mithun Mondal, Subhash Nag, Amitava Computer Science and Engineering Central Institute of Technology Kokrajhar BTR Assam Kokrajhar783370 India

ISBN: (纸本)9783031488757

Skin diseases are generally normal around the globe, as people get skin diseases because of inheritance and natural elements. Dermatologists rely heavily on visual examinations to diagnose skin diseases. However, this method can be inaccurate and time-consuming. The development of the technique in deep learning (DL) and the availability of GPUs can expand and improve the quality of computer-aided disease diagnostics systems. This paper proposes a DL-based smartphone application to aid a dermatologist in diagnosing skin disease in real-time. In the proposed work, we first used fine-tuned DenseNet201 for feature extraction and SVM to accurately classify normal and abnormal skin. A Deep Ensemble CNN (DECNN) framework with DenseNet-201, Resnet50, and MobileNet is further used for skin disease categorization if abnormal skin is detected. The experimental outcome of this study demonstrates that the framework can achieve an 84% accuracy in skin disease classification and outperform existing state-of-the-art works. The simple implementation and acceptable accuracy of the proposed method can be helpful for dermatologists in the diagnosis of skin disease. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhanced Gradient Boosting Technique to Detect the Malware in API

Enhanced Gradient Boosting Technique to Detect the Malware i...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing systems, ADICS 2024

作者： Balaji, M. Sathyalakshmi Hindustan Institute Of Technology And Sciences Department Of Computer Science And Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350364828

Currently, one of the most crucial jobs in information security is malware detection. Since hackers are always coming up with new ways to break into computer networks and systems, it's critical to have a reliable system in place to detect and prevent any unwanted activity. Traditional antivirus software frequently misses new viruses or malware, leaving your computer open to intrusion and important data theft. It is necessary to create a new method to detect the malware. In this paper used the Enhanced Gradient Boosting method to detect the malware. It is employed to verify the outcomes of analysis and enhance the precision of detection. The implementation of the suggested method enables the identification of malicious software with a precision ranging from 98.1%, indicating a significantly high level of accuracy. © 2024 IEEE.

关键词： Machine learning

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

An Efficient Detection of Phishing Website using Machine Learning 5

An Efficient Detection of Phishing Website using Machine Lea...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Menaga, D. Vijay, S. Vignesh, V. Ramalakshmi, S. St.Joseph's Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331504403

Phishing is the practice of creating fake websites to track and steal sensitive information of online users. It is a type of identity theft where thieves create fake accounts on targeted websites and tricking victims into revealing their personal information like passwords, PINs and more. Phishing attackers send phishing links via email, text messages and emails, social media. They use social engineering techniques to lure customers to phishing websites and provide sensitive personal information. Finally, stolen personal information is used to establish trust between legitimate websites or financial institutions for illegitimate gains. Enormous amount of information is simultaneously downloaded and published on the web. This makes it possible for criminals to seize sensitive personal information. Use of machine learning to solve these problems by developing an intelligent, efficient and flexible system. Phishing websites can be detected based on important characteristics like URL and registration number. Many ecommerce businesses can use this system to simplify the business process. Thanks to this system, in which users can purchase online without any hassle. Information is presented and reviewed. A website can be classified as legitimate or phishing using supervised classification algorithms such as logistic regression, gradient boosting, decision trees, and support vector machines. The proposed model achieved 97.4% accuracy in gradient enhancing classifiers among the other algorithms compared. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Research on YOLO model optimization of multi-modal data processing attention mechanism based on deep learning 4

Research on YOLO model optimization of multi-modal data proc...

引用

4th IEEE International Conference on Electronic technology, Communication and Information, ICETCI 2024

作者： Wu, Qiongfei Xie, Qubo Wuhan Institute of Design and Science School of Intelligent Engineering Wuhan China Huazhong University of Science and Technology School of Computer Science & Technology Wuhan China

ISBN: (纸本)9798350361643

In this study, a YOLO model method combining LightGBM and multi-modal data processing attention mechanism optimization is proposed to enhance the effectiveness and accuracy of object detection. The traditional YOLO model has the problem of insufficient utilization of multi-modal data when processing image data, while LightGBM has significant advantages in processing structured data. Therefore, this paper designs and implements an optimization framework by embedding CBAM module into the extraction of features part of YOLOv5 model to improve the capability of feature representation. Concurrently, LightGBM is employed to handle structured data, and a fusion module is used to combine the features from both sources with appropriate weighting. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Classification of diabetic macular edema severity using deep learning technique

引用

Research on Biomedical engineering 2022年第3期38卷 977-987页

作者： Kumar, Amit Tewari, Anand Shanker Singh, Jyoti Prakash Department of Computer Science & Engineering National Institute of Technology Patna Patna India

Purpose: Diabetic macular edema (DME) is a kind of hard exudates lesion seen near the diabetic macular region of the retina. DME causes visual loss and may result in complete blindness;early identification and treatment may be able to cure this. Identification of DME at an early stage is a challenging and error-prone task. To address this issue, the article presents a methodology that uses the notion of transfer learning to identify cases of DME from retinal fundus images. Methods: A pre-trained DenseNet121 is used in this technique to extract the useful set of feature vectors from the fundus images, which are then fed into a few additional fully connected layers and then into the classification layer to classify DME instances. A total of 577 fundus training images from 3 DME classes were used to train the proposed model, and 103 fundus testing images were used to verify the proposed model for classifying them into one of the three DME cases. Results: The suggested model is trained and tested on the Indian Diabetic Retinopathy Image Dataset (IDRiD). With the test images, the results demonstrate that the proposed model outperformed the state-of-the-art models presented in "Diabetic Retinopathy – Segmentation and Grading Challenge" held at ISBI-2018 with an accuracy of 86.4%. Conclusion: The proposed model diagnoses DME at an early stage for timely treatment and helps to reduce the workload of ophthalmologists. © 2022, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

LSTM Based Approach to Detect Fake News 2

LSTM Based Approach to Detect Fake News

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Khare, Sakhi Singh, Pushpa Kumar, Pankaj Gl Bajaj Institute of Technology Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350371055

In the age of technology, every day, we ingest a variety of news data, either willingly or accidentally. People will always use various social media apps and keep looking for information. The information passed through these social media apps is only sometimes valid. Many organizations or individuals spread the news to influence the mass public. This type of information is called fake news. Fake news is a common problem that naturally comes with social media. Detection of counterfeit news with ubiquitous data from social media is almost impossible. Fake news kills real journalism and spreads false information in society. Researchers are still looking for better solutions. In this paper, we find a better solution with Natural Language Processing (NLP). We used fake news challenge datasets for training and testing purposes. We aim to classify the news item into four stance labels: agree, disagree, discuss, and unrelated. We developed a Long Short-Term Memory (LSTM) based solution to organize the news article in the given stance label. We find that our approach classifies data effectively with 99% of accuracy © 2024 IEEE.

关键词： Fake News LSTM NLP Word Embedding

来源：评论

学校读者我要写书评

暂无评论

Deepfake Classification for Human Faces using Custom CNN 7

Deepfake Classification for Human Faces using Custom CNN

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Kalemullah, Amaan M. Prakash, P. Sakthivel, V. Vellore Institute of Technology Chennai School of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350372816

This paper emphasizes the urgent need for effective deepfake classification methods, particularly for human faces, due to the escalating threat of this technology. The research proposes a comprehensive approach using a Convolutional Neural Network (CNN) model and two Transfer Learning models (ResNet-50 and EfficientNet B7) to address this challenge. It investigates the synthesis of realistic-looking facial manipulations and their societal impacts, highlighting the importance of accurate classification in mitigating these effects. The study evaluates and compares the proposed models' accuracy in detecting manipulated facial content, analyzing their strengths and limitations. Overall, the paper provides a timely exploration of deepfake classification, offering practical solutions to enhance digital security and trustworthiness. © 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

A stable data transmission method of industrial internet of things communication based on bat algorithm

引用

International Journal of Internet Manufacturing and Services 2022年第3期8卷 208-219页

作者： Chen, YiPing Department of Computer Science and Engineering Guangzhou Institute of Technology Guangzhou510540 China

Aiming at the problems of poor transmission stability and long transmission time in the traditional industrial internet of things communication data transmission, a stable transmission method of industrial internet of things communication data based on bat algorithm is designed. Firstly, build the industrial internet of things network model. Then, the sparse basis matrix is used to collect the communication data of industrial internet of things, and the noise in the communication data is removed by Gaussian function to complete the data extraction and preprocessing. Finally, the bat algorithm is used to determine the suitability of the location of the communication data, the updated data is transmitted in the optimised industrial internet of things communication network environment, and the differential genetic algorithm is used to suppress the interference factors to complete the stable data transmission. The results show that the proposed method can effectively improve the stability of communication data transmission. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Deep Insight on Cricket Video to Text Summarization Using Neural Networks 10

A Deep Insight on Cricket Video to Text Summarization Using ...

引用

10th International Conference on Advanced Computing and Communication systems, ICACCS 2024

作者： Gopal, J. Vijay Prasad, K. Sai Kumar, Dhatrika Kamal Prashanth, Maddhe Sai Kumar, Vuppala Praneeth Teja, I. Nikhil Sri Sai Computer Science Engineering Artificial Intelligence and Machine Learning Mlr Institute of Technology Hyderabad India

ISBN: (纸本)9798350384369

In this modern era, the demand for efficient and automated cricket video summarization techniques is rapidly increasing. This paper introduces an innovative and advance neural network system that transforms the way cricket match videos are summarized. Cricket video-to-text summarization system overcomes the limitations of traditional manual summarization approach by utilizing various deep learning techniques to completely automate the summarization process, our system can extract crucial insights from lengthy cricket match footage and convert them into easily readable text formats. The system employs three-pronged approach which involves extraction of visual features using VGG16 Convolutional Neural Network (CNN), scoreboard information is extracted through Optical Character Recognition (OCR) technology, and Text Summarization performed by Long Short-Term Memory (LSTM) network. Our system revolutionizes the way cricket enthusiasts engage with match videos, providing a game-changing experience for fans worldwide. © 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：