检索结果-内蒙古大学图书馆

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Han, Ji-Won Lee, Yeon-Joon Hanyang University Major in Bio Artificial Intelligence Department of Applied Artificial Intelligence Seoul Korea Republic of Hanyang University Major in Bio Artificial Intelligence Department of Computer Science and Engineering Seoul Korea Republic of

ISBN: (纸本)9798350313277

Generative artificial intelligence (AI) has gained prominence, particularly in the field of radiological image data. This study investigates current trends and prospects of generative AI in X-ray, CT, MRI, and PET imaging. Emphasizing the importance of data quantity and quality, we ensure reliable and useful outputs. Given the significance of ethical dimensions in generative AI for radiological imaging, ethical considerations are also addressed. By analyzing recent advancements, this study offers insights into the evolution of generative AI in radiological image data and future directions. © 2023 IEEE.

关键词： CT GAN Generative AI MRI PET X-ray

来源：评论

学校读者我要写书评

暂无评论

Defense and Recovery Strategies for Flash-Based Storage Under Ransomware Attacks: A Survey

Defense and Recovery Strategies for Flash-Based Storage Unde...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Yin, Junhong Kang, Kyungtae Major in. Bio Artificial Intelligence Hanyang University Dept. Computer Science and Engineering Ansan Korea Republic of Hanyang University Dept. Artificial Intelligence Ansan Korea Republic of

ISBN: (纸本)9798331510756

As ransomware evolves, traditional OS-based de-tection mechanisms face growing challenges, particularly from advanced attacks exploiting system vulnerabilities and escalating privileges. The continuous evolution of ransomware attacks has driven researchers to explore storage-level defense strategies, focusing on the potential of Solid-State Drives (SSDs) to enhance data protection and recovery. This paper presents a compre-hensive survey of the current state and future developments in SSD firmware-level ransomware detection and recovery, based on literature published between 2015 and 2024. Firmware-level I/O monitoring helps detect ransomware by identifying the typical 'read-encrypt-overwrite' pattern. This low-level access offers an advantage in detecting ransomware activity. However, conventional detection methods are often prone to false pos-itives. To enhance detection accuracy, some systems integrate machine learning models within the SSD controllers, analyzing I/O request patterns and entropy values of written data to assess potential threats. The Garbage Collection(Gc)mechanism plays a crucial role in data recovery by retaining older versions of data until reclaimed, which can aid in restoring encrypted content. Similarly, backing up legitimate I/O operations incurs performance overhead. To address this, some systems utilize techniques such as neural networks and remote backups to reduce unnecessary performance degradation. Future research should prioritize developing lightweight solutions tailored for SSDs with limited computational resources. Emphasis should be placed on enhancing the timeliness of real-time detection to effectively respond to the rapidly evolving nature of ransomware attacks. © 2025 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

Leveraging Data Augmentation to Improve Deep Transfer Learning Models for Diabetic Retinopathy Severity Classification 14th

Leveraging Data Augmentation to Improve Deep Transfer Learni...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Nazir, Kinza Kim, Jisoo Byun, Yung-Cheol Department of Electronic Engineering Jeju National University Jeju63243 Korea Republic of Collage of Engineering Jeju National University Jeju Korea Republic of Department of Computer Engineering Major of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

Diabetic Retinopathy (DR) has become one of the major reasons for vision loss worldwide. It is a retinal complication resulting from diabetes. DR can lead to ultimate blindness if not detected in the early stages. Since the symptoms don’t show till the late stages, it is very important to detect the disease early on to prevent vision loss. Ophthalmologists use fundus images to find internal scars or lesions. For the past few years, machine learning specifically deep learning has played an important role in the automation of medical screening. One of the limitations of using machine learning for medical imaging is a shortage of large medical datasets. Data augmentation plays a vital role in avoiding overfitting problems. This study used six pre-trained models MobileNet, DenseNet201, InceptionV3, VGG16, Xception, and ResNet50 with suitable data augmentation techniques and compared the results. The results showed that the deep learning models trained on augmented DR images performed better compared to the models without prior augmentation. Inception-V3 in particular trained on an augmented dataset achieved the highest 96.02% validation accuracy and 98.06% AUC hence out-performed other pre-trained models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Selective face de-identification scheme using multiple face recognition and classification techniques 4

Selective face de-identification scheme using multiple face ...

引用

4th International Conference on Advances in computer Technology, Information Science and Communications, CTISC 2022

作者： Bae, Sang-Min Park, Ji-Sung Ju, Chan-Yang Lee, Dong-Ho Hanyang Univ. Computer Science and Engineering Major in Bio Artificial Intelligence Ansan Korea Republic of

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

Social media is rapidly growing through platforms that provide live-streaming service, video sharing service, etc. But, as the social media grows, the cases where faces of people in the media are indiscreetly exposed are also increasing. Personal sensitive information may be included in a photo and video, and representative data that can identify an individual is face. So, various face de-identification methods have been proposed. However, most face de-identification methods have tried to obfuscate every face in an image or video and tend to focus on minimizing the loss of facial features due to obfuscation for utilizing the rest of facial features as data except for features that can identify individuals. Therefore, those methods are not adequate for face de-identification in social media service because main characters' faces like media producers, creators or actors need to be exposed on purpose, whereas the other targets' faces like pedestrians or crowd should not be exposed in the videos. Selectively obfuscating targets' faces by classifying all faces in the video into exposing targets and obfuscating targets is necessary for improving the privacy in social media service. In this paper, we propose a selective face de-identification system that exposes main characters' faces and obfuscates the other targets' faces by recognizing and classifying all faces appeared in a video. Our system detects and tracks multiple faces using a deep learning-based face recognition, and classifies main characters' faces and the obfuscating targets' faces, and finally de-identifies only the faces of the obfuscating targets on purpose. We also propose an efficient pipelining scheme for batch processing of face de-identification that rearranges the order of faces to be identified in each frame by matching faces existing in continuous frames of a video. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Classification of Lung Cancer Using Machine Learning and Image Processing

Multi-Class Classification of Lung Cancer Using Machine Lear...

引用

2023 IEEE International Conference on Computing, ICOCO 2023

作者： Charnsripinyo, Teerapat Wattanapongsakorn, Naruemon Trium Udom Suksa School Mathematics and Sciences Major Bangkok Thailand King Mongkut's University of Technology Thonburi Department of Computer Engineering Bangkok Thailand

ISBN: (纸本)9798350302684

In this research paper, we present lung cancer classification using machine learning techniques. We used several techniques to classify the CT-scan images into three classes which are normal, benign and malignant (cancerous) classes. The dataset was obtained from a reliable source having 1096 images overall. The dataset was preprocessed to have balanced classes and feature extracted using multiple image filters. Many experimental cases were conducted using various machine learning techniques which are decision tree, random forest, support vector machine and K-nearest neighbor, and evaluated considering binary class classification and multi-class classification, which are normal vs. non-normal, cancerous vs. non-cancerous, and normal vs. benign vs. cancerous. Five performance metrices which are confusion matrix, accuracy, recall, precision and F1-score were considered. The results show that the random forest and K-nearest neighbor techniques that we consider performed very well. The normal class (healthy subjects) and the benign (not-harmful tumor) class can be correctly classified 97%-99%. Overall, we obtained the accuracy of 99.73 % for 2-class classification, and accuracy of 98.69 % for the 3-class classification. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Development of Augmented Reality-based Dental Surgical Guide System for Clinical Use 13

Development of Augmented Reality-based Dental Surgical Guide...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Fukuda, Yusuke Takebayashi, Akira Yamamoto, Hiroaki Kano, Toru Ibaraki University Dept. Major in Computer and Information Sience Ibaraki Japan Medical Engineering Lab. Saitama Japan Tsuda Dental Clinic Ibaraki Japan Ibaraki University Dept. of Mechanical Systems Engineering Ibaraki Japan

ISBN: (纸本)9798350355079

Surgical guide plates, which are used in dental implant treatments, have some limitations that cause problems for the operator and patient. This study aims to develop an augmented-reality-based surgical guide system to solve these problems and discusses its use in clinical practice. Our surgical guide system achieved a good accuracy in drilling simulations on training typodonts, demonstrating its potential in clinical practice. © 2024 IEEE.

关键词： Dental prostheses

来源：评论

学校读者我要写书评

暂无评论

LightSTATE: A Generalized Framework for Real-Time Human Activity Detection Using Edge-Based Video Processing and Vision Language Models

引用

IEEE Access 2025年 13卷 97609-97627页

作者： Debnath, Anik Kim, Yong-Woon Byun, Yung-Cheol Jeju National University Department of Computer Engineering Jeju-si63243 Korea Republic of Jeju National University Institute of Information Science & Technology Department of Computer Engineering Major of Electronic Engineering Jeju63243 Korea Republic of

Human activity detection plays a vital role in applications such as healthcare monitoring, smart environments, and security surveillance. However, traditional methods often rely on computationally intensive models, which are unsuitable for edge devices due to their limited resources and high latency. This research introduces a new approach named LightSTATE, a lightweight hybrid framework designed for real-time activity detection by integrating edge-based preprocessing with cloud-hosted Vision Language Models (VLMs). The system processes video streams through efficient frame extraction, edge detection and Root Mean Square Error (RMSE)-based frame filtering to identify significant motion events. These selected frames are transmitted to the cloud for semantic analysis and state recognition. The system utilizes GPT-4o as the vision-language model to generate rich, descriptive captions for human state understanding. LightSTATE was evaluated on a curated dataset of 9 real-world videos containing 634 frames, with 320 labeled frames used for testing. The framework demonstrated high accuracy in detecting predefined states, with an average precision of 0.98, an average recall of 0.98, and an average F1-score of 0.98. The experimental results confirm that the average frame processing time is approximately 0.8-0.9 seconds, ensuring suitability for real-time applications. Due to the scarcity of publicly accessible datasets, we compiled a custom dataset to effectively assess the performance of our proposed approach. The results validate the scalability and real-time capabilities of our proposed system, making it a promising solution for continuous monitoring applications. This study establishes LightSTATE as a scalable, efficient, and privacy-preserving framework for real-time human activity detection. Future work will focus on extending its applicability to dynamic and multi-person scenarios while enhancing system adaptability for diverse use cases. © 2013 IEEE.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Click Fraud Detection in Digital Advertising Through Ensemble Deep Learning 14th

Enhanced Click Fraud Detection in Digital Advertising Throug...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Batool, Amreen Kim, Jisoo Byun, Yung-Cheol Department of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of Collage of Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

As digital marketing becomes more and more crucial in today’s business strategies, the issue of click fraud. Which aims to deplete advertising budgets through activities. Has grown, leading to the need, for defenses. This research introduces a blend of Convolutional Neural Networks (CNN) Bidirectional Long Short Term Memory networks (BiLSTM) and Random Forest (RF) classifiers to effectively combat click fraud. This innovative model combines the power of learning for extracting features with RFs classification capabilities. By incorporating CNN and BiLSTM our method improves the identification of spatial features from data, which are then classified using an RF model. This ensemble approach is designed to address shortcomings in existing models that depend mainly on machine learning methods and often demand extensive feature manipulation. We showcase the efficiency of our model through testing on a dataset, achieving an impressive accuracy rate of 99.19% surpassing previous techniques. Additionally, we evaluate metrics such as precision, recall, and F1 score all highlighting the superiority of our approach. This research does not only push forward the tools for detecting click fraud but also offers a scalable framework for potential adaptation and implementation, in real world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Mining Association Rules for Classroom Concentration Based on Apriori Algorithm 7

Research on Mining Association Rules for Classroom Concentra...

引用

7th IEEE Information Technology and Mechatronics engineering Conference, ITOEC 2023

作者： Bai, Jingqiu Kong, Huafeng Hu, Wenhan Wuhan Business University Department of Information Engineering Hubei China Major in Data Science and Big Data Technology China The Main Research Direction Is the Computer Application China

ISBN: (纸本)9798350334197

This paper studies the correlation between students' concentration in class and learning interest, emotional state and other influencing factors. By collecting students' classroom status data, a data set suitable for data mining is constructed. Based on the idea of Apriori algorithm, the Anaconda Navigator programming tool is used to mine the association rules of students' classroom concentration. Through data mining based on Apriori algorithm, and the association rules between students' emotional state, learning interest and other factors and in-class test scores are output. The results of strong association rules show that the better students' emotional state, learning interest and other states are, the better their classroom concentration performance is. Mining the potential influencing factors of students' classroom concentration provides valuable reference theory for students to improve classroom concentration and teachers to improve classroom teaching effect, which is helpful for teachers and students to build a more efficient classroom together in the future. © 2023 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection Scheme Based on Sequential Tri-Way Decisions of Multiple Granularity for Intelligent Connected Vehicles

An Intrusion Detection Scheme Based on Sequential Tri-Way De...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Li, Yongzhong Wang, Qi Li, Yuheng Zhang, Shipeng School of Automotive Engineering Nantong Institute of Technology Nantong226010 China Internet of Things and Big Data Major of Macao Polytechnic University Macao China School of Computer Science Jiangsu University of Science and Technology Zhenjiang212003 China

ISBN: (纸本)9789819639762

With the rapid developing technology of the Internet of Things, intelligent connected vehicles are facing more and more serious cybersecurity threats and challenges. With the developing of cybersecurity technology for intelligent connected vehicles it has posed a comprehensive challenge to the existing cybersecurity technologies. Intrusion detection is an important research field of cybersecurity. An intrusion detection scheme based on sequential tri-way decisions of multiple granularities (S3WD-MG) is proposed for Intelligent Connected Vehicles. The S3WD-MG method obtains feature sets of multi-granularities through the auto-encoder of deep learning. This method combines multiple granularities and sequential tri-way decisions to make decisions by the most appropriate for network behavior through by the decision threshold. The experiment results on NSL-KDD show that S3WD-MG method does have a good performance in intrusion detection. Compared with other models, our proposed S3WD-MG method has a higher detection’s rate and the robustness of algorithm is stronger. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Network intrusion

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：