检索结果-内蒙古大学图书馆

Medical Image Encryption Method Using Cubic-Sin-Logistic-Tent Chaotic Pseudo-Random Number Sequence-Based Substitution

引用

SN computer Science 2023年第4期4卷 1-13页

作者： Adhikari, Subhajit Karforma, Sunil Department Of Computer Application Dinabandhu Andrews Institute of Technology and Management W.B Kolkata India Department Of Computer Science The University of Burdwan W.B Burdwan India

Transmission and storage of the medical images generated from various healthcare applications through the internet must be secured for the correct identification of diseases and successful treatment of them. The medical images of the patient’s data must be protected in transmission and storage phase from different types of security attacks. Therefore, to maintain confidentiality and privacy of sensitive medical data, encryption is obvious. This paper provides a detailed decryption and analysis of a novel medical image encryption approach based on chaos theory and pseudo-random number sequences. Using the symmetric key concept, our encryption method is made up of substitution and permutation phases. First, a set of unique PRN as pseudo_random_numbers is evolved from a Cubic Map-Logistic Map-Sine Map-Tent chaotic map. Again a new PRN sequence is obtained from a random_function. They are xored to create a single PRN sequence. This PRN is xored with the original pixel values in the substitution phase. In the process of permutation, a unique set of index numbers are produced using a random_function. Then, the substituted_image is shuffled using the index numbers and produces the cipher image. According to different statistical metrics, our technique for encrypting medical images is resistant to various security breaches in less time than others. Our method of medical image encryption can be applied for resource-constrained devices for IOT applications. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Chaotic pseudo random number Chi-square Correlation Cubic map Entropy Logistic map Medical image encryption NPCR Permutation Security analysis Sine map Substitution Tent map UACI

来源：评论

学校读者我要写书评

暂无评论

Continuous and generalized visual odometry based on FLANN_PSC-RANSAC_LSTM

引用

Journal of Intelligent and Fuzzy Systems 2024年第1-2期47卷 15-28页

作者： Li, Dengao Feng, Ran Wu, Fanming Zhao, Jinhua Zhao, Jumin College of Computer Science and Technology College of Data Science Taiyuan University of Technology Shanxi Taiyuan China College of Electronic Information and Optical Engineering Taiyuan University of Technology Shanxi Taiyuan China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan University of Technology Shanxi Taiyuan China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan China

In the field of simultaneous localization and mapping (SLAM), visual odometry (VO) always has great application prospects. In recent years, with the progress in the field of machine learning, methods based on neural networks are constantly being updated and applied. In this paper, we propose a continuous and generalized monocular visual odometry method based on features and neural networks. First, the feature information of adjacent image sequences is extracted by matching and troubleshooting algorithm (FLANN_PSC-RANSAC), then it and the corresponding six-degree-of-freedom information are simultaneously input into the long short-term memory artificial neural network (LSTM) for model construction, which not only ensures the reliability of the mode but also eliminates the influence of illumination on the data. In the real environment test, it has been effectively proved in terms of trajectory recovery accuracy and generalization ability to different environments and different illuminations. © 2024 - IOS Press. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Parameters Research of Facial Emotion Detection Algorithm Based on Machine Learning

Parameters Research of Facial Emotion Detection Algorithm Ba...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Zhou, Ting Yadav, Amit Shi, Xiao Jiang Khan, Asif Chengdu Neusoft University Department of Computer Science and Technology Chengdu611844 China Charles Darwin University College of Engineering IT and Environment Australia Integral University Department of Computer Application Lucknow India

ISBN: (纸本)9798350361537

The purpose of emotional state recognition is to let computers have the ability to analyze and understand human emotions and intentions, and deeply analyze human psychological activities, so as to play a role in the fields of entertainment, education, intelligent medical treatment and so on. Different emotion recognition algorithms and different parameters of the same algorithm have different recognition effects. Among them, muscle-based feature model and 68 feature point calibration are two common face emotion recognition methods. The former uses deep learning to judge the emotional state by analyzing the movement of face muscles, while the latter calculates various feature parameters through the position relationship of 68 key points of the face, and then judges the emotional state. This paper mainly discusses the calibration method of 68 feature points. Through the use of two machine learning algorithms (KNN, SVM) and the study of different parameters in the algorithm, the influence of different parameters on the emotion recognition effect is compared and analyzed. The experiment proves that by detecting 68 key points of face, we can find the optimal parameter value in the current classification task. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Survey of Privacy Preserving Methods based on Differential Privacy for Medical Data 7

A Survey of Privacy Preserving Methods based on Differential...

引用

7th World Conference on Computing and Communication Technologies, WCCCT 2024

作者： Yan, Haicao Yin, Menghan Yan, Chaokun Liang, Wenjuan Henan University School of Computer and Information Engineering Kaifeng China Henan University Henan Engineering Research Center of Intelligent Technology and Application Kaifeng China

ISBN: (纸本)9798350372328

Using deep learning and federated learning in the medical domain has facilitated convenience in diagnosing and treating patients. However, the current privacy leakage problem has made patients more cautious about personal privacy security. Privacy security has become an urgent issue. Differential privacy is a cryptography technique that makes it impossible for attackers to identify personal data by adding noise to the training process. In this work, we first provide a complete overview of differential privacy technologies. Then, we will review existing differential privacy works in the medical field. Finally, we analyze the existing problems of differential privacy and propose possible avenues for further research. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Vector knowledge transfer-driven representation learning for heterogeneous hypernetworks

引用

Knowledge and Information Systems 2025年 1-29页

作者： Chen, Yijian Zhu, Yu Wang, Xiaoying Huang, Jianqiang Cao, Tengfei Wang, Wei School of Computer Technology and Application Qinghai University Xining China Qinghai Provincial Laboratory for Intelligent Computing and Application Qinghai University Xining China School of Computer and Information Science Qinghai Institute of Technology Xining China

Unlike traditional networks, the hypernetworks have complex higher-order tuple relationships, i.e. hyperedges. However, most existing hypernetwork representation learning methods fail to adequately capture these complex higher-order tuple relationships. To address this issue, a vector knowledge transfer-driven representation learning method for heterogeneous hypernetworks abbreviated as VTRL is proposed. Firstly, a hyperedge-aware random walk algorithm with node importance preservation is proposed, which assigns greater random walk probabilities to more important nodes without decomposing the hyperedges. Secondly, based on hyperedge-aware random walk algorithm with node importance preservation, a hyperedge-aware topological structure model is proposed to learn pre-trained vectors. Finally, inspired by transfer learning, the pre-trained vectors are transfered to knowledge-enhanced similarity model to the final node representation vectors. The experiments on four real-world hypernetwork datasets demonstrate that as for link prediction tasks, our proposed method outperforms almost all baseline methods. As for hypernetwork reconstruction tasks, on the drug dataset, our proposed method outperforms all baseline methods when the reconstruction ratio is less than 0.8, meanwhile, on the GPS dataset, our proposed method shows competitive performance compared to the best baseline method HPHG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning to Predict Cardiovascular Disease: Systematic Meta-Analysis 6

Machine Learning to Predict Cardiovascular Disease: Systemat...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Shuja, Mirza Qtaishat, Ahmed Mishra, Hari Mohan Kumar, Mukesh Ahmed, Bilal Lovely Professional University School of Computer Application Phagwara India Sohar University Department of Information Technology Sohar Oman

ISBN: (纸本)9798350346961

People do not have much time to think about their health in today's fast-paced society because of how busy their lives are. The overscheduling of people's lives and a widespread disregard for their health are two factors that contribute to the rise in the incidence of disease. Additionally, the great majority of people have disability that prevents them from operating properly, such as cardiovascular illness. These people are unable to operate normally because of their disabilities. According to the statistics provided by the World Health organization (WHO), cardiovascular disease is responsible for more than one-third of all deaths. Because of this, it is very necessary for anybody working in the medical industry to be able to evaluate the chance that a patient may develop cardiovascular disease. However, because hospitals and the healthcare industry produce such a vast amount of data, it may be difficult to do research owing to the sheer amount of information that is available. The use of methods that are based on Machine Learning (ML) by medical professionals has the potential to cut down on the amount of time and effort spent formulating predictions and organising data. Because of this, we have been talking about the factors that lead to heart disease as well as the methods that are involved in machine learning. We evaluated and compared the efficacy of a wide variety of well-known ML algorithms that were utilised in the experiment, and we made inferences about cardiovascular disease using these techniques. In the end, the purpose of this research is to determine whether a ML system is capable of reliably predicting cardiac illness.. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis using Dictionary-Based Lexicon Approach: Analysis on the Opinion of Indian Community for the Topic of Cryptocurrency

引用

Annals of Data Science 2024年第6期11卷 2019-2034页

作者： Loomba, Sankalp Dave, Madhavi Arolkar, Harshal Sharma, Sachin School of Cyber Security and Digital Forensics National Forensic Sciences University Gujarat Gandhinagar India Adani Institute of Digital Technology Management Gujarat Ahmedabad India Faculty of Computer Application and Information Technology GLS University Gujarat Ahmedabad India Indrashil University Gujarat Mehsana India

Due to the ever-increasing computing power and easy availability, social-networking platforms like Facebook, Twitter, etc. have become a popular medium to express one’s views instantly, be it about political situations, commercial products, or social occurrences. Twitter is a powerful source of information, whose data can be utilized to investigate the opinions of users through a process called Opinion Mining or Sentiment Analysis. Using the principles of Natural Language Processing and data science, this paper presents a comparative evaluation of multiple lexicon-based sentiment analysis algorithms to extract public opinion from tweets. The study explores the nuances of sentiment analysis using data science methodology, assessing how various lexicon-based algorithms may successfully identify and classify sentiments expressed in tweets from the Indian community about cryptocurrency. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Improved Particle Swarm optimization Task Scheduling Algorithm Based on Multiple Swarm Molecular Dynamics Theory 24

Improved Particle Swarm optimization Task Scheduling Algorit...

引用

5th International Conference on computer Information and Big Data applications, CIBDA 2024

作者： Liu, Zilai Yu, Liang Li, Qiqian College of Computer Science Guangdong University of Science and Technology Guangdong AIoT Application Innovation Joint Laboratory AIoT Edge Computing Engineering Technology Research Center Dongguan523000 China

ISBN: (纸本)9798400718106

In light of the objective to optimize task scheduling in Cyber-physical systems (CPS) by establishing an efficient mapping between system resources and user tasks, a novel particle swarm optimization task scheduling algorithm is proposed. This algorithm incorporates the principles of multiple swarm molecular dynamics theory, thereby enhancing its performance. By integrating molecular dynamics theory and KMTOA into the particle swarm optimization algorithm, the proposed approach aims to achieve improved task time span and load balancing capabilities. To achieve this, the algorithm initially divides the particle population into distinct sub-populations. Subsequently, different gravitational rules are applied to guide the evolution of particles in each sub-population. This division and rule implementation greatly enhance the diversity of the population in the early stages and enhance the local search ability in the later stages. Simulation and comparative experiments have been conducted to evaluate the effectiveness of the improved task scheduling algorithm. The results demonstrate that the algorithm exhibits superior task time span and load balancing capabilities, effectively enhancing the efficiency of resource mapping. © 2024 ACM.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Future Directions of Artificial Intelligence and Machine Learning in Healthcare: A Systematic Analysis and Mapping Study 6

Future Directions of Artificial Intelligence and Machine Lea...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Mishra, Hari Mohan Ahmed, Bilal Shuja, Mirza Qtaishat, Ahmed Kumar, Mukesh Lovely Professional University School of Computer Application Phagwara India Sohar University Department of Information Technology Sohar Oman

ISBN: (纸本)9798350346961

In order to organise previously conducted research on using machine learning in medical contexts, the authors of this paper employ a method known as systematic mapping. In order to do this, we looked through the abstracts of a variety of publications, including medical journals, healthcare periodicals, and conference proceedings, looking for the phrase 'use of artificial intelligence and machine learning in healthcare.' After doing a search on Google Scholar, which resulted in the retrieval of 500 papers, we classified these studies in accordance with their objectives, approaches, primary concerns, and illnesses. With the use of this technique, we were able to organise our findings into the five categories that are as follows: privacy and security;a framework for privacy and security;interpretable machine learning;medical image assessment;electronic health record processing;and transfer learning. In addition, we found that the evaluation of medical images is the topic that receives the most research, that interpretable machine learning and explainable artificial intelligence are becoming increasingly popular, and that most authors are primarily interested in cancer research. To restate our mission, we want to provide future generations of scholars with an accurate picture of where the field is now and where it is headed.. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

DL-Based Somnolence Detection for Improved Driver Safety and Alertness Monitoring 5

DL-Based Somnolence Detection for Improved Driver Safety and...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Neeraja, Peddinti. Kumar, R.G. Kumar, M. Sunil Liyakat, Kazi Kutubuddin Sayyad Vani, M. Sowmya School of Computing Department of Computer Application AP Tirupathi India Siddharth Institute of Engineering & Technology Computer Science and Engineering AP Puttur India School of Computing Department of Computer Science and Engineering AP Tirupathi India Brahmdevdada Mane Institute of Technology Department of Computer Science and Engineering Maharashtra Solapur India

ISBN: (纸本)9798350383522

This abstract explores the utilization of deep learning for detecting driver somnolence, aiming to enhance driver safety and alertness monitoring. It investigates the integration of computer vision, physiological signals, and machine learning algorithms. Key considerations include real-time detection, accuracy, scalability, and driver intervention mechanisms. By leveraging deep learning techniques, effective driver somnolence detection systems can contribute to preventing accidents and promoting safer roads. © 2024 IEEE.

关键词： Convolution neural network deep learning Drowsiness detection transfer learning

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：