检索结果-内蒙古大学图书馆

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Bhairavi, R. Bhairavi, R. Lakshmi, M. Sankar, R. Sharma, V. Rama Krishna Anni Princy, B. Srm Institute of Science and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India S.A Engineering College Department of Mathematics Tamil Nadu Chennai India Chennai Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Mlr Institute of Technology Department of Electronics and Communication Engineering Dundigal Hyderabad India Panimalar Engineering College Department of Artificial Intelligence and Machine Learning Tamilnadu Chennai India

ISBN: (纸本)9798350354218

Rapid developments in e-commerce have led to a meteoric rise in credit card usage. More and more people are falling victim to credit card fraud as a result of this payment method's widespread use. Consequently, we want a robust and reliable fraud detection system to put a stop to these scams. We have covered the basics of credit card theft in this article. Finding a remedy to these sorts of scams is, thus, quite crucial. We developed a model to identify fraudulent credit card transactions in this article. The majority of the critical capabilities needed to identify fraudulent and unlawful transactions can be met by this system. The pattern and behaviour of illicit transactions are getting more difficult to trace due to the ongoing change in technology. Using technology that incorporates an enhanced deep learning scheme, known as an Elevated Neural learning Scheme (ENLS), can help find a solution. In order to determine how effective the suggested scheme is, this method is cross-validated using the traditional learning technique known as Logistic Regression (LR). In order to do this, we apply various classification models to the data, including ENLS and LR, and then we quantify the model's performance using quantitative metrics like accuracy. Our study's conclusion describes the optimal classifier by training and testing with the suggested methods, which yields a superior answer. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

IoT Based Effective Wearable Healthcare Monitoring System For Remote Areas

IoT Based Effective Wearable Healthcare Monitoring System Fo...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Tiwari, Shweta Jain, Nishi Devi, Nirmala Supraja, B. Chitra, N. Thulasi Sharma, Aditi GGITS Dept of Artificial Intelligence & Machine Learning M.P Jabalpur India IES College of Technology Department of Electrical & Electronics Engineering M.P Bhopal462044 India St. Martin's Engineering College Dept. of FME Telangana Secunderabad India Guru Nanak Institutions Technical Campus Department of CSE - AIML Hyderabad India MLR Institute of Technology Dept. of CSE Telangana Hyderabad India

ISBN: (纸本)9798331539948

The research introduces an IoT-based personal healthcare monitoring system for rural areas with poor healthcare. Data processing, machine learning, and deep learning monitor vital signs with 96.5% accuracy, better than current approaches. The complete technique employs many data points to demonstrate rural residents' social and health features. This ensures the system works in challenging scenarios. With 0.94 precision, health data recognition was accurate. This degree of information is crucial for making wise medical decisions, particularly in low-resource areas where traveling to a hospital is difficult. The system uses 2.5 W every hour, making it energy efficient. This allows it to operate reliably even when the power goes off. Comparing the recommended approach against established methods with various models consistently indicates its superiority. IoT-based personal healthcare tracking is more accurate, precise, and energy-efficient than existing approaches. These data demonstrate the system's power to transform remote healthcare. They demonstrate their ability to monitor key health variables and maintain stability, durability, and energy efficiency. The authors discuss the study's limitations and wider implications at the conclusion. Before the approach may be extensively employed, connection and device cost issues must be addressed. The research highlights how technology has enhanced healthcare monitoring and emphasizes the need for community-specific solutions for rural and underprivileged individuals. The recommended IoT-based smart healthcare monitoring system advances technology and makes healthcare access more equal and accessible to disadvantaged groups. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Email Spam Detection using Graph based Convolutional Neural Network with MALO

Email Spam Detection using Graph based Convolutional Neural ...

引用

Data Science and Information System (ICDSIS), IEEE International Conference on

作者： G N Keshava Murthy C P Nayana P Harshitha M Sandhya Department of Electronics and Instrumentation Engineering Siddaganga Institute of Technology Tumakuru Karnataka India Department of Computer Science and Engineering East West Institute of Technology Bengaluru India Artificial Intelligence and Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

Every day, millions of individuals and organizations rely on email as a fundamental tool for communication, business transactions, and information exchange. However, the pervasive issue of spam email has escalated in recent years, paralleling the exponential growth in email usage. This surge in spam poses a significant challenge for both individuals and businesses, hindering their ability to effectively manage and filter incoming emails. To confront the complexities inherent in spam email classification, such as the inability of conventional models to adequately capture pertinent information due to document length constraints and the lack of subject matter expertise leading to suboptimal classification outcomes, a novel approach is proposed. This study advocates for the integration of a knowledge graph and a graph convolutional neural network (GCNN) as the foundation for a robust classification model. Utilizing Bidirectional Encoder Representations from Transformers (BERT), the text data is encoded, ensuring a comprehensive representation of semantic meaning. The graph network is then initialized with vectors containing dense semantic information for each word. By leveraging a trained entity-relationship extraction model, the interdependencies between entities and other syntactic information are extracted and utilized as edges within the GCNN. Moreover, the model’s weights are optimized using the principle of Maximum A Posteriori (MAP) in Latent Optimization (MALO). The incorporation of graph structures enables the model to discern intricate semantic relationships between words, enhancing its ability to comprehend the underlying context of the text. This innovative technique transcends traditional email spam detection methods by amalgamating knowledge-driven characteristics with data-driven features, thereby advancing the efficacy of classification endeavors.

关键词： Accuracy Uncertainty Unsolicited e-mail Semantics Knowledge graphs Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification using G-XGB

Human Activity Classification using G-XGB

引用

2023 International Conference on Data Science and Network Security, ICDSNS 2023

作者： Kataria, Aman Puri, Vikram Pareek, Piyush Kumar Rani, Sita Amity Institute of Defence Technology Amity University Noida Campus Sector-125 Noida India Duy Tan University Center of Visualization and Simulation Da Nang Viet Nam Cell Nitte Meenakshi Institute of Technology Dept. of Artificial Intelligence and Machine Learning and Ipr Bengaluru India Guru Nanak Dev Engineering College Department of Computer Science and Engineering Ludhiana India

ISBN: (纸本)9798350301595

Wearable body sensors have recently gained popularity because they monitor user behaviors and vital indicators. These sensors are designed to monitor various physiological factors, such as motion, temperature, and heart rate, among others. Making sense of the data gathered by these sensors requires separating the dependent and independent features. The dependent parameters are those that body-worn sensors can read in this scenario. Examples of such elements include blood oxygen levels, heart rate, temperature, mobility, and airflow. These sensors capture data about a person's activity and health. The independent parameters in wearable body sensors are related to the dependent parameters, whereas the dependent parameters are those that the sensors can measure directly. Such characteristics include age, sex, weight, and environmental influences. For example, humidity and airflow might impair a temperature sensor's accuracy. The user's age or level of physical fitness may also influence the accuracy of a heart rate monitor. Activity monitors are used in this study to capture the actions of various people. Static and dynamic properties are derived from the activity monitor recording. The performance evaluations of the eight distinct machine-learning models that were created using the retrieved features are discussed in this paper. The Grid Search method is used to enhance the performance of the XGB model. © 2023 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Secure Electronic Health Record Storage in the Cloud Based on Multiple Fragmentation and Reconstruction Using Blockchain with Cryptographic Techniques

Secure Electronic Health Record Storage in the Cloud Based o...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： W. Mercy L. Sherly Puspha Annabel Dept. of CSE KCG College of Technology Anna University Chennai India Dept. of Artificial Intelligence and Machine Learning St. Joseph's College of Engineering Chennai India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Data privacy is an important factor in cloud data storage. Still there are some security issues such as hacking that may take place with respect to data. In the existing techniques the time and cost consumption are more in computing and data storage. Data privacy is a challenging one against hacking and to avoid hacking data can be fragmented over multiple locations when storing and reconstructed while accessing the data. In the existing implementation single field query is used to access the Electronic Health Records (EHR). It will take more time to fetch the data and the fetched data also will be huge with some unwanted data. This paper proposes multi field skyline conditional query to access the accurate EHR data for minimizing the accessing time to improve the performance by implementing B+-Tree indexing and skyline query. Cloud data storage privacy also will be improved with Cryptography and Blockchain techniques. Secure Hashing Algorithm (SHA 512), Consensus algorithm and Smart Contracts are used for data integrity and fault tolerance mechanism. The possible goals include effective data storage and access, reducing security breach, storage overhead, avoiding hacking, enhancing data privacy.

关键词： Data privacy Accuracy Smart contracts Memory Ubiquitous computing Blockchains Computer crime Electronic medical records Secure storage Indexing

来源：评论

学校读者我要写书评

暂无评论

Deep learning for Phishing Website Detection 2

Deep Learning for Phishing Website Detection

引用

2nd IEEE Mysore Sub Section International Conference, MysuruCon 2022

作者： Sushma, K.S.N. Jayalakshmi, M. Guha, Tapas Hkbk College of Engineering Dept. of Cse Bengaluru India Academy of Research and Education School of Computing Kalasalingam Department of Cse Krishnankoil India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (数字)9781665497909

ISBN: (纸本)9781665497909

Data security has become a major issue as digitalization across the world is rapidly increasing. Personal information of the user is extracted and exploited using one of the cyber-attack known as phishing. To detect phishing, and to avoid the user from visiting a non-legitimate website, a method is proposed in this paper. This method uses unique features of Uniform Resource Locator which can differentiate between legitimate and non-legitimate websites. To classify websites, Random forest and Support Vector machines are two machine learning methods that are employed in this work. The internet offers a wealth of information that may be accessed. Because of the rapid development of technology, an unavoidable dependency on the Internet has emerged in all aspects of life. As the number of apps that run on the Internet continues to rise, there is also a rising worry of threats and a need to address problems that are connected to security. There are numerous web application threats in the Internet domain. These threats aim to either steal sensitive information from users, change the database of web servers, or undermine the credibility of a particular web application. There are many web application threats in the Internet domain. These threats include: One of the most significant dangers to information security is the character. Attacks that Deny Service to Others Session Hijacking attempts The CrossSite Scripting Language XSS Phishing and Buffer Overflow are Two Common Scams Phishing is one of these methods, and it involves tricking people into giving sensitive information such as usernames and passwords, credit card details, and sensitive bank information by way of email spoofing, instant messaging, or fake web sites whose look and feel give the appearance of a legitimate one. Examples of such information include usernames and passwords for online accounts, credit card details, and sensitive bank information. Important forms of phishing include deceptive phishing, malwar

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Hybrid machine learning Based Predictive Model To Improve Cloud Application Performance In Cloud Saas

Hybrid Machine Learning Based Predictive Model To Improve Cl...

引用

Emerging Trends in engineering and Medical Sciences (ICETEMS), International Conference on

作者： Rushikesh Burle Sanskruti Gaurkhede Palash Gourshettiwar Sakshi Izankar Swapnil Gundewar Utkarsha Pacharaney Faculty of Engineering and Technology Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Faculty of Engineering and Technology Computer science And Design Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Faculty of Engineering and Technology Computer Science and Medical Engineering Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India

ISBN: (数字)9798331529352

ISBN: (纸本)9798331529390

Cloud computing provides IT resources like applications, infrastructure, and platforms as services over the Internet. Predictive maintenance leverages data-driven methods to anticipate equipment failures, allowing for more efficient maintenance management. This process involves monitoring equipment conditions by collecting data over time. Typically, industrial equipment is used without a clear scheduled maintenance plan. This study presents a new strategy for predictive maintenance in SaaS application cloud infrastructure, focusing on predicting customer churn in Customer Relationship Management (CRM) systems. During the data collection phase, consumer data is extracted from a churn dataset on Kaggle. Preprocessing steps include eliminating null values, scaling features, and converting categorical variables to enhance data quality before analysis. This research evaluates several ML models using recall, F1 score, accuracy, and precision. The findings indicate that the Hybrid SVM + Decision Tree model achieved a 92.71% accuracy rate, outperforming other models and offering more accurate predictions of customer churn in SaaS applications. Future research should explore advanced feature engineering techniques, consider temporal dynamics to improve prediction accuracy, and incorporate real-time data streams for dynamic model adaptation.

关键词： Support vector machines Cloud computing Adaptation models Accuracy machine learning Predictive models Real-time systems Churn Streams Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

HeLiMOS: A Dataset for Moving Object Segmentation in 3D Point Clouds From Heterogeneous LiDAR Sensors

arXiv

引用

arXiv 2024年

作者： Lim, Hyungtae Jang, Seoyeon Mersch, Benedikt Behley, Jens Myung, Hyun Stachniss, Cyrill The School of Electrical Engineering KAIST [Korea Advanced Institute of Science and Technology Daejeon Korea Republic of The Center for Robotics University of Bonn Germany The Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Moving object segmentation (MOS) using a 3D light detection and ranging (LiDAR) sensor is crucial for scene understanding and identification of moving objects. Despite the availability of various types of 3D LiDAR sensors in the market, MOS research still predominantly focuses on 3D point clouds from mechanically spinning omnidirectional LiDAR sensors. Thus, we are, for example, lacking a dataset with MOS labels for point clouds from solid-state LiDAR sensors which have irregular scanning patterns. In this paper, we present a labeled dataset, called HeLiMOS, that enables to test MOS approaches on four heterogeneous LiDAR sensors, including two solid-state LiDAR sensors. Furthermore, we introduce a novel automatic labeling method to substantially reduce the labeling effort required from human annotators. To this end, our framework exploits an instance-aware static map building approach and tracking-based false label filtering. Finally, we provide experimental results regarding the performance of commonly used state-of-the-art MOS approaches on HeLiMOS that suggest a new direction for a sensor-agnostic MOS, which generally works regardless of the type of LiDAR sensors used to capture 3D point clouds. Our dataset is available at https://***/view/helimos. © 2024, CC BY-NC-ND.

关键词： Solid-state sensors

来源：评论

学校读者我要写书评

暂无评论

HeLiMOS: A Dataset for Moving Object Segmentation in 3D Point Clouds From Heterogeneous LiDAR Sensors

HeLiMOS: A Dataset for Moving Object Segmentation in 3D Poin...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hyungtae Lim Seoyeon Jang Benedikt Mersch Jens Behley Hyun Myung Cyrill Stachniss School of Electrical Engineering KAIST (Korea Advanced Institute of Science and Technology) Daejeon Republic of Korea Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

关键词： Point cloud compression Laser radar Three-dimensional displays Filtering Object segmentation Robot sensing systems Labeling Spinning Object recognition Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Techniques and Approaches in Medical Image Fusion

Comprehensive Analysis of Techniques and Approaches in Medic...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Hayath T. M Sai Madhavi D Department of Computer Science and Engineering Ballari Institute of Technology and Management Ballari India Visvesvaraya Technological University Belagavi India Department of Artificial Intelligence and Machine Learning Rao Bahadur Y Mahabaleshwarappa Engineering College Ballari India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

Medical image fusion is a major area in the field of medical imaging, the main objective is to integrate information from multiple imaging modalities to improve diagnostic accuracy. Medical image fusion brings together different types of imaging data—like MRI, CT, and PET scans—to compensate for the weaknesses of using just one method. By merging these complementary views, medical professionals gain a clearer, more complete picture of what’s happening inside the body, which leads to better diagnoses and smarter treatment plans. This article explore the latest techniques for combining these images, from traditional approaches to cutting-edge AI tools. Older methods, such as wavelet transforms and principal component analysis (PCA), focus on preserving fine details like edges and textures but often struggle with noisy images or slow processing. Newer AI-driven methods, like generative adversarial networks (GANs) and transformers, excel at learning complex patterns from data, creating sharper fused images. By examining the strengths, limitations, and practical implications of each technique, this paper offers a structured analysis of fusion methods and their applications.

关键词： Deep learning Wavelet transforms Accuracy Computational modeling Image edge detection Wavelet analysis Integrated circuit modeling Medical diagnostic imaging Image fusion Principal component 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：