检索结果-内蒙古大学图书馆

7th World Symposium on Communication engineering, WSCE 2024

作者： Pasoi, Georgia E. Talattinis, Kyriacos A. Memos, Vasileios A. Goudos, Sotirios K. Sarigiannidis, Panagiotis G. Ishibashi, Yutaka Psannis, Konstantinos E. University of Macedonia Dept. of Applied Informatics Thessaloniki Greece Aristotle University of Thessaloniki Dept. of Physics Thessaloniki Greece University of Western Macedonia Dept. of Electrical and Computer Engineering Kozani Greece Aichi Sangyo University Faculty of Business Administration Dept. of Business Management Aichi444-0005 Japan

ISBN: (纸本)9798331542825

Predictions in financial markets have attracted much of scholars' interest. Since the stock market is generally defined as dynamic and volatile due to the affect of the well-known "Internet of Things"(IoT). It is a fact that IoT significantly impacts the financial market and stocks in various ways. Therefore, numerous researchers have attempted to detect patterns regarding the way financial markets react to various external factors. In the last decade, the integration of machine learning and sentiment analysis has appeared to be an effective approach for improving IoT-based stock price predictions in the financial field. This paper intends to propose an approach involving financial news as a source of information for forecasting the stock movement of noteworthy IoT-related companies, employing Big Data Analytics (BDA), Machine Learning, and Sentiment Analysis methods as well. A comparative analysis is conducted between lexicon-based and machine learning-based methods of sentiment analysis about their performance, particularly in the domain of IoT-related stock market prediction. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Detecting Digital Financial Transaction Frauds Using CNN Model 3

Detecting Digital Financial Transaction Frauds Using CNN Mod...

引用

3rd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2025

作者： Rani, Chadalavada Ester Raju, V. Purushothama Dept. of Computer Science & Engineering A.P Bhimavaram India

ISBN: (纸本)9798331543358

The Unified Payments Interface has become increasingly popular as a convenient and user-friendly digital payment platform. However, the surge in Digital Transaction has also resulted in a rise in fraudulent activities, presenting a significant security challenge. This paper introduces a novel approach to detecting fraudulent Digital Transaction by leveraging convolutional neural networks (CNN). By incorporating the CNN model, this study aims to offer a cost-effective solution for identifying Digital Financial fraud. The CNN's ability to analyse patterns in data makes it particularly suitable for fraud detection in Digital Financial Transactions. We evaluate our proposed methodology using a comprehensive dataset that includes both fraudulent and genuine transactions. Our results demonstrate a significant improvement in fraud detection accuracy and efficiency compared to existing methods. This research contributes to the advancement of secure digital payment systems by presenting an innovative approach to detect fraud transactions. Financial institutions and payment service providers can utilize this methodology to enhance the security of Digital Financial Transactions and protect users from fraudulent activities. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Short-term Voltage Stability Improvement in Power System through Grid-forming Hybrid PV Plants

引用

IEEE Transactions on Industry Applications 2025年

作者： Sarwar, Muhammad Ajjarapu, Venkataramana Matavalam, Amarsagar R. R. Roy, Soummya Pico, Hugo N. Villegas Iowa State Universityi Dept. of Electrical and Computer Engineering AmesIA50010 United States Arizona State University School of Electrical Computer and Energy Engineering TempeAZ United States

Short-term voltage stability problems are a major concern in power systems with high penetration of inverter-based resources (IBRs). Fault-induced delayed voltage recovery (FIDVR) is one such problem that can lead to short-term voltage instability. This paper investigates FIDVR mitigation using dynamic voltage support from hybrid PV plants and load control. We propose a deep reinforcement learning (DRL) based optimization framework for optimal dynamic reactive power injection from hybrid PV plants and optimal load control. The Q-injection and amount of load tripping depend on system operating conditions, so the data-driven framework gives optimal setpoints that are adaptable to the varying operating conditions. The numerical simulations show that the optimal dynamic reactive power injection and load control improve the voltage recovery and decrease the load trip amount to comply with the voltage recovery criterion. © 1972-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Understanding Worker Perceptions Toward Privacy When Working with Collaborative Robots That Provide As-Needed Assistance

Understanding Worker Perceptions Toward Privacy When Working...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Andrew Liu Natasha Kholgade Banerjee Sean Banerjee Dept. of Computer Science Clarkson University Potsdam NY USA Dept. of Computer Science & Engineering Wright State University Dayton OH USA

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

As robots increasingly integrate into manufacturing and warehousing environments, they are expected to perform tasks such as monitoring, lifting, stocking, assembly, and transportation, utilizing various sensing technologies including cameras, microphones, and physiological sensors. Collaborative robots, working alongside human workers, leverage these sensors to assess the environment, optimize task execution, and interact with workers. The use of cameras and microphones in such environments can lead to the collection of personally identifiable information (PII), raising worker concerns about surveillance and data misuse. In this study, we analyze survey data collected from 530 industrial workers to assess their perceptions of privacy in relation to data collection by robots in the workplace. Specifically, we explore worker attitudes toward the recording of video and audio data, as well as alternatives such as body joint tracking. Our findings suggest that country significantly influences privacy concerns, while gender has little impact on privacy perceptions related to audio data. Age affects privacy views, particularly with body joints data, where older adults express fewer concerns. Work location also influences privacy perceptions. For video, both middle-aged and older respondents show no significant difference in privacy concerns compared to younger adults.

关键词： Data privacy Privacy Robot vision systems Warehousing Collaborative robots Data collection Cameras Sensors Microphones Identification of persons

来源：评论

学校读者我要写书评

暂无评论

Big data analysis for multi-criteria decision making

引用

Recent Advances in computer science and Communications 2021年第5期14卷 1400-1401页

作者： Kumar, Akshi Bhatia, M.P.S. Dept. of Computer Science & Engineering Delhi Technological University New Delhi India Dept. of Computer Science & Engineering Netaji Subhas University of Technology New Delhi India

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Detection Using Machine Learning Models

引用

Procedia computer science 2024年 235卷 937-947页

作者： Amrit Singh Harisankar Mahapatra Anil Kumar Biswal Madhumita Mahapatra Debabrata Singh Milan Samantaray Department of Computer Science and Engineering NIST Institute of Science and Technology (Autonomous) Berhampur India Dept. of Computer Science Udayanath Autonomous College of Science and Technology Cuttack India Dept. of Computer Science and Engineering Delhi Technical Campus Greater Noida UP India Department of Computer Application Institute of Technical Education and Research (ITER) Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar India Department of Computer Science and Engineering Silicon Institute of Technology Bhubaneswar India

An enormous number of deaths occur every year as a result of heart disease, making it a major concern in world health. Improving patient outcomes and lowering death rates, early detection and correct diagnosis of cardiac disease play a key role. When the heart's arteries become blocked, oxygen-poor blood cannot reach the heart properly, resulting in coronary heart disease. Early detection of cardiac disease is viable because it reduces medical costs and potentially saves the patient's life. Recently presented methods have improved heart failure detection accuracy on testing data without sacrificing accuracy on training data, yet most of these algorithms are suffering from the issue of overfitting. Models that were created end up fitting the test data too well. In this study, we create a novel diagnostic system to address this issue, and the resulting system demonstrates high intelligence and excellent performance on both training and testing data. Machine learning (ML) algorithms have demonstrated promising potential in assisting healthcare professionals with timely and accurate diagnosis. In this paper, is based on supervised machine learning methods are decision tree (DT), random forest (RF), Support vector Machine (SVM), Principal Component Analysis(PCA). We compare their accuracy with each other by using bar plot.

关键词： Coronary Heart Disease Blood Pressure Health Care Machine Learning Imbalanced Data Decision Tree Random Forest SVM PCA

来源：评论

学校读者我要写书评

暂无评论

Fabrication and Database Management of Cubesat

Fabrication and Database Management of Cubesat

引用

2024 IEEE International Students' Conference on electrical, Electronics and computer science, SCEECS 2024

作者： Khulal, Nibesh Mergoju, Bhanu Kiran Ranganayakulu, S.V. Guru Nanak Institutions Technical Campus Dept. of Computer Science Engineering Hyderabad India Guru Nanak Institutions Technical Campus Dept. of Mechanical Engineering Hyderabad India Guru Nanak Institutions Technical Campus Research & Development Hyderabad India

ISBN: (纸本)9798350348460

The continuous evolution of technology necessitates the creation of cutting-edge innovations for the betterment of mankind. One remarkable achievement that emerged in 1999 is the concept of CubeSats, drastically reducing the cost of satellite development and launch, leading to numerous space experiment applications. CubeSats have emerged as a groundbreaking solution in the realm of satellite technology, comprising modular cubic units, each measuring 10cm x 10cm x 10cm. This standardized form factor enables unparalleled flexibility in design, empowering researchers and institutions to customize CubeSats for diverse missions. This paper presents the conceptualization and development of a CubeSat equipped with an advanced environmental parameter sensing system, including temperature, pressure, humidity, altitude, accelerometer, and gyroscope. The collected data is efficiently stored in a centralized XAMMP database management system, functioning as a compact ground station server. With externally mounted antennas and a dedicated onboard microcontroller, the CubeSat boasts an innovative local database system, offering unparalleled features. These CubeSats offer an affordable means of implementing coordinated sensing, low-bandwidth communications, and efficient local database management. The cost-effective local database management server provides compelling evidence that local database systems are a viable and dependable means of storing and maintaining mission-critical data for cube satellites. By showcasing the potential of small-scale satellite projects, this development empowers individuals and educational institutions to participate in hands-on space exploration, fostering creativity and inspiring future generations of space enthusiasts. © 2024 IEEE.

关键词： Cubesat local database management mission-critical data Sensors Space XAMPP Server

来源：评论

学校读者我要写书评

暂无评论

RFID Localization with Multistatic Interrogation and Deep Neural Networks

RFID Localization with Multistatic Interrogation and Deep Ne...

引用

IEEE International Conference on RFID

作者： Georgios Papadopoulos Dimitrios Angelou Aggelos Bletsas School of Electrical and Computer Engineering Technical University of Crete Chania Greece Dept. of Electrical and Computer Engineering Rutgers WINLAB The State University of New Jersey

ISBN: (数字)9798331509057

ISBN: (纸本)9798331509064

Deep neural networks (DNN) have become a widely used tool for improving efficiency in various problems; however, the time-consuming training process and the need for large amounts of labeled data often limit their practicality. This work presents a deep feed-forward neural network, designed for real-time tag localization, which addresses these challenges by lever-aging easily-generated simulation data for training. The network uses phase-based feature inputs, and performance is evaluated using simulation data, as well as real-world measurements from a custom multistatic RFID interrogation testbed. In the first part, state-of-the-art techniques are contrasted to neural networks in a simulated environment, and a pronounced advantage for the latter is demonstrated, for random tag positions. Then, a substantially improved setup is presented, which, by utilizing only one extra antenna, yields a remarkable 76% reduction in mean absolute error (MAE), in the order of 2.48 cm, while median absolute error is below 1 cm. This outcome is attributed to the increased distance between antenna pairs and not to phase ambiguity. In the second part, experimental data are used to evaluate the efficiency of DNNs in two real-world immobile scenarios, using a custom multistatic experimental setup with software-defined radios (SDR). Even though DNNs are trained exclusively on simulated data, they are found to perform in a comparable fashion to the conventional methods, with MAE ranging from 19 to 27 cm for the first and second scenarios, respectively; similarly, the median absolute error is found within 1 cm between the two scenarios, at approximately 8.5 cm. These results suggest that DNNs offer tremendous potential for further localization improvements, especially if more real-world measurements, possibly through future automated (e.g., robotic) processes, are blended into the training process.

关键词： Location awareness Training Phase measurement Artificial neural networks Robustness Real-time systems Antennas Robots Radiofrequency identification Software radio

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture-Based Food Quality Analysis with Healthcare Security System Using Cloud Machine Learning Model

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 389-398页

作者： Vaithianathan, V. Rebecca, B. Begum, M. Fathima Sundarraj, Antony Allwyn Kumar, M. Prema Kiran, Ajmeera Department of Electronics and Communication Engineering Sri Sivasubramaniya Nadar College of Engineering Kalavakkam Chennai 603110 India Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Hyderabad Telangana Dundigal 500043 India Assistant Professor Department of Computer Science and Engineering (Cyber Security) Madanapalle Institute of Technology and Science Andhra Pradesh-517325 Madanapalle India Department of Food Technology Sri Shakthi Institute of Engineering and Technology Coimbatore Tamilnadu Coimbatore India Dept. of ECE Shri Vishnu Engineering College for Women (A) Andhra Pradesh Bhimavaram 534202 India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

The primary sector of our Indian economy is agriculture. Today’s world’s most important and vital industries are agriculture and irrigation. Information and communication technology must be used in our agriculture sectors in order to support farmers and agriculturalists in improving their practices across the entire crop-growing and post-harvest processes. It is still challenging to define processed food, even in light of mounting research that suggests consuming more ultra-processed food has negative health effects. This research proposes novel technique in smart agriculture model based on cloud machine learning in cloud machine learning and healthcare system. By leveraging IoT and cloud-based data to create data-driven product decisions, cloud computing in agriculture can assist farmers with smart agriculture practices. Here, the input has been collected as food quality based on smart agriculture using a cloud model as well as processed for noise removal and normalisation. Then, based on this data, the healthcare security system has been analysed using reinforcement adversarial stacked encoder with Markov fuzzy algorithm. The experimental analysis has been carried out for various food quality datasets in terms of training accuracy, random precision, normalised correlation ratio, F-1 score, and AUC. The proposed technique achieved training accuracy of 96%, F-1 score of 94%, random precision of 97%, normalised correlation ratio of 93%, and AUC of 92%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Adversarial stacked encoder Cloud machine learning Cloud machine learning Healthcare system Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Fake Image Detection Utilizing Transfer Learning-Based Vision Transformer

Fake Image Detection Utilizing Transfer Learning-Based Visio...

引用

Intermountain engineering, Technology and Computing (IETC)

作者： Aney Rani Paul Farjana Eishita Mostafa M. Fouda Department of Computer Science Idaho State University Pocatello ID USA Electrical and Computer Engineering Dept. Idaho State University Pocatello ID USA

ISBN: (数字)9798331512828

ISBN: (纸本)9798331512835

In recent years, the creation of manipulated images has increased due to the widespread use of machine-learning techniques. Fake images generated by Generative Adversarial Networks (GANs) have led to security breaches. Many conventional image classification methods, such as Convolutional Neural Networks (CNNs), have been employed for detecting synthetic images but often struggle to address complex and varied manipulations. In this study, we propose an innovative method for identifying fake images by utilizing transfer learning in conjunction with Vision Transformers (ViT). This new architecture has shown exceptional performance in computer vision tasks. In this paper, we evaluate our approach using an image dataset comprising authentic and manipulated images. The model successfully catches complex patterns by fine-tuning a pre-trained ViT on a dataset of real and counterfeit images. The proposed transfer learning-based ViT model utilizes self-attention mechanisms for image identification, significantly outperforming CNN-based models in detecting fake images. We demonstrate that our proposed model achieves an accuracy of 99% on the test dataset. In conclusion, this study leverages the capabilities of transfer learning-based vision transformers for detecting fake images.

关键词： computer vision Accuracy Computational modeling Transfer learning computer architecture Transformers Robustness Real-time systems Security Residual 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：