检索结果-内蒙古大学图书馆

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Shravan, M. Ajitha, E. Arnone, Gioia Renu, Nekkanti Tiwari, Mohit Chouhan, Kuldeep Sr University School of Business Telangana Warangal India St. Joseph's Institute of Technology Computer Science and Engineering India Vrije Universiteit Brussel Department of Private and Economic Law Bruxelles Belgium Department of Computer Science and Engineering Duvvada India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi Delhi India Sharda University Sharda School of Engineering and Technology Department of Computer Science and Applications Greater Noida201310 India

ISBN: (纸本)9798331508685

This research looks into how deep learning methods can be used to find fake Bitcoin transfers. It's mostly about the unique problems and chances that come with trading in cryptocurrencies and blockchain. Deep learning models are used to look at transaction trends and find oddities that could be signs of fraud. This is because Bitcoin's open structure makes it harder to use traditional methods of fraud detection. We offer a structure that connects CNNs (convolutional neural networks) and RNNs (recurrent neural networks) so that strange patterns can be found in big sets of blockchain transactions. An AI-driven method aims to improve detection accuracy while lowering false positives by taking on scammers' complicated and always-changing strategies. Experienced researchers have shown that the model is good at finding strange things, which means it can be used to safely stop theft in Bitcoin networks in real time. It looks like deep learning could make digital money safer and give us data that can be used in bigger blockchain-based money systems. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Virtual Mouse Using Face Gesture and NLP 2

Virtual Mouse Using Face Gesture and NLP

引用

2nd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2023

作者： Zad, Ajay Jagannatha, S. Kumar, Manish Ajitha, S. Prakash, B.R. M S Ramaiah Institute of Technology Department of Masters of Computer Applications Bangalore India East Point College of Engineering Department of Computer Applications Bangalore India M S Ramaiah Institute of Technology Department of Master of Computer Applications Bangalore India Government First Grade College Department of Computer Science Karnataka Tumkur India

ISBN: (纸本)9798350314045

The mouse plays a very important role in interacting with laptop's and computer system, to perform necessary operations. In this paper, we are proposing a method to carry out mouse operations on the computer system without a physical mouse by utilizing voice commands and face-motion gestures. The system employs an internal webcam to detect facial gestures and an internal microphone to receive voice commands from the user. By employing a virtual mouse based on face gestures and natural language processing (NLP), we can accomplish all the fundamental functionalities of a mouse by issuing voice commands to the computer system. The system accepts these commands and executes corresponding mouse events such as "click,""right-click,""double-click,""scroll-up,""scroll-down,""minimize,"and "close."The mobility of the mouse cursor on the monitor is achieved through face motion gestures, enabling the cursor to move up, down, left, and right, respectively. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Medical Images Using Deep Reinforcement Learning 2

Anomaly Detection in Medical Images Using Deep Reinforcement...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rastogi, Divya Sharma, Aparna Yadav, R.K. Varshney, Neeraj Saraswat, Laxmi Computer Science and Application Sharda University UP Greater Noida India Electronics & Communication Engineering Raj Kumar Goel Institute of Technology UP Ghaziabad India Gla University Department of Computer Engineering and Applications UP Mathura India Abes Engineering College Department of Computer Science UP Ghaziabad India

ISBN: (纸本)9798350371055

Anomaly detection in clinical pix is vital to identify and diagnose diseases. Deep reinforcement gaining knowledge is a practical gadget-mastering approach implemented for more than a few medical obligations. This technique applies a synthetic intelligence version to research by revealing an iterative procedure to discover a set of top-of-the-line parameters for ultimate selection-making. The cause of this examination is to use deep reinforcement mastering for anomaly detection in medical pix. This approach is used to identify strange areas in clinical pix, including tumors, mental diseases, and other abnormalities. Deep reinforcement mastering is mixed with Convolutional Neural Networks (CNNs) to extract capabilities from the medical pictures and then classify them consistent with their deviation from normal. The detection accuracy is evaluated using a novel assessment metric, referred to as the precision-recollect (PR) curve, which is designed to degree the version's accuracy. The results show that deep reinforcement learning can gain high-performance anomaly detection accuracy compared with conventional methods. © 2024 IEEE.

关键词： Accuracy Anomalous Evaluated Evaluation Measure

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Network Based Machine Intelligence Model for Satellite Cloud Image Classification

引用

Big Data Mining and Analytics 2023年第1期6卷 32-43页

作者： Kalyan Kumar Jena Sourav Kumar Bhoi Soumya Ranjan Nayak Ranjit Panigrahi Akash Kumar Bhoi Department of Computer Science and Engineering Parala Maharaja Engineering CollegeBerhampur 761003India Amity School of Engineering and Technology Amity UniversityUttar Pradesh 201303India Department of Computer Applications Sikkim Manipal Institute of TechnologySikkim Manipal UniversitySikkim 737102India Directorate of Research Sikkim Manipal UniversityGangtokSikkim 737102India

As a huge number of satellites revolve around the earth,a great probability exists to observe and determine the change phenomena on the earth through the analysis of satellite images on a real-time ***,classifying satellite images plays strong assistance in remote sensing communities for predicting tropical *** this article,a classification approach is proposed using Deep Convolutional Neural Network(DCNN),comprising numerous layers,which extract the features through a downsampling process for classifying satellite cloud *** is trained marvelously on cloud images with an impressive amount of prediction *** time decreases for testing images,whereas prediction accuracy increases using an appropriate deep convolutional network with a huge number of training dataset *** satellite images are taken from the Meteorological&Oceanographic Satellite Data Archival Centre,the organization is responsible for availing satellite cloud images of India and its *** proposed cloud image classification shows 94% prediction accuracy with the DCNN framework.

关键词： satellite images satellite image classification cyclone prediction Deep Convolutional Neural Network(DCNN) features layers down-sampling process

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models 3

Hyperspectral Images for Crop Prediction using Machine and D...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Mahalakshmi, R. Kumutha, K. Sakthivanitha, M. Lakshmi, R. Bagavathi Sirajudeen, Mohamed Padmanabhan, Sankar Vels Institute of Science Technology & Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Information Technology Tamil Nadu Chennai India Nilgiri College of Arts and Science Pg and Research Department of Computer Science Tami Nadu The Nilgiris India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data. © 2025 IEEE.

关键词： Classification Deep Learning(DL) Hyperspectral Images(HSI) Machine Learning(ML)

来源：评论

学校读者我要写书评

暂无评论

Role of internet of things in protecting different wearable gadgets and materials

引用

Materials Today: Proceedings 2022年 56卷 3387-3393页

作者： Prasant, P. Bhardwaj, Shashank Gupta, Monisha Srivastava, Mahima Singh, Jitendra Maurya, Rajesh Kumar Computer Science and Technology Khalsa College of Engineering and Technology Amritsar India Department of Computer Applications KIET Group of Institutions Ghaziabad India Computer Science and Engineering Chandigarh University Punjab India College Uttarakhand Dehradun India Department of Computer Science Engineering SRM Institute of Science and Technology UP Ghaziabad India MCA ABES Engineering College Ghaziabad India

Out of the most entrusted technological revolutions applied for the advancement of living standards and creation of a more convenient operation in the professional world, the Internet of Things (IoT) has been progressing at the highest projected pace. The interconnectivity of gadgets and devices over the internet to produce smarter control, communication, and a swift and easy lifestyle makes it an amazing tech introduction. However, the IOT also brings along a huge flow of privacy and security concerns whilst considering the huge inflow of data breaches and cyberattacks in the network data. The advancements in the security protocols of the data thus bring along mistrust among the users of IoT networks who might then no longer wish to be a part of this technological revolution. Therefore, it is important to maintain security assurance in the IoT based connection networks of wearable gadgets. This paper discusses the symmetric and asymmetric approaches of encryption over IoT which can help protect the network of smart phones connected to the wearable to assure a safe and smart data commute and avoid access to private data over the same internet connection. © 2021

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Algorithm Based Task Scheduling in IoT Enabled Cloud Environment

引用

computers, Materials & Continua 2022年第4期71卷 1095-1109页

作者： R.Joshua Samuel Raj M.Varalatchoumy V.L.Helen Josephine A.Jegatheesan Seifedine Kadry Maytham N.Meqdad Yunyoung Nam Department of Information Science&Engineering CMR Institute of TechnologyBengaluru560037India Department of Computer Science&Engineering Cambridge Institute of TechnologyBengaluru560036India Department of Computer Applications CMR Institute of TechnologyBengaluru560037India Department of Computer Science&Engineering Swarnandhra College of Engineering and TechnologyNarasapur534280India Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Department of Computer Techniques Engineering Al-Mustaqbal University CollegeHillah51001Iraq Department of Computer Science and Engineering Soonchunhyang University31538Korea

Internet of Things (IoT) is transforming the technical setting ofconventional systems and finds applicability in smart cities, smart healthcare, smart industry, etc. In addition, the application areas relating to theIoT enabled models are resource-limited and necessitate crisp responses, lowlatencies, and high bandwidth, which are beyond their abilities. Cloud computing (CC) is treated as a resource-rich solution to the above mentionedchallenges. But the intrinsic high latency of CC makes it nonviable. The longerlatency degrades the outcome of IoT based smart systems. CC is an emergentdispersed, inexpensive computing pattern with massive assembly of heterogeneous autonomous systems. The effective use of task scheduling minimizes theenergy utilization of the cloud infrastructure and rises the income of serviceproviders by the minimization of the processing time of the user job. Withthis motivation, this paper presents an intelligent Chaotic Artificial ImmuneOptimization Algorithm for Task Scheduling (CAIOA-RS) in IoT enabledcloud environment. The proposed CAIOA-RS algorithm solves the issue ofresource allocation in the IoT enabled cloud environment. It also satisfiesthe makespan by carrying out the optimum task scheduling process with thedistinct strategies of incoming tasks. The design of CAIOA-RS techniqueincorporates the concept of chaotic maps into the conventional AIOA toenhance its performance. A series of experiments were carried out on theCloudSim platform. The simulation results demonstrate that the CAIOA-RStechnique indicates that the proposed model outperforms the original version,as well as other heuristics and metaheuristics.

关键词： Internet of things cloud computing task scheduling metaheuristics resource allocation

来源：评论

学校读者我要写书评

暂无评论

Fractal dimension analysis for improved decision-making in non-stationary multi-arm bandit problems: a machine learning approach

引用

The European Physical Journal Special Topics 2025年 1-16页

作者： Nandhini, S. Kala Pandian, J. Arun Department of Computer Applications School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

In this research, we propose a novel approach to addressing the exploration–exploitation dilemma in multi-armed bandit (MAB) algorithms using fractal dimensions. The fractal dimension is used in the algorithms to represent the reward distributions of arms which represents the uncertainty of the arm in receiving the reward. The fractal dimension of the reward distribution is implemented in the most popular MAB optimization algorithms, such as Epsilon-Greedy, Upper Confidence Bound (UCB), Exponential-weight algorithm for Exploration and Exploitation (EXP3), and Thompson Sampling in this study. The algorithm prefers to choose arm with the least fractal dimension, as a lower fractal dimension represents less uncertainty of the arm. The performance of the fractal-enhanced MAB optimization algorithms is compared with traditional algorithms in non-stationary environments with various numbers of arms. The proposed approach provides a novel way to quantify and utilize the uncertainty of each arm in MAB problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attack Detection and Mitigation in IoT using SVM 2

Attack Detection and Mitigation in IoT using SVM

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Srivastava, Animesh Tiwari, Shweta Saini, Parveen Kumar Sawan, Vikash Dhondiyal, Shiv Ashish Graphic Era Hill University Department of Computer Science & Engineering Dehradun India University Institute of Engineering Chandigarh University Department Computer Science & Engineering Department Punjab Mohali India Chandigarh University Department of Computer Science & Engineering Punjab Mohali India Gla University Department of Computer Engineering and Applications Mathura India Department of Computer Science & Engineering Dehradun India

ISBN: (纸本)9798350325799

As the Internet of Things (IoT) increases along with the cost of sensors decrease, more and more people are interested in the concept of the Internet of Things (IoT). Denial of service (DoS) and distributed denial of service (DDoS) attacks could be launched against these IoT devices. When there are many different types of IoT devices, security risks increase. There is currently no protocol in place to guarantee the security of IoT gadgets. However, resilience only works when there is constant observation and flexible planning. This can dynamically and flexibly deal with security threats to IoT devices without putting any extra load on the IoT devices themselves. This study proposes a strategy for quickly detecting and counteracting suspicious activity and malicious attacks. In Machine Learning, both Linear SVM and Non-Linear SVM techniques are employed, but the latter yields more accurate results. The accuracy of linear SVM is 93%. However, the accuracy increases to 97.8% when non-linear SVM is used. © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

AI in Medical Imaging: Enhancing Diagnostic Accuracy with Deep Convolutional Networks

AI in Medical Imaging: Enhancing Diagnostic Accuracy with De...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Shrivastava, Anurag Bhadula, Shuchi Kumar, Rakesh Kaliyaperumal, Gopal Rao, Bolleddu Devananda Jain, Alok Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India GLA University Department of Computer Engineering & Applications Mathura India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Lovely Professional University Phagwara India

ISBN: (纸本)9798331512965

The past has witnessed a time of astounding developments in AI, particularly notable deep convolutional networks, which has greatly facilitated medical imaging by opening up previously unattainable doors for both precision and effectiveness of diagnoses. This study is an investigation into how deep convolutional neural networks (CNNs) might be applied (using MRI, CT, and X-ray as examples) to medical imaging for the purposes of improving accuracy, consistency, and practicability of diagnostic procedures. Through automated feature extraction and categorization, convolutional neural networks (CNNs) enable earlier, and more accurate, detection of illnesses such as cancer, cardiovascular disease and neurological problems by detecting minor deviations that humans may miss. Here we evaluate the accuracy, sensitivity, and computing efficiency of several convolutional network (CNN) designs. ResNet and UNet are these architectures. The results indicate that CNN based models provide better performance compared to conventional diagnostic approaches with a substantial diminution in both false positives and false negatives. The article also covers combining CNNs with others AI methods such as transfer learning, ensemble methods, etc. to further improve diagnostic results. Although the encouraging outcomes, data protection, interpretability, and clinical acceptance continue to be obstacles. This study shows how AI driven technology can revolutionize medical imaging to enhance patient outcomes as well as tailored healthcare solutions. © 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

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：