检索结果-内蒙古大学图书馆

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

作者： Nimbarte, Mrudula Hussain, Alfiya Budhlani, Kanak Bansod, Chirag Ramdham, Mayur Kanhe, Om Khullar, Amit S.B. Jain Institute of Technology Management and Research Department of Computer Science and Engineering MS Nagpur India

ISBN: (纸本)9798350348460

This review provides a comprehensive review of the latest approaches and advances in text-to-image processing using artificial neural networks (GANs). The work under review uses GAN architecture, where generators and classifiers work together to extract corresponding images from descriptions. This research includes a comprehensive review of the GAN framework, delving into the complexities of the generator and discrimination during training. The project solves problems related to converting text input into visual images using a combination of natural language processing and computer vision. This article reviews the main concepts of the architecture as well as the use of advanced neural networks for text understanding and image synthesis. Particular attention is paid to the optimization process the generator uses to improve the quality and integrity of the resulting images. Additionally, the review highlights the evolution of different labels and discusses their implications for real-world applications. © 2024 IEEE.

关键词： Adversarial Training computer Vision Generative Adversarial Networks (GANs) Image Synthesis Multimodal Learning Natural Language Processing (NLP) Neural Network Architecture Text to Image Generation

来源：评论

学校读者我要写书评

暂无评论

Fortified Footsteps: A Scalable Anti-Theft Flooring System Integrating Facial Recognition and OTP Security

Fortified Footsteps: A Scalable Anti-Theft Flooring System I...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Bhoyar, Aniket Nazneen, Gulrukh Pawar, Ritu Shinde, Vaishnavi Tajane, Vaishnavi Sonewane, Premlata Hude, Siddhesh S. B. Jain Institute of Technology Management & Research Nagpur Computer Science & Engineering Nagpur India

ISBN: (纸本)9798331517953

The rise in unauthorized access and theft in homes and businesses has increased the need for security systems that go beyond traditional surveillance. Improve your steps: Scalable anti-theft floor system combined with facial recognition and OTP security offers a new IoT-based solution designed to enhance security through instant discovery and multiple layers of evidence. The system uses piezoelectric pressure sensors embedded in the floor to detect anomalies and allows the camera to capture images of the attacker's face. The image is then processed using facial recognition algorithms and compared with authorized facial data. If the face is recognized, the system generates a secure one-time password (OTP) that is sent to the mobile phone number by the GSM module to enter the correct OTP within the specified time to gain access. If the OTP is not entered correctly, the system will be locked and the intrusion attempt will be reported to the owner. Integrating IoT, facial recognition, and OTP-based two-factor authentication, this anti-theft floor system enhances security, reduces false alarms, and provides security for many locations such as homes, offices, and high-security areas. This study details the design, implementation, and performance of the proposed system, placing it as a robust security system that addresses the vulnerabilities of traditional systems and provides security protection. © 2024 IEEE.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Phishing Classification Based on Text Content of an Email Body Using Transformers

Phishing Classification Based on Text Content of an Email Bo...

引用

International Conference on Information Security, Privacy, and Digital Forensics, 2022

作者： Somesha, M. Pais, Alwyn R. Department of Computer Science and Engineering Information Security Research Lab National Institute of Technology Karnataka Surathkal575025 India

ISBN: (纸本)9789819950904

Phishing attacks steal sensitive credentials using different techniques, tools, and some sophisticated methods. The techniques include content injection, information re-routing, social engineering, server hacking, social networking, SMS and WhatsApp mobile applications. To overcome such attacks and minimize risks of such attacks, many phishing detection and avoidance techniques were introduced. Among various techniques, deep learning algorithms achieved the efficient results. In the proposed work, a transformers-based technique is used to classify phishing emails. The proposed method outperformed the other similar mechanisms for the classification of phishing emails. The phishing classification accuracy achieved by the proposed work is 99.51% using open-source datasets. The proposed model is also used to learn and validate the correctness of the in-house created datasets. The obtained results with in-house datasets are equally competitive. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electronic mail

来源：评论

学校读者我要写书评

暂无评论

MNIST Digit Classification using Parallelised Convolutional Neural Network 4

MNIST Digit Classification using Parallelised Convolutional ...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Aravindhraj, N. Vilasini, V. Kiruthik Vishaal, S. Jaiprakash, R. Cibi Siddaarth, R. Kongu Engineering College Department of Computer Science and Engineering Erode India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350300093

A program or piece of computer software is often built using serial computing techniques. In simple terms, a problem's solution is created by breaking it down into smaller instructions, which are then each individually carried out by a computer's Central Processing Unit (CPU). These modular instructions are first queued and then carried out one by one. Due to the fact that only one instruction was being performed at a time, this was a problem that could be plausibly argued to need to be solved in the computing industry. Hence, parallel computing is employed to benefit from serial computing. Using many processing elements simultaneously to solve a problem or carry out an instruction is known as parallel computing. Every operation is run or processed simultaneously, and problems are divided up into discrete instructions and solved that way. The number of Central Processing Units (CPU) in large-scale supercomputers is continually increasing, and parallelism is a key component of all modern supercomputer architectures. A deep learning technique called the Convolutional Neural Network (CNN) learns directly from the data. When dense layers are added, it transforms into a sizable polynomial time approximation technique. The Convolutional Neural Network (CNN) method will run faster and be greatly improved when it is parallelized. This strategy can be built on top of several convolution neural network -using applications. One such application that uses the convolution neural network technique to find numbers in images is MNIST classification. © 2023 IEEE.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Data Distribution Valuation 38

Data Distribution Valuation

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Xu, Xinyi Wang, Shuaiqi Foo, Chuan-Sheng Low, Bryan Kian Hsiang Fanti, Giulia Department of Computer Science National University of Singapore Singapore Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Infocomm Research Agency for Science Technology and Research Singapore

Data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces. Existing data valuation methods define a value for a discrete dataset. However, in many use cases, users are interested in not only the value of the dataset, but that of the distribution from which the dataset was sampled. For example, consider a buyer trying to evaluate whether to purchase data from different vendors. The buyer may observe (and compare) only a small preview sample from each vendor, to decide which vendor's data distribution is most useful to the buyer and purchase. The core question is how should we compare the values of data distributions from their samples? Under a Huber characterization of the data heterogeneity across vendors, we propose a maximum mean discrepancy (MMD)-based valuation method which enables theoretically principled and actionable policies for comparing data distributions from samples. We empirically demonstrate that our method is sample-efficient and effective in identifying valuable data distributions against several existing baselines, on multiple real-world datasets (e.g., network intrusion detection, credit card fraud detection) and downstream applications (classification, regression). © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GestureEcho: A Silent Symphony of Art with Hand Tracking and Voice-Guided Drawing

GestureEcho: A Silent Symphony of Art with Hand Tracking and...

引用

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

作者： Balvir, Sachin U. Tembhurney, Sameer Shaikh, Sarah N. Sathawane, Sarvesh S. Mane, Aditya Khatib, Mohd Raziullah Bawankule, Pranav S.B. Jain Institute of Technology Management and Research Department of Computer Science and Engineering Maharashtra Nagpur India

ISBN: (纸本)9798350348460

This study presents a revolutionary voice and gesture detection system with applications ranging from augmented reality to presentation control, painting, and sketching. The technology combines voice recognition to comprehend spoken directions with hand tracking to track user motions. These modules can be integrated such that the system can handle activities involving sketching while the hand tracking component draws on a canvas. Although the system has application potential in many areas, its main goals are to improve presentation control and make activities like drawing and painting easier. This logical and instinctive approach to computer interaction has wide-ranging effects on the entertainment, educational, and design sectors. © 2024 IEEE.

关键词： accessibility digital creativity drawing hand tracking speech recognition verbal and gesture recognition

来源：评论

学校读者我要写书评

暂无评论

MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation 40

MergeSFL: Split Federated Learning with Feature Merging and ...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Liao, Yunming Xu, Yang Xu, Hongli Wang, Lun Yao, Zhiwei Qiao, Chunming University of Science and Technology of China School of Computer Science and Technology China Suzhou Institute for Advanced Research University of Science and Technology of China China University at Buffalo Department of Computer Science and Engineering The State University of New York United States

ISBN: (纸本)9798350317152

Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To boost the performance of AI applications, large-scale models have received increasing attention due to their excellent generalized abilities. However, training and transmitting large-scale models will incur significant computing and communication burden on the resource-constrained workers, and the exchange of entire models may violate model privacy. To relax the burden of workers and protect model privacy, split federated learning (SFL) has been released by integrating both data and model parallelism. Despite resource limitations, SFL also faces two other critical challenges in EC systems, i.e., statistical heterogeneity and system heterogeneity. In order to address these challenges, we propose a novel SFL framework, termed MergeSFL, by incorporating feature merging and batch size regulation in SFL. Concretely, feature merging aims to merge the features from workers into a mixed feature sequence, which is approximately equivalent to the features derived from IID data and is employed to promote model accuracy. While batch size regulation aims to assign diverse and suitable batch sizes for heterogeneous workers to improve training efficiency. Moreover, MergeSFL explores to jointly optimize these two strategies upon their coupled relationship to better enhance the performance of SFL. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson edge devices, and the experimental results show that MergeSFL can improve the final model accuracy by 5.82% to 26.22%, with a speedup by about 1.39× to 4.14×, compared to the baselines. © 2024 IEEE.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Advancing Neurological Health- A Collaborative Ensemble Learning Approach for Enhancing Early Diagnosis of Amyotrophic Lateral Sclerosis (ALS) 10

Advancing Neurological Health- A Collaborative Ensemble Lear...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Srinivasan, Karthik Ravi, R. Durga Pavani, A. Mandadi, Sowmya Srivel, R. Saudi Electronic University Department of Information Technology Riyadh Saudi Arabia J. J College of Engineering and Technology Department of Computer Science and Engineering India Aurora's Technological and Research Institute Department of Computer Science and Engineering India Adhiparasakthi Engineering College Department of Computer Science and Engineering Melmaruvathur India

ISBN: (纸本)9798350353068

In this study, we propose the integration of Support Vector Machines (SVM) into an ensemble learning framework alongside K-Nearest Neighbors (K-NN) and Naive Bayes models to enhance the early diagnosis of Amyotrophic Lateral Sclerosis (ALS). ALS diagnosis is challenging due to its heterogeneous clinical manifestations. Leveraging diverse datasets including genetic data, medical imaging, and clinical records, we train SVM, K-NN, and Naive Bayes models independently. The ensemble approach amalgamates their predictions, harnessing the complementary strengths of each model. Through rigorous performance evaluation encompassing accuracy, precision, recall, and F1-score metrics, we demonstrate the superior diagnostic capabilities of the ensemble. Employing cross-validation ensures the robustness of our model, while fine-tuning hyperparameters optimizes its performance. Integration of SVM into the ensemble framework contributes additional discriminative power, enhancing the accuracy and reliability of ALS diagnosis. Our research underscores the pivotal role of ensemble learning in addressing the complexities of medical diagnosis, offering a notable advancement in ALS diagnostic methodologies. The proposed approach holds promise for improving patient care and setting new standards in clinical practice © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based E-commerce Site for Direct Subsidy Disbursement 15

Blockchain-based E-commerce Site for Direct Subsidy Disburse...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Sanjeev, S. Sannakki Patil, Asharani A. Rajpurohit, V.S. Niranjan, Prashant Y. Deshpande, G.R. Kuldeep, P. Sambrekar Sonwalkar, Prakash K. Department of Computer Science & Eng KLS Gogte Institute of Technology Karnataka Belagavi India Department of Computer Science Jain College of Engineering and Research Karnataka Belagavi India

ISBN: (纸本)9798331300579

India's prominence in the global agricultural sector cannot be overstated, with agriculture accounting for the main source of income for over 55% of the country's population. Karnataka, with its majority rural population, is no exception. Millions of workers depend on agriculture for their livelihoods, and the Indian government has been actively involved in efforts to improve the delivery of subsidies to those who deserve them. While the direct benefit transfer program has been helpful, it still faces certain drawbacks or challenges, such as a lack of auditability and control over the use of funds. However, the solution to this issue lies in the disruptive technology blockchain. With its immense potential to transform data processing, transmission, storage, and security, a blockchain-based system presents the ideal solution for automating subsidy disbursements, bypassing the necessity for banks in rural regions, and establishing an auditable and transparent ecosystem that effectively combats corruption and financial mismanagement. This smart blockchain system will undoubtedly transform the agricultural sector in India and ensure that deserving beneficiariesreceive the subsidies they need. © Grenze Scientific Society, 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Physical information-enhanced graph neural network for predicting phase separation

引用

Chinese Physics B 2024年第7期33卷 278-283页

作者：张亚强王煦文王雅楠郑文 Institute of Public-Safety and Big Data College of Computer Science and Technology(College of Data Science)Taiyuan University of TechnologyJinzhong 030600China Shanxi Engineering Research Centre for Intelligent Data Assisted Treatment Changzhi Medical CollegeChangzhi 046000China Innovation Academy for Microsatellites of Chinese Academy of Sciences Shanghai 200050China

Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt *** results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.

关键词： graph neural network phase separation machine learning dissipative particle dynamics

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：