检索结果-内蒙古大学图书馆

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Benedict Vinusha, V. Indhuja, V. Reddy, Medarametla Varshitha Nikhitha, Nagalla Pramila, R. Priyanka R.M.K. Engineering College Department of Artificial Intelligence and Data Science Kavaraipettai601206 India

ISBN: (纸本)9798350372748

Detecting ocular diseases is crucial for preventing vision impairment and blindness. However, various obstacles such as insufficient awareness, elevated healthcare expenses, and the necessity for technological advancements impede effective screening. This ground-breaking device, VisionSaver, presents a novel method of identifying eye pathologies. By employing a multi-layered deep Convolutional Neural Network, VisionSaver outperforms traditional models in the extraction of complex characteristics from medical images. VisionSaver stands out for its real-time detection capabilities, which are made possible by an easy-to-use Graphical User Interface. This feature gives medical professionals accurate results and makes it possible to make decisions quickly. The system's adaptability guarantees precise identification of a broad range of ocular diseases, encompassing Diabetic Retinopathy, glaucoma, and even uncommon ocular conditions. VisionSaver enhances efficiency and retains crucial features by integrating sophisticated techniques like convolutional layers, pooling layers, dense layers, and VGG models. This innovative strategy holds the potential to transform eye healthcare, ushering in a proactive treatment era and significantly enhancing patient outcomes. VisionSaver combines data collection and preparation, data preprocessing, feature extraction, model selection, and model training to provide a robust solution for ocular disease detection achieving the accuracy of 91%. The system's real-time capabilities, user-friendly interface, and adaptability make it a powerful tool in the fight against ocular diseases. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Trends in The Sustainability of Related Blockchain Technologies and Bitcoin 5

Trends in The Sustainability of Related Blockchain Technolog...

引用

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

作者： Pavitra, Mutyala Bardhiya, Himanshu S Gourshettiwar, Palash Computer Science and Design Sawangi India Artificial Intelligence & Data Science Sawangi India Computer Science and Medical Engineering Sawangi India

ISBN: (纸本)9798350383522

Based on an open-source software-powered peer-to-peer payment mechanism, Bitcoin is a digital currency that operates independently of a central bank. Its advantages over fiat money include cheaper transaction costs, increased security, and scalability. Scientists are becoming interested in it despite concerns about illicit usage and societal repercussions. This paper aims to describe and assess existing patterns inside the literature about the sustainability of bitcoin, considering social, economic, and environmental implications. Based on the study, it is evident that the entire system of money transitioning would need an exorbitant quantity of energy to the new cryptocurrency to operate the virtual currency system and mine new bitcoins, meaning that bitcoin is likely to remain a niche currency. A fragmented and democratic maintained public record of transactions is built on blockchain technology, which may open up new and difficult prospects. Block-layer and new state-driven cryptocurrency, the sharing of medical data, the production and distribution of energy in microgrids at the citizen level, and blockchain technology may all gain from the broad adoption of blockchain-based transactions. Bitcoin and associated blockchain technologies have the potential to transcend the concerns raised by many critics when seen as a catalyst for social change. © 2024 IEEE.

关键词： bitcoin digital money energy usage monetary transactions sustainability

来源：评论

学校读者我要写书评

暂无评论

Natural Language Translation Engine For Announcements and Information Dissemination At Stations 2

Natural Language Translation Engine For Announcements and In...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Reedy, Medarametla Varshitha Abdul Naeem, B. Reddy, Tunga Kartikeya Benedict Vinusha, V. Pramila, R. Priyanka R.M.K. Engineering College Department of Artificial Intelligence and Data Science Kavaraipettai601206 India

ISBN: (纸本)9798350328202

In today's fast-paced global travel landscape, effective communication is crucial, especially in dynamic environments like railway stations. This research paper addresses linguistic diversity challenges by developing a cutting-edge natural language translation engine tailored for railway communication. It integrates advanced technologies such as Transformer-based Automatic Speech Recognition (ASR) with noise reduction algorithms like Wav2Vec 2.0 and an Attention-based Convolutional Recurrent Neural Network (CRNN) to overcome background noise and diverse speech patterns. The system also includes multilingual Text-to-Speech (TTS) and Machine Translation (MT) capabilities for clear communication in real-time across multiple languages. Interactive features like a responsive Chatbot and Interactive Voice Response System (IVRS) enhance user engagement. This approach meets passengers' linguistic needs while promoting inclusivity. Technically, the project explores algorithms like the Transformer model, positional encoding, self-attention mechanisms, and feed-forward neural networks. The research aims to revolutionize railway communication and establish a precedent for technology-driven public transportation, creating universally accessible and user-friendly travel experiences. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Robust Approach to E-Banking Phishing Detection using Ensemble Methods and LSTM 1

A Robust Approach to E-Banking Phishing Detection using Ense...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Siva Reddy, Naga Venkata Rohith Saai, A.R. Ramanujan, T.V. Reddy, N Rajesh Kumar Pramila, R. Priyanka R.M.K. Engineering College Department of Artificial Intelligence and Data Science Kavaraipettai601206 India

ISBN: (纸本)9798350372748

Recently, the integration of Internet and banking technologies has shifted financial transactions primarily to online platforms. However, this transformation has exposed the financial sector to cyber threats, particularly phishing, resulting in substantial annual losses and widespread data breaches. Despite ongoing efforts to combat phishing, a comprehensive solution remains elusive, creating a vulnerability for cyber attackers to unlawfully access sensitive personal and financial data. In this research, a novel method for successfully recognizing phishing attempts is presented. This proposed methodology includes components such as URLs, HTML, and recurring themes in phishing efforts, which are thoroughly analyzed. These characteristics are consistently similar, resulting in a significant amount of data being collected and sent over the Internet. To preserve the integrity of online financial transactions and shield people from data breaches, a robust phishing attack detection system must be developed. This study applies machine learning techniques such as LSTM, Boosting, Random Forests, and Ensemble models for intelligent phishing detection, attaining a remarkable 97 percent accuracy. To capture complicated data relationships, minimize overfitting, and improve generalization performance, a voting classifier combines predictions and stacking and uses feedback from several models. By adopting this strategy, defenses against the constantly changing cyber threat landscape in the digital financial transaction environment are strengthened. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

An Al Powered Exam Proctoring: Comprehensive Monitoring for Integrity

An Al Powered Exam Proctoring: Comprehensive Monitoring for ...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Mewada, Dhruv Gaikwad, Shlok Gharat, Bhavika Kamble, Priyanshu Vidyavardhini's College of Engineering and Technology Dept. of Artificial Intelligence&Data Science Mumbai India

ISBN: (纸本)9798350359688

In recent times, remote learning has experienced significant growth, yet the challenge of conducting academic examinations in a secure manner persists. Various approaches have been adopted by universities, such as collecting assignments susceptible to plagiarism or implementing remote proctoring with manual supervision. As our current lifestyle appears to be transitioning towards a new normal, it becomes imperative to explore effective solutions. This paper introduces a proposed remedy: the development of an AI-based integrated system designed to prevent cheating during examinations. The system not only detects fraudulent activities but also records evidence, ensuring both security and cost-effectiveness. © 2024 IEEE.

关键词： online tests proctoring remote learning

来源：评论

学校读者我要写书评

暂无评论

Boothless Toll Collection System 4

Boothless Toll Collection System

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Sarkar, Swagata Selvabharathi, M. Sarveswaran, D. Arun Raja, M. Raju, Aswin Sri Sairam Engineering College Dept. of Artificial Intelligence and Data Science Tamil Nadu Chennai India

ISBN: (纸本)9798331508845

As a developing country, it is critical that we prioritize the construction and improvement of our road infrastructure in order to stimulate economic growth and promote easier logistics operations. However, the current toll collection system is hampered by difficulties such as overcharging and traffic congestion, reducing its effectiveness. To solve these issues, we propose implementing an advanced toll collection system that includes GPS technology, an ANPR camera, and a variety of machine learning algorithms. This new method will transform toll collecting by properly calculating toll charges based on the actual distance traveled by vehicles on the highway, removing the need for drivers to stop at toll booths. The system uses GPS technology to precisely compute the distance traveled by each car, while ANPR cameras guarantee the journey's validity. As a result, vehicles will only be paid for what distance they have traveled, reducing overcharging concerns and congestion at toll gates. Our major goal is to create a smooth and efficient tolling mechanism that overcomes the limitations of traditional tollgate systems. We hope to improve the toll collection process, shorten wait times, and reduce the consumption of fuel associated with long lines at toll booths by utilizing cutting-edge technologies. By applying this innovative strategy, we hope to improve not only toll collecting efficiency but also commuters' overall driving experience. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Multilingual Language Detection and Translation System with Multinomial Naive Bayes 5

Multilingual Language Detection and Translation System with ...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Vuddanti, Sowjanya Ariveni, Dhathri Sri Lekha Kethepalli, Niharika Sri Sandhya Manchimi, Lokesh Yajjavarapu, Jaswanth Bali Reddy College of Engineering Department of Artificial Intelligence and Data Science Lakireddy Andhra Pradesh Mylavaram India

ISBN: (纸本)9798350367171

Smooth communication becomes essential as the world unites different linguistic groupings. The proposed system for language recognition and translation addresses this difficulty. The proposed system uses a Google Translate-powered 'bridge' with a machine learning 'detective' to properly identify text language and translate between any supported combination. The Multinomial Naive Bayes classifier, a machine learning approach, is used by the language detection component to determine the language of input text. As the 'detective,' the Multinomial Naive Bayes classifier correctly determines the language of the input text with a remarkable accuracy rate of 97 %. The model can accurately classify language in a range of languages by preprocessing the text data and generating a representation of words in a bag. To translate text between languages, the text translation component uses the Google Translate API via the Google library. With the flexibility to choose the source and target languages provided by this component, users can translate text from any supported language to the language of their choice. Easy to use, it enables people to promote intercultural understanding and overcome language barriers in social media, business, education, and other domains, making the world more inclusive and connected. © 2024 IEEE.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Revisiting 30 years of the Network Time Protocol 24

Revisiting 30 years of the Network Time Protocol

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Woo, Simon S. Computer Science and Engineering Department Applied Data Science Department Department of Artificial Intelligence Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798400701726

Since the inception of the Internet and WWW, providing the time among multiple nodes on the Internet has been one of the most critical challenges. David Mills is the pioneer to provide time on the Internet, inventing the Network Time Protocol (NTP), and synchronizing the clocks in computer systems. Now, the NTP is predominantly used on the Internet and WWW. In this paper, we revisit the NTP, and present the overview of the NTP. In particular, we highlight the advanced research effort, the SpaceNTP, to synchronize the clocks among assets and entities in space. The SpaceNTP designed for space environments will be the fundamental medium and enabling block to provide the future web services in space. © 2024 Copyright held by the owner/author(s).

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Multi-task Genetic Programming with Semantic based Crossover for Multi-output Regression

Multi-task Genetic Programming with Semantic based Crossover...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Wang, Chunyu Chen, Qi Xue, Bing Zhang, Mengjie Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand

ISBN: (纸本)9798400704956

Multi-output regression involves predicting two or more target variables simultaneously. In contrast to its single-output counterpart, multi-output regression poses additional challenges primarily because the target variables are frequently interdependent. Achieving accurate predictions for one variable may necessitate a thorough consideration of its relationships with other variables. In this paper, multi-output regression problems are regarded as multi-task optimization problems where predicting one output variable is considered as one task. A new multi-task multi-population genetic programming method is proposed to solve the problem. The method utilizes the semantic based crossover operator to transfer positive knowledge and accelerate convergence. Additionally, it adopts an offspring reservation strategy to keep the quality of the individuals for the corresponding tasks. The empirical results demonstrate that our proposed method significantly enhances the training and the test performances of multi-task multi-population GP and also outperforms standard GP on five real-world multi-output regression datasets. © 2024 Copyright held by the owner/author(s).

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Modeling a Novel Hyper-Parameter Tuned Deep Learning Enabled Malaria Parasite Detection and Classification

引用

Computers, Materials & Continua 2023年第12期77卷 3289-3304页

作者： Tamal Kumar Kundu Dinesh Kumar Anguraj S.V.Sudha Department of Computer Science&Engineering Koneru Lakshmaiah Education FoundationVaddeswaramAndhra PradeshIndia Department of Artificial Intelligence and Data Science KPR Institute of Engineering and TechnologyCoimbatoreTamil Nadu641407India

A theoretical methodology is suggested for finding the malaria parasites’presence with the help of an intelligent hyper-parameter tuned Deep Learning(DL)based malaria parasite detection and classification(HPTDL-MPDC)in the smear images of human peripheral *** existing approaches fail to predict the malaria parasitic features and reduce the prediction *** trained model initiated in the proposed system for classifying peripheral blood smear images into the non-parasite or parasite classes using the available online *** Adagrad optimizer is stacked with the suggested pre-trained Deep Neural Network(DNN)with the help of the contrastive divergence method to *** features are extracted from the images in the proposed system to train the DNN for initializing the visible *** smear images show the concatenated feature to be utilized as the feature vector in the proposed ***,hyper-parameters are used to fine-tune DNN to calculate the class labels’*** suggested system outperforms more modern methodologies with an accuracy of 91%,precision of 89%,recall of 93%and F1-score of 91%.The HPTDL-MPDC has the primary application in detecting the parasite of malaria in the smear images of human peripheral blood.

关键词： Malaria parasite classification hyper-parameter deep neural network the feature vector

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：