检索结果-内蒙古大学图书馆

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： K. Praveen Kumar S. Sangeetha T Rajesh Kumar Bhuvaneswari R D. Rasi Mahaveerakannan R Department of Information Technology Kakatiya Institute of Technology and Science Warangal Dept. Of Information Technology Kakatiya Institute of Technology and Science Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu Computer Science and Applications D. K. M. College for Women (Autonomous) Vellore Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore

The world has altered since the World Health Organization (WHO) designated (COVID-19) a worldwide epidemic. Everything in society, from professions to routines, has shifted to accommodate the new reality. The World Health Organization warns that future pandemics of infectious diseases are likely and that people should be ready for the worst. Therefore, this study presents a framework for tracking and monitoring COVID-19 using a Deep Learning (DL) perfect. The suggested framework utilises UAVs (such as a quadcopter or drone) equipped with artificial intelligence (AI) and the Internet of Things (IoT) to keep an eye on and combat the spread of COVID-19. AI/IoT for COVID-19 nursing and a drone-based IoT scheme for sterilisation make up the bulk of the infrastructure. The proposed solution is based on the use of a current camera installed in a face-shield or helmet for use in emergency situations like pandemics. The developed AI algorithm processes the thermal images that have been detected using multi-scale similar convolution blocks (MPCs) and Res blocks that are trained using residual learning. When infected cases are detected, the helmet's embedded Internet of Things system can trigger the drone system to intervene. The infected population is eradicated with the help of the drone's sterilisation process. The developed system undergoes experimental evaluation, and the findings are presented. The developed outline delivers a novel and well-organized arrangement for monitoring and combating COVID-19 and additional future epidemics, as evidenced by the results

关键词： COVID-19 Head Pandemics Convolution Organizations Safety Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Federated Learning in Malware Detection

Federated Learning in Malware Detection

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Dimitrios Serpanos Georgios Xenos Computer Technology Institute and Press DIOPHANTUS & Dept. of Electrical and Computer Engineering University of Patras Patras Greece Computer Technology Institute and Press DIOPHANTUS University of Patras Campus Patras Greece

Malware detection constitutes a fundamental step in safe and secure computational systems, including industrial systems and the Internet of Things (IoT). Modern malware detection is based on machine learning methods that classify software samples as malware or benign, based on features that are extracted from the samples through static and/or dynamic analysis. State-of-the-art malware detection systems employ Deep Neural Networks (DNNs) whose accuracy increases as more data are analyzed and exploited. However, organizations also have significant privacy constraints and concerns which limit the data that they share with centralized security providers or other organizations, despite the malware detection accuracy improvements that can be achieved with the aggregated data. In this paper we investigate the effectiveness of federated learning (FL) methods for developing and distributing aggregated DNNs among autonomous interconnected organizations. We analyze a solution where multiple organizations use independent malware analysis platforms as part of their Security Operations Centers (SOCs) and train their own local DNN model on their own private data. Exploiting cross-silo FL, we combine these DNNs into a global one which is then distributed to all organizations, achieving the distribution of combined malware detection models using data from multiple sources without sample or feature sharing. We evaluate the approach using the EMBER benchmark dataset and demonstrate that our approach effectively reaches the same accuracy as the non-federated centralized DNN model, which is above 93%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards formal modeling and analysis of UPI protocols 3

Towards formal modeling and analysis of UPI protocols

引用

3rd International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2021

作者： Malladi, Sreekanth CMR Institute of Technology Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9780738111834

UPI (Unified Payments Interface) is a framework in India wherein customers can send payments to merchants from their smartphones. The framework consists of UPI servers that are connected to the banks at the sender and receiver ends. To send and receive payments, customers and merchants would have to first register themselves with UPI servers by executing a registration protocol using payment apps such as BHIM, PayTm, Google Pay, and PhonePe. Weaknesses were recently reported on these protocols that allow attackers to make money transfers on behalf of innocent customers and even empty their bank accounts. But the reported weaknesses were found after informal and manual analysis. However, as history has shown, formal analysis of cryptographic protocols often reveals flaws that could not be discovered with manual inspection. In this paper, we model UPI protocols in the pattern of traditional cryptographic protocols such that they can be rigorously studied and analyzed using formal methods. The modeling simplifies many of the complexities in the protocols, making it suitable to analyze and verify UPI protocols with popular analysis and verification tools such as the Constraint Solver, ProVerif and Tamarin. Our modeling could also be used as a general framework to analyze and verify many other financial payment protocols than just UPI protocols, giving it a broader applicability. © 2021 IEEE.

关键词： Formal methods

来源：评论

学校读者我要写书评

暂无评论

Crop Price Prediction for Coconut in Tamil Nadu Using Machine Learning

Crop Price Prediction for Coconut in Tamil Nadu Using Machin...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Mithuna R. J. Sebastian Terence Dept. of Computer Science and Engg. Karunya Institute of Technology and Sciences Coimbatore India

Agriculture is one of the most important sectors of the Indian economy, with a major contribution towards the country's GDP. The agricultural sector in India is still predominantly based on traditional farming methods, which makes it challenging for farmers to keep up with the ever-changing market prices of crops. In recent years, data-driven models have emerged as a powerful tool for crop price prediction. This paper aims to predict the prices of coconuts in India using Decision tree regression, gradient Boost regressor, random forest regressor and Extreme gradient boosting (XGBOOST) models. The study utilizes monthly coconut price data from 2010 to 2022. The results show that the xgboost model has the best performance, followed by the Gradient boosting and regression models. The findings of this study can help policymakers, farmers, and traders make informed decisions regarding coconut farming and trading.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Method for Judging Copyright Infringement of Illegally Distributed Streaming Videos Using Cloud Services

Method for Judging Copyright Infringement of Illegally Distr...

引用

Artificial Intelligence and Power engineering (AIPE), International Conference on

作者： Seyoung Jnag Byeongchan Park Injae Yoo Jaechung Lee Seok-Yoon Kim Youngmo Kim Dept. of Computer Science and Engineering Soongsil University Seoul Korea Institute of Technology BeyondTech Inc. Seoul Korea

Recently, copyright infringement crimes avoid crackdowns and investigations in various ways, such as operating servers overseas or using cloud services and disguising the IP of the server. Therefore, appropriate countermeasures are needed. In this paper, we propose a method for determining illegal distribution of copyright-infringing streaming videos using cloud services that quickly determines whether an illegal digital content is being served. Using this method, there is an advantage in that copyright infringing content sites using cloud services can be quickly found and blocked

关键词：

来源：评论

学校读者我要写书评

暂无评论

2D LiDAR-Based Eucalyptus Tree Measurement and Monitoring System using Mobile Application

2D LiDAR-Based Eucalyptus Tree Measurement and Monitoring Sy...

引用

International Electrical engineering Congress (iEECON)

作者： Pruek Vanna-Iampikul Visutr Boonnateephisit Somphop Limsoontharakul Jednipat Moonrinta Matthew Dailey Mongkol Ekpanyapong Department of Electrical Engineering Burapha University Chonburi Thailand School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Dept. Computational Science Prince of Songkla University Songkhla Thailand Computer Science Field of Study School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Information & Communication Tech. School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand Dept. of Industrial Systems Engineering School of Engineering and Technology Asian Institute of Technology Pathumthani Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

LiDAR technology has rapidly advanced, offering highly accurate solutions for tree geometry estimation, which is particularly valuable in agriculture and forestry. Its ability to capture precise 2D and 3D data has revolutionized tree detection and measurement. In Eucalyptus plantations, continuous monitoring is critical to maximizing growth, enhancing paper production, and mitigating environmental damage. However, existing solutions face challenges in real-time monitoring due to factors such as parasitic interference, low-light conditions, and uneven terrain. In this work, we present a novel, end-to-end framework that enhances Eucalyptus tree measurement and monitoring. Our framework significantly improves data collection efficiency by allowing measurements at walking speed, reducing measurement distance by 50% compared to traditional manual approaches. This system integrates 2D-LiDAR with additional environmental sensors to extract key tree parameters, including circumference, position, and tree count. The collected data is stored in real-time and uploaded to a centralized server for further analysis. Experimental evaluations across 160 trees, under five distinct farm conditions, demonstrate that our system achieves 89% accuracy in tree diameter estimation and 98.5% accuracy in tree counting, significantly outperforming traditional methods. These results establish our framework as a highly effective solution for improving the accuracy and efficiency of tree monitoring in challenging environments.

关键词： Geometry Accuracy Laser radar Plantations Estimation Vegetation Production Real-time systems Time measurement Monitoring

来源：评论

学校读者我要写书评

暂无评论

AssistTaxi: A Comprehensive Dataset for Taxiway Analysis and Autonomous Operations

AssistTaxi: A Comprehensive Dataset for Taxiway Analysis and...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Parth Ganeriwala Siddhartha Bhattacharyya Sean Gunther Brian Kish Mohammed Abdul Hafeez Khan Ankur Dhadoti Natasha Neogi Dept. of Computer Science Florida Institute of Technology Melbourne Florida Dept. of Aerospace Engineering Florida Institute of Technology Melbourne Florida Dept. of Mechanical Engineering Univeristy of Michigan Ann Arbor Michigan Dept. of Computer Science BITS Pilani Dubai Campus Dubai United Arab Emirates Langley Research Center NASA Hampton Virginia

The availability of high-quality datasets play a crucial role in advancing research and development especially, for safety critical and autonomous systems. In this paper, we present AssistTaxi, a comprehensive novel dataset which is a collection of images for runway and taxiway analysis. The dataset comprises of more than 300,000 frames of diverse and carefully collected data, gathered from Melbourne (MLB) and Grant-Valkaria (X59) general aviation airports. The importance of AssistTaxi lies in its potential to advance autonomous operations, enabling researchers and developers to train and evaluate algorithms for efficient and safe taxiing. Researchers can utilize AssistTaxi to benchmark their algorithms, assess performance, and explore novel approaches for runway and taxiway analysis. Addition-ally, the dataset serves as a valuable resource for validating and enhancing existing algorithms, facilitating innovation in autonomous operations for aviation. We also propose an initial approach to label the dataset using a contour based detection and line extraction technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Custom 8-bit floating point value format for reducing shared memory bank conflict in approximate nearest neighbor search

arXiv

引用

arXiv 2023年

作者： Ootomo, Hiroyuki Naruse, Akira Dept. of Computer Science Tokyo Institute of Technology Tokyo Japan NVIDIA Tokyo Japan

The k-nearest neighbor search is used in various applications such as machine learning, computer vision, database search, and information retrieval. While the computational cost of the exact nearest neighbor search is enormous, an approximate nearest neighbor search (ANNS) has been attracting much attention. IVFPQ is one of the ANNS methods. Although we can leverage the high bandwidth and low latency of shared memory to compute the search phase of the IVFPQ on NVIDIA GPUs, the throughput can degrade due to shared memory bank conflict. To reduce the bank conflict and improve the search throughput, we propose a custom 8-bit floating point value format. This format doesn’t have a sign bit and can be converted from/to FP32 with a few instructions. We use this format for IVFPQ on GPUs and achieved better performance without significant recall loss compared to FP32 and FP16. Copyright © 2023, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Paramanu: A Family of Novel Efficient Generative Foundation Language Models for Indian Languages

arXiv

引用

arXiv 2024年

作者： Niyogi, Mitodru Bhattacharya, Arnab Gyan AI Research IIT Kanpur India Dept. of Computer Science and Engineering Indian Institute of Technology Kanpur India Gyan AI Research India

We present Paramanu (which means "atom" in multiple Indian languages), a family of novel language models for Indian languages. It is a collection of auto-regressive monolingual, bilingual, and multilingual Indian language models pretrained from scratch, currently covering 10 Indian languages (Assamese, Bangla, Hindi, Konkani, Maithili, Marathi, Odia, Sanskrit, Tamil, Telugu) across 5 scripts (Bangla, Devanagari, Odia, Tamil, Telugu). The models are pretrained with a context size of 1024 on a single GPU, and are of varying sizes ranging from 13.29 M to 367.5 M parameters. We proposed a RoPE embedding scaling method that enables us to pretrain language models from scratch at larger sequence length context size than the equivalent GPU memory. We have also developed an efficient novel most advanced Indic tokenizer using combination of BPE and Unigram, mBharat, that can even tokenize unseen languages written in the same script and also in Roman script. mBharat tokenizer has the least fertility score for Indian languages (1.25 for Hindi) among LLMs. We also proposed language specific tokenization for multilingual models and domain specific tokenization for monolingual language models. In order to avoid the "curse of multi-linguality" in our multilingual mParamanu model, we pretrained on comparable corpora by typological grouping using the same script. From our results, we observed the language transfer phenomenon from low resource to high resource within languages of the same script and typology. We performed human evaluation of our pretrained models for open end text generation on grammar, coherence, creativity, and factuality metrics for Bangla, Hindi, and Sanskrit. Our Bangla, Hindi, and Sanskrit models outperformed GPT-3.5-Turbo (ChatGPT), Bloom 7B, LLaMa-2 7B, OPT 6.7B, GPTJ 6B, GPTNeo 1.3B, GPT2-XL large language models (LLMs) by a large margin despite being smaller in size by 64 to 20 times compared to standard 7B LLMs. To run inference on our pretrained models, CP

关键词： Systems analysis

来源：评论

学校读者我要写书评

暂无评论

Sustainable Cultural Tourism Strategy and Promotion: An ICT Management Platform

Sustainable Cultural Tourism Strategy and Promotion: An ICT ...

引用

International Conference on Application of Information and Communication Technologies (AICT)

作者： Kashyap Raiyani Shabnam Pasandideh Sajib Ahmed Pedro Pereira João Martins Dept. Electrical and Computer Engineering Center of Technology and Systems-UNINOVA NOVA School of Science and Technology NOVA University Lisbon Caparica Portugal

ISBN: (数字)9798350387537

ISBN: (纸本)9798350387544

Cultural Tourism (CT) is a significant element of today’s economy, accounting for around 37% of the total tourist industry and expanding at a pace of over 15% each year. This function and economic impact can benefit some EU and non-EU locations and areas with high cultural, social, and environmental potential. Other synergistic variables such as know-how, Information Communication Technologies (ICTs), gastronomy, identity, local culture, values, intangible legacy, or other characteristics also contribute to this influence. The work presented in this paper is part of the Social Innovation and TEchnologies for Sustainable Growth through Participative Cultural TOURism (TExTOUR) project, which brings together partners from the quintuple social innovation helix (knowledge, business, society, government, and entrepreneurs) to co-design, validate, and scale up policies and strategies that have a positive impact on socioeconomic territorial development based on cultural tourism. TExTOUR collaborates with eight CT Pilots in lesser-known destinations to develop collaborative work methodologies for developing CT strategies for local sites, utilizing ICTs and social innovation tools. The CT-Labs assist stakeholders in putting CT ad hoc strategies and action plans into action, monitoring them, and validating them. As a result, a technological platform (ICT tool) is presented in this paper, with its components outlined.

关键词： Industries Technological innovation Federated learning Government Information and communication technology Cultural differences Global communication Stakeholders Socioeconomics Monitoring

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：