检索结果-内蒙古大学图书馆

Traffic Sign Detection Using SSD Mobilenet & Faster RCNN 2

Traffic Sign Detection Using SSD Mobilenet & Faster RCNN

2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, ViTECoN 2023

作者： Asif, Shaik Mohammad Anil, T. Tangudu, Satwik Keertan, G.H. Sai Don, S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Applications Amritapuri India

ISBN: (纸本)9798350347982

This paper presents a deep learning-based approach to traffic sign detection. The proposed approach utilizes state- of-the-art object detection models, such as SSD and RCNN, to detect traffic signs in real time. Tensorflow is used as a platform for training deep learning models and the models are being implemented on Google Colab and Kaggle cloud due to the GPU availability on the respective platforms. The models are evaluated on a traffic sign dataset from Kaggle, and it achieves high detection accuracy. Moreover, the proposed approach is robust to different lighting and weather conditions and is capable of detecting traffic signs from various distances and angles. The findings of this study show that by effectively detecting and recognizing traffic signs, deep learning-based techniques can potentially increase the safety and effectiveness of transportation networks. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Impact of Text Data Augmentation on Text Classification Tasks using DistilBERT 2

Evaluating the Impact of Text Data Augmentation on Text Clas...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Nair, Aarathi Rajagopalan Singh, Rimjhim Padam Gupta, Deepa Kumar, Priyanka Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science University of Texas San AntonioTX United States

Data augmentation entails artificially expanding the dataset's size by applying various transformations to the existing raw data. Enhancing the quality and quantity of the datasets with varying sizes by employing varieddata augmentation techniques has immense importance in the field on Natural Language Processing. Several notable applications for instance text classification, sentiment analysis, text summarization, etc. have proven to be benefitted immensely with the employment of text augmentation techniques. Hence, the paper focuses on efficient text classification using varied datasets of different sizes;small- 500 instances, medium-5564 instances and large-43934 *** work considers the standard DistilBERT model, a popular transformer-based language model and presents the impact on the performance of the modelafter employing different text augmentation techniques. The study specifically focuses on three augmentation methods: (a) Synonym augmentation:that involves replacing words with their synonyms to enhance vocabulary diversity and generalization, (b) Contextual word embeddings that enriches semantic understanding by leveraging pre-trained language models, and (c) Black translation that entails translating the text into a another different language and then translating it back, introducing variations in the data and capturing different linguistic ***,the work also discusses the combined effect of employing all three augmentation techniques simultaneously. Moreover, the study also aims compares the relation between the dataset sizes and the performance of the augmentation techniques. The study considers three standard datasets for the analysis and presents a comprehensive analysis using accuracy and F1 score as evaluation metrics. The results highlight the efficacy of each technique across small, medium, and large datasets, enabling a nuanced understanding of their benefits in different data scenarios. The findings indicate the varying

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Identification and Detection of Leaf Miner, Pests Infestation in Cucurbitaceae Family in Real Time Infield Scenarios using YOLOv5s Object Detection Model 18

Identification and Detection of Leaf Miner, Pests Infestatio...

引用

18th INDIAcom;11th International Conference on computing for Sustainable Global Development, INDIACom 2024

作者： Keerthi Prasad, M.A. Shobha Rani, N. Sangamesha, M.A. Vinay, K.V. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science Mysuru India The National Institute of Engineering Department of Chemistry Mysuru India The National Institute of Engineering Department of Computer Science Mysuru India

ISBN: (纸本)9789380544519

This study contributes to technological developments in precision agriculture by developing a YOLOv5sbased model with a high F1 score and mAP, highlighting its potential for real-world use in wax gourd plants. In precision agriculture, early disease identification is crucial for effective harvesting. The present research focuses on the creation and evaluation of a YOLOv5s-based model for detecting pests and leaf miner infections in wax gourd plants in real time infield conditions at various stages of plant growth. Using a dataset of over 2000 samples collected in a variety of in-field settings, the model was trained for 200 epochs with a low learning rate (0.00001) and a batch size of 32. The achieved F1 score of 0.96 demonstrates the model's remarkable combination of precision and recall, ensuring precise disease detection. Furthermore, a mean Average Precision (mAP) greater than 0.45 demonstrates the model's proficiency in precise leaf localization and overall detection ability. The model's ability to detect numerous occurrences of disease in different leaves simultaneously is a crucial strength, reflecting the complexities common in real-world agricultural scenarios. The dataset's quantity and diversity help the model be robust and generalizable across diverse infection types and growth stages. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： crop health monitoring Data-driven agriculture object detection precision agriculture Smart agriculture sustainable farming

来源：评论

学校读者我要写书评

暂无评论

Exploring Network Security Metric and Enhancing the Secure computing for Cloud through Honeypot 4

Exploring Network Security Metric and Enhancing the Secure C...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： Anusha, B. Kruthi, V. Joshi, Pallavi School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science Mysuru India

ISBN: (纸本)9798350387063

Rapid user growth is causing problems with website performance, web hosting, and data space and memory allocation, all of which can directly or indirectly result in data loss. We use cloud computing techniques to provide services that are dependable, quick, and affordable. This technology is developing at a rapid rate, which increases the possibility that hostile people will breach its security. Using honeypots is one method of rerouting harmful traffic away from computers. It's a massive method that has improved system security somewhat. The idea of Honeypot is applied to a file-sharing program that is hosted on a cloud server, taking into consideration the several legal concerns that could arise from installing Honeypot on servers owned by third-party cloud vendors. This research presents a novel method to identify attacks in cloud-based environments by discussing the use of honeypots for security and detecting assaults in such environments. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

An enhanced three factor based authentication protocol using wireless medical sensor networks for healthcare monitoring

引用

Journal of Ambient Intelligence and Humanized computing 2024年第1期15卷 1165-1186页

作者： Ali, Rifaqat Pal, Arup Kumar Kumari, Saru Sangaiah, Arun Kumar Li, Xiong Wu, Fan Dhanbad826004 India Department of Mathematics Ch. Charan Singh University Uttar Pradesh Meerut250004 India School of Computing Science and Engineering VIT University Vellore Tamil Nadu632014 India School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Department of Computer Science and Engineering Xiamen Institute of Technology Xiamen361021 China

With the rapid growth of wireless medical sensor networks (WMSNs) based healthcare applications, protecting both the privacy and security from illegitimate users, are major concern issues since patient’s precise information is vital for the proper diagnosis procedure. So, authentication protocol is one of the efficient mechanisms to deal with trustworthy and authentic users. Several authentication protocols have been proposed in WMSNs environment. However, the most of these protocols are so susceptible to security threats and not suitable for practical use. In this article, recently proposed Amin et al.’s authentication scheme is reviewed and some vulnerabilities like off-line password guessing attack, user impersonation attack, known session-key temporary information attack, the revelation of secret parameters, and identity guessing attack are pointed out. To overcome all the above mentioned vulnerabilities, we have proposed an enhanced three-factor based remote user authentication protocol in WMSNs environment. Further, the proposed protocol is validated using Burrows–Abadi–Needham logic and then simulated using Automated Validation of Internet Security Protocols and Applications tool. Moreover, the security analysis ensures that the proposed protocol is well protected from various types of malicious attacks. In addition, the performance evaluation shows better efficiency and suitability of our protocol over other related protocols. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Advancing Web Browser Forensics: Critical Evaluation of Emerging Tools and Techniques

引用

SN computer science 2025年第4期6卷 1-28页

作者： Chand, Rishal Ravikesh Sharma, Neeraj Anand Kabir, Muhammad Ashad Department of Computer Science and Mathematics The University of Fiji Lautoka Fiji School of Computing Mathematics and Engineering Charles Sturt University Bathurst 2795 NSW Australia

As the use of web browsers continues to grow, the potential for cybercrime and web-related criminal activities also increases. Digital forensic investigators must understand how different browsers function and the critical areas to consider during web forensic analysis. Web forensics, a subfield of digital forensics, involves collecting and analyzing browser artifacts, such as browser history, search keywords, and downloads, which serve as potential evidence. While existing research has provided valuable insights, many studies focus on individual browsing modes or limited forensic scenarios, leaving gaps in understanding the full scope of data retention and recovery across different modes and browsers. This paper addresses these gaps by defining four browsing scenarios and critically analyzing browser artifacts across normal, private, and portable modes using various forensic tools. We define four browsing scenarios to perform a comprehensive evaluation of popular browsers—Google Chrome, Mozilla Firefox, Brave, Tor, and Microsoft Edge—by monitoring changes in key data storage areas such as cache files, cookies, browsing history, and local storage across different browsing modes. Overall, this paper contributes to a deeper understanding of browser forensic analysis and identifies key areas for enhancing privacy protection and forensic methodologies. © The Author(s) 2025.

关键词： Browser artifacts Browser forensics Cybercrime Digital forensics Forensics tool Web browser

来源：评论

学校读者我要写书评

暂无评论

An Effective Optimization Method for Integrated Scheduling of Multiple Automated Guided Vehicle Problems

引用

Tsinghua science and Technology 2024年第5期29卷 1355-1367页

作者： Hongyan Sang Zhongkai Li M.Fatih Tasgetiren School of Computer Science Liaocheng UniversityLiaocheng 252000China Industrial Engineering Department Baskent UniversityAnkara 06000Türkiye

Automated Guided Vehicle(AGV)scheduling problem is an emerging research topic in the recent *** paper studies an integrated scheduling problem comprising task assignment and path planning for *** reduce the transportation cost of AGVs,this work also proposes an optimization method consisting of the total running distance,total delay time,and machine loss cost of AGVs.A mathematical model is formulated for the problem at hand,along with an improved Discrete Invasive Weed Optimization algorithm(DIWO).In the proposed DIWO algorithm,an insertion-based local search operator is developed to improve the local search ability of the algorithm.A staggered time departure heuristic is also proposed to reduce the number of AGV collisions in path *** experiments are conducted,and 100 instances from actual factories have proven the effectiveness of the optimization method.

关键词： Automated Guided Vehicle(AGV) integrated scheduling staggered time departure heuristics

来源：评论

学校读者我要写书评

暂无评论

Divide and Conquer: Legal Concept-guided Criminal Court View Generation

Divide and Conquer: Legal Concept-guided Criminal Court View...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Xu, Qi Wei, Xiao Yu, Hang Liu, Qian Fei, Hao School of Computer Engineering and Science Shanghai University China School of Computer Science University of Auckland New Zealand School of Computing National University of Singapore Singapore

ISBN: (纸本)9798891761681

The Criminal Court View Generation task aims to produce explanations that inform judicial decisions. This necessitates a nuanced understanding of diverse legal concepts, such as Recidivism, Confess, and Robbery, which often coexist within cases, complicating holistic analysis. However, existing methods mainly rely on the generation capability of language models, without paying enough attention to the important legal concepts. To enhance the precision and depth of such explanations, we introduce Legal Concept-guided Criminal Court Views Generation (LeGen), a three-stage approach designed for iterative reasoning tailored to individual legal concepts. Specifically, in the first stage, we design a decomposer to divide the court views into focused sub-views, each anchored around a distinct legal concept. Next, a concept reasoning module generates targeted rationales by intertwining the deconstructed facts with their corresponding legal frameworks, ensuring contextually relevant interpretations. Finally, a verifier and a generator are employed to align the rationale with the case fact and obtain synthesized comprehensive and legally sound final court views, respectively. We evaluate LeGen by conducting extensive experiments on a real-world dataset and experimental results validate the effectiveness of our proposed model. Our codes and dataset are available at https://***/xuqi220/LeGen. © 2024 Association for Computational Linguistics.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

SMARTGOV: Strategic Management of Assets for Resilient and Transparent Government Operations 9

SMARTGOV: Strategic Management of Assets for Resilient and T...

引用

9th International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2024

作者： Chauhan, Naman Atri, Pranshul Tomar, Riya Kumar, Aman Chauhan, Chhavi Kumar, Kaitala Charan Sophiya, E. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India School of Computer Science University of Petroleum and Energy Studies Dehradun India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mechanical Engineering Chennai India

ISBN: (纸本)9798350350845

In this age, we introduce an application that aims to revolutionize the management of government buildings. With a commitment, to supporting Digital India initiative, proposed project addresses the changing needs of governance and public service delivery. This application serves a purpose;it provides authorities with an easy-To-use platform for efficient building management while also empowering the public with real-Time information and a streamlined channel for expressing concerns. We leverage technologies like GPS camera Lite, Google Maps, Automatic fire detection using CNN with a mAP of 98.61% and Cloud Firestore to seamlessly integrate our application with Android Studio and Kotlin ensuring an optimal user experience. Our motivation behind this initiative stems from the need to contribute to our nation's progress by promoting governance and aligning with India's aspirations for Digital India. By fostering communication, transparency and accountability our application becomes a tool, in building an empowered and prosperous India. Proposed Work outlines the features, technological framework and societal benefits of our solution that resonates with both government requirements and public aspirations. © 2024 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Market Analysis and Prototype Developement of an Assistive Device 2

A Data-Driven Market Analysis and Prototype Developement of ...

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： Shrutha, P. Mary, Shobha Sarkar, Sayantika Das, Thrisha Santhosh Kumar, B.J. Amrita Vishwa Vidyapeetham Department of Computer Science School of Computing Mysuru India

ISBN: (纸本)9798350367461

The proposed work landscape of assistive devices available for differently-abled individuals in India. The study encompasses a comprehensive market analysis of existing assistive devices based on their import and export details for the current year with offering insights into the growth in the usage of assistive devices for the current year 2024. Work investigates the wide knowledge of the existence of such devices in the society by carrying out a manual survey and comparing the obtained results which aids in identifying patterns within this critical domain along with the prototype development of an assistive device "Smart Stick"for the visually impaired. Showcasing the market growth of various assistive devices purchased across various countries like India, Vietnam, US etc through implementation of one such robust machine learning technique like ARIMA integrated auto regressive moving average (ARIMA) for predicting time series data. The entire work for dying need for differently abled. © 2024 IEEE.

关键词： accessibility affordability assistive devices differently-abled individuals emerging market trends market analysis user preferences

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：