检索结果-内蒙古大学图书馆

6th International Conference on Computational Intelligence and Communication Technologies, CCICT 2024

作者： Kumar, Sudhanshu Yadav, Himanshu Kumar, Ashutosh Kaur, Mandeep Department of Computer Science & Engineering School of Engineering & Technology Sharda University Greater Noida India

ISBN: (纸本)9798350374629

With the increased usage of two-wheeler vehicles, traffic accidents are being recorded at an alarming rate each year. This research paper introduces RideGuard, an innovative helmet project designed to enhance rider safety by integrating advanced sensors and accelerometers. The core focus of this research is the development of a notification and aid system app, seamlessly integrated with the RideGuard helmet which is able to detect alcohol levels and accident in real-time. In the event of an accident, the system automatically triggers alerts to nearby hospitals and the rider's designated emergency contacts, including family members. This timely notification aims to expedite emergency response, potentially reducing the severity of injuries and improving overall outcomes. The RideGuard app is designed with user-friendly interfaces, enabling efficient communication between the helmet and the user's smartphone. The app provides real-time status updates, ensuring users are informed about their safety and the system's functionality. The integration of GPS technology enhances the accuracy of accident location detection, facilitating a quicker response from emergency services. ©2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Translation for Hindi-English: A Comparative Performance Analysis of Multilingual and Code-Mixed Text 10

Translation for Hindi-English: A Comparative Performance Ana...

引用

10th International Conference on Advanced Computing and Communication systems, ICACCS 2024

作者： Afsal, C.P. Kuppusamy, K.S. School of Engineering and Technology Pondicherry University Department of Computer Science Puducherry India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

The importance of code-mixed text is significant in light of India's rich diverse languages and cultures. Its significance is particularly notable in this modern era, as people are spending more and more time on social media platforms. Here, people use code-mixed text for convenience in conversations. Therefore, it's crucial to focus research efforts on these important topics. In this study, we aim to investigate the comparative performance of machine translation from Hindi to English and Hindi-English code-mixed text to English. We used a publicly available dataset HinGE introduced by Srivastava et al. Due to the relatively small size of our dataset, we opted for the MarianMT model, a transformer-based architecture that has been recognized for its ability to perform machine translation tasks, even when dealing with limited data. The BLEU scores of 0.91 for multilingual translation and a remarkable 0.97 for code-mixed Hindi-English translation indicate that our choice performed well. These findings highlight the model's excellent results and ability to perform in situations with limited training data. © 2024 IEEE.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Infield disease detection in citrus plants: integrating semantic segmentation and dynamic deep learning object detection model for enhanced agricultural yield

引用

Neural Computing and Applications 2024年第35期36卷 22485-22510页

作者： Rani, N. Shobha Krishna, Arun Sri Sunag, M. Sangamesha, M.A. Pushpa, B.R. University Bengaluru India Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysuru India Department of Chemistry The National Institute of Engineering Mysuru India

Simultaneous and dynamic detection of diseases from infield images of citrus plants is the primary objective of this investigation. Refraining from discarding the disease-related issues would reduce agricultural yield and production, resulting in significant crop loss and economic instability. computer Vision offers an inexpensive and efficient solution for detecting and predicting multiple diseases from infield images of citrus plants in various stages of plant growth. This study aims to perform simultaneous detection and prediction of cankers, mites, and nutritional deficiencies from infield images of citrus plants. For this purpose, over 4914 samples are annotated that are obtained from 441 image samples collected from orchards of citrus plants. Initially, the input image is subject to preprocessing followed by segmentation of prominent leaf regions and disease prediction. Contributions investigated in this work are two-fold: a deep semantic segmentation model named Dynamic U-Net is employed to extract prominent regions of interest, and a dynamic, lightweight object detection deep learning model for predicting diseases. From experimental outcomes, the segmentation efficiency is found to be 89.07% foreground accuracy, 0.7881 of IoU, and 0.9188 of the Dice coefficient. The object detection performance is quantified using the mapped metric, resulting in 0.85, 0.71, 0.64, and 0.27 efficiency concerning plant diseases, cankers, mites, and nutritional deficiency. As per the findings, the proposed approach is an effective solution to perform automated detection and prediction from infield images of citrus plants. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

A Decentralized Communication Framework Based on Dual-Level Recurrence for Multiagent Reinforcement Learning

引用

IEEE Transactions on Cognitive and Developmental systems 2024年第2期16卷 640-649页

作者： Li, Xuesi Li, Jingchen Shi, Haobin Hwang, Kao-Shing Northwestern Polytechnical University School of Computer Science and Engineering Xi'an710129 China National Sun Yat-sen University Department of Electrical Engineering Kaohsiung804 Taiwan

Designing communication channels for multiagent is a feasible method to conduct decentralized learning, especially in partially observable environments or large-scale multiagent systems. In this work, a communication model with dual-level recurrence is developed to provide a more efficient communication mechanism for the multiagent reinforcement learning field. The communications are conducted by a gated-attention-based recurrent network, in which the historical states are taken into account and regarded as the second-level recurrence. We separate communication messages from memories in the recurrent model so that the proposed communication flow can adapt changeable communication objects in the case of limited communication, and the communication results are fair to every agent. We provide a sufficient discussion about our method in both partially observable and fully observable environments. The results of several experiments suggest our method outperforms the existing decentralized communication frameworks and the corresponding centralized training method. © 2016 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Spatial data trusts:an emerging governance framework for sharing spatial data

引用

International Journal of Digital Earth 2023年第1期16卷 1607-1639页

作者： Nenad Radosevic Matt Duckham Mohammad Saiedur Rahaman Serene Ho Katherine Williams Tanzima Hashem Yaguang Tao School of Science RMIT UniversityMelbourneAustralia School of Computing Technologies RMIT UniversityMelbourneAustralia Frontier SI MelbourneAustralia Department of Computer Science and Engineering Bangladesh University of Engineering and TechnologyDhakaBangladesh

Data Trusts are an important emerging approach to enabling the much wider sharing of data from many different sources and for many different purposes,backed by the confidence of clear and unambiguous data *** Trusts combine the technical infrastructure for sharing data with the governance framework of a legal *** concept of a data Trust applied specifically to spatial data offers significant opportunities for new and future applications,addressing some longstanding barriers to data sharing,such as location privacy and data *** paper introduces and explores the concept of a‘spatial data Trust’by identifying and explaining the key functions and characteristics required to underpin a data Trust for spatial *** work identifiesfive key features of spatial data Trusts that demand specific attention and connects these features to a history of relevant work in thefield,including spatial data infrastructures(SDIs),location privacy,and spatial data *** conclusions identify several key strands of research for the future development of this rapidly emerging framework for spatial data sharing.

关键词： Data governance spatial information location privacy indigenous data sovereignty spatial data quality

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of computer science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

Review on Predicting the Landslide Susceptibility using Machine Learning Techniques 2

Review on Predicting the Landslide Susceptibility using Mach...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Sinha, Abhishek Giri, Shivam Kumar Yadav, Himanshu Prasad, Sanjeev Kumar Mishra, Priya School of Computer Science and Engineering Galgotias University Greater Noida India Department of Computer Application ABES Engineering College Ghaziabad India

ISBN: (纸本)9798331530389

This Landslide susceptibility prediction is a critical task for Alleviating the risks associated with landslide hazards, which have significant socio-economic and environmental impacts. Existing techniques face challenges related to data quality, model coherence, and generalizability across diverse geographical and climatic regions. Additionally, while advanced machine learning (ML) and deep learning (DL) models offer high accuracy, they often require significant computational resources, which limits their practical application in real-time scenarios. In this review, we aim to highlight the strengths, limitations, and potential improvements of machine learning techniques in predicting landslide susceptibility, providing a comprehensive reference for researchers and practitioners in this domain. Furthermore, the role of Explainable AI is examined to address the critical need for interpretable and transparent models in real-world applications. Hybrid ML-DL models outperform traditional methods in handling complex spatial-temporal data, with dynamic factors improving accuracy and reliability. Explainable AI enhances interpretability, while advancements and collaborations address data and generaliz ability challenges. © 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

Unlocking Security: A Comprehensive Exploration of Biometric Authentication Techniques 14

Unlocking Security: A Comprehensive Exploration of Biometric...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Sriman, Jindam Thapar, Puneet Alyas, Arsalan Ahmed Singh, Urvashi School of Computer Science Engineering Lovely Professional University Phagwara India Wilmington University Information System Technologies United States

ISBN: (纸本)9798350344837

Biometric authentication is a rapidly evolving field in information security, providing a personalized and reliable approach to identity verification. This paper explores various biometric methods, including fingerprints, iris scans, facial recognition, voice authentication, and behavioral biometrics, highlighting their strengths and vulnerabilities. Addressing challenges like spoofing attacks, multimodal integration, and privacy concerns, the paper emphasizes the need for robust security measures. The thorough analysis considers critical factors such as accuracy, user-friendliness, and vulnerability to fraudulent activities, providing a well-rounded assessment of their strengths and weaknesses. Besides, the review delves into the convergence of diverse biometric modalities and the evolving landscape of multimodal authentication systems, underscoring the pressing need for sustained research and advancement to address security challenges and privacy issues. The ultimate objective is to support user acceptance and instill confidence in biometric authentication. By critically appraising established techniques and contemplating potential future developments, this paper aims to provide profound insights for researchers and practitioners in the field of biometric authentication. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Efficient Radon Levels Detection in Residential Areas using Cloud-Enabled Decision Trees for Real-Time Analysis 8

Efficient Radon Levels Detection in Residential Areas using ...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Lenin, J. Rohit, V.Robin Nisha, F. Vasudevan, B. Sivakumar, S. Murugan, S. Alliance College of Engineering and Design Alliance University Department of Computer Science & Engineering Bangalore India Presidency University Computer Science & Engineering School of Computer Science & Engineering and Information Science Bengaluru India Cmr University School of Engineering and Technology Computer Science & Engineering Bangalore India Srm Institute of Science and Technology Department of Electronics and Communication Engineering Kattankulathur SRM Nagar Tamil Nadu Chennai India Department of Computer Science Tamil Nadu Perambalur India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376425

This research introduces a new approach to radon detection in homes utilizing Decision Trees (DTs) enabled by the cloud in real-time. High radon levels, a natural radioactive gas, are dangerous to human health. Quick evaluation and mitigation efforts are hindered by the long processes required by traditional detection systems. Using DTs, a machine learning methodology, the proposed method sorts of radon levels according to variables, including building materials, ventilation systems, and geographic location. These trees may handle both numerical and categorical data and provide interpretability. Fast processing of massive data sets and real-time analysis across varied residential areas are made possible by integrating cloud computing, increasing efficiency and scalability. Stakeholders may remotely access crucial information due to the solution's accessibility and flexibility. Results from controlled experiments demonstrate that this method can accurately identify radon levels in the air in real time, allowing for preventative actions to lessen potential health hazards. People living in areas prone to radon may benefit from this practice in terms of their health. © 2024 IEEE.

关键词： Indoor air pollution

来源：评论

学校读者我要写书评

暂无评论

Early Diagnosis of Lung Tumors for Extending Patients’ Life Using Deep Neural Networks

引用

computers, Materials & Continua 2023年第7期76卷 993-1007页

作者： A.Manju R.Kaladevi Shanmugasundaram Hariharan Shih-Yu Chen Vinay Kukreja Pradip Kumar Sharma Fayez Alqahtani Amr Tolba Jin Wang Department of Computer Science and Engineering SRM Institute of Science and TechnologyRamapuramChennaiIndia Department of Computer Science and Engineering Saveetha Engineering CollegeChennaiIndia Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabadIndia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin 64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin 64002Taiwan Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjabIndia Department of Computing Science University of AberdeenAberdeenUK Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh 12372Saudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadh 11437Saudi Arabia School of Computer&Communication Engineering Changsha University of Science&TechnologyChangshaChina

The medical community has more concern on lung cancer *** experts’physical segmentation of lung cancers is time-consuming and needs to be *** research study’s objective is to diagnose lung tumors at an early stage to extend the life of humans using deep learning ***-Aided Diagnostic(CAD)system aids in the diagnosis and shortens the time necessary to detect the tumor *** application of Deep Neural Networks(DNN)has also been exhibited as an excellent and effective method in classification and segmentation *** research aims to separate lung cancers from images of Magnetic Resonance Imaging(MRI)with threshold *** Honey hook process categorizes lung cancer based on characteristics retrieved using several *** this principle,the work presents a solution for image compression utilizing a Deep Wave Auto-Encoder(DWAE).The combination of the two approaches significantly reduces the overall size of the feature set required for any future classification process performed using *** proposed DWAE-DNN image classifier is applied to a lung imaging dataset with Radial Basis Function(RBF)*** study reported promising results with an accuracy of 97.34%,whereas using the Decision Tree(DT)classifier has an accuracy of 94.24%.The proposed approach(DWAE-DNN)is found to classify the images with an accuracy of 98.67%,either as malignant or normal *** contrast to the accuracy requirements,the work also uses the benchmark standards like specificity,sensitivity,and precision to evaluate the efficiency of the *** is found from an investigation that the DT classifier provides the maximum performance in the DWAE-DNN depending on the network’s performance on image testing,as shown by the data acquired by the categorizers themselves.

关键词： Lung tumor deep wave auto encoder decision tree classifier deep neural networks extraction techniques

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：