检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Hariharan Ravishankar Prasad Sudhakar Phaneendra K. Yalavarthy Department of Computational and Data Sciences Indian Institute of Science Bangalore GE Healthcare Bangalore

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

This study proposes a fully automated framework TTA-FM: for patient-specific, test-time adaptation of pre-trained prostate segmentation models using vision foundation models in magnetic resonance (MR) images. The proposed frame-work utilizes salient properties of foundation models and task-specific models to filter, impute, and generate high-confidence pseudolabels for model adaptation. Existing test-time adaptation methods are often not patient-specific, require strong anatomical priors or modify training procedure rendering them impractical. Vision foundation models often fail to perform adequately on medical images due to differences in texture and shape properties of objects of interest. The proposed TTA-FM framework designed to overcome these limitations, outperforms both sets of methods for prostate segmentation from MR images. The TTA-FM method was evaluated on a challenging cross-site domain adaptation setting and achieves state-of-the-art results with no additional constraints, making it first of its kind adaptation framework. Further, results from a set of ablation studies are reported, demonstrating value of each step of the proposed method.

关键词： Training Adaptation models Image segmentation Shape Biological system modeling Magnetic resonance Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Approaches to the Development of an Effective Regulatory Ecosystem and Policies for Big data Analytics in the Republic of Kazakhstan

Approaches to the Development of an Effective Regulatory Eco...

引用

2022 International Conference on Smart Information Systems and Technologies, SIST 2022

作者： Akatov, Kamil Yedilkhan, Didar Urnaliyev, Alibi Astana It University Department Of Computational And Data Science Nur-Sultan Kazakhstan Astana It University Department Of Computer Engineering Nur-Sultan Kazakhstan

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

This paper studies the Big data ecosystem and regulatory approaches for the technological issues used in Kazakhstan. Key points are considered in terms of the importance and necessity of managing data at various levels for decision-making and facilitating their introduction into economic circulation, including an analysis of international approaches and cases in the use of data by authorities and organizations. The main aim of this paper is to make analysis and prepare model for improving policies for the development of Big data policies included analytics at national level. © 2022 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Nature-Inspired Algorithms for Autism Spectrum Disorder Detection Using 3D Video dataset

arXiv

引用

arXiv 2025年

作者： Panchal, Aneesh Khan, Kainat Katarya, Rahul Department of Computational and Data Sciences Indian Institute of Science Karnataka Bangalore560012 India Big Data Analytics and Web Intelligence Laboratory Department of Computer Science & Engineering Delhi Technological University Delhi110042 India

Autism Spectrum Disorder (ASD) is a chronic neurodevelopmental disorder symptoms of which includes repetitive behaviour and lack of social and communication skills. Even though these symptoms can be seen very clearly in social but a large number of individuals with ASD remains undiagnosed. In this paper, we worked on a methodology for detection of ASD from 3-dimensional walking video dataset, utilizing supervised machine learning (ML) classification algorithms and using nature-inspired optimization algorithms for feature extraction from dataset. The proposed methodology involve the classification of ASD using supervised ML classification algorithm and extracting important and relevant features from the dataset using nature-inspired optimization algorithms. We also included the ranking coefficients for finding the initial leading particle. This selection of particle significantly reduces the computation time and hence, improving the total efficiency and accuracy for the ASD detection. To evaluate the efficiency of the proposed methodology, we deployed various combination of classification algorithm and nature-inspired algorithms resulting in an outstanding classification accuracy of 100% using random forest classification algorithm and gravitational search algorithm for feature selection. The application of the proposed methodology with different datasets would enhance the robustness and generalizability of the proposed methodology. Due to high accuracy and less total computation time, the proposed methodology will offer a significant contribution to the medical and academia fields, providing a foundation for future research and advancements in ASD diagnosis. Copyright © 2025, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

PVDM-YOLOv8l: a solution for reliable pedestrian and vehicle detection in autonomous vehicles under adverse weather conditions

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Tahir, Noor Ul Ain Zhang, Zuping Asim, Muhammad Iftikhar, Sundas A. Abd El-Latif, Ahmed School of Computer Science and Engineering Central South University Changsha410083 China EIAS Data Science Lab College of Computer and Information Sciences and Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh11586 Saudi Arabia Gianforte School of Computing Montana State University Bozeman59717 United States Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom32511 Egypt

Ensuring the safe navigation of autonomous vehicles in intelligent transportation system depends on their ability to detect pedestrians and vehicles. While transformer-based models for object detection have shown remarkable advancements, accurately identifying pedestrians and vehicles in adverse weather conditions remains a challenging task. Adverse weather introduces image quality degradation, leading to issues such as low contrast, reduced visibility, blurred edges, false detection, misdetection of tiny objects, and other impediments that further complicate the accuracy of detection. This paper introduces a novel Pedestrian and Vehicle Detection Model under adverse weather conditions, denoted as PVDM-YOLOv8l. In our proposed model, we first incorporate the Swin-Transformer method, which is designed for global extraction of feature of small objects to identify in poor visibility, into the YOLOv8l backbone structure. To enhance detection accuracy and address the impact of inaccurate features on recognition performance, CBAM is integrated between the neck and head networks of YOLOv8l, aiming to gather crucial information and obtain essential data. Finally, we adopted the loss function Wise-IOU v3. This function was implemented to mitigate the adverse effects of low-quality instances by minimizing negative gradients. Additionally, we enhanced and augmented the DAWN dataset and created a custom dataset, named DAWN2024, to cater to the specific requirements of our study. To verify the superiority of PVDM-YOLOV8l, its performance was compared against several commonly used object detectors, including YOLOv3, YOLOv3-tiny, YOLOv3-spp, YOLOv5, YOLOv6, and all the versions of YOLOv8 (n, m, s, l, and x) and some traditional models. The experimental results demonstrate that our proposed model achieved a 6.6%, 5.4%, 6%, and 5.1% improvement in precision, recall, F1-score and mean Average Precision (mAP) on the custom DAWN2024 dataset. This substantial improvement in accuracy ind

关键词： Vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Non-English Natural Language Interface to databases: A Systematic Review 13

Non-English Natural Language Interface to Databases: A Syste...

引用

13th IEEE Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2022

作者： Karimi, Sadullah Rasel, Annajiat Alim Abdullah, Matin Saad Department of Computer Science and Engineering School of Data and Sciences Brac University Dhaka Bangladesh

ISBN: (数字)9781665463164

ISBN: (纸本)9781665463164

A natural language interface (NLI) facilitates communication between a user and a system using a natural language used by a human as a medium. Instead of a complex user interface with numerous controls, the user enters input via natural language in the form of text, speech, signs, etc. The system responds via natural language in the form of text, speech, signs, etc. The use of a natural language interface has been increasing. To interact with a dataset or a database, such a system or interface is not always available. To access data, users need the knowledge of Structured Query Language (SQL) or need to learn an alternative graphical tool or database browser with varying limitations. For non-English speakers, it may create further issues in accessing data. English users can access the database using the natural language interface to database (NLIDB) which converts natural language to English-like Structured Query Language (SQL). For non-English users, the query in non-English language needs to be converted to SQL directly or via the English language as an intermediary. Researchers have proposed NLIDB systems for native speakers of many languages. In this research, we present results from a systematic review of non-English NLIDB with their various approaches. This research aims to assist future NLIDB researchers in understanding the current state and to identify the research gaps. © 2022 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Dynamic channel estimation-aware routing protocol in mobile cognitive radio networks for smart IIoT applications

引用

Digital Communications and Networks 2023年第2期9卷 367-382页

作者： Qusay M.Salih Md Arafatur Rahman A.Taufiq Asyhari Muhammad Kamran Naeem Mohammad Patwary Ryan Alturki Mohammed Abdulaziz Ikram Faculty of Computing Universiti Malaysia Pahang26300GambangPahangMalaysia School of Engineering Computing and Mathematical SciencesUniversity of WolverhamptonUK Data Science Program Monash UniversityIndonesiaand Birmingham City UniversityB47XGUK Department of Information Science College of Computer and Information SystemsUmm Al-Qura UniversitySaudi Arabia Computer Science Department Al Jumoum University CollegeUmm Al-Qura UniversitySaudi Arabia

Cognitive Radio Networks(CRNs)have become a successful platform in recent years for a diverse range of future systems,in particularly,industrial internet of things(IIoT)*** order to provide an efficient connection among IIoT devices,CRNs enhance spectrum utilization by using licensed ***,the routing protocol in these networks is considered one of the main problems due to node mobility and time-variant channel ***,the channel selection for routing protocol is indispensable in CRNs to provide an adequate adaptation to the Primary User(PU)activity and create a robust routing *** study aims to construct a robust routing path by minimizing PU interference and routing delay to maximize throughput within the IIoT ***,a generic routing framework from a cross-layer perspective is investigated that intends to share the information resources by exploiting a recently proposed method,namely,Channel Availability ***,a novel cross-layer-oriented routing protocol is proposed by using a time-variant channel estimation *** protocol combines lower layer(Physical layer and data Link layer)sensing that is derived from the channel estimation ***,it periodically updates and stores the routing table for optimal route ***,in order to achieve higher throughput and lower delay,a new routing metric is *** evaluate the performance of the proposed protocol,network simulations have been conducted and also compared to the widely used routing protocols,as a *** simulation results of different routing scenarios demonstrate that our proposed solution outperforms the existing protocols in terms of the standard network performance metrics involving packet delivery ratio(with an improved margin of around 5–20%approximately)under varying numbers of PUs and cognitive users in Mobile Cognitive Radio Networks(MCRNs).Moreover,the cross-layer routing protocol successfully achiev

关键词： Channel selection Cross-layer design Mobile cognitive radio networks Routing protocol IIoT applications

来源：评论

学校读者我要写书评

暂无评论

Research on Large-scale Structured and Unstructured data Processing based on Large Language Model 24

Research on Large-scale Structured and Unstructured Data Pro...

引用

2024 International Conference on Machine Learning, Pattern Recognition and Automation Engineering, MLPRAE 2024

作者： Li, Bohang Jiang, Gaozhe Li, Ningxin Song, Chaoda Department of Data Science Shopee Pte. Ltd. Singapore Institute of Operations Research and Analytics National University of Singapore Singapore Fu Foundation School of Engineering and Applied Science Columbia University United States School of Engineering Department of Computer and Data Sciences United States

ISBN: (纸本)9798400709876

Since the beginning of the internet era, there has been an explosion of growth in structured data (such as numbers, symbols, and labels) as well as unstructured data (including images, videos, and text). Efficient and accurate mixed query of these two types of data is a key technology to achieve high-quality information retrieval, and it is also a major challenge that needs to be solved urgently in the industry. In this study, we employ an advanced Transformer model that combines strategies and fine-tuning techniques for multi-task learning. Specifically, the model is first pre-trained on a large-scale, general-purpose dataset to learn different types of data representations and basic language comprehension skills. After that, we fine-tuned the parameters of the model to better suit these specific data processing tasks for specific application scenarios, such as image annotation, video content analysis, and structured data query. At the heart of the model is the self-attention mechanism, which allows the model to automatically emphasize the important parts and ignore irrelevant information when processing the input data. In addition, we have introduced task-specific adaptation layers that are designed to add additional processing power to the original Transformer architecture, such as a semantic analysis layer for unstructured text data and a relational extraction layer for structured data. This combination of general pre-training and task-specific fine-tuning allows the model to flexibly process and integrate information from different data sources, improving processing efficiency and accuracy. Experimental results show that the model performs well in a variety of data processing tasks, significantly improves the accuracy and efficiency of information retrieval, and verifies the strong potential and adaptability of large language models in processing mixed data types. © 2024 ACM.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

Leveraging Internet of Things (IoT) Sensors and Deep Learning Techniques for Precision Agriculture 1

Leveraging Internet of Things (IoT) Sensors and Deep Learnin...

引用

1st International Conference on Innovative Engineering sciences and Technological Research, ICIESTR 2024

作者： Wilfred Blessing, N.R. Pyingkodi, M. Wasim Haidar, S.K. Palarimath, Suresh Paravathavarthini, S. Balakumar, C. Sheeja Kumari, V. Sutherlin Subitha, G. Seldev Christopher, S. University of Technology and Applied Sciences-Ibri College of Computing and Information Sciences Ibri Oman Kongu Engineering College Department of Computer Applications Erode India University of Technology and Applied Sciences-Salalah College of Computing and Information Sciences Salalah Oman Kongu Engineering College Department of Computer Technology Erode India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Saveetha Institute of Medical and Technical Sciences Department of Computational Intelligence Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Aruthenganvilai India St. Xavier's Catholic College of Engineering Department of Computer Science and Engineering Nagercoil India

ISBN: (纸本)9798350348637

Precision agriculture, driven by advancements in technology, aims to optimize farming practices by utilizing data and technology to enhance efficiency, productivity, and sustainability This research introduces an innovative pilot investigation centered on the convergence of two revolutionary technologies are the Internet of Things (IoT) and Deep Learning. With a specific focus on advancing precision agriculture, the primary objective of this study is to evaluate the combined effects of data collection facilitated by IoT and analytical capabilities of deep learning in enhancing and optimizing various agricultural processes. The integration of IoT in agriculture has revolutionized data acquisition, employing an array of sensors to monitor critical parameters such as soil moisture, temperature, and crop health. Concurrently, Deep Learning, a subset of artificial intelligence, exhibits the potential to glean actionable insights from voluminous datasets, offering advanced analytics and predictive capabilities. This study investigates the practical implementation and efficacy of this integration in a controlled agricultural setting. Sensors strategically positioned in the pilot study capture real-time data, while deep learning algorithms process and analyze this information. The primary objectives include evaluating the effectiveness of this combined technology in optimizing irrigation schedules, predicting crop yields, and identifying anomalies in crop health. Preliminary findings underscore the transformative potential of IoT and Deep Learning, empowering farmers with real-time data for informed decision-making. Key considerations encompassed in the study include IoT Sensors, Deep learning algorithms, and user adoption. The research not only sheds light on the technical intricacies of the integration but also delves into the challenges and opportunities inherent in merging these technologies within the agricultural landscape. As agriculture transitions towards the next

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Can Automated Metadata Extraction Make Scientific data More Navigable? 19

Can Automated Metadata Extraction Make Scientific Data More ...

引用

19th IEEE International Conference on e-science, e-science 2023

作者： Skluzacek, Tyler J. Chard, Kyle Foster, Ian National Center for Computational Sciences Oak Ridge National Lab Oak RidgeTN United States University of Chicago Department of Computer Science ChicagoIL United States Data Science and Learning Division Argonne National Lab LemontIL United States

ISBN: (纸本)9798350322231

FAIR principles require that scientific data be findable, discoverable, and reusable by users. To enable FAIRness, practioners of a science repository will often construct a rich, searchable index of metadata derived from the data. Unfortunately, manual metadata annotation methods do not scale to the many data files generated by many projects;and instead automated extraction systems are needed to scalably parse these files - often with nonstandard schema requiring specialized parsing strategies - and deposit representative metadata into a search index. In this work, we evaluate whether, and the extent to which, automatically extracted metadata make research repositories more navigable. We present a two-part user study conducted with scientists at two U.S. national laboratories from projects spanning spectroscopy and battery modeling. We constructed research indexes automatically by using the Xtract metadata extraction system. In the first part of our study, we learned about each user's role and identified key navigation concerns for scientists. We found that participants wished to navigate for purposes of discovery, retrieval, and organization. In the second part, participants completed simulated research data navigation tasks crafted to reflect real-world navigability concerns. We found that regardless of the interface used, participants consistently solved navigation tasks with high degrees of confidence and correctness, and significantly (1.2X-50×) faster than via their alternative methods (e.g., manual directory scans or designing a customized navigational tool). © 2023 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

A Web Group Decision Support System Based on Granular Computing 21

A Web Group Decision Support System Based on Granular Comput...

引用

21st International Conference on New Trends in Intelligent Software Methodologies, Tools and Techniques, SoMeT 2022

作者： Cabrerizo, Francisco Javier González-Quesada, Juan Carlos Pérez, Ignacio Javier Cobo, Manuel Jesús Herrera-Viedma, Enrique Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain

ISBN: (纸本)9781643683164

Achieving a good agreement level between decision-makers is a crucial point to solve group decision-making processes. Habitually, it is the duty of the moderator, a person in charge of assuring that the consensus reaching process is conducted correctly. This person also offers advice to the decision-makers with the objective that they modify their assessments and narrow their differences. A great number of theoretical models have been introduced to help or substitute the moderator's tasks. However, few of them have been implemented in practice. In this study, we present a web group decision support system helping, and even substituting, the moderator's functions during the whole decision-making process. This system is based on the granular computing paradigm to improve both the consistency and the consensus achieved between the decision-makers. In addition, the system improves them with the possible minimum adjustment, i.e., it tries to modify the decision-makers' assessments as minimum as possible. This group decision support system provides a web interface allowing to conduct group decision-making processes in which the decision-makers do not have the choice to meet together physically. © 2022 The authors and IOS Press. All rights reserved.

关键词： Decision support systems

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：