检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Song, Shuang Morelli, Luca Wu, Xinyi Qin, Rongjun Albanwan, Hessah Remondino, Fabio Geospatial Data Analytics Lab The Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus United States Department of Electrical and Computer Engineering The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States Trento Italy Department of Civil Environmental and Mechanical Engineering University of Trento Italy Civil Engineering Department Kuwait University Kuwait

A critical step in the digital surface models (DSM) generation is feature matching. Off-track (or multi-date) satellite stereo images, in particular, can challenge the performance of feature matching due to spectral distortions between images, long baseline, and wide intersection angles. Feature matching methods have evolved over the years from handcrafted methods (e.g., SIFT) to learning-based methods (e.g., SuperPoint and SuperGlue). In this paper, we compare the performance of different features, also known as feature extraction and matching methods, applied to satellite imagery. A wide range of stereo pairs (~ 500) covering two separate study sites are used. SIFT, as a widely used classic feature extraction and matching algorithm, is compared with seven deep-learning matching methods: SuperGlue, LightGlue, LoFTR, ASpanFormer, DKM, GIM-LightGlue, and GIM-DKM. Results demonstrate that traditional matching methods are still competitive in this age of deep learning, although for particular scenarios learning-based methods are very promising. Copyright © 2024, The Authors. All rights reserved.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence Maximization 40

BIM: Improving Graph Neural Networks with Balanced Influence...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Wentao Gao, Xinyi Yang, Ling Cao, Meng Huang, Ping Shan, Jiulong Yin, Hongzhi Cui, Bin Peking University Center for Machine Learning Research China Institute of Advanced Algorithms Research Shanghai China National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Peking University Key Lab of High Confidence Software Technologies China Apple Inc. Institute of Computational Social Science Peking University Qingdao China

ISBN: (纸本)9798350317152

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Text-Based Image Retrieval System Using Semantic Visual Content for Re-Ranking

SSRN

引用

SSRN 2024年

作者： Topcu, Berkay Mıtıncık, Alper Erdem, Merve Gülnaz Yanikoglu, Berrin Department of Advanced Analytics Yıldız Tech İstanbul34692 Turkey Artificial Intelligence and Data Analytics Turkcell Technology İstanbul34854 Turkey Faculty of Engineering and Natural Sciences Sabancı University İstanbul34956 Turkey Sabancı University İstanbul34956 Turkey

We address the problem of retrieving relevant images from the web in response to a text query. Text-based image retrieval is a challenging multi-modal problem that requires understanding of the user-intent from a few keywords and a semantic understanding of the images to predict relevance. In this paper, we present the hybrid search approach of the Turkcell-Yaani Search Engine, which was the leading search engine for queries in the Turkish language in 2017-2022. With over 1 million monthly users and processing millions of requests per month, its hybrid image search approach demonstrates the practical relevance and effectiveness of integrating text and visual information for enhanced image retrieval. The initial stage of the system focuses on retrieving images by comparing the query text with textual information associated with previously crawled and indexed images. The second stage aims to address the limitations of relying solely on text-based information by incorporating the post-processing steps based on semantic analysis of retrieved images. This stage, which is the main contribution of this paper, involves clustering, filtering and reordering the retrieved images using their embedded representations that are obtained from pretrained deep neural networks. The experimental results show that incorporating visual content improves the performance of the text-based retrieval engine significantly. © 2024, The Authors. All rights reserved.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Advanced VANET Technology for Emergency Vehicle Safety in Time-Critical Scenario

Advanced VANET Technology for Emergency Vehicle Safety in Ti...

引用

International Conference on Science Technology engineering and Management (ICONSTEM)

作者： Murali N D. Beulah David Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamilnadu India Department of Data Analytics Saveetha School of Engineering SIMATS Institute of Information Technology Chennai Tamilnadu

The most pressing issue with ITS is minimal latency in communication between vehicles, especially given that unstable traffic flow and road safety are two of their main concerns. Because to these problems, I have concentrated my study on employing a vehicular ad hoc network to track speedy object detection and provide the quickest warning to drivers. These systems require ongoing monitoring to function properly, making it possible to use machine learning techniques on vast amounts of data produced by various VANET applications. Machine learning is a technique used to prevent accidents for emergency vehicles by automatically learning and improving the system's rapid object detection stage in situations with high traffic. Our methods effectively implement the VANET aim by providing efficient unsupervised learning of the collected data. In this research, we suggested a unique real-time (DT-YOLO) algorithm-based automatic discovering vehicle gap approach for detecting and identifying objects in congested metropolitan regions. By using VANET technologies, we were able to address traffic, communication, and safety concerns in metropolitan areas. We investigated, using DT-YOLO technology, how these problems may be resolved in a transparent object-tracking system via machine learning techniques. Fast-moving EVs have a high probability of finding a gap to let the driver to make a decision. Moreover, a case study demonstrating a VANET-based scenario of nearest-object and gap-finding to flee from congested traffic with the ideal vehicle moment is shown. The paper examined current challenges and future directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Residual minimization formulations for model reduction of steady hypersonic flow

Residual minimization formulations for model reduction of st...

引用

AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2023

作者： Van Heyningen, R. Loek Ching, David S. Blonigan, Patrick J. Parish, Eric J. Rizzi, Francesco Massachusetts Institute of Technology Department of Aeronautics and Astronautics CambridgeMA02139 United States Sandia National Laboratories Thermal/Fluid Science and Engineering MS 9042 LivermoreCA94550 United States Sandia National Laboratories Extreme-Scale Data Science and Analytics MS 9060 LivermoreCA94550 United States Sandia National Laboratories LivermoreCA94550 United States NexGen Analytics SheridanWY82801 United States

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

Computational simulations of high-speed flow play an important role in the design of hypersonic vehicles, for which experimental data are scarce;however, high-fidelity simulations of hypersonic flow are computationally expensive. Reduced order models (ROMs) have the potential to make many-query problems, such as design optimization and uncertainty quantification, tractable for this domain. Residual minimization-based ROMs, which formulate the projection onto a reduced basis as an optimization problem, are one promising candidate for model reduction of large-scale fluid problems. This work analyzes whether specific choices of norms and objective functions can improve the performance of ROMs of hypersonic flow. Specifically, we investigate the use of dimensionally consistent inner products and modifications designed for convective problems, including 1 minimization and constrained optimization statements to enforce conservation laws. Particular attention is paid to accuracy for problems with strong shocks, which are common in hypersonic flow and challenging for projection-based ROMs. We demonstrate that these modifications can improve the predictability and efficiency of a ROM, though the impact of such formulations depends on the quantity of interest and problem considered. © 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

IoT Smart Door System with Motion Sensing and Facial Recognition

IoT Smart Door System with Motion Sensing and Facial Recogni...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Muhammad Kamil Hamzah NorakmarArbain Sulaiman Murizah Kassim Shuria Saaidin Suhaili Beeran Kutty School of Electrical Engineering College of Engineering Universiti Teknologi MARA Shah Alam Selangor Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Shah Alam Selangor Malaysia

ISBN: (数字)9798350382310

ISBN: (纸本)9798350382327

The advancement of technology has brought about significant transformations in various domains, including home security systems. This study has developed a system that enhances the functionality and security of smart doors using Internet of Things (IoT) technology called IoT Smart Door System with Motion Sensing and Visual Facial Recognition. The smart door system integrates multiple access control mechanisms, including keypad entry and remote access via a mobile application called Blynk. Additionally, it incorporates a motion sensor that triggers a camera to capture images of individuals approaching the door. These images are sent as notifications to the owner’s smartphone, enabling them to visually verify the visitor’s identity and the system to inform the condition of the door access. The system enhances home security by providing real-time monitoring and control over door access. The prototype implementation of the system allows for evaluating critical parameters such as response time, security, scalability, and user experience. The results obtained from testing provide valuable insights into the strengths and limitations of the system, enabling further refinement and optimization. This method can transform home security systems, enhancing homeowners’ convenience and safety environments.

关键词： Access control Visualization Face recognition Authentication Speech recognition Transforms User experience

来源：评论

学校读者我要写书评

暂无评论

Customized Movie Recommendation for Enhanced Entertainment

Customized Movie Recommendation for Enhanced Entertainment

引用

Cybernation and Computation (CYBERCOM), International Conference on

作者： M.S. Minu Srikar Talapalli Saahithi Chevuri Medhasri T.S. Department of Computer Science Engineering SRM Institute of Science And Technology Ramapuram Chennai India Department of Computer Science Engineering with Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331542344

ISBN: (纸本)9798331542351

The surging popularity of online movie databases has created a challenge for viewers: choosing a film from a massive library can be overwhelming. In this paper, it proposes to design a new hybrid movie recommendation powered by machine learning techniques as a solution to improve user experience. Among those techniques, two are combined into this paper: content-based filtering, using the real features of a movie such as genre and a director, and collaborative filtering, which uses the rating provided by users. This hybrid approach thus improves the intrinsic weaknesses that reside in both these methods individually. On the other hand, content-based filtering tends to reduce exploration to movies of the exact type one is doing well at, whereas, inversely, collaborative filtering settings often mean that a user will be exposed only to films within his or her already-recognized taste profile. It is expected that the proposed hybrid system will solve both problems by balancing this line between exploring familiar cinematic territory and making new recommendations based on both user preferences and the entire collective intelligence of the user base. The approach would aim to enrich user satisfaction by facilitating the selection of movies and providing a richer and more diversified movie-viewing experience.

关键词： Hands Filtering Collaborative filtering Transforms Machine learning Motion pictures User experience Libraries Hamming distances Recommender systems

来源：评论

学校读者我要写书评

暂无评论

De-identification of Thai Free-text Clinical Notes 15

De-identification of Thai Free-text Clinical Notes

引用

15th Biomedical engineering International Conference, BMEiCON 2023

作者： Suvirat, Kerdkiat Chairat, Sawrawit Horsiritham, Kanakorn Kongkamol, Chanon Chaichulee, Sitthichok Prince of Songkla University Faculty of Medicine Department of Biomedical Sciences and Biomedical Engineering Songkhla Thailand Prince of Songkla University Division of Digital Innovation and Data Analytics Faculty of Medicine Songkhla Thailand Prince of Songkla University Faculty of Medicine Department of Family Medicine and Preventive Medicine Songkhla Thailand

ISBN: (纸本)9798350345247

The use of electronic health record (EHR) systems enables the storage of extensive historical patient data. However, accessing this data for secondary use is limited due to the presence of personally identifiable information (PII) and protected health information (PHI), which raises ethical concerns and requiring compliance with data protection regulations. In the United States, Health Insurance Portability and Accountability Act (HIPAA) governs PHI use, mandating strict security and privacy measures. De-identification research must follow HIPAA guidelines to safeguard patient confidentiality. Similarly, in Thailand, the Personal data Protection Act (PDPA) regulates personal data, including health information. Complying with the PDPA is crucial for research on Thai patient data, ensuring adherence to data de-identification provisions. This study investigated the use of transformer-based language models for the de-identification of Thai clinical notes. We used a dataset comprising 6,134 clinical notes, with PHI entities annotated by experts. We explored three pretrained language models: Multilingual BERT, WangChanBERTa, and MEDPSU-RoBERTa, for de-identification purposes. The results demonstrate that the model based on MEDPSU-RoBERTa outperforms the other models in overall de-identification performance, emphasizing the significance of domain-specific training data. It achieved a precision of 0.9320, a recall of 0.9718, and a F1 score of 0.9552. Our algorithm was able to identify and remove six PHI categories: age, contact, datetime, identifier, location, and name. The study also confirms the potential of language models for effective de-identification and highlights the benefits of domain-specific training for anonymizing clinical text. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Findings of shared task on Sentiment Analysis and Homophobia Detection of YouTube Comments in Code-Mixed Dravidian Languages 22

Findings of shared task on Sentiment Analysis and Homophobia...

引用

Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation

作者： Subalalitha Chinnaudayar Navaneethakrishnan Bharathi Raja Chakravarthi Kogilavani Shanmugavadivel Malliga Subramanian Prasanna Kumar Kumaresan Bharathi Lavanya Sambath Kumar Rahul Ponnusamy SRM Institute of Science and Technology India Insight Centre for Data Analytics National University of Galway Ireland Kongu Engineering College India Indian Institute of Information Technology and Management-Kerala India SSN College of Engineering India Techvantage Analytics India

ISBN: (纸本)9798400700231

We present an overview of sentiment analysis and homophobia detection of YouTube comments in code-mixed Dravidian languages in this paper. We provide the details of this task and the submitted systems for the tasks. We introduce two studies: task A for detecting sentiment analysis and task B on homophobia detection, which is organized by the FIRE 2022. A total of 95 participants registered for the shared task, 13 teams finally submitted their results for task-A a, and 10 teams submitted their results for task B. The teams explored tasks A and B using traditional machine learning and deep learning models. Most of the benchmark systems have been analyzed by participants capable of handling code-mixed scenarios in Dravidian languages.

关键词： datasets Homophobia Sentiment Evaluations

来源：评论

学校读者我要写书评

暂无评论

Fast Moving Consumer Goods Object Detection Using YOLOV8

Fast Moving Consumer Goods Object Detection Using YOLOV8

引用

Electronic Systems and Intelligent Computing (ICESIC), International Conference on

作者： A. Umamageswari Mukund. P.U Abhishek. V.B Y. Devi Vaishnavi Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering With Specialization in Big Data Analytics SRM Institute of Science and Technology Ramapuram Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

The basis of this project is to investigate whether the YOLO, an object detection algorithm where 'You Only Look Once' constitutes the name, could be applied to develop FMCG management; together with the management of FMCG, it becomes the gateway to increasing retail precision, efficiency, and agility. Under real-time processing, the system detects and counts FMCG products on retail shelves with an accuracy rate of 92.5%. This accuracy ensures that the optimum stock levels are maintained and there will be no discrepancies. The system processes video feeds at 0.08 seconds per frame, thus allowing inventory data to be updated in real-time to enable quick, data-driven decisions. YOLO's flexibility ensures consistent performance across different store layouts and product types. This system integrates with other retail management tools and allows integrating inventory data in the real time. This means that it would be made available with invaluable insights which would prevent stock depletion while helping to curtail costs. This project takes YOLO ahead of just being a game changer in the FMCG inventory management while operating to reduce expenses and customer satisfaction due to product availability.

关键词： YOLO Training Accuracy Scalability Refining Streaming media Logic gates Real-time systems Mobile handsets 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：