检索结果-内蒙古大学图书馆

Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zeng, Zelong Wang, Zheng Yang, Fan Satoh, Shin'ichi The School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China The Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan The Digital Content and Media Sciences Research Division National Institute of Informatics Japan

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark, we aim to achieve cross-view geo-localization by searching out its corresponding satellite-view images. Specifically, the challenge comes from the gap between ground-view and satellite-view, which includes not only large viewpoint changes (some parts of the landmark may be invisible from front view to top view) but also highly irrelevant background (the target landmark tend to be hidden in other surrounding buildings), making it difficult to learn a common representation or a suitable mapping. To address this issue, we take advantage of drone-view information as a bridge between ground-view and satellite-view domains. We propose a Peer Learning and Cross Diffusion (PLCD) framework. PLCD consists of three parts: 1) a peer learning across ground-view and drone-view to find visible parts to benefit ground-drone cross-view representation learning;2) a patch-based network for satellite-drone cross-view representation learning;3) a cross diffusion between ground-drone space and satellite-drone space. Extensive experiments conducted on the University-Earth and University-Google datasets show that our method outperforms state-of-the-arts significantly. Copyright © 2022, The Authors. All rights reserved.

关键词： Satellites

Rem sleep stage detection of parkinson’s disease patients with rbd 23rd

学校读者我要写书评

暂无评论

Rem sleep stage detection of parkinson’s disease patients w...

23rd International Conference on Business Information Systems, BIS 2020

作者： Bisgin, Pinar Houta, Salima Burmann, Anja Lenfers, Tim Fraunhofer Institute for Software and Systems Engineering HealthCare Dortmund Germany Department of Medical Informatics Heilbronn University Heilbronn Germany Ruprecht-Karls University Heidelberg Heidelberg Germany

ISBN: (纸本)9783030533366

REM sleep behavior disorder (RBD) is commonly associated with Parkinson’s disease. In order to find adequate therapy for affected persons and to seek suitable early Parkinson Patterns, the investigation of this phenomenon is highly relevant. The analysis of sleep is currently done by manual analysis of polysomnography (PSG), which leads to divergent scoring results by different experts. Automated sleep stage detection can help deliver accurate, reproducible scoring results. In this paper, we evaluate different machine learning models from the PSG signals for automatic sleep stage detection. The highest accuracy of 87.57% was achieved by using the Random Forest algorithm. © Springer Nature Switzerland AG 2020.

关键词： Neurodegenerative diseases

Evaluating the Inclusiveness of Artificial Intelligence software in Enhancing Project Management Efficiency – A review and examples of quantitative measurement methods

学校读者我要写书评

暂无评论

Evaluating the Inclusiveness of Artificial Intelligence Soft...

Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), International Conference on

作者： Vasileios Alevizos Ilias Georgousis Akebu Simasiku Antonis Messinis Sotiria Karypidou Dimitra Malliarou Department of Learning Informatics Managament and Ethics Karolinska Institute Stockholm Sweden Department of Computer Science MLV Research Group International Hellenic University Kavala Greece Department Of Computer Software Engineering Zambia University Ndola Zambia HEDNO SA (Hellenic Electricity Distribution Network Operator) Department of Computer Science MLV Research Group International Hellenic University IntelliSolutions Athens Greece

The escalating integration of Artificial Intelligence (AI) in various domains, especially Project Management (PM), has brought to light the imperative need for inclusivity in AI systems. This paper investigates the role of AI software in augmenting both the inclusiveness and efficiency within the realm of PM. The research pivots around specific criteria that define and measure the inclusiveness of AI in PM, highlighting how AI, when developed with inclusiveness in mind, can significantly enhance project outcomes. However, there are inherent challenges in achieving this inclusiveness, primarily due to biases embedded in AI learning databases and the design and development processes of AI systems. The study offers a comprehensive examination of AI's potential to revolutionize PM by enabling managers to concentrate more on people-centric aspects of their work. This is achieved through AI’s ability to perform tasks such as data collection, reporting, and predictive analysis more consistently and efficiently than human counterparts. However, the incorporation of AI in PM extends beyond mere efficiency; it represents a paradigm shift in the epistemology of PM, calling for a deeper understanding of AI's role and impact on society. Despite these advantages, the adoption of AI comes with significant challenges, particularly in terms of bias and inclusiveness. Biased AI learning databases, which use shared and reusable datasets, often perpetuate initially discriminatory algorithms. Moreover, unconscious biases and stereotypes of AI designers, developers, and trainers can inadvertently influence the behavior of the AI systems they create. This necessitates a paradigmatic shift in how AI systems are developed and governed to ensure they do not replicate or exacerbate existing social inequalities. The research proposes a methodological approach involving the development of criteria for inclusion and exclusion, alongside data extraction, to evaluate the inclusiveness and efficien

关键词：

Applications of Machine Learning in Diabetic Foot Ulcer Diagnosis using Multimodal Images: A Review

学校读者我要写书评

暂无评论

IAENG International Journal of Applied Mathematics 2023年第3期53卷 75页

作者： Mayya, Veena Tummala, Venkat Reddy, Chaduvula Upendra Mishra, Pranjal Boddu, Rajasekhar Olivia, Diana Kamath, S Sowmya Department of Information & Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India Department of Information & Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India Department of Software Engineering College of Computing and Informatics Haramaya University Dire Dawa Ethiopia Department of Information & Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India Department of Information Technology National Institute of Technology Karnataka SurathkalMangalore575025 India

Diabetes related complications such as Diabetic Foot Ulcers (DFU) may necessitate recurrent hospitalisations and expensive treatments. Uncontrolled diabetes can result in severe DFUs, resulting in amputation of lower limbs or feet, prolonged debilitation and diminished quality of life. Early diagnosis and proactive management are reported to significantly enhance the prognosis and reduce the onset of further complications. In this study, research works on developing clinical decision support systems (CDSS) for the identification and segmentation of DFU are systematically reviewed. The techniques employed range from traditional image processing techniques to approaches based on deep learning (DL). A taxonomy of DFU CDSSs is presented, categorised into two groups: RGB-based techniques and thermal imaging-based approaches. To the best of our knowledge, this is the first attempt at a comprehensive study of CDSSs for DFU related investigative tasks, based on different imaging modalities. We also delve into the difficulties experienced in the process of creating efficient, reliable, and accurate models for the early detection of DFU, and highlight the vast potential for further research in this emerging domain. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Diseases

Technical Debt Management: The Road Ahead for Successful software Delivery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Avgeriou, Paris Ozkaya, Ipek Chatzigeorgiou, Alexander Ciolkowski, Marcus Ernst, Neil A. Koontz, Ronald J. Poort, Eltjo Shull, Forrest Dept. of Computing Science University of Groningen Groningen Netherlands Software Engineering Institute Carnegie Mellon University PittsburghPA United States Dept. of Applied Informatics University of Macedonia Thessaloniki Greece QAware GmbH München Germany Department of Computer Science University of Victoria Victoria Canada The Boeing Company MesaAZ United States CGI Rotterdam Netherlands

Technical Debt, considered by many to be the 'silent killer' of software projects, has undeniably become part of the everyday vocabulary of software engineers. We know it compromises the internal quality of a system, either deliberately or inadvertently. We understand Technical Debt is not all derogatory, often serving the purpose of expediency. But, it is associated with a clear risk, especially for large and complex systems with extended service life: if we do not properly manage Technical Debt, it threatens to "bankrupt" those systems. software engineers and organizations that develop softwareintensive systems are facing an increasingly more dire future state of those systems if they do not start incorporating Technical Debt management into their day to day practice. But how? What have the wins and losses of the past decade of research and practice in managing Technical Debt taught us and where should we focus next? In this paper, we examine the state of the art in both industry and research communities in managing Technical Debt;we subsequently distill the gaps in industrial practice and the research shortcomings, and synthesize them to define and articulate a vision for what Technical Debt management looks like five years hence. © 2024, CC BY-NC-ND.

关键词： Industrial research

WcDT: World-centric Diffusion Transformer for Traffic Scene Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Chen He, Yangfan Tian, Aaron Xuxiang Chen, Dong Wang, Jianhui Shi, Tianyu Heydarian, Arsalan Liu, Pei Department of Computer Science and Informatics Cardiff University United Kingdom College of Libera Arts University of Minnesota - Twin Cities United States United States Agricultural & Biological Engineering Mississippi State University United States Information and Software Engineering University of Electronic Science and Technology of China China Transportation Research Institute University of Toronto Canada Link Lab & Civil and Environmental Engineering University of Virginia United States Intelligent Transportation Thrust The Hong Kong University of Science and Technology Guangzhou China

In this paper, we introduce a novel approach for autonomous driving trajectory generation by harnessing the complementary strengths of diffusion probabilistic models (a.k.a., diffusion models) and transformers. Our proposed framework, termed the "World-centric Diffusion Transformer"(WcDT), optimizes the entire trajectory generation process, from feature extraction to model inference. To enhance the scene diversity and stochasticity, the historical trajectory data is first preprocessed into "Agent Move Statement" and encoded into latent space using Denoising Diffusion Probabilistic Models (DDPM) enhanced with Diffusion with Transformer (DiT) blocks. Then, the latent features, historical trajectories, HD map features, and historical traffic signal information are fused with various transformer-based encoders that is used to enhance the interaction of agents with other elements in the traffic scene. The encoded traffic scenes are then decoded by a trajectory decoder to generate multimodal future trajectories. Comprehensive experimental results show that the proposed approach exhibits superior performance in generating both realistic and diverse trajectories, showing its potential for integration into automatic driving simulation systems. Our code is available at https://***/yangchen1997/WcDT. © 2024, CC BY.

关键词： Stochastic systems

Is larger always better? Evaluating and prompting large language models for non-generative medical tasks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Yinghao Gao, Junyi Wang, Zixiang Liao, Weibin Zheng, Xiaochen Liang, Lifang Wang, Yasha Pan, Chengwei Harrison, Ewen M. Ma, Liantao Institute of Artificial Intelligence Beihang University Beijing100191 China Centre for Medical Informatics University of Edinburgh EdinburghEH8 9YL United Kingdom Health Data Research UK United Kingdom School of Computer Science Peking University Beijing100871 China National Engineering Research Center for Software Engineering Peking University Beijing100871 China ETH Zürich Zürich8092 Switzerland

Background: The deployment of Large Language Models (LLMs) in medical fields is increasing, but few research evaluate their ability to manage both structured Electronic Health Record (EHR) data and unstructured clinical notes. This study provides a comprehensive benchmark of various models, including GPT-based LLMs, BERT-based language models, and conventional clinical predictive models to determine their efficacy in non-generative medical tasks using widely recognized datasets. Methods: We evaluated 14 language models (9 GPT-based and 5 BERT-based) alongside 7 conventional clinical predictive models on the MIMIC dataset, which encompasses comprehensive ICU patient records, and the TJH dataset, which includes EHR data from early COVID-19 patients. The performance of these models was assessed through a series of both supervised and unsupervised tasks, including mortality and readmission predictions, disease hierarchy reconstruction, and biomedical sentence matching. The study focused on comparing zero-shot prediction capabilities of LLMs with conventional models and the effectiveness of finetuned BERT-based models in handling clinical texts. Results: LLMs demonstrated promising zero-shot predictive abilities on structured EHR data when equipped with well-designed prompting strategies, often surpassing traditional models trained with limited datasets. However, in tasks involving unstructured medical texts, LLMs did not outperform existing BERT-based models. Both in supervised and unsupervised scenarios, the performance of finetuned BERT models was superior, suggesting that the additional cost and complexity of implementing LLMs might not be justifiable for non-generative tasks. Conclusion: While LLMs show significant potential in interpreting structured EHR data through zero-shot learning, their application in processing unstructured medical texts is less advantageous compared to finetuned BERT models. The findings underscore the importance of selecting appropriate mo

关键词： Clinical research

Categorical data clustering: 25 years beyond K-modes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dinh, Tai Hauchi, Wong Fournier-Viger, Philippe Lisik, Daniil Ha, Minh-Quyet Dam, Hieu-Chi Huynh, Van-Nam The Kyoto College of Graduate Studies for Informatics 7 Tanaka Monzencho Sakyo Ward Kyoto City Kyoto Japan College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen City China University of Gothenburg Medicinaregatan 1F Göteborg413 90 Sweden Japan Advanced Institute of Science and Technology 1-1 Asahidai Ishikawa Nomi Japan

The clustering of categorical data is a common and important task in computer science, offering profound implications across a spectrum of applications. Unlike purely numerical data, categorical data often lack inherent ordering as in nominal data, or have varying levels of order as in ordinal data, thus requiring specialized methodologies for efficient organization and analysis. This review provides a comprehensive synthesis of categorical data clustering in the past twenty-five years, starting from the introduction of K-modes. It elucidates the pivotal role of categorical data clustering in diverse fields such as health sciences, natural sciences, social sciences, education, engineering, and economics. Practical comparisons are conducted for algorithms having public implementations, highlighting distinguishing clustering methodologies and revealing the performance of recent algorithms on several benchmark categorical datasets. Finally, challenges and opportunities in the field are discussed. © 2024, CC BY.

关键词： Data assimilation

TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Ruiteng Wei, Jianguo Lu, Xugang Lu, Wenhuan Jin, Di Xu, Junhai Zhang, Lin Ji, Yantao Dang, Jianwu College of Intelligence and Computing Tianjin University Tianjin China Computer College Qinghai Nationalities University Xining China National Institute of Information and Communications Technology Kyoto Japan National Institute of Informatics Tokyo Japan School of Software Engineering Xi'an Jiaotong University Xi’an China

Speaker embedding is an important front-end module to explore discriminative speaker features (e.g., X-vector) for many speech applications where speaker information is needed. Current state-of-the-art backbone networks for speaker embedding are designed to aggregate multi-scale features from an utterance with multi-branch network architectures for speaker representation (e.g., ECAPA-TDNN). However, naively adding many branches of multi-scale features with the simple fully convolutional operation could not efficiently improve the performance due to the rapid increase of model parameters and computational complexity. Therefore, in the most current state-of-the-art network architectures, only a few branches corresponding to a limited number of temporal scales could be designed for speaker embeddings. To address this problem, in this paper, we propose an effective temporal multi-scale (TMS) model where multi-scale branches could be efficiently designed in a speaker embedding network almost without increasing computational costs. The new model is based on the conventional time-delay neural network (TDNN), where the network architecture is smartly separated into two modeling operators: a channel-modeling operator and a temporal multi-branch modeling operator. Adding temporal multi-scale in the temporal multi-branch operator needs only a little bit increase of the number of parameters, and thus save more computational budget for adding more branches with large temporal scales. Moreover, after the model was trained, in the inference stage, we further developed a systemic re-parameterization method to convert the multi-branch network topology into a single-path-based topology in order to increase inference speed. We investigated the performance of the new TMS method for automatic speaker verification (ASV) on in-domain (VoxCeleb) and out-of-domain (CNCeleb) conditions. Results show that the model based on the TMS method obtained a significant increase in the performance ove

关键词： Network architecture