检索结果-内蒙古大学图书馆

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： P B Hemanthkumar Ruth Moly Benjamin Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

Railways often faces the challenge of obstructions on the tracks especially passing through the forest area as not much precautions or announcements will be given to there also animals won't be able to understand the arrival of the train. Which results a significant safety risk to trains, travelling passengers and intruding creatures. This paper addresses for identifying the obstacles on railway tracks especially in forest areas which helps to take necessary actions to avoid those obstructions above. The system needs a camera, that has to be installed on the adjacent sides of the railway path which captures the real time data of the track. This captured data is then processed and analyzed to identify any potential obstruction on the tracks using Convolutional Neural Networks You Only Look Once version 8 is used. YOLOv8 is a high speed and accurate model; is trained with a custom dataset which is proposed in this paper. If any obstruction is detected it will inform to the train pilot and nearest stations for testing purpose mailing service is used which helps in taking necessary actions. With appropriate alerts will improve safety and efficiency on railway tracks in the forest areas by providing real time information about potential obstructions on the tracks. This directly helps in preventing accidents and delays. Ensures a safer and more reliable railway network.

关键词： YOLO Training Accuracy Computational modeling Forestry Streaming media Real-time systems data models Safety Object recognition

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

arXiv

引用

arXiv 2024年

作者： Shiri, Fatemeh Guo, Xiao-Yu Far, Mona Golestan Yu, Xin Haffari, Gholamreza Li, Yuan-Fang Department of Data Science & AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia School of Electrical Engineering and Computer Science University of Queensland Australia

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs’ spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs’ spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning. © 2024, CC BY.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Enhanced Radiological Anomaly Detection using Optimized YOLO-NAS Model

Enhanced Radiological Anomaly Detection using Optimized YOLO...

引用

Advances in Modern Age Technologies for Health and Engineering science (AMATHE), International Conference on

作者： Leka Shree J Emmanuel Joy Sri Ram M S Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350371567

ISBN: (纸本)9798350371574

Chest X-rays are commonly used to detect lung diseases. Chest radiographs often have a lot of perceptual errors. The application of image processing in diagnosing lung diseases has improved medical imaging. This has also enabled the creation of databases for classifying chest radiographs. However, current methods are not accurate enough to reliably detect anomalies. Aimed at improving the shortcomings of existing techniques, the proposed approach uses the Automated Neural Architecture Construction (AutoNAC) engine, a proprietary of Neural Architecture Search (NAS). Comparative evaluations against established models, including YOLOv3, YOLOv5, YOLOv7, and YOLOv8, showcase the superiority of YOLO-NAS in mean Average Precision (mAP@0.5), precision, and recall metrics. The originality of this study lies in introducing NAS specifically AutoNAC, to optimize neural network architectures for chest X-ray anomaly detection, marking a significant advancement in diagnostic capabilities in medical imaging.

关键词： YOLO Pulmonary diseases X-rays Reliability Diagnostic radiography Anomaly detection X-ray imaging

来源：评论

学校读者我要写书评

暂无评论

data Assimilation for Microstructure Evolution in Kinetic Monte Carlo 152nd

Data Assimilation for Microstructure Evolution in Kinetic Mo...

引用

152nd Annual Meeting and Exhibition of The Minerals, Metals and Materials Society, TMS 2023

作者： Tran, Anh Wang, Yan Rodgers, Theron Scientific Machine Learning Sandia National Laboratories AlbuquerqueNM United States Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332 United States Computational Materials and Data Science Sandia National Laboratories AlbuquerqueNM United States

ISBN: (纸本)9783031225239

Modeling grain growth has been a subject of interest in computational material science, as it occurs in thermal-based processing methods such as annealing and sintering. Kinetic Monte Carlo with Potts model is often used as an integrated computational materials engineering (ICME) grain growth model and can generate high-fidelity synthetic microstructures. In this paper, we offer a data-driven stochastic calculus perspective on the kinetics of grain growth and model the microstructure evolution through the lens of stochastic differential equations, based on Langevin dynamics and Fokker-Planck equation to forecast the grain size distribution. We demonstrate that our proposed approach agrees reasonably well with the hybrid Potts-phase field model using SPPARKS in forecasting the long-term evolution of grain size distribution. © 2023, The Minerals, Metals & Materials Society.

关键词： Grain growth

来源：评论

学校读者我要写书评

暂无评论

Identifying general mechanism shifts in linear causal representations 24

Identifying general mechanism shifts in linear causal repres...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Tianyu Chen Kevin Bello Francesco Locatello Bryon Aragam Pradeep Ravikumar Department of Statistics and Data Sciences University of Texas at Austin Booth School of Business University of Chicago and Machine Learning Department Carnegie Mellon University Institute of Science and Technology Austria Booth School of Business University of Chicago Machine Learning Department Carnegie Mellon University

ISBN: (纸本)9798331314385

We consider the linear causal representation learning setting where we observe a linear mixing of d unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent factors as well as the underlying structural causal model over them, up to permutation and scaling, provided that we have at least d environments, each of which corresponds to perfect interventions on a single latent node (factor). After this powerful result, a key open problem faced by the community has been to relax these conditions: allow for coarser than perfect single-node interventions, and allow for fewer than d of them, since the number of latent factors d could be very large. In this work, we consider precisely such a setting, where we allow a smaller than d number of environments, and also allow for very coarse interventions that can very coarsely change the entire causal graph over the latent factors. On the flip side, we relax what we wish to extract to simply the list of nodes that have shifted between one or more environments. We provide a surprising identifiability result that it is indeed possible, under some very mild standard assumptions, to identify the set of shifted nodes. Our identifiability proof moreover is a constructive one: we explicitly provide necessary and sufficient conditions for a node to be a shifted node, and show that we can check these conditions given observed data. Our algorithm lends itself very naturally to the sample setting where instead of just interventional distributions, we are provided datasets of samples from each of these distributions. We corroborate our results on both synthetic experiments as well as an interesting psychometric dataset. The code can be found at https://***/TianyuCodings/iLCS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TC-PDM: Temporally Consistent Patch Diffusion Models for Infrared-to-Visible Video Translation

arXiv

引用

arXiv 2024年

作者： Doan, Anh-Dzung Phan, Vu Minh Hieu Gupta, Surabhi Wagner, Markus Chin, Tat-Jun Reid, Ian Australian Institute for Machine Learning The University of Adelaide Australia Department of Data Science and Artificial Intelligence Monash University Australia Safran Electronics and Defense Australasia Australia

Infrared imaging offers resilience against changing lighting conditions by capturing object temperatures. Yet, in few scenarios, its lack of visual details compared to daytime visible images, poses a significant challenge for human and machine interpretation. This paper proposes a novel diffusion method, dubbed Temporally Consistent Patch Diffusion Models (TC-DPM), for infrared-to-visible video translation. Our method, extending the Patch Diffusion Model, consists of two key components. Firstly, we propose a semantic-guided denoising, leveraging the strong representations of foundational models. As such, our method faithfully preserves the semantic structure of generated visible images. Secondly, we propose a novel temporal blending module to guide the denoising trajectory, ensuring the temporal consistency between consecutive frames. Experiment shows that TC-PDM outperforms state-of-the-art methods by 35.3% in FVD for infrared-to-visible video translation and by 6.1% in AP50 for day → night object detection. Our code is publicly available at https://***/dzungdoan6/tc-pdm Copyright © 2024, The Authors. All rights reserved.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Smart Finance: An overview of Artificial Intelligence Integration in Fintech 2

Smart Finance: An overview of Artificial Intelligence Integr...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Akre, Parth Dhananjay Pacharaney, Utkarsha Siraskar, Warsha Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Yeshwantrao Chavan College of Engineering Maharashtra Nagpur441110 India

ISBN: (纸本)9798331528713

The role of FinTech in advancing contemporary economies, societies, and technologies is growing. Smart FinTech is the next wave of FinTech that leverages artificial intelligence and data science methodologies to drive major advancements in fields including blockchain, cryptocurrencies, InsurTech, PayTech, BankingTech, TradeTech, LendTech, InsurTech, WealthTech, and RiskTech. An overview of these domains, as well as the artificial intelligence and data science techniques applied, is given in this paper. These techniques include augmentation, optimization, privacy-preserving processing, deep learning, federated learning, and intelligent interactions, complex system methods, mathematical approaches, knowledgeable communication, recognition and responses, and data analytics. This study offers a thorough analysis of smart financial companies, the obstacles they face, the smart FinTech environment, the artificial intelligence and data science methods that make smart FinTech possible, and potential future research areas for the artificial intelligence and data science community. To improve comprehension and analysis, the work makes use of visual aids such as figures and tables. The relevance of data quality, including data augmentation and manipulation, as well as enhancing fairness and decision-support, is emphasized in the study for financial firms. It also covers ethical and explicable FinTech, with a focus on privacy preservation, accountability, openness, and objectivity in FinTech and business designs. The potential for more research and innovation at the heart of analytics, data science, and FinTech is highlighted in the paper's conclusion. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Review on machine learning Assisted Drying Behaviour Prediction of Agricultural Seeds and Fruits 2

A Review on Machine Learning Assisted Drying Behaviour Predi...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Jawre, Sandip Verma, Prateek Kothare, Chandrakant B. Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India Shri Shankarprasad Agnihotri College of Engineering Department of Mechanical Engineering Maharashtra Wardha India

ISBN: (纸本)9798331528713

machine learning approaches have been more popular in recent years across many scientific and engineering fields, with the potential to improve drying behavior and thermal property predictions in terms of accuracy and efficiency. Agricultural seeds and fruits must be handled carefully after harvest because drying has a considerable impact on their quality, shelf life, and overall worth. To optimize drying processes and guarantee product quality, drying kinetics and thermal characteristics must be accurately predicted. This review article outlines the basic principles of drying, emphasizes their significance in determining the ideal drying conditions, and provides a thorough overview of the application of machine learning methods for predicting the drying kinetics and thermal properties of agricultural seeds and fruits. Then, in the context of their applications to drying prediction, a summary of several machine learning approaches, including artificial neural networks, support vector machines, and decision trees have been discussed. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Review of machine learning Algorithms in Diabetes Management 4

A Review of Machine Learning Algorithms in Diabetes Manageme...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Gayaki, Unnati Daronde, Subodh Tale, Abhay Barhate, Aditya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha India Faculty of Engineering and Technology Department of Biomedical Engineering Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India

ISBN: (纸本)9798331523923

Diabetes is a prevalent and chronic disease affecting millions worldwide, posing significant challenges in its management and treatment. This review article aims to explore the current and potential future roles of machine learning (ML) in diabetes management, focusing on progress, applications, and challenges. It discusses various ML techniques, including support vector machines (SVM), logistic regression, decision trees, ensemble methods, and advanced deep learning approaches such as long short-term memory (LSTM) networks and convolutional neural networks (CNN). These methods have demonstrated benefits in analytics, patient monitoring, decision support systems, personalised treatment, and patient engagement. However, significant challenges persist, such as computational complexity, data quality, limited interoperability of systems, and ethical concerns regarding AI use in healthcare. The article addresses these challenges by fostering collaboration between AI implementers and health care professionals. This collaboration is essential to develop long-term, legally compliant, and solution-oriented frameworks that enhance patient care and diabetes management and pave the way for more efficient and ethical AI applications in healthcare. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

machine learning With data Assimilation and Uncertainty Quantification for Dynamical Systems:A Review

引用

IEEE/CAA Journal of Automatica Sinica 2023年第6期10卷 1361-1387页

作者： Sibo Cheng César Quilodrán-Casas Said Ouala Alban Farchi Che Liu Pierre Tandeo Ronan Fablet Didier Lucor Bertrand Iooss Julien Brajard Dunhui Xiao Tijana Janjic Weiping Ding Yike Guo Alberto Carrassi Marc Bocquet Rossella Arcucci Data Science Institute Department of ComputingImperial College LondonSW72AZ London Department of Earth Science and Engineering Imperial College LondonSW72AZ London Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China the IMT Atlantique Lab-STICCUMR CNRS 6285France and OdysseyInria/IMTFrance.P.Tandeo is also with RIKEN Center for Computational ScienceKobeJapan the CEREA École des Ponts and EDF R&Dîle-de-FranceFrance the Laboratoire Interdisciplinaire des Sciences du Numérique CNRSParis-Saclay UniversityF-91403OrsayFrance the Electricitéde France(EDF) 78401 ChatouFranceInstitut de Mathématiques de Toulouse31062 ToulouseFrance and SINCLAIR AI LabSaclayFrance the Sorbonne University ParisFranceand also with Nansen Environmental and Remote Sensing Center(NERSC)BergenNorway the School of Mathematical Sciences Tongji UniversityShanghai 200092China the Mathematical Institute for Machine Learning and Data Science KU Eichstaett-IngolstadtBavariaGermany the School of Information Science and Technology Nantong UniversityNantong 226019China the Department of Physics and Astronomy“Augusto Righi” University of Bologna40124 BolognaItaly

data assimilation(DA)and uncertainty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal *** applications span from computational fluid dynamics(CFD)to geoscience and climate ***,much effort has been given in combining DA,UQ and machine learning(ML)*** research efforts seek to address some critical challenges in high-dimensional dynamical systems,including but not limited to dynamical system identification,reduced order surrogate modelling,error covariance specification and model error correction.A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains,resulting in the necessity for a comprehensive *** paper provides the first overview of state-of-the-art researches in this interdisciplinary field,covering a wide range of *** review is aimed at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models,but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their ***,this article has a special focus on how ML methods can overcome the existing limits of DA and UQ,and vice *** exciting perspectives of this rapidly developing research field are also *** Terms-data assimilation(DA),deep learning,machine learning(ML),reduced-order-modelling,uncertainty quantification(UQ).

关键词： assimilation overcome apply

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：