Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights
The Ohio State University(俄亥俄州立大学)
Sobhan Moosavi, Mohammad Hossein Samavatian, Srinivasan Parthasarathy, Radu Teodorescu, Rajiv Ramnath
备注:
In Proceedings of the 27th ACM SIGSPATIAL, International Conference on Advances in Geographic Information Systems (2019). arXiv admin note: substantial text overlap with arXiv:1906.05409
Reducing traffic accidents is an important public safety challenge, therefore, accident analysis and prediction has been a topic of much research over the past few decades. Using small-scale datasets with limited coverage, being dependent on extensive set of data, and being not applicable for real-time purposes are the important shortcomings of the existing studies. To address these challenges, we propose a new solution for real-time traffic accident prediction using easy-to-obtain, but sparse data. Our solution relies on a deep-neural-network model (which we have named DAP, for Deep Accident Prediction); which utilizes a variety of data attributes such as traffic events, weather data, points-of-interest, and time. DAP incorporates multiple components including a recurrent (for time-sensitive data), a fully connected (for time-insensitive data), and a trainable embedding component (to capture spatial heterogeneity). To fill the data gap, we have - through a comprehensive process of data collection, integration, and augmentation - created a large-scale publicly available database of accident information named US-Accidents. By employing the US-Accidents dataset and through an extensive set of experiments across several large cities, we have evaluated our proposal against several baselines. Our analysis and results show significant improvements to predict rare accident events. Further, we have shown the impact of traffic information, time, and points-of-interest data for real-time accident prediction.
LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data
Harbin Institute of Technology(哈尔滨工业大学);University of Iowa(爱荷华大学);Northern Illinois University(北伊利诺伊大学);Massachusetts Institute of Technology(麻省理工学院);Logistics and Supply Chain MultiTech R&D Centre(物流及供应链多元技术研发中心)
Accident Impact Prediction based on a deep convolutional and recurrent neural network model
Department of Industrial Engineering, Sharif University of Technology(谢里夫理工大学工业工程系);School of Industrial and System Engineering, Georgia Institute of Technology(佐治亚理工学院工业与系统工程学院);Department of Computer Science and Engineering, Ohio State University(俄亥俄州立大学计算机科学与工程系)
Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs
GIPSA-lab(GIPSA实验室);UGA(格勒诺布尔阿尔卑斯大学);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔国立高等物理、数学与信息学院);L2S(信号与系统实验室);CentraleSupélec(中央理工-高等电力学院);University of Paris Saclay(巴黎萨克雷大学)
MAPN: Enhancing Heterogeneous Sparse Graph Representation by Mamba-based Asynchronous Aggregation
School of Computer Science, Fudan University(复旦大学计算机科学学院);School of Software, Fudan University(复旦大学软件学院);Shanghai Key Laboratory of Data Science(上海数据科学重点实验室)
Learnable Sparse Customization in Heterogeneous Edge Computing
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Institute for Network Sciences and Cyberspace, Tsinghua University(清华大学网络科学与网络空间研究院);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Zhongguancun Laboratory(中关村实验室)
SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
Meta;Center of Excellence for Molecular Prediction of IBD (PREDICT)(分子预测IBD中心(PREDICT));Department of Clinical Medicine, Aalborg University(临床医学系,奥胡斯大学);Department of Gastroenterology & Hepatology, Aalborg University Hospital(消化内科与肝病科,奥胡斯大学医院);University of Copenhagen(哥本哈根大学);Imperial College London(伦敦帝国理工学院);Department of Biomedical Engineering, Tel-Aviv University(生物医学工程系,特拉维夫大学);Sagol School of Neuroscience, Tel-Aviv University(神经科学学院,特拉维夫大学)
UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models
School of Computer Science and Statistics, Trinity College Dublin, Ireland(特里尼蒂学院都柏林分校计算机科学与统计学学院);School of Computer Science, University College Dublin, Ireland(都柏林大学学院计算机科学学院)
A Sparse-Attention Deep Learning Model Integrating Heterogeneous Multimodal Features for Parkinson's Disease Severity Profiling
School of Computing, Mathematics, and Engineering, Charles Sturt University(计算、数学与工程学院,查尔斯·斯特劳特大学);School of Dentistry and Medical Sciences, Charles Sturt University(牙科学院与医学科学学院,查尔斯·斯特劳特大学);AI and Cyber Futures Centre (AICF)(人工智能与未来技术中心(AICF));Hawkins Clinic General Medical Practice(霍金斯诊所普通医疗实践)
Semantic4Safety: Causal Insights from Zero-shot Street View Imagery Segmentation for Urban Road Safety
School of Geospatial Engineering and Science, Sun Yat-sen University(地理空间工程与科学学院,中山大学);School of Geographical and Earth Sciences, University of Glasgow(地理与地球科学学院,格拉斯哥大学);School of Economics and Management, Shanxi University(经济学与管理学院,山西大学)
混合专家模型(Mixture of Experts,MoE)是在回归、聚类和分类等统计学习问题中为异构数据建模的成功模型。通常通过期望最大化算法用极大似然估计拟合,因此它们在高维问题中的应用仍然具有挑战性。我们考虑在MoE模型的拟合和特征选择的问题,并提出了一个正则化的极大似然估计的方法,鼓励稀疏解决方案的异质回归数据模型与潜在的高维预测。与最先进的正则化MLE MoE,所提出的建模不需要近似的惩罚函数。本文提出了两种混合期望最大化算法:期望-优化-最大化(EM/MM)算法和带有坐标上升算法的期望最大化算法。所提出的算法允许自动获得稀疏的解决方案,而无需阈值,并避免矩阵求逆,允许单变量参数更新。实验研究表明,该算法在恢复实际稀疏解、参数估计和异质回归数据聚类等方面具有良好的性能。
我们研究了高维异质数据分析中统计精度和计算易处理性之间的基本权衡。作为实例,我们研究了稀疏高斯混合模型、稀疏线性回归混合模型和稀疏相位恢复模型。对于这些模型,我们利用一个基于甲骨文的计算模型,建立无故障的计算可行的极大极小下界,量化的最小信号强度的存在所需的任何算法,这是计算上易于处理和统计上准确的。我们的分析表明,计算上可行的极大极小风险和经典的存在显着的差距。这些差距量化了我们在数据异质性存在的情况下为实现计算易处理性而必须付出的统计代价。我们的研究结果涵盖了检测,估计,支持恢复和聚类的问题,此外,解决了Azizyan et al.(2013,2015); Verzelen and Arias-Castro(2017); Cai et al.(2016)的几个问题。有趣的是,我们的研究结果揭示了异构数据分析中一个新的但反直觉的现象,即更多的数据可能会导致更低的计算复杂性。
Random matrix theory of sparse neuronal networks with heterogeneous timescales
Complex Systems, Department of Physics, Faculty of Science, Chulalongkorn University, Bangkok, Thailand;High Energy Physics Research Unit, Faculty of Science, Chulalongkorn University, Bangkok, Thailand;International Solvay Institutes, Brussels, Belgium;Mark Kac Center for Complex Systems Research, Jagiellonian University, Krak\'ow, Poland;Department of Mathematics, King's College London, London, UK
FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models
King Abdullah University of Science and Technology (KAUST)(国王阿卜杜勒-阿齐兹大学科学与技术学院);SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence (SDAIA-KAUST AI)(SDAIA-KAUST数据科学与人工智能卓越中心)