Filters








8 Hits in 10.5 sec

A Novel Prediction Approach for Exploring PM2.5 Spatiotemporal Propagation Based on Convolutional Recursive Neural Networks [article]

Hsing-Chung Chen, Karisma Trinanda Putra, Jerry Chun-WeiLin
2021 arXiv   pre-print
This study presents a new model based on the convolutional recursive neural network to generate the prediction map.  ...  According to the idea of transformative computing, the approach we propose in this paper allows computation on the dataset obtained from massive-scale PM2.5 sensor nodes via wireless sensor network.  ...  In addition, the spatial patterns on the dataset learned by using Convolutional Neural Network (CNN) modeling.  ... 
arXiv:2101.06213v1 fatcat:gh2o7vddanfwtlhcf4tl6ghz2a

An Integrated Approach of Belief Rule Base and Deep Learning to Predict Air Pollution

Sami Kabir, Raihan Ul Islam, Mohammad Shahadat Hossain, Karl Andersson
2020 Sensors  
Hence, this paper proposes a novel predictive model that is based on the integrated approach of BRBES and Deep Learning.  ...  Belief Rule Based Expert System (BRBES), a knowledge-driven approach, is a widely employed prediction algorithm to deal with such uncertainties based on knowledge base and inference engine.  ...  Acknowledgments: This research is based on the Master's Thesis [60] of Sami Kabir, conducted at the Pervasive and Mobile Computing Laboratory, Luleå University of Technology, Skellefteå, Sweden.  ... 
doi:10.3390/s20071956 pmid:32244380 fatcat:efkzbpmr6rgapeqm62qz7otksy

PM2.5 Prediction Model Based on Combinational Hammerstein Recurrent Neural Networks

Yi-Chung Chen, Tsu-Chiang Lei, Shun Yao, Hsin-Ping Wang
2020 Mathematics  
The CHRNN comprises a based-neural network tasked with learning gradual (long-term) fluctuations in conjunction with add-on neural networks to deal with dramatic (short-term) fluctuations.  ...  Many researchers have been reporting highly accurate numerical predictions based on raw PM2.5 data imported directly into deep learning models; however, there is still considerable room for improvement  ...  [23] used micro-satellite images in conjunction with a convolutional neural network and random forest approach to estimate PM2.5 values on the surface.  ... 
doi:10.3390/math8122178 fatcat:jhfr7ckgozcznpizls4kgvfhmq

Deep Learning for Spatio-Temporal Data Mining: A Survey [article]

Senzhang Wang, Jiannong Cao, Philip S. Yu
2019 arXiv   pre-print
Recently, with the advances of deep learning techniques, deep leaning models such as convolutional neural network (CNN) and recurrent neural network (RNN) have enjoyed considerable success in various machine  ...  In this paper, we provide a comprehensive survey on recent progress in applying deep learning techniques for STDM.  ...  Based on the Linkage Network model, a novel online predictor, named Graph Recurrent Neural Network (GRNN), is designed to learn the propagation patterns in the graph.  ... 
arXiv:1906.04928v2 fatcat:4zrdtgkvirfuniq3rb2gl7ohpy

A review of machine learning applications in wildfire science and management [article]

Piyush Jain, Sean C P Coogan, Sriram Ganapathi Subramanian, Mark Crowley, Steve Taylor, Mike D Flannigan
2020 arXiv   pre-print
We also discuss the advantages and limitations of various ML approaches and identify opportunities for future advances in wildfire science and management within a data science context.  ...  Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems.  ...  Acknowledgments The motivation for this paper arose from the "Not the New Normal" BC AI Wildfire Symposium held in Vancouver, BC, on 12 October 2018.  ... 
arXiv:2003.00646v1 fatcat:5ufhtbwlsvd2rdk3ogbmqpnxuu

Spatiotemporal enabled Content-based Image Retrieval

Mariana Belgiu, Martin Sudmanns, Tiede Dirk, Andrea Baraldi, Stefan Lang
2016 International Conference on GIScience Short Paper Proceedings  
In this paper, we propose a probabilistic method for estimation of the coverage of a sensor network based on 3D vector representation of the environment.  ...  The efficiency of the coverage of a sensor network depends on optimal position of each sensor node within the network.  ...  Future Work Future research will extend our machine learning approach on Spark in the following four directions: (1) scanning a wider parameterization space and further optimizing search methods for the  ... 
doi:10.21433/b311729295dw fatcat:fulw4pw3kfh5nmfzcsy3pkisvm

CFE-CMStatistics 2017 PROGRAMME AND ABSTRACTS 11th International Conference on Computational and Methodological Statistics (CMStatistics 2017) CMStatistics 2017 Co-chairs: CMStatistics 2017 Programme Committee

Ana Colubi, Erricos Kontoghiorghes, Marc Levene, Bernard Rachet, Herman Van, Dijk, Veronika Czellar, Hashem Pesaran, Mike Pitt, Stefan Sperlich, Knut Aastveit, Alessandra Amendola (+81 others)
unpublished
Two different approaches for the spatial latent effects are explored: one based on a movingaverage (convolution) construction, the other on a multilevel structure.  ...  By an innovation approach, a recursive algorithm for the LS linear filter of the augmented state based on the augmented observations is derived, from which the required LS quadratic filter of the original  ...  We focus on providing a compact form for the covariance matrix of the disturbance vector of this model.  ... 
fatcat:b6vjhxhuwvapnlla6r3etpiwb4

Analysis of Whole Building Life Cycle Environmental Impact Assessment (EIA) Tools

Thais Sartori, Robin Drogemuller, Sara Omrani, Fiona Lamari
2020 unpublished
This is achieved by passing UAV visual data through a convolutional neural network (CNN) to identify and localize target objects, followed by applying geometric transformation to instantaneously project  ...  This paper presents a method for real-time aerial data collection and GPSfree mapping.  ...  ACKNOWLEDGEMENT The authors want to thank the European Investment Bank for the funding of a grant for this research and the opportunity of this interesting case.  ... 
doi:10.46421/2706-6568.37.2020.paper033 fatcat:xp7wmxjyfngklfozrmu3o5p4ou