61 Hits in 8.6 sec

Prophet model for forecasting occupancy presence in indoor spaces using non-intrusive sensors

Alec Parise, Miguel A. Manso-Callejo, Hung Cao, Monica Wachowicz
2021 AGILE: GIScience Series  
The usefulness of this analytical workflow is demonstrated with the implementation of an IoT platform for an experiment operating non-intrusive sensing in a classroom.  ...  The Internet of Things is a multi-sensor technology with the unique advantage of supporting non-intrusive and non-device occupancy detection, while also allowing us to explore new forecasting occupancy  ...  The authors contributed equally to this work. All authors have read and agreed to the published version of this manuscript.  ... 
doi:10.5194/agile-giss-2-9-2021 fatcat:asds3z2lajcvfeo6fpnljpbati

Applying Convolutional Neural Networks for Stock Market Trends Identification [article]

Ekaterina Zolotareva
2021 arXiv   pre-print
The proposed framework requires the sequential interaction of three CNN submodels, which identify the presence of a changepoint in a window, locate it and finally recognize the type of new tendency - upward  ...  In this paper we apply a specific type ANNs - convolutional neural networks (CNNs) - to the problem of finding start and endpoints of trends, which are the optimal points for entering and leaving the market  ...  If the ChP-c model detects the presence of a changepoint in the window (value 1), then the ChP-r model is activated, which determines exactly where in this data slice the last trend started (win_srt).  ... 
arXiv:2104.13948v1 fatcat:yrzdivearbcz7adr355ahlsd7i

Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture [article]

Kieran Wood, Sven Giegerich, Stephen Roberts, Stefan Zohren
2021 arXiv   pre-print
We find changepoint detection (CPD) [2105.13727], another technique for responding to regime change, can complement multi-headed attention, especially when we run CPD at multiple timescales.  ...  However, some of the key challenges in recent years involve learning long-term dependencies, degradation of performance when considering returns net of transaction costs and adapting to new market regimes  ...  ACKNOWLEDGEMENTS We would like to thank the Oxford-Man Institute of Quantitative Finance for financial and computing support.  ... 
arXiv:2112.08534v1 fatcat:2sz62hwvercyfhztbywedp6ppi

Segmenting Hybrid Trajectories using Latent ODEs [article]

Ruian Shi, Quaid Morris
2021 arXiv   pre-print
Where it is possible to train a Latent ODE on the smooth dynamical flows between discontinuities, we apply the pruned exact linear time (PELT) algorithm to detect changepoints where latent dynamics restart  ...  We propose usage of the marginal likelihood as a score function for PELT, circumventing the need for model complexity-based penalization.  ...  Resources used in preparing this research were provided, in part, by the Memorial Sloan Kettering Cancer Center, Province of Ontario, the Government of Canada through CIFAR, and companies sponsoring the  ... 
arXiv:2105.03835v2 fatcat:7xiw3azxuzeftcbfdulkohqfei

Guaranteed Local Maximum Likelihood Detection of a Change Point in Nonparametric Logistic Regression

A. Vexler, G. Gurevich
2006 Communications in Statistics - Theory and Methods  
Finding efficient methods for detection and estimation of a threshold is a very important task in these studies. This article proposes such methods in a context of nonparametric logistic regression.  ...  The procedure allows estimation of the biomarker trend over time and the changepoint distribution. We provide the details of the estimation procedure.  ...  presence of a changepoint or changed segment are investigated and exemplified in the context of modelling non-coding deoxyribonucleic acid (DNA).  ... 
doi:10.1080/03610920500498923 fatcat:jxva2knaxvbpbfmovc7yfwwlhu

Sensors and Actuators in Smart Cities

Mohammad Hammoudeh, Mounir Arioua
2018 Journal of Sensor and Actuator Networks  
Author Contributions: Alex Adim Obinikpo and Burak Kantarci conceived and pursued the literature survey on deep learning techniques on big sensed data for smart health applications, reviewed the state  ...  The authors are grateful to the Middle East University, Amman, Jordan for the financial support granted to cover the publication fee of this research article. Author Contributions: Abdelhamied A.  ...  Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 2011, 12, 2825-2830. 57. Killick, R.; Fearnhead, P.; Eckley, I.A. Optimal Detection of Changepoints with a Linear Computational Cost. J.  ... 
doi:10.3390/jsan7010008 fatcat:pt7nkf4oaraijkmsndohahqtnq

Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx [article]

Kin G. Olivares and Cristian Challu and Grzegorz Marcjasz and Rafał Weron and Artur Dubrawski
2021 arXiv   pre-print
learning methods specialized for these tasks.  ...  The resulting method, called NBEATSx, improves on a well performing deep learning model, extending its capabilities by including exogenous variables and allowing it to integrate multiple sources of useful  ...  of application of deep transfer learning.  ... 
arXiv:2104.05522v4 fatcat:ypwi3d6nyrhathn4gbwrqyeg44

Data Management in Industry 4.0: State of the Art and Open Challenges [article]

Theofanis P. Raptis, Andrea Passarella, Marco Conti
2019 arXiv   pre-print
from the field level deep in the physical deployments, up to the cloud and applications level.  ...  The concepts presented in this article thematically cover the largest part of the industrial automation pyramid layers.  ...  However, it is a nontrivial task to train a deep learning model efficiently since the deep learning model often includes a great number of parameters.  ... 
arXiv:1902.06141v2 fatcat:4uvwquinx5h65dy4udx24bhrmm

Sleep Well: A Sound Sleep Monitoring Framework for Community Scaling

H M Sajjad Hossain, Nirmalya Roy, MD Abdullah Al Hafiz Khan
2015 2015 16th IEEE International Conference on Mobile Data Management  
In this paper we propose to detect the microscopic states of the sleep which fundamentally constitute the components of a good or bad sleeping behavior and help shape the formative assessment of sleep  ...  For a larger deployment of our proposed model across a community of individuals we propose an active learning based methodology by reducing the effort of ground truth data collection.  ...  Also in Fig. 14 represents the trend of loss function for different datasets. 2) Active Learning Experiments: In addition to supervised learning, we evaluate how we can improve the classification result  ... 
doi:10.1109/mdm.2015.42 dblp:conf/mdm/HossainRK15 fatcat:wxgol7ngbrbkdbdyx4moksgf2a

Towards Continual Reinforcement Learning: A Review and Perspectives [article]

Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup
2020 arXiv   pre-print
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL.  ...  We go on to discuss evaluation of continual RL agents, providing an overview of benchmarks used in the literature and important metrics for understanding agent performance.  ...  This work originated as a class project undertaken in the graduate-level course on Continual Learning: Towards "Broad" AI (IFT-6760B) at Mila, Montreal.  ... 
arXiv:2012.13490v1 fatcat:vcleqjnpgrbkvg477d4prmzg2q

Human Motion Trajectory Prediction: A Survey [article]

Andrey Rudenko, Luigi Palmieri, Michael Herman, Kris M. Kitani, Dariu M. Gavrila, Kai O. Arras
2019 arXiv   pre-print
We provide an overview of the existing datasets and performance metrics. We discuss limitations of the state of the art and outline directions for further research.  ...  With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand and anticipate human behavior becomes increasingly important.  ...  Lilienthal for valuable feedback and suggestions.  ... 
arXiv:1905.06113v3 fatcat:cnomix2fs5gqvb6ormldgti2bm

Modelling the dynamic pattern of surface area in basketball and its effects on team performance

Rodolfo Metulini, Marica Manisera, Paola Zuccolotto
2018 Journal of Quantitative Analysis in Sports (JQAS)  
Specifically, we first employ a Markov Switching Model (MSM) to detect structural changes in the surface area.  ...  Because of the advent of GPS techniques, a wide range of scientific literature on Sport Science is nowadays devoted to the analysis of players' movement in relation to team performance in the context of  ...  The rule generalizes the optimal linear shrinkage rule to broader parametric families of rules. The families include, for instance, polynomial and spline rules.  ... 
doi:10.1515/jqas-2018-0041 fatcat:b3qwsi7tqjg2vdo7gbjtiorv6m

The complexity dividend: when sophisticated inference matters [article]

Gaia Tavoni, Vijay Balasubramanian, Joshua I. Gold
2019 bioRxiv   pre-print
We construct a hierarchy of strategies that vary in complexity between these limits and find a power law of diminishing returns: increasing complexity gives progressively smaller gains in accuracy.  ...  Animals continuously infer latent properties of the world from noisy and changing observations.  ...  GT is supported by the Swartz Foundation and the Computational Neuroscience Initiative of the University of Pennsylvania. VB and JG are supported in part by NIH BRAIN Initiative grant R01EB026945.  ... 
doi:10.1101/563346 fatcat:bwgfnxsyk5d5rjupyskx2nsgnq

Ship speed prediction based on full scale sensor measurements of shaft thrust and environmental conditions

Andreas Brandsæter, Erik Vanem
2018 Ocean Engineering  
Acknowledgement The study presented in this paper is partly carried out within the centre for researchbased innovation, BigInsight.  ...  Acknowledgements The work is carried out in collaboration with the Big Insight project, and is partly funded by the Research Council of Norway , project number 237718 and 251396 .  ...  of deep learning systems is proposed.  ... 
doi:10.1016/j.oceaneng.2018.05.029 fatcat:j4hnf3uox5f57b2naoe76rp5km

International Research Conference on Smart Computing and Systems Engineering SCSE 2020 Proceedings [Full Conference Proceedings]

2020 2020 International Research Conference on Smart Computing and Systems Engineering (SCSE)  
in the University of Kelaniya for their immense support and encouragement they gave throughout the development phase of the data sets.  ...  ACKNOWLEDGMENT The authors would like to thank the Department of Census and Department of Irrigation, Sri Lanka for providing the paddy yield and climate data for this study.  ...  In the oneclass classification approach we trained a supervised machine learning model using non-anomalous data so, the model can detect(classify) the non-anomalous data in the presence of anomalous data  ... 
doi:10.1109/scse49731.2020.9313027 fatcat:gjk5az2mprgvrpallwh6uhvlfi
« Previous Showing results 1 — 15 out of 61 results