Výsledky vyhledávání

Sensitivity and robustness of end-to-end data-driven approach for building performance optimization

Autor: Gautam Biswas, Marcos Quiñones-Grueiro, Avisek Naug

Publikováno v: BuildSys@SenSys

This paper discusses an approach to optimizing the performance of an end-to-end data-driven control approach for building energy management. The proposed approach, designed for systems that exhibit non-stationary behavior, involves two primary compon

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0f8c1fd3cf9071e13c84ba79c21bf908
https://doi.org/10.1145/3486611.3488728

Zobrazit plný text záznamu

Deep reinforcement learning control for non-stationary building energy management

Autor: Avisek Naug, Marcos Quinones-Grueiro, Gautam Biswas

Publikováno v: Energy and Buildings. 277:112584

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::55541f2dc6665c23735655e7837cea19
https://doi.org/10.1016/j.enbuild.2022.112584

Zobrazit plný text záznamu

Continual adaptation in deep reinforcement learning-based control applied to non-stationary building environments

Autor: Gautam Biswas, Avisek Naug, Marcos Quiñones-Grueiro

Publikováno v: Proceedings of the 1st International Workshop on Reinforcement Learning for Energy Management in Buildings & Cities.

This paper develops a continual deep reinforcement relearning (RL) controller for large buildings that exhibit non-stationary behaviors. The non-stationarity in building operations caused by unexpected changes in weather patterns, occupancy, and faul

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::047b0c14e3e8b991825fa00d1ddda1d9
https://doi.org/10.1145/3427773.3427867

Zobrazit plný text záznamu

A Relearning Approach to Reinforcement Learning for Control of Smart Buildings

Autor: Marcos Q'uiñones Grueiro, Gautam Biswas, Avisek Naug

This paper demonstrates that continual relearning of control policies using incremental deep reinforcement learning (RL) can improve policy learning for non-stationary processes. We demonstrate this approach for a data-driven 'smart building environm

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dbf916f299291cec0f4903df710187dd
http://arxiv.org/abs/2008.01879

Zobrazit plný text záznamu

A Data Driven Method for Prediction of Energy Demand in Commercial Buildings

Autor: Gautam Biswas, Avisek Naug

Publikováno v: CASE

Modeling energy consumption for large HVAC systems can be complex and expensive. Hard to model interactions among the HVAC sub systems and between the subsystems and the building make the energy estimation problem difficult to derive using thermodyna

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::97ff71625cc99bfd86f884f028b41518
https://doi.org/10.1109/coase.2018.8560520

Zobrazit plný text záznamu

Data Driven Methods for Energy Reduction in Large Buildings

Autor: Gautam Biswas, Avisek Naug

Publikováno v: SMARTCOMP

Modeling of HVAC components and energy flows for energy prediction purposes can be computationally expensive in large commercial buildings. More recently, the increased availability of building operational data has made it possible to develop data-dr

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::790eeee7de9eeebfd56595382396e52a
https://doi.org/10.1109/smartcomp.2018.00083

Zobrazit plný text záznamu

Qualitative conditional assessment of human limb using force masking technique with a strain gauge setup

Autor: Spandan Basu, Krishnendu Sanyal, Avisek Naug, Arghya Bhattacharya

Publikováno v: 2016 IEEE First International Conference on Control, Measurement and Instrumentation (CMI).

This The M curves, force vs. phase curves for gait analysis, are utilized for obtaining variation of voltage output during different stages of the gait cycle. The proposed method in this paper suggests a novel technique by calibration of the voltage

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::84dea7a5a519929d90cd9012728eb50d
https://doi.org/10.1109/cmi.2016.7413751

Zobrazit plný text záznamu

Texture and color feature based WLS framework aided skin cancer classification using MSVM and ELM

Autor: Avisek Naug, Dwaipayan Choudhury, Susmita Ghosh

Publikováno v: 2015 Annual IEEE India Conference (INDICON).

This paper proposes a multilayer decomposition aided method based on textural and color feature for detection and classification of skin cancer images. Firstly, images are decomposed into a piecewise base layer and detail layer by weighted least squa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9480a28d3cec27ae6758cd6dc8cbfb44
https://doi.org/10.1109/indicon.2015.7443780

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání