scholarly journals Smart Building Energy Inefficiencies Detection through Time Series Analysis and Unsupervised Machine Learning

Energies ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 6042
Author(s):  
Hanaa Talei ◽  
Driss Benhaddou ◽  
Carlos Gamarra ◽  
Houda Benbrahim ◽  
Mohamed Essaaidi
Keyword(s):  
Time Series ◽  
Energy Efficiency ◽  
Time Series Analysis ◽  
Unsupervised Learning ◽  
Energy Savings ◽  
Efficiency Analysis ◽  
Hvac Systems ◽  
Series Analysis ◽  
Learning Techniques ◽  
Energy Efficiency Analysis

The climate of Houston, classified as a humid subtropical climate with tropical influences, makes the heating, ventilation, and air conditioning (HVAC) systems the largest electricity consumers in buildings. HVAC systems in commercial buildings are usually operated by a centralized control system and/or an energy management system based on a fixed schedule and scheduled control of a zone setpoint, which is not appropriate for many buildings with changing occupancy rates. Lately, as part of energy efficiency analysis, attention has focused on collecting and analyzing smart meters and building-related data, as well as applying supervised learning techniques, to propose new strategies to operate HVAC systems and reduce energy consumption. On the other hand, unsupervised learning techniques have been used to study the consumption information and profile characterization of different buildings after cluster analysis is performed. This paper adopts a different approach by revealing the power of unsupervised learning to cluster data and unveiling hidden patterns. In this study, we also identify energy inefficiencies after exploring the cluster results of a single building’s HVAC consumption data and building usage data as part of the energy efficiency analysis. Time series analysis and the K-means clustering algorithm are successfully applied to identify new energy-saving opportunities in a highly efficient office building located in the Houston area (TX, USA). The paper uses 1-year data from a highly efficient Leadership in Energy and Environment Design (LEED)-, Energy Star-, and Net Zero-certified building, showing a potential energy savings of 6% using the K-means algorithm. The results show that clustering is instrumental in helping building managers identify potential additional energy savings.

scholarly journals An Unsupervised Learning Approach for Early Damage Detection by Time Series Analysis and Deep Neural Network to Deal with Output-Only (Big) Data

2020 ◽  
Vol 2 (1) ◽  
pp. 17
Author(s):  
Alireza Entezami ◽  
Hassan Sarmadi ◽  
Stefano Mariani
Keyword(s):  
Time Series ◽  
Feature Extraction ◽  
Big Data ◽  
Time Series Analysis ◽  
Damage Detection ◽  
Unsupervised Learning ◽  
Data Driven ◽  
Structural Safety ◽  
Series Analysis ◽  
Early Damage

Dealing with complex engineering problems characterized by Big Data, particularly in structural engineering, has recently received considerable attention due to its high societal importance. Data-driven structural health monitoring (SHM) methods aim at assessing the structural state and detecting any adverse change caused by damage, so as to guarantee structural safety and serviceability. These methods rely on statistical pattern recognition, which provides opportunities to implement a long-term SHM strategy by processing measured vibration data. However, the successful implementation of the data-driven SHM strategies when Big Data are to be processed is still a challenging issue, since the procedures of feature extraction and/or feature classification may end up being time-consuming and complex. To enhance the current damage detection procedures, in this work we propose an unsupervised learning method based on time series analysis, deep learning and the Mahalanobis distance metric for feature extraction, dimensionality reduction and classification. The main novelty of this strategy is the simultaneous dealing with the significant issue of Big Data analytics for damage detection, and distinguishing damage states from the undamaged one in an unsupervised learning manner. Large-scale datasets relevant to a cable-stayed bridge have been handled to validate the effectiveness of the proposed data-driven approach. Results have shown that the approach is highly successful in detecting early damage, even when Big Data are to be processed.

Dynamical Peculiarities of Concatenational Changes in Functional Cardiovascular Parameters

2018 ◽  
Vol 3 (82) ◽  
Author(s):  
Eurelija Venskaitytė ◽  
Jonas Poderys ◽  
Tadas Česnaitis
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Functional State ◽  
The Body ◽  
Functional Changes ◽  
High Intensity Training ◽  
Series Analysis ◽  
Greco Roman ◽  
St Segment ◽  
Standard Lead

Research  background  and  hypothesis.  Traditional  time  series  analysis  techniques,  which  are  also  used  for the analysis of cardiovascular signals, do not reveal the relationship between the  changes in the indices recorded associated with the multiscale and chaotic structure of the tested object, which allows establishing short-and long-term structural and functional changes.Research aim was to reveal the dynamical peculiarities of interactions of cardiovascular system indices while evaluating the functional state of track-and-field athletes and Greco-Roman wrestlers.Research methods. Twenty two subjects participated in the study, their average age of 23.5 ± 1.7 years. During the study standard 12 lead electrocardiograms (ECG) were recorded. The following ECG parameters were used in the study: duration of RR interval taken from the II standard lead, duration of QRS complex, duration of JT interval and amplitude of ST segment taken from the V standard lead.Research  results.  Significant  differences  were  found  between  inter-parametric  connections  of  ST  segment amplitude and JT interval duration at the pre and post-training testing. Observed changes at different hierarchical levels of the body systems revealed inadequate cardiac metabolic processes, leading to changes in the metabolic rate of the myocardium and reflected in the dynamics of all investigated interactions.Discussion and conclusions. It has been found that peculiarities of the interactions of ECG indices interactions show the exposure of the  functional changes in the body at the onset of the workload. The alterations of the functional state of the body and the signs of fatigue, after athletes performed two high intensity training sessions per day, can be assessed using the approach of the evaluation of interactions between functional variables. Therefore the evaluation of the interactions of physiological signals by using time series analysis methods is suitable for the observation of these processes and the functional state of the body.Keywords: electrocardiogram, time series, functional state.

Sign in / Sign up

Export Citation Format

Share Document