scholarly journals Development of an Improved Model to Predict Building Thermal Energy Consumption by Utilizing Feature Selection

Energies ◽  
2019 ◽  
Vol 12 (21) ◽  
pp. 4187 ◽  
Author(s):  
Jihoon Jang ◽  
Joosang Lee ◽  
Eunjo Son ◽  
Kyungyong Park ◽  
Gahee Kim ◽  
...  
Keyword(s):  
Feature Selection ◽  
Energy Consumption ◽  
Prediction Model ◽  
Thermal Energy ◽  
Prediction Accuracy ◽  
Selection Process ◽  
Ghg Emissions ◽  
Efficient Operation ◽  
Artificial Neural Network Ann ◽  
Improved Model

Humans spend approximately 90% of the daytime in buildings, and greenhouse gases (GHGs) emitted by buildings account for approximately 20% of total GHG emissions. As the energy consumed during building operation from a building life-cycle perspective amounts to approximately 70–90% of the total energy, it is essential to accurately predict the energy consumption of buildings for their efficient operation. This study aims to optimize a model for predicting the thermal energy consumption of buildings by (i) first extracting major variables through feature selection and deriving significant variables in addition to the collected data and (ii) predicting the thermal energy consumption using a machine learning model. Feature selection using random forest was performed, and 11 out of 17 available data were selected. The accuracy of the prediction model was significantly improved when the hour of day variable was added. The prediction model was constructed using an artificial neural network (ANN), and the improvement in the prediction accuracy was analyzed by comparing different cases of variable combinations. The ANN prediction accuracy was improved by 15% using the feature selection process compared to when all data were used as input data, and 25% coefficient of variation of the root mean square error (CVRMSE) accuracy was achieved.

scholarly journals Failure Prediction Model Using Iterative Feature Selection for Industrial Internet of Things

Symmetry ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 454 ◽  
Author(s):  
Jung-Hyok Kwon ◽  
Eui-Jik Kim
Keyword(s):  
Feature Selection ◽  
Internet Of Things ◽  
Prediction Model ◽  
Prediction Accuracy ◽  
Model Building ◽  
Failure Prediction ◽  
Support Vector ◽  
Industrial Internet Of Things ◽  
Industrial Internet ◽  
New Feature

This paper presents a failure prediction model using iterative feature selection, which aims to accurately predict the failure occurrences in industrial Internet of Things (IIoT) environments. In general, vast amounts of data are collected from various sensors in an IIoT environment, and they are analyzed to prevent failures by predicting their occurrence. However, the collected data may include data irrelevant to failures and thereby decrease the prediction accuracy. To address this problem, we propose a failure prediction model using iterative feature selection. To build the model, the relevancy between each feature (i.e., each sensor) and the failure was analyzed using the random forest algorithm, to obtain the importance of the features. Then, feature selection and model building were conducted iteratively. In each iteration, a new feature was selected considering the importance and added to the selected feature set. The failure prediction model was built for each iteration via the support vector machine (SVM). Finally, the failure prediction model having the highest prediction accuracy was selected. The experimental implementation was conducted using open-source R. The results showed that the proposed failure prediction model achieved high prediction accuracy.

scholarly journals Demand Forecasting for a Mixed-Use Building Using Agent-Schedule Information with a Data-Driven Model

Energies ◽  
2020 ◽  
Vol 13 (4) ◽  
pp. 780 ◽  
Author(s):  
Zihao Li ◽  
Daniel Friedrich ◽  
Gareth P. Harrison
Keyword(s):  
Feature Selection ◽  
Energy Consumption ◽  
Selection Process ◽  
Demand Forecasting ◽  
Electricity Demand ◽  
Data Driven ◽  
Feature Sets ◽  
Demand Prediction ◽  
Heat Demand ◽  
Mixed Use

There is great interest in data-driven modelling for the forecasting of building energy consumption while using machine learning (ML) modelling. However, little research considers classification-based ML models. This paper compares the regression and classification ML models for daily electricity and thermal load modelling in a large, mixed-use, university building. The independent feature variables of the model include outdoor temperature, historical energy consumption data sets, and several types of ‘agent schedules’ that provide proxy information that is based on broad classes of activity undertaken by the building’s inhabitants. The case study compares four different ML models testing three different feature sets with a genetic algorithm (GA) used to optimize the feature sets for those ML models without an embedded feature selection process. The results show that the regression models perform significantly better than classification models for the prediction of electricity demand and slightly better for the prediction of heat demand. The GA feature selection improves the performance of all models and demonstrates that historical heat demand, temperature, and the ‘agent schedules’, which derive from large occupancy fluctuations in the building, are the main factors influencing the heat demand prediction. For electricity demand prediction, feature selection picks almost all ‘agent schedule’ features that are available and the historical electricity demand. Historical heat demand is not picked as a feature for electricity demand prediction by the GA feature selection and vice versa. However, the exclusion of historical heat/electricity demand from the selected features significantly reduces the performance of the demand prediction.

Predicting Financial Distress in the Indian Banking Sector: A Comparative Study Between the Logistic Regression, LDA and ANN Models

2021 ◽  
pp. 097215092110267
Author(s):  
Nandita Mishraz ◽  
Shruti Ashok ◽  
Deepak Tandon
Keyword(s):  
Prediction Model ◽  
Financial Distress ◽  
Prediction Accuracy ◽  
Banking Sector ◽  
Banking System ◽  
Bankruptcy Prediction ◽  
Linear Discriminant ◽  
Ann Models ◽  
Artificial Neural Network Ann ◽  
Indian Banks

Financial distress is a socially and economically significant issue that affects almost every firm across the world. Predicting financial distress in the banking industry can substantially aid in the reduction of losses and can help avoid misallocation of banks’ financial resources. Models for financial distress prediction of banks are being increasingly employed as important tools to identify early warning signals for the whole banking system. This study attempts to forecast the financial distress of commercial banks by developing a bankruptcy prediction model for banks. The sample size for the study is 75 Indian banks. Logistic, linear discriminant analysis (LDA) and artificial neural network (ANN) models have been applied on the last 5 years’ (2015–2019) data of these banks. Data analysis results reveal the logistic and LDA models exhibiting similar prediction accuracy. The results of the ANN prediction model exhibit better prediction accuracy. It is expected that the results of this study will be useful for managers, depositors, regulatory bodies and shareholders to better manage their interests in the banking sector of the country.

scholarly journals Intelligent Prediction Method of Building Energy Consumption Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Bingqian Fan ◽  
Xuanxuan Xing
Keyword(s):  
Deep Learning ◽  
Energy Consumption ◽  
Prediction Model ◽  
Prediction Accuracy ◽  
Simulation Experiment ◽  
Short Term Memory ◽  
Building Energy ◽  
Building Energy Consumption ◽  
Energy Consumption Prediction ◽  
Consumption Prediction

Building energy consumption prediction plays an important role in realizing building energy conservation control. Limited by some external factors such as temperature, there are some problems in practical applications, such as complex operation and low prediction accuracy. Aiming at the problem of low prediction accuracy caused by poor timing of existing building energy consumption prediction methods, a building energy consumption prediction and analysis method based on the deep learning network is proposed in this paper. Before establishing the energy consumption prediction model, the building energy consumption data source is preprocessed and analyzed. Then, based on the Keras deep learning framework, an improved long short-term memory (ILSTM) prediction model is built to support the accurate analysis of the whole cycle of the prediction network. At the same time, the adaptive moment (Adam) estimation algorithm is used to update and optimize the weight parameters of the model to realize the adaptive and rapid update and matching of network parameters. The simulation experiment is based on the actual dataset collected by a university in Southwest China. The experimental results show that the evaluation indexes MAE and RMSE of the proposed method are 0.015 and 0.109, respectively, which are better than the comparison method. The simulation experiment proves that the proposed method is feasible.

scholarly journals Empirical Processing of Breast Cancer Prediction Strategies using DEFS Algorithm

2020 ◽  
Vol 8 (5) ◽  
pp. 3081-3087
Keyword(s):  
Breast Cancer ◽  
Feature Selection ◽  
Differential Evolution ◽  
Ensemble Learning ◽  
Prediction Accuracy ◽  
Selection Process ◽  
False Negative ◽  
Pollution Level ◽  
Survival Ratio ◽  
True Negative

Now-a-days an important threat to women over global manner is Breast-Cancer, which is the major disease cause drastic affection to female especially. Identification of Breast Cancer over earlier stages is must to save one's life and the significant affection range of Breast-Cancer is drastically improved day by day due to the improper food-habits, pollution-level and improper-life style as well as genetic-issues also. The main cause of this disease is the arising of breast-ample over the ‘breast-area, which develops the cancer to women in several cases. If the detection or prediction of such masses over earlier stage will helps to women to get more survival ratio as well as this leads a proportion to researchers to make an systematic process to detect such diseases on initial stages by using intelligent prediction methodologies with high accuracy rates. In this paper, the proposed system handles several stages of processing to make sure the prediction accuracy, such steps are as follows: Data acquisition, Feature vector formation by normalization, Feature Selection by using Differential Evolution based selection methodology, Classification using Subspace Ensemble Learning and different Performance Measures. By using these strategies the entire work assures the proposed system is perfect to predict or identify the breast cancer benign/malignant stages more accurately compare to the classical Margin-Based Feature-Selection process. Compared to the classical biopsy methodology, a systematic diagnosis attains more impact due to its prediction accuracy. This proposed system is powered by a powerful approach called Differential-Evolution Feature’-Selection (“DEFS”) with the association of Subspace Ensemble Learning Classification principle, which provides highest accuracy and prediction rates compare to the classical methodologies. This proposed paper assures effective and robust mining strategies in Breast Cancer identification/prediction as well as efficient decision-making norms. The proposed outcome proves the good accuracy and resulting levels by means of Precision-Recall, Sensitivity and Specificity, True Positive/True Negative, False Positive/False Negative, Accuracy and Time Consumption.

A Fast Feature Selection Method Based on Coefficient of Variation for Diabetics Prediction Using Machine Learning

2019 ◽  
Vol 1 (1) ◽  
pp. 55-65 ◽  
Author(s):  
Tengyue Li ◽  
Simon Fong
Keyword(s):  
Feature Selection ◽  
Prediction Model ◽  
Coefficient Of Variation ◽  
Selection Process ◽  
Age Groups ◽  
Selection Criterion ◽  
Feature Selection Method ◽  
Selection Scheme ◽  
Large Populations ◽  
Process Computer

Diabetes has become a prevalent metabolic disease nowadays, affecting patients of all age groups and large populations around the world. Early detection would facilitate early treatment that helps the prognosis. In the literature of computational intelligence and medical care communities, different techniques have been proposed in predicting diabetes based on the historical records of related symptoms. The researchers share a common goal of improving the accuracy of a diabetes prediction model. In addition to the model induction algorithms, feature selection is a significant approach in retaining only the relevant attributes for the sake of building a quality prediction model later. In this article, a novel and simple feature selection criterion called Coefficient of Variation (CV) is proposed as a filter-based feature selection scheme. By following the CV method, attributes that have a data dispersion too low are disqualified from the model construction process. Thereby the attributes which are factors leading to poor model accuracy are discarded. The computation of CV is simple, hence enabling an efficient feature selection process. Computer simulation experiments by using the Prima Indian diabetes dataset is used to compare the performance of CV with other traditional feature selection methods. Superior results by CV are observed.

scholarly journals An Improved Power System Transient Stability Prediction Model Based on mRMR Feature Selection and WTA Ensemble Learning

2020 ◽  
Vol 10 (7) ◽  
pp. 2255
Author(s):  
Jun Liu ◽  
Huiwen Sun ◽  
Yitong Li ◽  
Wanliang Fang ◽  
Shuanbao Niu
Keyword(s):  
Feature Selection ◽  
Power Systems ◽  
Power System ◽  
Prediction Model ◽  
Ensemble Learning ◽  
Prediction Accuracy ◽  
Transient Stability ◽  
Stability Assessment ◽  
Stability Prediction ◽  
Electromagnetic Power

Fast online transient stability assessment (TSA) is very important to maintain the stable operation of power systems. However, the existing transient stability assessment methods suffer the drawbacks of unsatisfactory prediction accuracy, difficult applicability, or a heavy computational burden. In light of this, an improved high accuracy power system transient stability prediction model is proposed, based on min-redundancy and max-relevance (mRMR) feature selection and winner take all (WTA) ensemble learning. Firstly, the contributions of four different series of raw sampled data from all of the three-time stages, namely the pre-fault, during-fault and post-fault, to transient stability are compared. The new feature of generator electromagnetic power is introduced and compared with three conventional types of input features, through a support vector machine (SVM) classifier. Furthermore, the two types of most contributive input features are obtained by the mRMR feature selection method. Finally, the prediction results of the electromagnetic power of generators and the voltage amplitude of buses are combined using the WTA ensemble learning method, and an improved transient stability prediction model with higher accuracy for unstable samples is obtained, whose overall prediction accuracy would not decrease either. The real-time data collected by wide area monitoring systems (WAMS) can be fed into this model for fast online transient stability prediction; the results can also provide a basis for the future emergency control decision-making of power systems.

A Backward Feature Selection by Creating Compact Neural Network Using Coherence Learning and Pruning

2007 ◽  
Vol 11 (6) ◽  
pp. 570-581 ◽  
Author(s):  
Md. Monirul Kabir ◽  
◽  
Md. Shahjahan ◽  
Kazuyuki Murase ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Selection Process ◽  
Feature Selection Method ◽  
Attribute Selection ◽  
Classification Problems ◽  
Good Classification ◽  
Straightforward Computation ◽  
Artificial Neural Network Ann ◽  
Pruning Technique

In this paper we propose a new backward feature selection method that generates compact classifier of a three-layered feed-forward artificial neural network (ANN). In the algorithm, that is based on the wrapper model, two techniques, coherence and pruning, are integrated together in order to find relevant features with a network of minimal numbers of hidden units and connections. Firstly, a coherence learning and a pruning technique are applied during training for removing unnecessary hidden units from the network. After that, attribute distances are measured by a straightforward computation that is not computationally expensive. An attribute is then removed based on an error-based criterion. The network is retrained after the removal of the attribute. This unnecessary attribute selection process is continued until a stopping criterion is satisfied. We applied this method to several standard benchmark classification problems such as breast cancer, diabetes, glass identification and thyroid problems. Experimental results confirmed that the proposed method generates compact network structures that can select relevant features with good classification accuracies.

scholarly journals Evolutionary Hybrid System for Energy Consumption Forecasting for Smart Meters

Energies ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1794
Author(s):  
Diogo M. F. Izidio ◽  
Paulo S. G. de Mattos Neto ◽  
Luciano Barbosa ◽  
João F. L. de Oliveira ◽  
Manoel Henrique da Nóbrega Marinho ◽  
...  
Keyword(s):  
Time Series ◽  
Feature Selection ◽  
Energy Consumption ◽  
Hybrid System ◽  
Smart Grids ◽  
Energy Demand ◽  
Mean Squared Error ◽  
Selection Process ◽  
Linear Component ◽  
Non Linear

The usage of smart grids is growing steadily around the world. This technology has been proposed as a promising solution to enhance energy efficiency and improve consumption management in buildings. Such benefits are usually associated with the ability of accurately forecasting energy demand. However, the energy consumption series forecasting is a challenge for statistical linear and Machine Learning (ML) techniques due to temporal fluctuations and the presence of linear and non-linear patterns. Traditional statistical techniques are able to model linear patterns, while obtaining poor results in forecasting the non-linear component of the time series. ML techniques are data-driven and can model non-linear patterns, but their feature selection process and parameter specification are a complex task. This paper proposes an Evolutionary Hybrid System (EvoHyS) which combines statistical and ML techniques through error series modeling. EvoHyS is composed of three phases: (i) forecast of the linear and seasonal component of the time series using a Seasonal Autoregressive Integrated Moving Average (SARIMA) model, (ii) forecast of the error series using an ML technique, and (iii) combination of both linear and non-linear forecasts from (i) and (ii) using a a secondary ML model. EvoHyS employs a Genetic Algorithm (GA) for feature selection and hyperparameter optimization in phases (ii) and (iii) aiming to improve its accuracy. An experimental evaluation was conducted using consumption energy data of a smart grid in a one-step-ahead scenario. The proposed hybrid system reaches statistically significant improvements when compared to other statistical, hybrid, and ML approaches from the literature utilizing well known metrics, such as Mean Squared Error (MSE).

Sign in / Sign up

Export Citation Format

Share Document