scholarly journals Energy demand prediction with machine learning supported by auto-tuning: a case study

2021 ◽  
Vol 2069 (1) ◽  
pp. 012143
Author(s):  
Sorana Ozaki ◽  
Ryozo Ooka ◽  
Shintaro Ikeda
Keyword(s):  
Machine Learning ◽  
Energy Demand ◽  
Random Search ◽  
Bayesian Optimization ◽  
Learning Models ◽  
Time Step ◽  
Efficient Operation ◽  
Tuning Methods ◽  
Machine Learning Models

Abstract The operational energy of buildings is making up one of the highest proportions of life-cycle carbon emissions. A more efficient operation of facilities would result in significant energy savings but necessitates computational models to predict a building’s future energy demands with high precision. To this end, various machine learning models have been proposed in recent years. These models’ prediction accuracies, however, strongly depend on their internal structure and hyperparameters. The time demand and expertise required for their finetuning call for a more efficient solution. In the context of a case study, this paper describes the relationship between a machine learning model’s prediction accuracy and its hyperparameters. Based on time-stamped recordings of outdoor temperatures and electricity demands of a hospital in Japan, recorded every 30 minutes for more than four years, using a deep neural network (DNN) ensemble model, electricity demands were predicted for sixty time steps to follow. Specifically, we used automatic hyperparameter tuning methods, such as grid search, random search, and Bayesian optimization. A single time step ahead, all tuning methods reduced the RSME to less than 50%, compared to non-optimized tuning. The results attest to machine learning models’ reliance on hyperparameters and the effectiveness of their automatic tuning.

scholarly journals The Tabu_Genetic Algorithm: A Novel Method for Hyper-Parameter Optimization of Learning Algorithms

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 579 ◽  
Author(s):  
Baosu Guo ◽  
Jingwen Hu ◽  
Wenwen Wu ◽  
Qingjin Peng ◽  
Fenghe Wu
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Parameter Optimization ◽  
Random Search ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Parameters Optimization ◽  
Bayesian Optimization ◽  
Learning Models ◽  
Machine Learning Models

Machine learning algorithms have been widely used to deal with a variety of practical problems such as computer vision and speech processing. But the performance of machine learning algorithms is primarily affected by their hyper-parameters, as without good hyper-parameter values the performance of these algorithms will be very poor. Unfortunately, for complex machine learning models like deep neural networks, it is very difficult to determine their hyper-parameters. Therefore, it is of great significance to develop an efficient algorithm for hyper-parameter automatic optimization. In this paper, a novel hyper-parameter optimization methodology is presented to combine the advantages of a Genetic Algorithm and Tabu Search to achieve the efficient search for hyper-parameters of learning algorithms. This method is defined as the Tabu_Genetic Algorithm. In order to verify the performance of the proposed algorithm, two sets of contrast experiments are conducted. The Tabu_Genetic Algorithm and other four methods are simultaneously used to search for good values of hyper-parameters of deep convolutional neural networks. Experimental results show that, compared to Random Search and Bayesian optimization methods, the proposed Tabu_Genetic Algorithm finds a better model in less time. Whether in a low-dimensional or high-dimensional space, the Tabu_Genetic Algorithm has better search capabilities as an effective method for finding the hyper-parameters of learning algorithms. The presented method in this paper provides a new solution for solving the hyper-parameters optimization problem of complex machine learning models, which will provide machine learning algorithms with better performance when solving practical problems.

scholarly journals Predictive modelling of turbofan engine components condition using machine and deep learning methods

2021 ◽  
Vol 23 (2) ◽  
pp. 359-370
Author(s):  
Michał Matuszczak ◽  
Mateusz Żbikowski ◽  
Andrzej Teodorczyk
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Predictive Modelling ◽  
Continuous Variable ◽  
Environmental Data ◽  
Bayesian Optimization ◽  
Aviation Industry ◽  
Learning Models ◽  
Turbofan Engine ◽  
Machine Learning Models

The article proposes an approach based on deep and machine learning models to predict a component failure as an enhancement of condition based maintenance scheme of a turbofan engine and reviews currently used prognostics approaches in the aviation industry. Component degradation scale representing its life consumption is proposed and such collected condition data are combined with engines sensors and environmental data. With use of data manipulation techniques, a framework for models training is created and models' hyperparameters obtained through Bayesian optimization. Models predict the continuous variable representing condition based on the input. Best performed model is identified by detemining its score on the holdout set. Deep learning models achieved 0.71 MSE score (ensemble meta-model of neural networks) and outperformed significantly machine learning models with their best score at 1.75. The deep learning models shown their feasibility to predict the component condition within less than 1 unit of the error in the rank scale.

Explainable machine learning: A case study on impedance tube measurements

2021 ◽  
Vol 263 (3) ◽  
pp. 3223-3234
Author(s):  
Merten Stender ◽  
Mathies Wedler ◽  
Norbert Hoffmann ◽  
Christian Adams
Keyword(s):  
Machine Learning ◽  
Absorption Coefficient ◽  
Specimen Thickness ◽  
Learning Models ◽  
Impedance Tube ◽  
Frequency Regime ◽  
Hidden Patterns ◽  
Model Diagnosis ◽  
Machine Learning Models

Machine learning (ML) techniques allow for finding hidden patterns and signatures in data. Currently, these methods are gaining increased interest in engineering in general and in vibroacoustics in particular. Although ML methods are successfully applied, it is hardly understood how these black box-type methods make their decisions. Explainable machine learning aims at overcoming this issue by deepening the understanding of the decision-making process through perturbation-based model diagnosis. This paper introduces machine learning methods and reviews recent techniques for explainability and interpretability. These methods are exemplified on sound absorption coefficient spectra of one sound absorbing foam material measured in an impedance tube. Variances of the absorption coefficient measurements as a function of the specimen thickness and the operator are modeled by univariate and multivariate machine learning models. In order to identify the driving patterns, i.e. how and in which frequency regime the measurements are affected by the setup specifications, Shapley additive explanations are derived for the ML models. It is demonstrated how explaining machine learning models can be used to discover and express complicated relations in experimental data, thereby paving the way to novel knowledge discovery strategies in evidence-based modeling.

scholarly journals GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction

Processes ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 23
Author(s):  
Kexin Bi ◽  
Dong Zhang ◽  
Tong Qiu ◽  
Yizhen Huang
Keyword(s):  
Machine Learning ◽  
Evaluation System ◽  
Gas Chromatography Mass Spectrometry ◽  
Learning Models ◽  
Fingerprint Image ◽  
Whole Process ◽  
Evaluation Problem ◽  
Potential Issue ◽  
Machine Learning Models

Food flavor quality evaluation is attracting continuous attention, but a suitable evaluation system is severely lacking. Gas chromatography-mass spectrometry/olfactometry (GC-MS/O) is widely used to solve the food flavor evaluation problem, but the olfactometry evaluation is unfeasible to be carried out in large batches and is unreliable due to potential issue of an operator or systematic laboratory effect. Thus, a novel fingerprint modeling and profiling process was proposed based on several machine learning models including convolutional neural network (CNN). The fingerprint template was created by the data analysis of existing GC-MS spectrum dataset. Then the fingerprint image generation program was applied for structuring the complex instrumental data. Food olfactometry result was obtained by a machine learning method based on CNN using fingerprint image as the input. The case study on peanut oil samples demonstrated the model accuracy of around 93%. By structure optimization and further dataset expansion, the whole process has the potential to be utilized by sensory laboratories for aroma analysis instead of humans.

Sign in / Sign up

Export Citation Format

Share Document