scholarly journals Thermal Imagery Feature Extraction Techniques and the Effects on Machine Learning Models for Smart HVAC Efficiency in Building Energy

2021 ◽  
Vol 13 (19) ◽  
pp. 3847
Author(s):  
Yaa Takyiwaa Acquaah ◽  
Balakrishna Gokaraju ◽  
Raymond C. Tesiero ◽  
Gregory H. Monty
Keyword(s):  
Energy Efficiency ◽  
Feature Extraction ◽  
Transfer Learning ◽  
Residential Buildings ◽  
Building Energy ◽  
Haar Wavelet ◽  
Support Vector ◽  
Extraction Techniques ◽  
Thermal Imagery ◽  
Occupancy Detection

The control of thermostats of a heating, ventilation, and air-conditioning (HVAC) system installed in commercial and residential buildings remains a pertinent problem in building energy efficiency and thermal comfort research. The ability to determine the number of people at a particular time in an area is imperative for energy efficiency in order to condition only occupied regions and thermally deficient regions. In this study of the best features comparison for detecting the number of people in an area, feature extraction techniques including wavelet scattering, wavelet decomposition, grey-level co-occurrence matrix (GLCM) and feature maps convolution neural network (CNN) layers were explored using thermal camera imagery. Specifically, the pretrained CNN networks explored are the deep residual (Resnet-50) and visual geometry group (VGG-16) networks. The discriminating potential of Haar, Daubechies and Symlets wavelet statistics on different distributions of data were investigated. The performance of VGG-16 and ResNet-50 in an end-to-end manner utilizing transfer learning approach was investigated. Experimental results showed the classification and regression trees (CART) model trained on only GLCM and Haar wavelet statistic features, individually achieved accuracies of approximately 80% and 84%, respectively, in the detection problem. Moreover, k-nearest neighbors (KNN) trained on the combined features of GLCM and Haar wavelet statistics achieved an accuracy of approximately 86%. In addition, the performance accuracy of the multi classification support vector machine (SVM) trained on deep features obtained from layers of pretrained ResNet-50 and VGG-16 was between 96% and 97%. Furthermore, ResNet-50 transfer learning outperformed the VGG-16 transfer learning model for occupancy detection using thermal imagery. Overall, the SVM model trained on features extracted from wavelet scattering emerged as the best performing classifier with an accuracy of 100%. A principal component analysis (PCA) on the wavelet scattering features proved that the first twenty (20) principal components achieved a similar accuracy level instead of training on the whole feature set to reduce the execution time. The occupancy detection models can be integrated into HVAC control systems for energy efficiency and security systems, and aid in the distribution of resources to people in an area.

scholarly journals Plant Recognition Using Morphological Feature Extraction and Transfer Learning over SVM and AdaBoost

Symmetry ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 356
Author(s):  
Shubham Mahajan ◽  
Akshay Raina ◽  
Xiao-Zhi Gao ◽  
Amit Kant Pandit
Keyword(s):  
Feature Extraction ◽  
Transfer Learning ◽  
Plant Species ◽  
Species Recognition ◽  
Morphological Features ◽  
Support Vector ◽  
Additional Advantage ◽  
Adaptive Boosting ◽  
Vast Number ◽  
Axis Length

Plant species recognition from visual data has always been a challenging task for Artificial Intelligence (AI) researchers, due to a number of complications in the task, such as the enormous data to be processed due to vast number of floral species. There are many sources from a plant that can be used as feature aspects for an AI-based model, but features related to parts like leaves are considered as more significant for the task, primarily due to easy accessibility, than other parts like flowers, stems, etc. With this notion, we propose a plant species recognition model based on morphological features extracted from corresponding leaves’ images using the support vector machine (SVM) with adaptive boosting technique. This proposed framework includes the pre-processing, extraction of features and classification into one of the species. Various morphological features like centroid, major axis length, minor axis length, solidity, perimeter, and orientation are extracted from the digital images of various categories of leaves. In addition to this, transfer learning, as suggested by some previous studies, has also been used in the feature extraction process. Various classifiers like the kNN, decision trees, and multilayer perceptron (with and without AdaBoost) are employed on the opensource dataset, FLAVIA, to certify our study in its robustness, in contrast to other classifier frameworks. With this, our study also signifies the additional advantage of 10-fold cross validation over other dataset partitioning strategies, thereby achieving a precision rate of 95.85%.

Smart paddy field monitoring system using deep learning and IoT

2021 ◽  
pp. 1063293X2198894
Author(s):  
Prabira Kumar Sethy ◽  
Santi Kumari Behera ◽  
Nithiyakanthan Kannan ◽  
Sridevi Narayanan ◽  
Chanki Pandey
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Transfer Learning ◽  
Paddy Field ◽  
New Technology ◽  
Support Vector ◽  
Nitrogen Status ◽  
Deep Feature ◽  
Per Capita ◽  
Deep Feature Extraction

Paddy is an essential nutrient worldwide. Rice gives 21% of worldwide human per capita energy and 15% of per capita protein. Asia represented 60% of the worldwide populace, about 92% of the world’s rice creation, and 90% of worldwide rice utilization. With the increase in population, the demand for rice is increased. So, the productivity of farming is needed to be enhanced by introducing new technology. Deep learning and IoT are hot topics for research in various fields. This paper suggested a setup comprising deep learning and IoT for monitoring of paddy field remotely. The vgg16 pre-trained network is considered for the identification of paddy leaf diseases and nitrogen status estimation. Here, two strategies are carried out to identify images: transfer learning and deep feature extraction. The deep feature extraction approach is combined with a support vector machine (SVM) to classify images. The transfer learning approach of vgg16 for identifying four types of leaf diseases and prediction of nitrogen status results in 79.86% and 84.88% accuracy. Again, the deep features of Vgg16 and SVM results for identifying four types of leaf diseases and prediction of nitrogen status have achieved an accuracy of 97.31% and 99.02%, respectively. Besides, a framework is suggested for monitoring of paddy field remotely based on IoT and deep learning. The suggested prototype’s superiority is that it controls temperature and humidity like the state-of-the-art and can monitor the additional two aspects, such as detecting nitrogen status and diseases.

PERFORMANCE INDICATORS FOR ENERGY EFFICIENCY RETROFITTING IN MULTIFAMILY RESIDENTIAL BUILDINGS

2019 ◽  
Vol 14 (2) ◽  
pp. 109-136
Author(s):  
Chaitali Basu ◽  
Virendra Kumar Paul ◽  
M.G. Matt Syal
Keyword(s):  
Energy Efficiency ◽  
Performance Assessment ◽  
Performance Indicators ◽  
Residential Buildings ◽  
Building Energy ◽  
Energy Performance ◽  
Building Envelope ◽  
Assessment Process ◽  
Second Phase ◽  
A Priority

The energy performance of an existing building is the amount of energy consumed to meet various needs associated with the standardized use of a building and is reflected in one or more indicators known as Building Energy Performance Indicators (EnPIs). These indicators are distributed amongst six main factors influencing energy consumption: climate, building envelope, building services and energy systems, building operation and maintenance, occupants' activities and behaviour, and indoor environmental quality. Any improvement made to either the existing structure or the physical and operational upgrade of a building system that enhances energy performance is considered an energy efficiency retrofit. The main goal of this research is to support the implementation of multifamily residential building energy retrofits through expert knowledge consensus on EnPIs for energy efficiency retrofit planning. The research methodology consists of a comprehensive literature review which has identified 35 EnPIs for assessing performance of existing residential buildings, followed by a ranking questionnaire survey of experts in the built-environment to arrive at a priority listing of indicators based on mean rank. This was followed by concordance analysis and measure of standard deviation. A total of 280 experts were contacted globally for the survey, and 106 completed responses were received resulting in a 37.85% response rate. The respondents were divided into two groups for analysis: academician/researchers and industry practitioners. The primary outcome of the research is a priority listing of EnPIs based on the quantitative data from the knowledge-base of experts from these two groups. It is the outcome of their perceptions of retrofitting factors and corresponding indicators. A retrofit strategy consists of five phases for retrofitting planning in which the second phase comprises an energy audit and performance assessment and diagnostics. This research substantiates the performance assessment process through the identification of EnPIs.

scholarly journals RESEARCH ON DIFFERENT FEATURE EXTRACTION AND MAMMOGRAM CLASSIFICATION TECHNIQUES

2019 ◽  
pp. 1-3
Author(s):  
Anita Kaklotar
Keyword(s):  
Feature Extraction ◽  
Association Rule ◽  
Support Vector ◽  
Common Disease ◽  
Extraction Techniques ◽  
Scale Invariant ◽  
Invariant Feature ◽  
Feature Transform ◽  
Scale Invariant Feature ◽  
Mammogram Images

Breast cancer is the primary and the most common disease found among women. Today, mammography is the most powerful screening technique used for early detection of cancer which increases the chance of successful treatment. In order to correctly detect the mammogram images as being cancerous or malignant, there is a need of a classier. With this objective, an attempt is made to analyze different feature extraction techniques and classiers. In the proposed system we rst do the preprocessing of the mammogram images, where the unwanted noise and disturbances in the mammograms are removed. Features are then extracted from the mammogram images using Gray Level Co-Occurrences Matrix (GLCM) and Scale Invariant Feature Transform (SIFT). Finally, the features are classied using classiers like HiCARe (Classier based on High Condence Association Rule Agreements), Support Vector Machine (SVM), Naïve Bayes classier and K-NN Classier. Further we test the images and classify them as benign or malignant class.

scholarly journals User Perception of High-Performance Schools

2018 ◽  
Vol 3 (10) ◽  
pp. 191-202
Author(s):  
Mohd Najib Mohd Salleh ◽  
Mohd Zin Kandar ◽  
Siti Rasidah Md Sakip
Keyword(s):  
Energy Efficiency ◽  
Energy Demand ◽  
High Performance ◽  
User Behavior ◽  
Residential Buildings ◽  
Publishing House ◽  
Building Energy ◽  
Building Energy Efficiency ◽  
School Building ◽  
User Perception

Energy demand in buildings can reduce by improving energy efficiency. MS1525 has recommended that energy efficiency for Non-Residential Buildings in Malaysia to be not more than 135kWh/m²/year. A school building is a non-residential building and has major social responsibilities. Based on the theory of building energy-efficiency, energy efficiency can be achieved through three main factors: a) design of buildings; b) design of services; and c) user behavior. This study aims to investigate the user perceptions in High-Performance Schools. Keywords: User perception; building energy index; building energy efficiency; school building. eISSN 2514-7528 © 2018. The Authors. Published for AMER ABRA cE-Bs by e-International Publishing House, Ltd., UK. This is an open-access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer–review under responsibility of AMER (Association of Malaysian Environment-Behaviour Researchers), ABRA (Association of Behavioural Researchers on Asians) and cE-Bs (Centre for Environment-Behaviour Studies), Faculty of Architecture, Planning & Surveying, Universiti Teknologi MARA, Malaysia. DOI:https://doi.org/10.21834/jabs.v3i10.318  

scholarly journals Target Setting Outlook for New Residential Building Energy Efficiency Promotion in China: A Frontline Perspective Using Delphi

Energies ◽  
2019 ◽  
Vol 12 (9) ◽  
pp. 1629
Author(s):  
Yinan Li ◽  
Neng Zhu ◽  
Beibei Qin
Keyword(s):  
Energy Efficiency ◽  
Evaluation System ◽  
Energy Intensity ◽  
Residential Buildings ◽  
Residential Building ◽  
Building Energy ◽  
Successful Implementation ◽  
Building Energy Efficiency ◽  
Target Setting ◽  
Intensity Index

Promoting energy efficiency (EE) requirements for new residential buildings has been proven to be an effective way to slow down the rapid increase of energy consumption. Its successful implementation relies significantly on the attitudes and participation of various stakeholders within the industry, yet they are normally taken for granted. This paper explores and reports both the consensus among and the diversity of the attitudes of frontline stakeholders toward future EE requirements in the new residential building sector via a nationwide Delphi questionnaire distributed to 29 institutes and 25 experts. Results indicate that promotion of approximately 30% EE every five years until 2030 is suggested and that 20% EE promotion every five years is the most likely to be achieved. In addition, China should progressively adopt the energy intensity index into the current building EE evaluation system. This paper also gives a detailed description of opinions from frontline stakeholders. The findings are expected to help researchers and policymakers better understand the true attitudes of stakeholders, thereby enabling the formation of a proper outlook for new residential building EE promotion.

Performance Evaluation of MadBoost on Face Detection

2019 ◽  
Vol 892 ◽  
pp. 200-209
Author(s):  
Rayner Pailus ◽  
Rayner Alfred
Keyword(s):  
Feature Extraction ◽  
Face Detection ◽  
Recognition Performance ◽  
Principal Component ◽  
Haar Wavelet ◽  
Extraction Methods ◽  
Face Image ◽  
Support Vector ◽  
Feature Extraction Method ◽  
Face Images

Adaboost Viola-Jones method is indeed a profound discovery in detecting face images mainly because it is fast, light and one of the easiest methods of detecting face images among other techniques of face detection. Viola Jones uses Haar wavelet filter to detect face images and it produces almost 80%accuracy of face detection. This paper discusses proposed methodology and algorithms that involved larger library of filters used to create more discrimination features among the images by processing the proposed 15 Haar rectangular features (an extension from 4 Haar wavelet filters of Viola Jones) and used them in multiple adaptive ensemble process of detecting face image. After facial detection, the process continues with normalization processes by applying feature extraction such as PCA combined with LDA or LPP to extract our week learners’ wavelet for more classification features. Upon the process of feature extraction proposed feature selection to index these extracted data. These extracted vectors are used for training and creating MADBoost (Multiple Adaptive Diversified Boost)(an improvement of Adaboost, which uses multiple feature extraction methods combined with multiple classifiers) is able to capture, recognize and distinguish face image (s) faster. MADBoost applies the ensemble approach with better weights for classification to produce better face recognition results. Three experiments have been conducted to investigate the performance of the proposed MADBoost with three other classifiers, Neural Network (NN), Support Vector Machines (SVM) and Adaboost classifiers using Principal Component Analysis (PCA) as the feature extraction method. These experiments were tested against obstacles of POIES (Pose, Obstruction, Illumination, Expression, Sizes). Based on the results obtained, Madboost is found to be able to improve the recognition performance in matching failures, incorrect matching, matching success percentages and acceptable time taken to perform the classification task.

scholarly journals Aerial Scene Classification through Fine-Tuning with Adaptive Learning Rates and Label Smoothing

2020 ◽  
Vol 10 (17) ◽  
pp. 5792 ◽  
Author(s):  
Biserka Petrovska ◽  
Tatjana Atanasova-Pacemska ◽  
Roberto Corizzo ◽  
Paolo Mignone ◽  
Petre Lameski ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Feature Extraction ◽  
Image Classification ◽  
Transfer Learning ◽  
Remote Sensing Image ◽  
Learning Rate ◽  
Fine Tuning ◽  
Support Vector ◽  
Learning Rates

Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common approach in the literature is employing CNNs for feature extraction, and subsequently train classifiers exploiting such features. In this paper, we propose the adoption of transfer learning by fine-tuning pre-trained CNNs for end-to-end aerial image classification. Our approach performs feature extraction from the fine-tuned neural networks and remote sensing image classification with a Support Vector Machine (SVM) model with linear and Radial Basis Function (RBF) kernels. To tune the learning rate hyperparameter, we employ a linear decay learning rate scheduler as well as cyclical learning rates. Moreover, in order to mitigate the overfitting problem of pre-trained models, we apply label smoothing regularization. For the fine-tuning and feature extraction process, we adopt the Inception-v3 and Xception inception-based CNNs, as well the residual-based networks ResNet50 and DenseNet121. We present extensive experiments on two real-world remote sensing image datasets: AID and NWPU-RESISC45. The results show that the proposed method exhibits classification accuracy of up to 98%, outperforming other state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document