scholarly journals Multi-Quantile Recurrent Neural Network for Feeder-Level Probabilistic Energy Disaggregation Considering Roof-Top Solar Energy

2021 ◽  
Author(s):  
Xiao-Yu Zhang ◽  
Chris Watkins ◽  
Stefanie Kuenzel
Keyword(s):  
Neural Network ◽  
Solar Energy ◽  
Recurrent Neural Network ◽  
Regression Tree ◽  
Prediction Intervals ◽  
Gradient Boosting ◽  
Training Time ◽  
Light Gradient ◽  
Energy Disaggregation ◽  
Net Load

The purpose of feeder-level energy disaggregation is to decouple the net load measured at the feeder-head into various components. This technology is vital for power system utilities since increased visibility of controllable loads enables the realization of demand-side management strategies. However, energy disaggregation at the feeder level is difficult to realize since the high-penetration of embedded generation masks the actual demand and different loads are highly aggregated. In this paper, the solar energy at the grid supply point is separated from the net load at first via either an unsupervised upscaling method or the supervised gradient boosting regression tree (GBRT) method. To deal with the uncertainty of the load components, the probabilistic energy disaggregation models based on multi-quantile recurrent neural network model (multi-quantile long short-term memory (MQ-LSTM) model and multi-quantile gated recurrent unit (MQ-GRU) model) are proposed to disaggregate the demand load into controlled loads (TCLs), non-thermostatically controlled loads (non-TCLs), and non-controllable loads. A variety of relevant information, including feeder measurements, meteorological measurements, calendar information, is adopted as the input features of the model. Instead of providing point prediction, the probabilistic model estimates the conditional quantiles and provides prediction intervals. A comprehensive case study is implemented to compare the proposed model with other state-of-the-art models (multi-quantile convolutional neural network (MQ-CNN), quantile gradient boosting regression tree (Q-GBRT), Quantile Light gradient boosting machine (Q-LGB)) from training time, reliability, sharpness, and overall performance aspects. The result shows that the MQ-LSTM can estimate reliable and sharp Prediction Intervals for target load components. And it shows the best performance among all algorithms with the shortest training time. Finally, a transfer learning algorithm is proposed to overcome the difficulty to obtain enough training data, and the model is pre-trained via synthetic data generated from a public database and then tested on the local dataset. The result confirms that the proposed energy disaggregation model is transferable and can be applied to other feeders easily. <br>

scholarly journals Multi-Quantile Recurrent Neural Network for Feeder-Level Probabilistic Energy Disaggregation Considering Roof-Top Solar Energy

2021 ◽  
Author(s):  
Xiao-Yu Zhang ◽  
Chris Watkins ◽  
Stefanie Kuenzel
Keyword(s):  
Neural Network ◽  
Solar Energy ◽  
Recurrent Neural Network ◽  
Regression Tree ◽  
Prediction Intervals ◽  
Gradient Boosting ◽  
Training Time ◽  
Light Gradient ◽  
Energy Disaggregation ◽  
Net Load

The purpose of feeder-level energy disaggregation is to decouple the net load measured at the feeder-head into various components. This technology is vital for power system utilities since increased visibility of controllable loads enables the realization of demand-side management strategies. However, energy disaggregation at the feeder level is difficult to realize since the high-penetration of embedded generation masks the actual demand and different loads are highly aggregated. In this paper, the solar energy at the grid supply point is separated from the net load at first via either an unsupervised upscaling method or the supervised gradient boosting regression tree (GBRT) method. To deal with the uncertainty of the load components, the probabilistic energy disaggregation models based on multi-quantile recurrent neural network model (multi-quantile long short-term memory (MQ-LSTM) model and multi-quantile gated recurrent unit (MQ-GRU) model) are proposed to disaggregate the demand load into controlled loads (TCLs), non-thermostatically controlled loads (non-TCLs), and non-controllable loads. A variety of relevant information, including feeder measurements, meteorological measurements, calendar information, is adopted as the input features of the model. Instead of providing point prediction, the probabilistic model estimates the conditional quantiles and provides prediction intervals. A comprehensive case study is implemented to compare the proposed model with other state-of-the-art models (multi-quantile convolutional neural network (MQ-CNN), quantile gradient boosting regression tree (Q-GBRT), Quantile Light gradient boosting machine (Q-LGB)) from training time, reliability, sharpness, and overall performance aspects. The result shows that the MQ-LSTM can estimate reliable and sharp Prediction Intervals for target load components. And it shows the best performance among all algorithms with the shortest training time. Finally, a transfer learning algorithm is proposed to overcome the difficulty to obtain enough training data, and the model is pre-trained via synthetic data generated from a public database and then tested on the local dataset. The result confirms that the proposed energy disaggregation model is transferable and can be applied to other feeders easily. <br>

scholarly journals ECG-AI: electrocardiographic artificial intelligence model for prediction of heart failure

2021 ◽  
Author(s):  
Oguz Akbilgic ◽  
Liam Butler ◽  
Ibrahim Karabayir ◽  
Patricia P Chang ◽  
Dalane W Kitzman ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Heart Failure ◽  
Convolutional Neural Network ◽  
Prediction Models ◽  
Smoking Status ◽  
Characteristic Curve ◽  
Gradient Boosting ◽  
Model Output ◽  
Light Gradient

Abstract Aims Heart failure (HF) is a leading cause of death. Early intervention is the key to reduce HF-related morbidity and mortality. This study assesses the utility of electrocardiograms (ECGs) in HF risk prediction. Methods and results Data from the baseline visits (1987–89) of the Atherosclerosis Risk in Communities (ARIC) study was used. Incident hospitalized HF events were ascertained by ICD codes. Participants with good quality baseline ECGs were included. Participants with prevalent HF were excluded. ECG-artificial intelligence (AI) model to predict HF was created as a deep residual convolutional neural network (CNN) utilizing standard 12-lead ECG. The area under the receiver operating characteristic curve (AUC) was used to evaluate prediction models including (CNN), light gradient boosting machines (LGBM), and Cox proportional hazards regression. A total of 14 613 (45% male, 73% of white, mean age ± standard deviation of 54 ± 5) participants were eligible. A total of 803 (5.5%) participants developed HF within 10 years from baseline. Convolutional neural network utilizing solely ECG achieved an AUC of 0.756 (0.717–0.795) on the hold-out test data. ARIC and Framingham Heart Study (FHS) HF risk calculators yielded AUC of 0.802 (0.750–0.850) and 0.780 (0.740–0.830). The highest AUC of 0.818 (0.778–0.859) was obtained when ECG-AI model output, age, gender, race, body mass index, smoking status, prevalent coronary heart disease, diabetes mellitus, systolic blood pressure, and heart rate were used as predictors of HF within LGBM. The ECG-AI model output was the most important predictor of HF. Conclusions ECG-AI model based solely on information extracted from ECG independently predicts HF with accuracy comparable to existing FHS and ARIC risk calculators.

scholarly journals Multistep-Ahead Solar Radiation Forecasting Scheme Based on the Light Gradient Boosting Machine: A Case Study of Jeju Island

2020 ◽  
Vol 12 (14) ◽  
pp. 2271 ◽  
Author(s):  
Jinwoong Park ◽  
Jihoon Moon ◽  
Seungmin Jung ◽  
Eenjun Hwang
Keyword(s):  
Solar Radiation ◽  
Global Solar Radiation ◽  
Jeju Island ◽  
Gradient Boosting ◽  
Probabilistic Forecasting ◽  
Training Time ◽  
Light Gradient ◽  
Proposed Model ◽  
Gradient Boosting Machine ◽  
Time Problem

Smart islands have focused on renewable energy sources, such as solar and wind, to achieve energy self-sufficiency. Because solar photovoltaic (PV) power has the advantage of less noise and easier installation than wind power, it is more flexible in selecting a location for installation. A PV power system can be operated more efficiently by predicting the amount of global solar radiation for solar power generation. Thus far, most studies have addressed day-ahead probabilistic forecasting to predict global solar radiation. However, day-ahead probabilistic forecasting has limitations in responding quickly to sudden changes in the external environment. Although multistep-ahead (MSA) forecasting can be used for this purpose, traditional machine learning models are unsuitable because of the substantial training time. In this paper, we propose an accurate MSA global solar radiation forecasting model based on the light gradient boosting machine (LightGBM), which can handle the training-time problem and provide higher prediction performance compared to other boosting methods. To demonstrate the validity of the proposed model, we conducted a global solar radiation prediction for two regions on Jeju Island, the largest island in South Korea. The experiment results demonstrated that the proposed model can achieve better predictive performance than the tree-based ensemble and deep learning methods.

scholarly journals Convolutional Neural Network Classifies Pathological Voice Change in Laryngeal Cancer with High Accuracy

2020 ◽  
Vol 9 (11) ◽  
pp. 3415
Author(s):  
HyunBum Kim ◽  
Juhyeong Jeon ◽  
Yeon Jae Han ◽  
YoungHoon Joo ◽  
Jonghwan Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sensitivity And Specificity ◽  
Laryngeal Cancer ◽  
Healthy Subjects ◽  
Gradient Boosting ◽  
Support Vector ◽  
Vowel Sound ◽  
Light Gradient ◽  
Extreme Gradient Boosting

Voice changes may be the earliest signs in laryngeal cancer. We investigated whether automated voice signal analysis can be used to distinguish patients with laryngeal cancer from healthy subjects. We extracted features using the software package for speech analysis in phonetics (PRAAT) and calculated the Mel-frequency cepstral coefficients (MFCCs) from voice samples of a vowel sound of /a:/. The proposed method was tested with six algorithms: support vector machine (SVM), extreme gradient boosting (XGBoost), light gradient boosted machine (LGBM), artificial neural network (ANN), one-dimensional convolutional neural network (1D-CNN) and two-dimensional convolutional neural network (2D-CNN). Their performances were evaluated in terms of accuracy, sensitivity, and specificity. The result was compared with human performance. A total of four volunteers, two of whom were trained laryngologists, rated the same files. The 1D-CNN showed the highest accuracy of 85% and sensitivity and sensitivity and specificity levels of 78% and 93%. The two laryngologists achieved accuracy of 69.9% but sensitivity levels of 44%. Automated analysis of voice signals could differentiate subjects with laryngeal cancer from those of healthy subjects with higher diagnostic properties than those performed by the four volunteers.

scholarly journals Deep Capsule Network for Facial Emotion Recognition

2021 ◽  
pp. 1-6
Author(s):  
Tegani Salem ◽  
Telli Abdelmoutia
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Facial Emotion Recognition ◽  
Facial Emotion ◽  
Gradient Boosting ◽  
Expression Recognition ◽  
Light Gradient ◽  
Gradient Boosting Machine ◽  
Artificial Neural Network Ann ◽  
Classification Of Images

Although the classification of images has become one of the most important challenges, neural networks have had the most success with this task; this has shifted the focus towards architecture-based engineering rather than feature engineering. However, the enormous success of the convolutional neural network (CNN) is still far from comparable to the human brain's performance. In this context, a new and promising algorithm called a capsule net that is based on dynamic routing and activity vectors between capsules appeared as an efficient technique to exceed the limitations of the artificial neural network (ANN), which is considered to be one of the most important existing classifiers. This paper presents a new method-based capsule network with light-gradient-boosting-machine (LightGBM) classifiers for facial emotion recognition. To achieve our aim, there were two steps to our technique. Initially, the capsule networks were merely employed for feature extraction. Then, using the outputs computed from the capsule networks, a LightGBM classifier was utilised to detect seven fundamental facial expressions. Experiments were carried out to evaluate the suggested facial-expression-recognition system's performance. The efficacy of our proposed method, which achieved an accuracy rate of 91%, was proven by its testing the results on the CK+ dataset. KEYWORDS Image classifications, LightGBM, machine learning, computer vision, CNN, deep learning

scholarly journals Time Series Data Prediction using Elman Recurrent Neural Network on Tourist Visits in Tanah Lot Tourism Object

2019 ◽  
Vol 9 (1) ◽  
pp. 314-320 ◽  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Time Series Data ◽  
Network Models ◽  
Series Data ◽  
Neural Network Models ◽  
Training Time ◽  
Sliding Windows ◽  
Learning Time

The prediction of time series data is a forecast using the analysis of a relationship pattern between what will be predicted (prediction) and the time variable. The prediction process using the recurrent neural network (RNN) model could recognize and learn the data pattern of time series, but the presence of fluctuations in data makes the introduction of data patterns difficult to be learned. The data used for forecasting are tourist visits to Tanah Lot Bali tourist attraction for 10 years (2008-2017). The training process uses the RNN method on high fluctuating data, which requires a relatively long time in recognizing and studying the data patterns. Modification of the RNN method on learning rate and momentum by using dynamic values, can shorten learning time. The results showed the learning time using the RNN dynamic value, smaller than the variants of the RNN method such as the RNN Elman, Jordan RNN, Fully RNN, LSTM and the feedforward method (Backpropagation). The resulting error value is 0,05105 MSE. This value is smaller than the Fully RNN, Jordan RNN, LSTM and Feedforward methods. The elman method has the shortest training time among other models. The purpose of this research is to make a prediction design consisting of sliding windows techniques, training with neural network models and validation of results with k-fold cross-validation.

Sign in / Sign up

Export Citation Format

Share Document