Search

Smart WiFi thermostats have moved well beyond the function they were originally designed for; namely, controlling heating and cooling comfort in buildings. They are now also learning from occupant behaviors and permit occupants to control their comfort remotely. This research seeks to go beyond this state of the art by utilizing smart WiFi thermostat data in residences to develop dynamic predictive models for room temperature and cooling/heating demand. These models can then be used to estimate the energy savings from new thermostat temperature schedules and estimate peak load reduction achievable from maintaining a residence in a minimum thermal comfort condition. Back Propagation Neural Network (BPNN), Long-Short Term Memory (LSTM), and Encoder-Decoder LSTM dynamic models are explored. Results demonstrate that LSTM outperforms BPNN and Encoder-Decoder LSTM approach, yielding and a MAE error of 0.5 °C, equal to the resolution error of the measured temperature. Additionally, the models developed are shown to be highly accurate in predicting savings from aggressive thermostat set point schedules, yielding deep reduction of up to 14.3% for heating and cooling, as well as significant energy reduction from curtailed thermal comfort in response to a high demand event. [ABSTRACT FROM AUTHOR]

• Physical load levels associated with construction activities were predicted from wearable sensor data. • Walking pattern changes caused by physical loads were analyzed for the prediction. • Prediction model using bidirectional long-short term memory was developed. • Results indicated 74.6 to 98.6% accuracy and 0.59 to 0.99 F-score in classification. Work-related musculoskeletal disorders (WMSDs) are the leading cause of the nonfatal injuries for construction workers, and a worker's overexertion is a major source of such WMSDs. Pushing, pulling, and carrying movements—which are all activities largely associated with physical loads—account for 35% of WMSDs. However, most previous studies have focused on the identification of non-ergonomic postures, and there has been limited effort expended on measuring a worker's exposures to the physical loads caused by materials or tools during construction tasks. With the advantage of using a wearable inertial measurement sensor to monitor a worker's bodily movements, this study investigates the feasibility of identifying various physical loading conditions by analyzing a worker's lower body movements. In the experiment with laboratory settings, workers performed a load carrying task by moving concrete bricks. A bidirectional long short-term memory algorithm is employed to classify physical load levels; this approach achieved 74.6 to 98.6% accuracy and 0.59 to 0.99 F-score in classification. The results demonstrate the feasibility of the proposed approach in identifying the states of physical loads. The findings of this study contribute to the literature on classifying ergonomically at-risk workers and on preventing WMSDs in high physical demand occupations, thereby helping enhance the health and safety of the construction workplace. [ABSTRACT FROM AUTHOR]

Rolling bearing fault diagnosis is closely related to the safety of mechanical system. In real-world diagnosis, it is difficult to obtain abundant labeled data due to varying operation conditions, complex working environment and inevitable indirect measurement, which will affect the ability of diagnosing. To tackle this problem, a deep transfer maximum classifier discrepancy method is proposed under few labeled data, which utilizes fully deep learning and transfer learning. Firstly, a batch-normalized long-short term memory (BNLSTM) model which can learn the mapping relationship between two kinds of datasets is designed to generate some auxiliary samples. Then, a transfer maximum classifier discrepancy (TMCD) method, which considers the characteristics of each data type by an adversarial strategy, is applied to align probability distributions of auxiliary samples generated by BNLSTM and unlabeled data from target domain. Sufficient experimental results indicate the effectiveness of the proposed method under few labeled data. [ABSTRACT FROM AUTHOR]

• Soybean yield at municipality-level was forecasted using satellite and weather data. • LSTM neural networks outperformed conventional machine learning algorithms in soybean yield prediction. • The model accuracy decreased as we anticipated earlier dates of the predictions. • Soybean yield can be forecasted with MAE of 0.42 Mg ha−1 ~70 days before harvesting. Soybean yield predictions in Brazil are of great interest for market behavior, to drive governmental policies and to increase global food security. In Brazil soybean yield data generally demand various revisions through the following months after harvest suggesting that there is space for improving the accuracy and the time of yield predictions. This study presents a novel model to perform in-season ("near real-time") soybean yield forecasts in southern Brazil using Long-Short Term Memory (LSTM), Neural Networks, satellite imagery and weather data. The objectives of this study were to: (i) compare the performance of three different algorithms (multivariate OLS linear regression, random forest and LSTM neural networks) for forecasting soybean yield using NDVI, EVI, land surface temperature and precipitation as independent variables, and (ii) evaluate how early (during the soybean growing season) this method is able to forecast yield with reasonable accuracy. Satellite and weather data were masked using a non-crop-specific layer with field boundaries obtained from the Rural Environment Registry that is mandatory for all farmers in Brazil. Main outcomes from this study were: (i) soybean yield forecasts at municipality-scale with a mean absolute error (MAE) of 0.24 Mg ha−1 at DOY 64 (march 5) (ii) a superior performance of the LSTM neural networks relative to the other algorithms for all the forecast dates except DOY 16 where multivariate OLS linear regression provided the best performance, and (iii) model performance (e.g., MAE) for yield forecast decreased when predictions were performed earlier in the season, with MAE increasing from 0.24 Mg ha−1 to 0.42 Mg ha−1 (last values from OLS regression) when forecast timing changed from DOY 64 (March 5) to DOY 16 (January 6). This research portrays the benefits of integrating statistical techniques, remote sensing, weather to field survey data in order to perform more reliable in-season soybean yield forecasts. [ABSTRACT FROM AUTHOR]

Developing an accurate and reliable multi-step ahead prediction model is a key problem in many Prognostics and Health Management (PHM) applications. Inevitably, the further one attempts to predict into the future, the harder it is to achieve an accurate and stable prediction due to increasing uncertainty and error accumulation. In this paper, we address this problem by proposing a prediction model based on Long Short-Term Memory (LSTM), a deep neural network developed for dealing with the long-term dependencies in time-series data. Our proposed prediction model also tackles two additional issues. Firstly, the hyperparameters of the proposed model are automatically tuned by a Bayesian optimization algorithm, called Tree-structured Parzen Estimator (TPE). Secondly, the proposed model allows assessing the uncertainty on the prediction. To validate the performance of the proposed model, a case study considering steam generator data acquired from different French nuclear power plants (NPPs) is carried out. Alternative prediction models are also considered for comparison purposes. • The paper presents an original multi-step ahead prediction framework for PHM applications. • An LSTM neural network and an MIMO prediction strategy are integrated to predict a long-term horizon. • Automatic hyperparameter optimization and prediction uncertainty quantification are addressed. • A case study considering SG data acquired from French NPPs is carried out. [ABSTRACT FROM AUTHOR]

The volatile and intermittent nature of solar energy itself presents a significant challenge in integrating it into existing energy systems. Accurate photovoltaic power prediction plays an important role in solving this problem. With the development of deep learning, more and more scholars have applied the deep learning model to time series prediction and achieved very good results. In this paper, a hybrid deep learning model (LSTM-Convolutional Network) is proposed and applied to photovoltaic power prediction. In the proposed hybrid prediction model, the temporal features of the data are extracted first by the long-short term memory network, and then the spatial features of the data are extracted by the convolutional neural network model. In order to show the superior performance of the proposed hybrid prediction model, the prediction results of the hybrid model are compared with those of the single model (long-short term memory network, convolutional neural network) and the hybrid network (Convolutional-LSTM Network) model, and the results of eight error evaluation indexes are given. The results show that the hybrid prediction model has better prediction effect than the single prediction model, and the proposed hybrid model (extract the temporal characteristics of data first, and then extract the spatial characteristics of data) is better than Convolutional-LSTM Network (extract the spatial characteristics of data first, and then extract the temporal characteristics of data). • Hybrid deep learning neural network (LSTM-Convolutional Network) is used for PV power forecasting. • The performance of hybrid proposed network is better than single model. • The placement order of the hybrid model has a great influence on the accuracy of the prediction. • The better effect of deep learning network on PV power forecasting is demonstrated. [ABSTRACT FROM AUTHOR]

In response to the impact of wind power ramp events on power system, a forecast and coordinated dispatch method for wind power ramp events is proposed. Firstly, the LSTM neural network is utilized to multi-step forecast the wind power, which can identify the features such as amplitude and duration of wind power ramp event in advance. Then, an ahead-delay adjustment method (ADAM) for wind power ramp events is proposed, which coordinates the thermal power generation units (referred to as units) and the energy storage system (referred to as ESS) to make two-step adjustments during the period before and after wind power ramp event. Thereby reducing the ramp rate of wind power, while reducing the requirement for the output power and capacity of ESS. Based on the above methods, a coordinated dispatch model of units and ESS considering wind power ramp events is established. The units are coordinated in advance to ensure sufficient adjustable reserves during wind power ramp events. A more economical and reliable dispatch plan can be achieved by coordinating the units and ESS according to the judging conditions. Finally, the forecast performance test and the ramp dispatch simulation are carried out in case study to verify the effectiveness of the forecast and dispatch method. • LSTM is used to forecast wind power ramp event in advance. • An ahead-delay adjustment method (ADAM) for wind power ramp event is proposed. • A thermal-storage coordinated economic dispatch model is established. [ABSTRACT FROM AUTHOR]

Land use change (LUC) is a dynamic process that significantly affects the environment, and various approaches have been proposed to analyze and model LUC for sustainable land use management and decision making. Recurrent neural network (RNN) models are part of deep learning (DL) approaches, which have the capability to capture spatial and temporal features from time-series data and sequential data. The main objective of this study was to examine variants of the RNN models by applying and comparing them when forecasting LUC in short time periods. Historical land use data for the City of Surrey, British Columbia, Canada were used to implement the several variants of the RNN models. The land use (LU) data for years 1996, 2001, 2006, and 2011 were used to train the DL models to enable the short-term forecast for the year 2016. For the 2011 to 2016 period, only 4.5% of the land use in the study area had changed. The results indicate that an overall accuracy of 86.9% was achieved, while actual changes in each LU type were forecasted with a relatively lower accuracy. However, only 25% of changed raster cells correctly forecasted the land use change. This research study demonstrates that RNN models provide a suite of valuable tools for short-term LUC forecast that can inform and complement the traditional long-term planning process; however, further additional geospatial data layers and considerations of driving factors of LUC need to be incorporated for model improvements. [ABSTRACT FROM AUTHOR]

A biomechanical understanding of gait stability is needed to reduce falling risk. As a typical parameter, the COM-COP (center of mass–center of pressure) inclination angle (IA) could provide valuable insight into postural control and balance recovery ability. In this study, an artificial neural network (ANN) model was developed to estimate COM-COP IA based on signals using an inertial sensor. Also, we evaluated how different types of ANN and the cutoff frequency of the low-pass filter applied to input signals could affect the accuracy of the model. An inertial measurement unit (IMU) including an accelerometer, gyroscope, and magnetometer sensors was fabricated as a prototype. The COM-COP IA was calculated using a 3D motion analysis system including force plates. In order to predict the COM-COP IA, a feed-forward ANN and long-short term memory (LSTM) network was developed. As a result, the feed-forward ANN showed a relative root-mean-square error (rRMSE) of 15% while the LSTM showed an improved accuracy of 9% rRMSE. Additionally, the LSTM displayed a stable accuracy regardless of the cutoff frequency of the filter applied to the input signals. This study showed that estimating the COM-COP IA was possible with a cheap inertial sensor system. Furthermore, the neural network models in this study can be implemented in systems to monitor the balancing ability of the elderly or patients with impaired balancing ability. [ABSTRACT FROM AUTHOR]

In recent years, analyzing Synthetic Aperture Radar (SAR) data has turned into one of the challenging and interesting topics in remote sensing. Radar sensors are capable of imaging Earth's surface independently of the weather conditions, local time of day, penetrating of waves through clouds, and containing spatial information on agricultural crop types. Based on these characteristics, the main goal sought in this research is to reveal the SAR imaging data capability in recognizing various agricultural crops in the main growth season in a more clarified and detailed way by using a deep-learning-based method. In the present research, the multi-temporal C-band Sentinel 1 images were used to classify 14 major classes of agricultural crops plus background in Denmark. By considering the capability of a deep learning method in analyzing satellite images, a novel, optimal, and lightweight network structure was developed and implemented based on a combination of a fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM) network. The average pixel-based accuracy and Intersection over Union obtained from the proposed network were 86% and 0.64, respectively. Winter rapeseed, winter barley, winter wheat, spring barley, and sugar beet had the highest pixel-based accuracies of 95%, 94%, 93%, 90%, and 90%; respectively. The pixel-based accuracies for eight crop types and the background class were more than 84%. The network prediction showed that in field borders the classification confidence was lower than the center regions of the fields. However, the proposed structure has been able to identify different crops in multi-temporal Sentinel 1 data of a large area of around 254 thousand hectares with high performance. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) has been widely studied because it plays a very important role in improving the economy and security of electric system operations. Many types of neural networks have been successfully used for STLF. In most of these methods, common neural networks were used, but without a systematic comparative analysis. In this paper, we first compare the most frequently used neural networks' performance on the load dataset from the State Grid Sichuan Electric Power Company (China). Then, considering the current neural networks' disadvantages, we propose a new architecture called a gate-recurrent neural network (RNN) based on an RNN for STLF. By evaluating all the methods on our dataset, the results demonstrate that the performance of different neural network methods are related to the data time scale, and our proposed method is more accurate on a much shorter time scale, particularly when the time scale is smaller than 20 min. [ABSTRACT FROM AUTHOR]

Designing advanced health monitoring systems is still an active research topic. Wearable and remote monitoring devices enable monitoring of physiological and clinical parameters (heart rate, respiration rate, temperature, etc.) and analysis using cloud-centric machine-learning applications and decision-support systems to predict critical clinical states. This paper moves from a totally cloud-centric concept to a more distributed one, by transferring sensor data processing and analysis tasks to the edges of the network. The resulting solution enables the analysis and interpretation of sensor-data traces within the wearable device to provide actionable alerts without any dependence on cloud services. In this paper, we use a supervised-learning approach to detect heartbeats and classify arrhythmias. The system uses a window-based feature definition that is suitable for execution within an asymmetric multicore embedded processor that provides a dedicated core for hardware assisted pattern matching. We evaluate the performance of the system in comparison with various existing approaches, in terms of achieved accuracy in the detection of abnormal events. The results show that the proposed embedded system achieves a high detection rate that in some cases matches the accuracy of the state-of-the-art algorithms executed in standard processors. [ABSTRACT FROM AUTHOR]

This study applied a GR4J model in the Xiangjiang and Qujiang River basins for rainfall-runoff simulation. Four recurrent neural networks (RNNs)—the Elman recurrent neural network (ERNN), echo state network (ESN), nonlinear autoregressive exogenous inputs neural network (NARX), and long short-term memory (LSTM) network—were applied in predicting discharges. The performances of models were compared and assessed, and the best two RNNs were selected and integrated with the lumped hydrological model GR4J to forecast the discharges; meanwhile, uncertainties of the simulated discharges were estimated. The generalized likelihood uncertainty estimation method was applied to quantify the uncertainties. The results show that the LSTM and NARX better captured the time-series dynamics than the other RNNs. The hybrid models improved the prediction of high, median, and low flows, particularly in reducing the bias of underestimation of high flows in the Xiangjiang River basin. The hybrid models reduced the uncertainty intervals by more than 50% for median and low flows, and increased the cover ratios for observations. The integration of a hydrological model with a recurrent neural network considering long-term dependencies is recommended in discharge forecasting. [ABSTRACT FROM AUTHOR]

The development and improvement of methods to map agricultural land cover are currently major challenges, especially for radar images. This is due to the speckle noise nature of radar, leading to a less intensive use of radar rather than optical images. The European Space Agency Sentinel-1 constellation, which recently became operational, is a satellite system providing global coverage of Synthetic Aperture Radar (SAR) with a 6-days revisit period at a high spatial resolution of about 20 m. These data are valuable, as they provide spatial information on agricultural crops. The aim of this paper is to provide a better understanding of the capabilities of Sentinel-1 radar images for agricultural land cover mapping through the use of deep learning techniques. The analysis is carried out on multitemporal Sentinel-1 data over an area in Camargue, France. The data set was processed in order to produce an intensity radar data stack from May 2017 to September 2017. We improved this radar time series dataset by exploiting temporal filtering to reduce noise, while retaining as much as possible the fine structures present in the images. We revealed that even with classical machine learning approaches (K nearest neighbors, random forest, and support vector machines), good performance classification could be achieved with F-measure/Accuracy greater than 86% and Kappa coefficient better than 0.82. We found that the results of the two deep recurrent neural network (RNN)-based classifiers clearly outperformed the classical approaches. Finally, our analyses of the Camargue area results show that the same performance was obtained with two different RNN-based classifiers on the Rice class, which is the most dominant crop of this region, with a F-measure metric of 96%. These results thus highlight that in the near future these RNN-based techniques will play an important role in the analysis of remote sensing time series. [ABSTRACT FROM AUTHOR]

Long-short term memory networks (LSTMs), which have recently emerged in sequential data analysis, are the most widely used type of recurrent neural networks (RNNs) architecture. Progress on the topic of deep learning includes successful adaptations of deep versions of these architectures. In this study, a new model for deep bidirectional LSTM network-based wavelet sequences called DBLSTM-WS was proposed for classifying electrocardiogram (ECG) signals. For this purpose, a new wavelet-based layer is implemented to generate ECG signal sequences. The ECG signals were decomposed into frequency sub-bands at different scales in this layer. These sub-bands are used as sequences for the input of LSTM networks. New network models that include unidirectional (ULSTM) and bidirectional (BLSTM) structures are designed for performance comparisons. Experimental studies have been performed for five different types of heartbeats obtained from the MIT-BIH arrhythmia database. These five types are Normal Sinus Rhythm (NSR), Ventricular Premature Contraction (VPC), Paced Beat (PB), Left Bundle Branch Block (LBBB), and Right Bundle Branch Block (RBBB). The results show that the DBLSTM-WS model gives a high recognition performance of 99.39%. It has been observed that the wavelet-based layer proposed in the study significantly improves the recognition performance of conventional networks. This proposed network structure is an important approach that can be applied to similar signal processing problems., (Copyright © 2018 Elsevier Ltd. All rights reserved.)