Search

Short-range, wireless communications in the vicinity of, or inside, a human body (but not limited to humans) are specified in this standard. It uses existing industrial scientific medical (ISM) bands as well as frequency bands approved by national medical and/or regulatory authorities. These sensors provide accurate and reliable information about the situation or activity occurring at any time. This high responsiveness of these sensors has made lives easy and safe. This article will perform an investigation on the WBAN's application for motion detection based on android smartwatch. The main problem is how to the sensors that attached on the human body can send of data via Bluetooth and read the motion and orientation of the body and display in the graph form. However, if the sensors do not match, the result of output display inappropriate. This article proposed method by using accelerometer and gyroscope sensors which are integrated with smartwatch to overcome the main problem. This application will display results in the form of numeric values and then convert in graph form. These results have proven that WBAN's application for motion sensing can be used for detection of motion and orientation via Bluetooth based on android smartwatch.

This research paper proposes a new hybrid methodology for very short-term load forecasting of hourly or designed to predict load for 1 hour ahead. The proposed hybrid methodology is based on weather data especially for optimizing the operation of power generating electricity from thermal generation. This hybrid modelling is a combination of the Fuzzy-Multi-Objective Decision-Making and feed-forward-Neural Network method. The novelty of this hybrid model is taking into account the weather and meteorology data. The first hybrid model implements Fuzzy-Multi Objective Decision Making as an input data pre-processing technique before the feed-forward Neural Network model. The error statistical indicators of the Fuzzy-Multi Objective Decision Making-Feed Forward Neural Network) model for mean square error is the mean value error 0.001 and root mean square error is mean value error 0.2. Note that the highest root means square error was 4.43 MW and the mean square error was 837.8 MW during the sixteen periods. [ABSTRACT FROM AUTHOR]

This paper proposes a novel methodology for very short term load forecasting of hourly. The proposed methodology is based on meteorology data i.e. temperature, humidity, especially for optimizing the operation of power generating electricity from thermal unit generation. This modelling methodology is a combination of k-nearest neighbor (k-NN) method and feed forward- Neural Network (Feed-Forward-NN) method. The k-NN-Feed-Forward NN model is designed to prediction load for 1 hour ahead based on meteorology data for the target Thermal Unit Generation which position adjacent by twelve hydro thermal unit generation. The novelty of this model is taking into account the meteorology data. A set of load measurement samples was available from the hydro thermal unit generation in Indonesia Region 4 which is used as test data. The first model implements k-NN as a input data preprocessing technique prior to feed forward NN model. The error statistical indicators of k-NN-Feed-Forward-NN method The mean absolute deviation error statistical indicators of k-NN model is 103.48 MW and MAPE is 18.8%. On the other hand, the error statistical indicator for proposed model (Euclidean k-NNfeed forward-NN model) MAD is 19.37 MW and MAPE is 2.21%. Note that the highest mean absolute deviation (MAD) was 75,11 MW and mean absolute percentage error (MAPE) was 10.38% during the twelve period. The models forecasts are then compared to measured data and simulation results indicate that the k-NN-Feed Forward NN-based method presented in this research can calculate hourly load with satisfactory accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a novel methodology for very short term forecasting of hourly global solar irradiance (GSI). The proposed methodology is based on meteorology data, especially for optimizing the operation of power generating electricity from photovoltaic (PV) energy. This methodology is a combination of k-nearest neighbor (k-NN) algorithm modelling and artificial neural network (ANN) model. The k-NN-ANN method is designed to forecast GSI for 60 min ahead based on meteorology data for the target PV station which position is surrounded by eight other adjacent PV stations. The novelty of this method is taking into account the meteorology data. A set of GSI measurement samples was available from the PV station in Taiwan which is used as test data. The first method implements k-NN as a preprocessing technique prior to ANN method. The error statistical indicators of k-NN-ANN model the mean absolute bias error (MABE) is 42 W/m2 and the root-mean-square error (RMSE) is 242 W/m2. The models forecasts are then compared to measured data and simulation results indicate that the k-NN-ANN-based model presented in this research can calculate hourly GSI with satisfactory accuracy. [ABSTRACT FROM AUTHOR]