Investors need analytical tools to predict the price and to determine trading positions. Candlestick pattern is one of the analytical tools that predict price trends. However, the patterns are difficult to recognize, and some studies show doubts regarding the robustness of the recognizing system. In this study, we tested the predictive ability of candlestick patterns to determine trading positions. We use Gramian Angular Field (GAF) to encode candlestick patterns as images to recognize 3-hour and 5-hour of 6 candlestick patterns with Convolutional Neural Network (CNN), coupled with the Long short-term memory (LSTM) model to predict the close price. The trading position consists of buying and selling position with a hold period of several hours. Our results show CNN successfully detected 3-hour and 5-hour GAF candlestick patterns with an accuracy of 90% and 93%. LSTM can predict the close price trend with 155.458 RMSE scores and 0.9754% MAPE with 10-hour look back. With a hold duration of three hours and CNN-LSTM as an additional model, the test data's 85 candlestick patterns are recognized with 82.7% accuracy, compared to 60% accuracy of profitable trading positions when CNN candlestick pattern recognition is used alone. Compared to employing CNN candlestick pattern identification alone, the CNN-LSTM model combination can improve the prediction power of candlestick patterns and offer more lucrative trading positions.
An accurate rainfall data has an important role in the Indonesia Fire Danger Rating System (Ina-FDRS) which has been developed by PTPSW – BPPT since 2017. Continuing the previous study, during wet and dry season, an accurate rainfall data becomes one of the important inputs and has big impact on the Ina-FDRS. Unfortunately, surface rainfall data from AWS and ARG have limited availability especially on the spatial resolution data, therefore Ina-FDRS will use HIMAWARI-8 rain rate data as an input. On the other hand, satellite rainfall data also has limitation on the accuracy, HIMAWARI-8 detects top cloud temperature, then by using IMSRA method to calculate rainfall values. This preliminary study aims to validate rain rate from HIMAWARI-8 satellite image data with ground-based rainfall data from AWS/ARG during fire and non-fire period, from 1 – 31 August 2015 and 15 April – 15 May 2018. Afterward, we will use the validated rainfall data as an input for Ina-FDRS.
Ground Penetrating Radar (GPR) employs an ultra-wideband (UWB) signal for detecting objects under the ground surface. In a certain GPR application, a proper UWB signal is needed to obtain a good detection result. Ricker wavelet is one type of UWB signal that can be used in GPR operation. The effect of adjusting the Ricker wavelet duty cycle on the B-scan result was investigated and the result is discussed in this paper. Laboratory experiments were performed by modelling the GPR system using Vector Network Analyzer (VNA). The result shows that selecting a Ricker wavelet’s duty cycle is successful to show the target clearly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.