This study presents pre-processing methods for detecting lane detection using camera and Light Detection and Ranging (LiDAR) sensor technologies. Standard image processing methods are not suitable for complicated roads with various sign on the ground. Thus, determining the right techniques for pre-processing such data would be a challenge. The objectives of this study are to pre-process the scanned images and apply the image recognition algorithm for lane detection. The study employed Canny Edge Detection and Hough Transform algorithms on several sets of images. A different region of interest was experimented to find the optimal one. The experimental results showed that the proposed algorithms could be practical in terms of effectively detecting road lines and generate lane detection.
Electricity is one of the most important resources and fundamental infrastructure for every nation. Its milestone shows a significant contribution to world development that brought forth new technological breakthroughs throughout the centuries. Electricity demand constantly fluctuates, which affects the supply. Suppliers need to generate more electrical energy when demand is high, and less when demand is low. It is a common practice in power markets to have a reserve margin for unexpected fluctuation of demand. This research paper investigates regression techniques: multiple linear regression (MLR) and vector autoregression (VAR) to forecast demand with predictors of economic growth, population growth, and climate change as well as the demand itself. Auto-Regressive Integrated Moving Average (Auto-ARIMA) was used in benchmarking the forecasting. The results from MLR and VAR (lag-values=20) and Auto-ARIMA are monitored for five months from June to October of 2019. Using the root mean square error (RMSE) as an indicator for accuracy, Auto-ARIMA has the lowest RMSE for four months except in June 2019. VAR (lag-values=20) shows good forecasting capabilities for all five months, considering it uses the same lag values (20) for each month. Three different techniques have been successfully examined in order to find the best model for the prediction of the demand.