Claim Missing Document
Check
Articles

Found 18 Documents
Search

Vehicle Speed Estimation Using Optical Flow on Traffic Video Under Day and Night Lighting Condition Anggisa, Ahmad Bramdimas; Prahara, Adhi
Signal and Image Processing Letters Vol 3, No 2 (2021)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/simple.v3i2.30

Abstract

Traffic violation and congestion can happen at day or night. As a preventive measure, CCTV is installed at strategic locations on the road to monitor the traffic violation and congestion. Usually, some speed sensors also installed to measure the speed of vehicles then through a system, it will inform the operator about speedy vehicles or predict a congestion. However, it is not effective because it needs a lot of sensors to be able to monitor the vehicle speed in many locations especially in the highway and before the intersection all the time. This problem leads to the development of intelligent traffic monitoring system using computer vision technology. In this research, an optical flow-based vehicle speed estimation method is proposed. The method takes a CCTV video as an input, defines the road region of interest/ROI, performs orthographic projection transformation to find the ratio of distance, uses optical flow Farneback to track the vehicle movements, and estimates the vehicle’s average speed on the road. The method is tested using CCTV video under day and night lighting condition. From the experiment, the proposed method achieves 9.8% of average RMSE.
Multivariate Time Series Stock Price Data Prediction in The Banking Sector in Indonesia Using Bidirectional Long Short-Term Memory (BiLSTM) Pramesti, Mara Indar; Indikawati, Fitri Indra; Prahara, Adhi
Signal and Image Processing Letters Vol 4, No 2 (2022)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/simple.v4i2.33

Abstract

The capital market is a place for individuals or business entities to carry out investment activities, especially in the banking sector, one of the sectors in the LQ45 stock index which is in great demand by investors in Indonesia. In the capital market, one of the investments that can be made is stock investment, but investors will be faced with uncertainty by fluctuations in stock prices caused by several factors, one of which is macroeconomic factors. Therefore, a predictive analysis of stock prices is needed to prevent uncertainty and minimize losses. Accurate prediction models can use deep learning algorithm methods. In the prediction of stock price movements, the data used is historical data on stock prices which is time series type data. This study conducted stock price predictions using the Bidirectional Long Short-Term Memory (biLSTM) method. biLSTM is another variation of the LSTM model. The object of this study uses the variables open, close, adj close, low, high, volume, value, buying rate, selling rate. The data that has been obtained will be preprocessing. Next build a prediction model using hyperparameter tuning with Genetic Algorithm (GA), train the model and evaluate the model. Data testing was carried out using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) with 4 data from the banking sector in Indonesia including Bank BRI, Bank BNI, Bank BCA, and Bank Mandiri. Based on the data testing that has been carried out, the results of the biLSTM algorithm can predict stock prices accurately because it has a relatively low RMSE value with a MAPE value below 10%.
Horizontal Lines and Haar-like Features for Car Detection Using Support Vector Machine on Traffic Imagery Abdillah, Aldi Khoirul; Prahara, Adhi
Signal and Image Processing Letters Vol 3, No 1 (2021)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/simple.v3i1.29

Abstract

Traffic monitoring system in Indonesia is not yet efficient. CCTV cameras had been installed to monitor the traffic in strategic locations. However, it is difficult to monitor each traffic point all the time. This problem leads to the development of intelligent traffic monitoring system using computer vision technology. In this research, a car detection method is proposed. Car detection still poses challenges especially when dealing with various situations on the road. The proposed car detection method uses horizontal lines and Haar-like features trained with Support Vector Machine (SVM) to detect cars on traffic imagery. The car detector is trained on frontal-view car dataset. The test result shows 0.2 log average miss rate and 0.9 average precision. From the low miss rate and high precision, the proposed method shows promising solution in detecting cars on traffic imagery.
Application of Genetic Algorithms for Multiple Traveling Salesman Problems: A Case Study of Distribution of Sacrificial Animal Meat at the Islamic Center in Mataram City Alqorni, Wais; Prahara, Adhi
Signal and Image Processing Letters Vol 4, No 1 (2022)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/simple.v4i1.31

Abstract

Islamic Center of Mataram is the center of Islamic religious activities. On Eid al-Adha and Tasyrik Day, animals are slaughtered. The average amount of animal meat that will be distributed annually is 7500 Kg of raw meat where will be distributed to 9 (nine) urban villages in Mataram City. In distributing the meat of the sacrificial animal, they only have limited time and staff, which is only done on 3 days of Tasyrik or sometimes only 2 days because the slaughtering is not carried out immediately after Eid prayer. Distribution starts from 12.00 - 16.00 every day. To help the problem of the distribution process, known as the Multiple Traveling Salesman Problem, the author uses a genetic algorithm to solve the problem. To build a software to implement Genetic Algorithm on the M-TSP problem in the distribution of sacrificial animal meat, several stages are carried out, starting from collecting data used to apply genetic algorithms, designing display prototypes and features to be able to process the data that has been collected, stages of system coding become a web-based system and finally testing the system that has been made. By implementing officer data and distribution locations which will then be tested using one of algorithms, namely the Genetic Algorithm. The accuracy and efficiency of the total distance that will be taken in making a distribution route using this algorithm where calculation is carried out by finding the largest fitness value from several kromosomal populations that are generated after going through crossover process and gene mutations on each kromosome. The result from this system tests with different method are 100% from using a black box, and 81.7 from using SUS testing which is classified as good. The best average fitness value resulting from testing the distribution system of sacrificial animal meat using the number of chromosomes 9 as many as 5 experiments using the number of generations 3, and the crossover parameter = 40% and mutation = 40% which is 0.045 with a total distance of 22.33 km. The design of this system is very useful for the administrators Islamic Center of Mataram ta'mir as a reference in determining optimal route in process of distributing sacrificial animal meat as well as for authors in applying the scientific theory they have.
Real-time Facial Expression Recognition to Track Non-verbal Behaviors as Lie Indicators During Interview Setiawan, Arif Budi; Anwar, Kaspul; Azizah, Laelatul; Prahara, Adhi
Signal and Image Processing Letters Vol 1, No 1 (2019)
Publisher : Association for Scientific Computing Electrical and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/simple.v1i1.85

Abstract

During interview, a psychologist should pay attention to every gesture and response, both verbal and nonverbal language/behaviors, made by the client. Psychologist certainly has limitation in recognizing every gesture and response that indicates a lie, especially in interpreting nonverbal behaviors that usually occurs in a short time. In this research, a real time facial expression recognition is proposed to track nonverbal behaviors to help psychologist keep informed about the change of facial expression that indicate a lie. The method tracks eye gaze, wrinkles on the forehead, and false smile using combination of face detection and facial landmark recognition to find the facial features and image processing method to track the nonverbal behaviors in facial features. Every nonverbal behavior is recorded and logged according to the video timeline to assist the psychologist analyze the behavior of the client. The result of tracking nonverbal behaviors of face is accurate and expected to be useful assistant for the psychologists.
Capacity building for LAZIS administration through Google Applications Training Yuliansyah, Herman; Fahana, Jefree; Prahara, Adhi; Masitha, Alya
KACANEGARA Jurnal Pengabdian pada Masyarakat Vol 8, No 4 (2025): November
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/kacanegara.v8i4.3039

Abstract

The rapid development of information technology has prompted social institutions such as LazisMU to adopt digital administrative systems. However, technical limitations among staff hinder optimal implementation. This community service aimed to enhance the administrative capacity of LazisMU staff through targeted training in Google Applications. The training involved needs assessment, module development, and interactive sessions covering Google Drive, Docs, Sheets, and Forms. Results indicate significant improvement in participants’ understanding and skills, particularly in document management, financial reporting, and data handling. Pre-test and post-test comparisons, along with direct observation, showed over 60% improvement in comprehension scores. These outcomes highlight the positive impact of digital training on operational efficiency. Further training and periodic monitoring are recommended to ensure continued digital competence development.
Texton Based Segmentation for Road Defect Detection from Aerial Imagery Prahara, Adhi; Akbar, Son Ali; Azhari, Ahmad
International Journal of Artificial Intelligence Research Vol 4, No 2 (2020): December 2020
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1055.466 KB) | DOI: 10.29099/ijair.v4i2.179

Abstract

Road defect such as potholes and road cracks, became a problem that arose every year in Indonesia. It could endanger drivers and damage the vehicles. It also obstructed the goods distribution via land transportation that had major impact to the economy. To handle this problem, the government released an online complaints system that utilized information system and GPS technology. To follow up the complaints especially road defect problem, a survey was conducted to assess the damage. Manual survey became less effective for large road area and might disturb the traffic. Therefore, we used road aerial imagery captured by Unmanned Aerial Vehicle (UAV). The proposed method used texton combined with K-Nearest Neighbor (K-NN) to segment the road area and Support Vector Machine (SVM) to detect the road defect. Morphological operation followed by blob analysis was performed to locate, measure, and determine the type of defect. The experiment showed that the proposed method able to segment the road area and detect road defect from aerial imagery with good Boundary F1 score.
Image Classification of Wayang Using Transfer Learning and Fine-Tuning of CNN Models Banjaransari, Muhammad; Prahara, Adhi
Buletin Ilmiah Sarjana Teknik Elektro Vol. 5 No. 4 (2023): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v5i4.9977

Abstract

Wayang (shadow puppetry) is a traditional puppetry used in a performance to tell a story about the heroism of its main characters. Wayang has gained recognition as a cultural masterpiece by UNESCO. However, this cultural heritage now declining and not many people know about wayang. One of the solutions is using computer vision technology to classify wayang images. In this research, a transfer learning approach using Convolutional Neural Network (CNN) models namely MobileNetV2 and VGG16 followed by fine-tuning was proposed to classify wayang. The dataset consists of 3,000 images divided into 30 classes. This data is split into training and test data that are utilized for training and evaluating the model. Based on the evaluation, the MobileNetV2 model achieved precision, recall, F1-score, and accuracy of 95%, 94%, 94%, and 94.17%, respectively. Meanwhile, the VGG-16 model obtained 93% for all metrics. It can be concluded that transfer learning and fine-tuning using the MobileNetV2 model produces the best result in classifying wayang images compared to the VGG16 model. With good performance, the proposed method can be implemented on mobile applications to provide information about wayang from the captured images, thus indirectly supporting the preservation of cultural heritage in Indonesia.