Article Per Year (5 Year)
p-Index From 2021 - 2026
1.978
P-Index
This Author published in this journals
All Journal Jurnal Sarjana Teknik Informatika International Journal of Artificial Intelligence Research KACANEGARA Jurnal Pengabdian pada Masyarakat Buletin Ilmiah Sarjana Teknik Elektro Mobile and Forensics Signal and Image Processing Letters Science in Information Technology Letters Signal and Image Processing Letters
Adhi Prahara, Adhi
Universitas Ahmad Dahlan
Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Neuroscience

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Signal and Image Processing Letters

 1 
Gender classification using fisherface and support vector machine on face image Fatkhannudin, Muhammad Noor; 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.v1i1.86

Abstract

Computer vision technology has been widely used in many applications and devices that involves biometric recognition. One of them is gender classification which has notable challenges when dealing with unique facial characteristics of human races. Not to mention the challenges from various poses of face and the lighting conditions. To perform gender classification, we resize and convert the face image into grayscale then extract its features using Fisherface. The features are reduced into 100 components using Principal Component Analysis (PCA) then classified into male and female category using linear Support Vector Machine (SVM). The test that conducted on 1014 face images from various human races resulted in 86% of accuracy using standard k-NN classifier while our proposed method shows better result with 88% of accuracy.
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.
Co-Authors A.A. Ketut Agung Cahyawan W Abdillah, Aldi Khoirul Ahmad Azhari Alqorni, Wais ALYA MASITHA Anggisa, Ahmad Bramdimas Anwar, Kaspul Arif Budi Setiawan Banjaransari, Muhammad Fatkhannudin, Muhammad Noor Fatkhannudin, Muhammad Noor Habibillah, Ahmad Yasin Herman Yuliansyah, Herman Indikawati, Fitri Indra Jefree Fahana Laelatul Azizah, Laelatul Munif, Rihwan Murinto Murinto Pramesti, Mara Indar Ramadayanti, Susanti Aulia Rani, Siti Sofia Romadhoni, Ilham Fauzi Son Ali Akbar