Amil Ahmad Ilham

Amil Ahmad Ilham

Auto-generated profile, based on publicly available information

Amil Ahmad Ilham

Department of Informatics, Universitas Hasanuddin, Jl. Poros Malino Km. 6, Bontomarannu, Gowa, Sulawesi Selatan 92171, Indonesia

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2022
Verified
Conference Paper
Closed access
RBRunal Rezkiawan Baharuddin
Runal Rezkiawan Baharuddin
MNMuhammad Niswar
Muhammad Niswar
AIAmil Ahmad Ilham
Amil Ahmad Ilham
SKShigeru Kashihara
Shigeru Kashihara
Soft-shell crab is an export product in which foreign demand is much higher than production. The production of soft-shell crabs done by selecting the crabs just prior to molting and placing them in a box until the molting occurs. Molting is a natural process of shedding the shell when crabs respond to the lack of growth space within its shell. Shortly after molting, the new crab shells are still very soft and will be hardened in a few hours after the crabs absorb calcium from water. Farmer must harvest the crab while the crabs’ shell is soft. This study investigates the initial identification of crab molting using machine learning classifier. We collected 1060 image datasets of crab molting and we divide data into 1000 training data and 60 testing data. We use three machine learning classifiers, namely K-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and the Random Forest Classifier (RFC). This study aims to compare and determine the best classification algorithm to be used for crab’s molting identification. The experimental results show that, KNN is the best classification algorithm for initial identification of crab’s molting.

20 March 2024 in Journal of Advanced Computational Intelligence and Intelligent Informatics
Verified
Journal Article
Open access
AIAmil Ahmad Ilham
Amil Ahmad Ilham
INIngrid Nurtanio
Ingrid Nurtanio
RIRidwang
Ridwang
SYSyafaruddin
Syafaruddin
This research uses a real-time, human-computer interaction application to examine sign language recognition. This work develops a rule-based hand gesture approach for Indonesian sign language in order to interpret some words using a combination of hand movements, mimics, and poses. The main objective in this study is the recognition of sign language that is based on hand movements made in front of the body with one or two hands, movements which may involve switching between the left and right hand or may be combined with mimics and poses. To overcome this problem, a research framework is developed by coordinating hand gestures with poses and mimics to create features by using holistic MediaPipe. To train and test data in real time, the long short time memory (LSTM) and gated recurrent unit (GRU) approaches are used. The research findings presented in this paper show that hand gestures in real-time interactions are reliably recognized, and some words are interpreted with the high accuracy rates of 94% and 96% for the LSTM and GRU methods, respectively.

1 December 2019
Verified
Conference Paper
Closed access
CIChairi Nur Insani
Chairi Nur Insani
INIngrid Nurtanio
Ingrid Nurtanio
AIAmil Ahmad Ilham
Amil Ahmad Ilham
This study aims to translate the Indonesian signaling system (SIBI), which focuses on 24 SIBI alphabets by comparing several lighting conditions of the room lights. The sensor used is the Leap Motion controller (LMC) to capture hand movements, the Leap Application Programming Interface (API) for the extraction of hand gestures, and Support Vector Machine (SVM) to classify sign languages. The data used consisted of 720 training data and 240 test data. Optimal results are obtained by using a 25W white light with LMC position under the light with 96.2% accuracy.

29 February 2024 in PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
Verified
Journal Article
Open access
PDF file
MYMukarramah Yusuf
Mukarramah Yusuf
AIAmil Ahmad Ilham
Amil Ahmad Ilham
APAdy Wahyudi Paundu
Ady Wahyudi Paundu
EWElly Warni
Elly Warni
AUA Sungkurawira Batara U
A Sungkurawira Batara U
ZSZulfiqry Saadputra
Zulfiqry Saadputra
Posyandu volunteers (cadre) have an essential role in the early detection of stunting in children under two years, achieved through routine weighing and monitoring of children's growth. This community service activity helps Posyandu volunteers in their role of recording and reporting. Posyandu volunteers use the SIP Book (Posyandu Information System) to record and report the results of activities at Posyandu and monitor maternal and child health, including children's nutritional status. Manually recording the nutritional status of children registered in Posyandu by the volunteers creates time inefficiencies in organizing the Posyandu. For this reason, an information system was built to precisely meet the needs of Posyandu volunteers in their role to monitor stunting in their work area. This information system is website-based and manages nutritional status data for toddlers at Posyandu. This system was tested on Posyandu volunteers in Nisombalia village, Maros Regency, South Sulawesi. Evaluation through questionnaire shows an improvement (from bad to very good) in terms of ease of recording and monitoring the nutritional status of children registered with Posyandu.

10 November 2020
Verified
Conference Paper
Closed access
SUSuherwin
Suherwin
ZZZahir Zainuddin
Zahir Zainuddin
AIAmil Ahmad Ilham
Amil Ahmad Ilham
Achieving low recognition time and high accuracy in real-time face recognition is challenging. This study implements Viola-Jones, Local Binary Pattern Histogram, and Euclidean Distance for real-time face recognition and calculates the face detection time. The face image is detected using the Viola-Jones method; its features are extracted using the Local Binary Pattern Histogram, and the face is recognized using Euclidean Distance. This study processes sample images from 1013 students as training data, with 20 images represent each student. The experiments show that 268 of 342 testing data are recognized correctly, resulting in an accuracy of 78.4%, with average real-time recognition time of 0.93 seconds.

31 March 2024 in JOIV : International Journal on Informatics Visualization
Verified
Journal Article
Open access
PDF file
DKDewi Kusumawati
Dewi Kusumawati
AIAmil Ahmad Ilham
Amil Ahmad Ilham
AAAndani Achmad
Andani Achmad
INIngrid Nurtanio
Ingrid Nurtanio
This study aims to determine which model is more effective in detecting lies between models with Mel Frequency Cepstral Coefficient (MFCC) and Short Time Fourier Transform (STFT) processes using Convolutional Neural Network (CNN). MFCC and STFT processes are based on digital voice data from video recordings that have been given lie or truth information regarding certain situations. Data is then pre-processed and trained on CNN. The results of model performance evaluation with hyper-tuning parameters and random search implementation show that using MFCC as Voice data processing provides better performance with higher accuracy than using the STFT process. The best parameters from MFCC are obtained with filter convolutional=64, kerneconvolutional1=5, filterconvolutional2=112, kernel convolutional2=3, filter convolutional3=32, kernelconvolutional3 =5, dense1=96, optimizer=RMSProp, learning rate=0.001 which achieves an accuracy of 97.13%, with an AUC value of 0.97. Using the STFT, the best parameters are obtained with filter convolutional1=96, kernel convolutional1=5, convolutional2 filters=48, convolutional2 kernels=5, convolutional3 filters=96, convolutional3 kernels=5, dense1=128, Optimizer=Adaddelta, learning rate=0.001, which achieves an accuracy of 95.39% with an AUC value of 0.95. Prosodics are used to compare the performance of MFCC and STFT. The result is that prosodic has a low accuracy of 68%. The analysis shows that using MFCC as the process of sound extraction with the CNN model produces the best performance for cases of lie detection using audio. It can be optimized for further research by combining CNN architectural models such as ResNet, AlexNet, and other architectures to obtain new models and improve lie detection accuracy.