Taufik Abidin

Prof. Taufik Abidin

Universitas Syiah Kuala
orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
26 July 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KMKhairul Munadi
Khairul Munadi
KSKhairun Saddami
Khairun Saddami
MOMaulisa Oktiana
Maulisa Oktiana
RRRoslidar Roslidar
Roslidar Roslidar
Kahlil MuchtarKahlil Muchtar
Kahlil Muchtar
Fitri ArniaFitri Arnia
Fitri Arnia
Diabetes mellitus (DM) is one of the major diseases that cause death worldwide and lead to complications of diabetic foot ulcers (DFU). Improper and late handling of a diabetic foot patient can result in an amputation of the patient’s foot. Early detection of DFU symptoms can be observed using thermal imaging with a computer-assisted classifier. Previous study of DFU detection using thermal image only achieved 97% of accuracy, and it has to be improved. This article proposes a novel framework for DFU classification based on thermal imaging using deep neural networks and decision fusion. Here, decision fusion combines the classification result from a parallel classifier. We used the convolutional neural network (CNN) model of ShuffleNet and MobileNetV2 as the baseline classifier. In developing the classifier model, firstly, the MobileNetV2 and ShuffleNet were trained using plantar thermogram datasets. Then, the classification results of those two models were fused using a novel decision fusion method to increase the accuracy rate. The proposed framework achieved 100% accuracy in classifying the DFU thermal images in binary classes of positive and negative cases. The accuracy of the proposed Decision Fusion (DF) was increased by about 3.4% from baseline ShuffleNet and MobileNetV2. Overall, the proposed framework outperformed in classifying the images compared with the state-of-the-art deep learning and the traditional machine-learning-based classifier.

1 January 2024 in Applied Computational Intelligence and Soft Computing
Verified
Journal Article
Open access
HAHendri Ahmadian
Hendri Ahmadian
Taufik AbidinTaufik Abidin
Taufik Abidin
HRHammam Riza
Hammam Riza
Kahlil MuchtarKahlil Muchtar
Kahlil Muchtar
The swift growth of social networks has enabled easy access to a wealth of user‐created information for public assessment. These data hold potential for various uses, including analyzing comments and reviews through text analysis. The study utilizes a specialized version of the Bidirectional Encoder Representations from Transformers (BERT) model known as IndoBERT, tailored explicitly for Bahasa Indonesia. It aims to improve accuracy in the Indonesian natural language understanding benchmark by boosting performance in sentiment analysis and emotion classification tasks. The testing for both tasks involved a hybrid methodology that merged the summations of the four last hidden layers from the IndoBERT model with a combination of bidirectional long short‐term memory (BiLSTM), bidirectional gated recurrent unit (BiGRU), and an attention model. The resulting model’s performance was assessed using the F1‐score metric. Based on the experimental results, the proposed model achieves an accuracy of 93% for sentiment analysis and 78% for emotion classification on the Indonesian natural language understanding (IndoNLU) benchmark dataset. The implementation result shows that the optimal accuracy of the models’ performance evaluation was obtained using different hybrid models.

1 September 2018 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
MSM Saputra
M Saputra
Taufik AbidinTaufik Abidin
Taufik Abidin
BAB I Ansari
B I Ansari
MHM Hidayat
M Hidayat
Learning media is a tool to deliver the materials to students during teaching and learning process and used as a source of learning like textbooks. However, textbooks are sometimes considered less practical and boring. The innovation that follows the technology advancement is undeniably needed. Nowadays, students are very creative using smartphones. The students' creativity should be supported for better learning. One of the efforts is making use of a smartphone or mobile technology as a learning media. This study aims to develop an Android-based learning media called Trigonometry app and evaluate the validity and practicality of the learning media. This learning media is expected to help students learn mathematics. This study used the ADDIE development model. The learning media was validated by six experts and tested by 95 respondents. The results show that the learning media met the valid criteria with kappa value ranged from 0.562 to 0.843. The learning media was also considered practical based on the responses from the users. 86.32% of the users stated that the learning media was excellent and best imaginable. Therefore, the learning media is declared valid and practical to use in the classroom. It is necessary to conduct further research to investigate the use of the media in the classroom and its impact on students' learning and teaching practices.

17 April 2024 in Narra J
Verified
Journal Article
Open access
PDF file
Farrah FahdhienieFarrah Fahdhienie
Farrah Fahdhienie
Mudatsir MudatsirMudatsir Mudatsir
Mudatsir Mudatsir
Taufik AbidinTaufik Abidin
Taufik Abidin
Nurjannah NurjannahNurjannah Nurjannah
Nurjannah Nurjannah
Tuberculosis (TB) remains one of the most widespread infectious diseases in the world, with high mortality and morbidity rates, contributing to a significant disease burden, particularly in developing countries. The aim of this study was to determine the risk factors of TB among the population aged 17 years (late adolescent) and above in one of the high TB prevalence countries, Indonesia. A case-control study was conducted in Banda Aceh, Indonesia, involving newly diagnosed pulmonary TB patients who visited one of the eleven community health centers in Banda Aceh. The controls were individuals matched by age and sex who lived near the cases and had no TB infection. A total of 16 risk factors were assessed. Hierarchical multivariable logistic regression models were used to examine the association between the risk factors and the occurrence of TB. A total of 196 cases and 196 controls were included in the study. Multivariable logistic regression analysis identified 11 independent predictors for the occurrence of TB after controlling possible confounders. Patients who lived in houses with insufficient light exposure were 77 times more likely to develop TB compared to those living in houses with sufficient light exposure (adjusted odds ratio (AOR): 77.69; 95%CI: 27.09, 222.79). The study also showed that people who had close contact with TB patients (AOR: 25.39; 95%CI: 2.10, 306.52), had poor knowledge of TB (AOR: 24.2; 95%CI: 6.89, 85.17), had comorbidities (AOR: 4.49; 95%CI: 1.35, 14.89), insufficient food utilization (AOR: 3.41; 95%CI: 1.51, 7.71), negative preventive behavior (AOR: 3.39; 95%CI: 1.49, 7.72), low education level (AOR: 3.08; 95%CI: 1.26, 7.55), and insufficient housing humidity (AOR: 2.89; 95%CI: 1.18, 7.12) were associated with increased the odds of having TB. Being employed, having income above minimum wage, and having good nutritional intake were protective factors for developing TB. In conclusion, the determinants of TB among people aged 17 years and older are a clear indication of the need for TB prevention programs targeting not only individual risk factors but also environmental risk factors, particularly providing adequate housing conditions. This study provided useful information that might help to develop and adopt effective policies for TB control in Indonesia.

1 September 2018
Verified
Conference Paper
Closed access
VMViska Mutiawani
Viska Mutiawani
SRSarah Rahmany
Sarah Rahmany
Taufik AbidinTaufik Abidin
Taufik Abidin
The number of vehicle users in Indonesia keep on increasing each year and this triggers probability of criminal activities especially vehicle theft. There were at least 1,688 cases of vehicle theft reported in Aceh Province throughout year 2016. Therefore, it is essentially important to keep vehicles save. One way to do it is by utilising an Android application that is capable to monitor and track the vehicles. This application has a special built-in feature: the ability to locate the position of user's vehicle with the usage of GPS and Google maps. If the vehicle moves from its original position, the application will notify the user and track its new position. Then, the vehicle owner can ask for help from friends and nearby polices. This application was developed using the Agile software methodology. Three tests were conducted for the application. The first test is the functional testing. This test was conducted to ensure that the application works in public and crowded places. The result shows that the application is functioning properly. The second test is the distance accuracy test, tested using altitude and without altitude. The results show that the error rates when altitude is used are 24.24% and 14.94% indoor and outdoor, respectively. When the altitude is not used, the error rates are 26.55% for indoor and 20.55% for outdoor. It is clear that incorporating altitude is more accurate than without using altitude. The last test is the response time between the application and Firebase as web service. We found that the average response time is 2.15 seconds which is considered good for a smartphone application.

1 October 2017
Verified
Conference Paper
Closed access
Taufik AbidinTaufik Abidin
Taufik Abidin
MHMauliana Hasanuddin
Mauliana Hasanuddin
VMViska Mutiawani
Viska Mutiawani
Twitter is one of popular microblogging services that allows users to write short messages up to 140 characters. Twitter active users in Indonesia have reached 29.4 million in 2017 and they have created an enormous number of tweets, a potential data source for supervised learning. In this work, six different set of n-grams words dictionaries were generated and they were used as references for creating numerical features of the tweets. We classified the tweets using k-Nearest Neighbors (k-NN) and Naive Bayes Classifier and compared the accuracy using F-measure. We also observed the classification times of each algorithm. The results show that k-NN algorithm performed better than Naive Bayes Classifier, i.e. 81.2% for F-measure using k=7. However, in terms of classification time, Naive Bayes Classifier is faster than k-NN for all k parameters.