Claim Missing Document
Check
Articles

Found 26 Documents
Search

Decision Tree versus k-NN: A Performance Comparison for Air Quality Classification in Indonesia Sasmita, Novi Reandy; Ramadeska, Siti; Kesuma, Zurnila Marli; Noviandy, Teuku Rizky; Maulana, Aga; Khairul, Mhd; Suhendra, Rivansyah
Infolitika Journal of Data Science Vol. 2 No. 1 (2024): May 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v2i1.179

Abstract

Air quality can affect human health, the environment, and the sustainability of ecosystems, so efforts are needed to monitor and control air quality. The Plume Air Quality Index (PAQI) is one of the indices to measure and determine the level of air quality. In measuring the accuracy of the air quality level, it is necessary to do the right classification. Some previous studies have conducted classification analysis using the decision tree and K-Nearest Neighbor (k-NN) methods, but only evaluated using accuracy values. Therefore, this study uses both methods to evaluate the results of air quality level classification not only with accuracy but also with precision, recall, and F1-score. Secondary data of pollutant concentration values and PAQI categories based on particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), and ozone (O3) derived from Plume Labs for 33 provincial capitals in Indonesia in the time period from July 1 to December 31, 2022, were used in this study. From the results of comparing the performance of the two methods, it is found that the decision tree has a greater performance value than the performance value of k-NN. The decision tree performance values for accuracy, precision, recall and F1-score are 90.67%, 90.61%, 90.67%, and 90.63%, respectively. So, it can be concluded that the decision tree performs better than k-NN in classifying PAQI categories with better overall evaluation metric values.
Backpropagation Neural Network-Based Prediction of Kovats Retention Index for Essential Oil Compounds Safhadi, Aulia Al-Jihad; Noviandy, Teuku Rizky; Irvanizam, Irvanizam; Suhendra, Rivansyah; Karma, Taufiq; Idroes, Rinaldi
Infolitika Journal of Data Science Vol. 2 No. 1 (2024): May 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v2i1.197

Abstract

The identification of chemical compounds in essential oils is crucial in industries such as pharmaceuticals, perfumery, and food. Kovats Retention Index (RI) values are essential for compound identification using gas chromatography-mass spectrometry (GC-MS). Traditional RI determination methods are time-consuming, labor-intensive, and susceptible to experimental variability. Recent advancements in data science suggest that artificial intelligence (AI) can enhance RI prediction accuracy and efficiency. However, the full potential of AI, particularly artificial neural networks (ANN), in predicting RI values remains underexplored. This study develops a backpropagation neural network (BPNN) model to predict the Kovats RI values of essential oil compounds using five molecular descriptors: ATSc1, VCH-7, SP-1, Kier1, and MLogP. We trained the BPNN on a dataset of 340 essential oil compounds and optimized it through hyperparameter tuning. We show that the optimized BPNN model, with an epoch count of 100, a learning rate of 0.1, a hidden layer size of 10 neurons, and the ReLU activation function, achieves an R² value of 0.934 and a Root Mean Squared Error (RMSE) of 76.98. These results indicate a high correlation between predicted and actual RI values and a low average prediction error. Our findings demonstrate that BPNNs can significantly improve the efficiency and accuracy of compound identification, reducing reliance on traditional experimental methods.
Advanced Anemia Classification Using Comprehensive Hematological Profiles and Explainable Machine Learning Approaches Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Suhendra, Rivansyah; Bakri, Tedy Kurniawan; Idroes, Rinaldi
Infolitika Journal of Data Science Vol. 2 No. 2 (2024): November 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v2i2.237

Abstract

Anemia is a common health issue with serious clinical effects, making timely and accurate diagnosis essential to prevent complications. This study explores the use of machine learning (ML) methods to classify anemia and its subtypes using detailed hematological data. Six ML models were tested: Gradient Boosting, Random Forest, Naive Bayes, Logistic Regression, Support Vector Machine, and K-Nearest Neighbors. The dataset was preprocessed using feature standardization and the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Gradient Boosting delivered the highest accuracy, sensitivity, and F1-score, establishing itself as the top-performing model. SHapley Additive exPlanations (SHAP) analysis was applied to enhance model interpretability, identifying key predictive features. This study highlights the potential of explainable ML to develop efficient, accurate, and scalable tools for anemia diagnosis, fostering improved healthcare outcomes globally.
Integrating Genetic Algorithm and LightGBM for QSAR Modeling of Acetylcholinesterase Inhibitors in Alzheimer's Disease Drug Discovery Noviandy, Teuku Rizky; Maulana, Aga; Idroes, Ghazi Mauer; Maulydia, Nur Balqis; Patwekar, Mohsina; Suhendra, Rivansyah; Idroes, Rinaldi
Malacca Pharmaceutics Vol. 1 No. 2 (2023): October 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/mp.v1i2.60

Abstract

This study explores the use of Quantitative Structure-Activity Relationship (QSAR) studies using genetic algorithm (GA) and LightGBM to search for acetylcholinesterase (AChE) inhibitors for Alzheimer's disease. The study uses a dataset of 6,157 AChE inhibitors and their IC50 values. A LightGBM model is trained and evaluated for classification performance. The results show that the LightGBM model achieved high performance on the training and testing set, with an accuracy of 92.49% and 82.47%, respectively. This study demonstrates the potential of GA and LightGBM in the drug discovery process for AChE inhibitors in Alzheimer's disease. The findings contribute to the drug discovery process by providing insights about AChE inhibitors that allow more efficient screening of potential compounds and accelerate the identification of promising candidates for development and therapeutic use.
Psoriasis severity assessment: Optimizing diagnostic models with deep learning Maulana, Aga; Noviandy, Teuku R.; Suhendra, Rivansyah; Earlia, Nanda; Prakoeswa, Cita RS.; Kairupan, Tara S.; Idroes, Ghifari M.; Subianto, Muhammad; Idroes, Rinaldi
Narra J Vol. 4 No. 3 (2024): December 2024
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narra.v4i3.1512

Abstract

Psoriasis is a chronic skin condition with challenges in the accurate assessment of its severity due to subtle differences between severity levels. The aim of this study was to evaluate deep learning models for automated classification of psoriasis severity. A dataset containing 1,546 clinical images was subjected to pre-processing techniques, including cropping and applying noise reduction through median filtering. The dataset was categorized into four severity classes: none, mild, moderate, and severe, based on the Psoriasis Area and Severity Index (PASI). It was split into 1,082 images for training (70%) and 463 images for validation and testing (30%). Five modified deep convolutional neural networks (DCNN) were evaluated, including ResNet50, VGGNet19, MobileNetV3, MnasNet, and EfficientNetB0. The data were validated based on accuracy, precision, sensitivity, specificity, and F1-score, which were weighted to reflect class representation; Pairwise McNemar's test, Cochran's Q test, Cohen’s Kappa, and Post-hoc test were performed on the model performance, where overall accuracy and balanced accuracy were determined. Findings revealed that among the five deep learning models, ResNet50 emerged as the optimum model with an accuracy of 92.50% (95%CI: 91.2–93.8%). The precision, sensitivity, specificity, and F1-score of this model were found to be 93.10%, 92.50%, 97.37%, and 92.68%, respectively. In conclusion, ResNet50 has the potential to provide consistent and objective assessments of psoriasis severity, which could aid dermatologists in timely diagnoses and treatment planning. Further clinical validation and model refinement remain required.
Leveraging Machine Learning for Sentiment Analysis in Hotel Applications: A Comparative Study of Support Vector Machine and Random Forest Algorithms Suryadi, Suryadi; Syahputra , Dedek; Astrianda, Nica; Syahputra, Rizki Agam; Suhendra, Rivansyah
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4877

Abstract

This research aims to conduct sentiment analysis on user reviews of hotel booking applications such as Trivago, Tiket, Booking, Traveloka, and Agoda, collected from the Google Play Store. The dataset used consists of 5,000 user reviews, with 80% of the data allocated for training and 20% for testing. Two algorithms applied in this study are Support Vector Machine (SVM) and Random Forest, with performance evaluation based on accuracy, precision, recall, and F1-score metrics. The test results show that the Random Forest algorithm delivers the best performance on the Trivago application with 94% accuracy, 94% precision, 100% recall, and a 97% F1-score. Random Forest proves to be more effective in handling diverse review data, while the Support Vector Machine (SVM) algorithm also produces good results in sentiment classification. This research contributes to the development of sentiment analysis based on user reviews, which can be utilized by app developers and hotel management to improve service quality and user experience.
Evaluation of Machine Learning Methods for Identifying Carbonic Anhydrase-II Inhibitors as Drug Candidates for Glaucoma Noviandy, Teuku Rizky; Imelda, Eva; Idroes, Ghazi Mauer; Suhendra, Rivansyah; Idroes, Rinaldi
Malacca Pharmaceutics Vol. 3 No. 1 (2025): March 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/mp.v3i1.271

Abstract

Glaucoma is a leading cause of irreversible blindness, primarily managed by lowering intraocular pressure (IOP). Carbonic Anhydrase-II (CA-II) inhibitors play a crucial role in this treatment by reducing aqueous humor production. However, existing CA-II inhibitors often suffer from poor selectivity, side effects, and limited bioavailability, highlighting the need for more efficient and targeted drug discovery approaches. This study uses machine learning-driven Quantitative Structure-Activity Relationship (QSAR) modeling to predict CA-II inhibition based on molecular descriptors, significantly enhancing screening efficiency over traditional experimental methods. By evaluating multiple machine learning models, including Support Vector Machine, Gradient Boosting, and Random Forest, we identify SVM as the most effective classifier, achieving the highest accuracy (83.70%) and F1-score (89.36%). Class imbalance remains challenging despite high sensitivity, necessitating further improvements through resampling and hyperparameter optimization. Our findings underscore the potential of machine learning-based virtual screening in accelerating CA-II inhibitor identification and advocate for integrating AI-driven approaches with traditional drug discovery techniques. Future directions include deep learning enhancements and hybrid machine learning-docking frameworks to improve prediction accuracy and facilitate the development of more potent and selective glaucoma treatments.
Penerapan CNN Arsitektur VGG16 untuk Deteksi Kesegaran Ikan Berdasarkan Citra Digital Suhendra, Rivansyah; Ayu, Ratih Sari; Qaisa, Rara Syifa; Juliwardi, Ilham; Astrianda, Nica; Arisna, Puput; Syahril, Alfis; Hasanah, Uswatun
Jurnal Teknologi Informasi Vol 4, No 1 (2025): Mei
Publisher : Universitas Teuku Umar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35308/jti.v4i1.12301

Abstract

Kesegaran ikan merupakan indikator utama dalam menentukan kualitas dan keamanan produk perikanan. Penilaian secara manual masih bersifat subjektif dan memerlukan keahlian khusus. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi tingkat kesegaran ikan secara otomatis menggunakan algoritma Convolutional Neural Network (CNN) dengan arsitektur VGG16. Data berupa 1.378 citra mata ikan dikumpulkan dari pasar ikan di Meulaboh dan Blangpidie, kemudian melalui proses preprocessing menggunakan teknik contrast stretching. Dataset dibagi menjadi data latih (80%) dan data validasi (20%). Proses pelatihan dilakukan dengan menerapkan augmentasi dan normalisasi data guna meningkatkan kemampuan generalisasi model. Hasil pengujian menunjukkan bahwa model mampu mengklasifikasikan citra dengan akurasi, precision, recall, dan F1-score sebesar 100%. Analisis confusion matrix menunjukkan tidak adanya kesalahan klasifikasi pada data validasi. Temuan ini menunjukkan bahwa citra mata ikan merupakan fitur visual yang efektif untuk mengidentifikasi tingkat kesegaran. Sistem yang dikembangkan memiliki potensi untuk diimplementasikan dalam proses sortir dan kontrol mutu hasil perikanan. Penelitian selanjutnya disarankan untuk memperluas cakupan jenis ikan dan pengujian dalam kondisi lingkungan nyata guna meningkatkan robustitas model.
The Impact of Barcode Technology, Decision Making, and Resource Efficiency on Performance in Oil Palm Company Zulham, Zulham; Aulia, Muhammad Reza; Suhendra, Rivansyah; Muzammil, Abdul; Fuqara, Fantashir Awwal
Jurnal Bisnis Tani Vol 11, No 1 (2025): Jurnal Bisnis Tani Volume 11 Nomor 1 April 2025
Publisher : Universitas Teuku Umar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35308/jbt.v11i1.11865

Abstract

This study aims to determine how barcode systems in oil palm firms impact overall performance, resource efficiency, and decision-making processes in the context of optimizing output. This study used 424 employees’sample data, which were gathered by proportional random sampling from April 2024 until June 2024. Partial least squares structural equation Modeling (PLS-SEM) was used to analyze the data. The Barcode System strongly influences resource efficiency and decision making. The overall performance is impacted by both resource efficiency and decision-making. In contrast to the Barcode System, which does not exert a direct influence on performance, its impact is indirect. This implies that the enhancement of performance is not automatically elevated by the Barcode System; instead, improvement must go through mediating variables, namely, resource efficiency and decision-making.
Leveraging Machine Learning for Sentiment Analysis in Hotel Applications: A Comparative Study of Support Vector Machine and Random Forest Algorithms Suryadi, Suryadi; Syahputra , Dedek; Astrianda, Nica; Syahputra, Rizki Agam; Suhendra, Rivansyah
Brilliance: Research of Artificial Intelligence Vol. 4 No. 2 (2024): Brilliance: Research of Artificial Intelligence, Article Research November 2024
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v4i2.4877

Abstract

This research aims to conduct sentiment analysis on user reviews of hotel booking applications such as Trivago, Tiket, Booking, Traveloka, and Agoda, collected from the Google Play Store. The dataset used consists of 5,000 user reviews, with 80% of the data allocated for training and 20% for testing. Two algorithms applied in this study are Support Vector Machine (SVM) and Random Forest, with performance evaluation based on accuracy, precision, recall, and F1-score metrics. The test results show that the Random Forest algorithm delivers the best performance on the Trivago application with 94% accuracy, 94% precision, 100% recall, and a 97% F1-score. Random Forest proves to be more effective in handling diverse review data, while the Support Vector Machine (SVM) algorithm also produces good results in sentiment classification. This research contributes to the development of sentiment analysis based on user reviews, which can be utilized by app developers and hotel management to improve service quality and user experience.