Claim Missing Document
Check
Articles

Found 25 Documents
Search

QSAR Classification of Beta-Secretase 1 Inhibitor Activity in Alzheimer's Disease Using Ensemble Machine Learning Algorithms Noviandy, Teuku Rizky; Maulana, Aga; Emran, Talha Bin; Idroes, Ghazi Mauer; Idroes, Rinaldi
Heca Journal of Applied Sciences Vol. 1 No. 1 (2023): June 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/hjas.v1i1.12

Abstract

This study focuses on the development of a machine learning ensemble approach for the classification of Beta-Secretase 1 (BACE1) inhibitors in Quantitative Structure-Activity Relationship (QSAR) analysis. BACE1 is an enzyme linked to the production of amyloid beta peptide, a significant component of Alzheimer's disease plaques. The discovery of effective BACE1 inhibitors is difficult, but QSAR modeling offers a cost-effective alternative by predicting the activity of compounds based on their chemical structures. This study evaluates the performance of four machine learning models (Random Forest, AdaBoost, Gradient Boosting, and Extra Trees) in predicting BACE1 inhibitor activity. Random Forest achieved the highest performance, with a training accuracy of 98.65% and a testing accuracy of 82.53%. In addition, it exhibited superior precision, recall, and F1-score. Random Forest's superior performance was a result of its ability to capture a wide variety of patterns and its randomized ensemble approach. Overall, this study demonstrates the efficacy of ensemble machine learning models, specifically Random Forest, in predicting the activity of BACE1 inhibitors. The findings contribute to ongoing efforts in Alzheimer's disease drug discovery research by providing a cost-effective and efficient strategy for screening and prioritizing potential BACE1 inhibitors.
Evaluation of Gradient Boosted Classifier in Atopic Dermatitis Severity Score Classification Suhendra, Rivansyah; Suryadi, Suryadi; Husdayanti, Noviana; Maulana, Aga; Noviandy, Teuku Rizky; Sasmita, Novi Reandy; Subianto, Muhammad; Earlia, Nanda; Niode, Nurdjannah Jane; Idroes, Rinaldi
Heca Journal of Applied Sciences Vol. 1 No. 2 (2023): October 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/hjas.v1i2.85

Abstract

This study investigates the application of the Gradient Boosting machine learning technique to enhance the classification of Atopic Dermatitis (AD) skin disease images, reducing the potential for manual classification errors. AD, also known as eczema, is a common and chronic inflammatory skin condition characterized by pruritus (itching), erythema (redness), and often lichenification (thickening of the skin). AD affects individuals of all ages and significantly impacts their quality of life. Accurate and efficient diagnostic tools are crucial for the timely management of AD. To address this need, our research encompasses a multi-step approach involving data preprocessing, feature extraction using various color spaces and evaluating classification outcomes through Gradient Boosting. The results demonstrate an accuracy of 93.14%. This study contributes to the field of dermatology by providing a robust and reliable tool to support dermatologists in identifying AD skin disease, facilitating timely intervention and improved patient care.
Evaluation of atopic dermatitis severity using artificial intelligence Maulana, Aga; Noviandy, Teuku R.; Suhendra, Rivansyah; Earlia, Nanda; Bulqiah, Mikyal; Idroes, Ghazi M.; Niode, Nurdjannah J.; Sofyan, Hizir; Subianto, Muhammad; Idroes, Rinaldi
Narra J Vol. 3 No. 3 (2023): December 2023
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narra.v3i3.511

Abstract

Atopic dermatitis is a prevalent and persistent chronic inflammatory skin disorder that poses significant challenges when it comes to accurately assessing its severity. The aim of this study was to evaluate deep learning models for automated atopic dermatitis severity scoring using a dataset of Aceh ethnicity individuals in Indonesia. The dataset of clinical images was collected from 250 patients at Dr. Zainoel Abidin Hospital, Banda Aceh, Indonesia and labeled by dermatologists as mild, moderate, severe, or none. Five pre-trained convolutional neural networks (CNN) architectures were evaluated: ResNet50, VGGNet19, MobileNetV3, MnasNet, and EfficientNetB0. The evaluation metrics, including accuracy, precision, sensitivity, specificity, and F1-score, were employed to assess the models. Among the models, ResNet50 emerged as the most proficient, demonstrating an accuracy of 89.8%, precision of 90.00%, sensitivity of 89.80%, specificity of 96.60%, and an F1-score of 89.85%. These results highlight the potential of incorporating advanced, data-driven models into the field of dermatology. These models can serve as invaluable tools to assist dermatologists in making early and precise assessments of atopic dermatitis severity and therefore improve patient care and outcomes.
Design Concept of Information Control Systems for Green Manufacturing Industries with IoT-Based Energy Efficiency and Productivity Yandri, Erkata; Idroes, Rinaldi; Maulana, Aga; Zahriah, Zahriah
Leuser Journal of Environmental Studies Vol. 1 No. 1 (2023): July 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v1i1.36

Abstract

In today's and future industrial competition, IoT and the Fourth Industrial Revolution are unavoidable. Indonesia must be prepared to compete globally in an increasingly efficient and integrated industry, including efficient energy use and renewable energy. This issue has received little strategic and scientific thought, particularly in Indonesia. This study purposes to create a conceptual model of an information control system in the industry, which will include operational performance. The method involves four steps. Firstly, the process flow within the industry is comprehensively analyzed, including the input, process, and output (IPO) aspects. Secondly, all information pertaining to each production process is integrated into the information system. Thirdly, a management control system (MCS) is proposed, incorporating key performance indicators (KPIs), allowing real-time monitoring by management. Lastly, real-time information data on resource sharing is submitted to the information sharing control system within similar industrial clusters. This enables related business parties to optimize their resource utilization based on the provided information. The results show that green manufacturing can be initiated by controlling energy-saving and productivity-related KPIs. The concept of IoT green manufacturing depends on active involvement from the government, industry and the public. A crucial aspect of this system is how the industry effectively manages production performance through shop floor control (SFC).
TeutongNet: A Fine-Tuned Deep Learning Model for Improved Forest Fire Detection Idroes, Ghazi Mauer; Maulana, Aga; Suhendra , Rivansyah; Lala, Andi; Karma, Taufiq; Kusumo, Fitranto; Hewindati, Yuni Tri; Noviandy, Teuku Rizky
Leuser Journal of Environmental Studies Vol. 1 No. 1 (2023): July 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v1i1.42

Abstract

Forest fires have emerged as a significant threat to the environment, wildlife, and human lives, necessitating the development of effective early detection systems for firefighting and mitigation efforts. In this study, we introduce TeutongNet, a modified ResNet50V2 model designed to detect forest fires accurately. The model is trained on a curated dataset and evaluated using various metrics. Results show that TeutongNet achieves high accuracy (98.68%) with low false positive and false negative rates. The model's performance is further supported by the ROC curve analysis, which indicates a high degree of accuracy in classifying fire and non-fire images. TeutongNet demonstrates its effectiveness in reliable forest fire detection, providing valuable insights for improved fire management strategies.
Exploring Geothermal Manifestations in Ie Jue, Indonesia: Enhancing Safety with Unmanned Aerial Vehicle Aprianto, Aprianto; Maulana, Aga; Noviandy, Teuku Rizky; Lala, Andi; Yusuf, Muhammad; Marwan, Marwan; Afidh, Razief Perucha Fauzie; Irvanizam, Irvanizam; Nizamuddin, Nizamuddin; Idroes, Ghazi Mauer
Leuser Journal of Environmental Studies Vol. 1 No. 2 (2023): November 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v1i2.75

Abstract

Geothermal energy is a renewable resource derived from the Earth's interior that provides an environmentally friendly alternative. Indonesia is at the forefront of geothermal potential, possessing ample resources primarily concentrated in places like Sumatra. However, there is a requirement for greater exploitation of this potential. This research utilizes unmanned aerial vehicles (UAVs) and thermal imaging to detect geothermal indications in the Ie Jue region of Sumatra within the province of Aceh, Indonesia. The analysis focuses on three main manifestation locations using FLIR One thermal camera and water temperature gauges. The study leverages satellite imagery for comparative purposes. Temperature data highlights variations among distinct manifestations, underscoring the necessity for thorough exploration. Moreover, the study devises a secure pathway for researchers to access the site. This investigation contributes to comprehending geothermal activity and its possible role in sustainable energy and other domains.
Urban Air Quality Classification Using Machine Learning Approach to Enhance Environmental Monitoring Idroes, Ghazi Mauer; Noviandy, Teuku Rizky; Maulana, Aga; Zahriah, Zahriah; Suhendrayatna, Suhendrayatna; Suhartono, Eko; Khairan, Khairan; Kusumo, Fitranto; Helwani, Zuchra; Abd Rahman, Sunarti
Leuser Journal of Environmental Studies Vol. 1 No. 2 (2023): November 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v1i2.99

Abstract

Urban areas worldwide grapple with environmental challenges, notably air pollution. DKI Jakarta, Indonesia's capital city, is emblematic of this struggle, where rapid urbanization contributes to increased pollutants. This study employed the CatBoost machine learning algorithm, known for its resistance to overfitting and capability to handle missing data, to predict urban air quality based on pollutant levels from 2010 to 2021. The dataset, sourced from Jakarta's air quality monitoring stations, includes pollutants such as PM10, SO2, CO, O3, and NO2. After preprocessing, we used 80% of the data for training and 20% for testing. The model displayed high accuracy (0.9781), precision (0.9722), and recall (0.9728). The feature importance chart revealed O3 (Ozone) as the top influencer of air quality predictions, followed by PM10. Our findings highlight the dominant pollutants affecting urban air quality in Jakarta, Indonesia and emphasizing the need for targeted strategies to reduce their concentrations and ensure a cleaner and healthier urban environment.
Deep Learning-Based Bitcoin Price Forecasting Using Neural Prophet Noviandy, Teuku Rizky; Maulana, Aga; Idroes, Ghazi Mauer; Suhendra, Rivansyah; Adam, Muhammad; Rusyana, Asep; Sofyan, Hizir
Ekonomikalia Journal of Economics Vol. 1 No. 1 (2023): July 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/eje.v1i1.51

Abstract

This study focuses on using the Neural Prophet framework to forecast Bitcoin prices accurately. By analyzing historical Bitcoin price data, the study aims to capture patterns and dependencies to provide valuable insights and predictive models for investors, traders, and analysts in the volatile cryptocurrency market. The Neural Prophet framework, based on neural network principles, incorporates features such as automatic differencing, trend, seasonality considerations, and external variables to enhance forecasting accuracy. The model was trained and evaluated using performance metrics such as RMSE, MAE, and MAPE. The results demonstrate the model's effectiveness in capturing trends and predicting Bitcoin prices while acknowledging the challenges posed by the inherent volatility of the cryptocurrency market.
Evaluating Extraction Methods for Caffeine Content in Gayo Arabica Coffee Oil through Gas Chromatography-Mass Spectroscopy Khairan, Khairan; Musvira, Intan; Lala, Andi; Diah, Muhammad; Maulana, Aga; Idroes, Ghazi Mauer; Awang, Khalijah
Grimsa Journal of Science Engineering and Technology Vol. 2 No. 1 (2024): April 2024
Publisher : Graha Primera Saintifika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61975/gjset.v2i1.31

Abstract

This study aims to determine physicochemical properties, and caffeine analysis of green bean coffee essential oil (GBCEO) and roasted bean coffee essential oil (RBCEO) by maceration and soxhlet extraction methods. The results indicated that RBCEO by maceration method have higher percentage of yield compared to GBCEO. By the same to soxhlet extraction method, RBCEO also showed higher percentage of yield compared to GBCEO. The refractive index of the GBCEOm and GBCEOs have a lower acid value compared to RBCEOm and RBCEOs. The specific gravity obtained for GBCEOm, RBCEOm, GBCEOs, and RBCEOs ranged from 0.87 to 0.97. The results showed that GBCEOm has the highest saponification value followed by RBCEOs. GBCEOm has the highest iodine value followed by RBCEOs, while RBCEOm and GBCEOs have a similar iodine value. The peroxide value showed that GBCEOs, and RBCEOs by soxhlet extraction method have higher peroxide value. The GC-MS analysis revealed that GBCEOm has higher caffeine followed by GBCEOs with the percentages area of 9.31% and 7.36% respectively. Meanwhile RBCEOm has lower caffeine followed by RBCEOs with the percentages area of 7.36% and 4.28% respectively. This finding showed that GBCEO shows higher caffeine compound compared with RBCEO.
Optimizing University Admissions: A Machine Learning Perspective Maulana, Aga; Noviandy, Teuku Rizky; Sasmita, Novi Reandy; Paristiowati, Maria; Suhendra, Rivansyah; Yandri, Erkata; Satrio, Justinus; Idroes, Rinaldi
Journal of Educational Management and Learning Vol. 1 No. 1 (2023): August 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/jeml.v1i1.46

Abstract

The university admission process plays a pivotal role in shaping the future of aspiring students. However, traditional methods of admission decisions often fall short in capturing the holistic capabilities of individuals and may introduce bias. This study aims to improve the admission process by developing and evaluating machine learning approach to predict the likelihood of university admission. Using a dataset of previous applicants' information, advanced algorithms such as K-Nearest Neighbors, Random Forest, Support Vector Regression, and XGBoost are employed. These algorithms are applied, and their performance is compared to determine the best model to predict university admission. Among the models evaluated, the Random Forest algorithm emerged as the most reliable and effective in predicting admission outcomes. Through comprehensive analysis and evaluation, the Random Forest model demonstrated its superior performance, consistency, and dependability. The results show the importance of variables such as academic performance and provide insights into the accuracy and reliability of the model. This research has the potential to empower aspiring applicants and bring positive changes to the university admission process.