Claim Missing Document
Check
Articles

Found 19 Documents
Search

Identifying Types of Waste as Efforts in Plastic Waste Management Based on Deep Learning Buyung, Irawadi; Munir, Agus Qomaruddin; Wijaya, Nurhadi; Listyalina, Latifah
Telematika Vol 20, No 3 (2023): Edisi Oktober 2023
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v20i3.10804

Abstract

Purpose: This research aims at designing a computer algorithm for automatic waste sorting.Design/methodology/apprach: This research is quantitative and uses secondary data, specifically images of various types of waste. The images will be classified into organic and inorganic waste types with the assistance of a deep learning model. In this research, we propose the EfficientNet method for Waste Type Identification as an Effort in Plastic Waste Management. Experiments were conducted on a secondary dataset from Kaggle.com, which involved classifying various types of waste into 'Plastic' and 'Non-Plastic' categories, showing the effectiveness of the proposed method.Findings/result: The measurement is performed to compute the accuracy of the designed deep learning model in classifying waste images into the appropriate waste types. Based on the research results, our system achieved the highest accuracy of 97% during testing.Originality/value/state of the art: The designed method can perform fast and automatic waste sorting, which is useful in reducing the increasing amount of waste accumulating each year. 
Performance Comparison of Convolutional Neural Network with Traditional Machine Learning Methods in Adult Autism Detection Wijaya, Nurhadi; Muliani, Sri Hasta; Nurain, Maisarah
TEKNOLOGI DITERAPKAN DAN JURNAL SAINS KOMPUTER Vol 7 No 1 (2024): June
Publisher : Universitas Nahdlatul Ulama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Diagnosing Autism Spectrum Disorder (ASD) in adults is a challenging task, requiring precise and efficient early detection methods. However, there is limited research in this area. Hence, this study seeks to address this gap by evaluating the effectiveness of Convolutional Neural Networks (CNNs) compared to traditional machine learning techniques for detecting autism in adults. The study introduces a CNN-based model and conducts a performance comparison with conventional algorithms such as Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), and Gradient Boosting (GBoost). The objectives are to evaluate the efficacy of CNNs in adult autism detection, identify algorithm strengths and weaknesses, and explore healthcare implications. The research utilizes the Autism Screening on Adults dataset, with 704 records and 21 features, employing preprocessing steps to optimize data quality. The proposed CNN model encompasses convolutional layers, max-pooling, dropout, and dense layers, while baseline algorithms serve as benchmarks. Evaluation metrics include the Confusion Matrix and Classification Report. The CNN model achieved remarkable accuracy (99%) and precision in adult autism detection, outperforming traditional algorithms. SVM emerged as the closest competitor but fell short. This study underscores CNN's potential for precise autism detection in adults, with implications for early intervention and telehealth applications. The research highlights CNNs' effectiveness and superiority over traditional machine learning algorithms, suggesting their promise for accurate diagnosis. Future research opportunities include expanding datasets, optimizing model parameters, and addressing ethical considerations for practical healthcare implementation
Optimizing Breast Cancer Detection: A Comparative Study of SVM and Naive Bayes Performance Diqi, Mohammad; Hiswati, Marselina Endah; Hamzah, Hamzah; Ordiyasa, I Wayan; Mulyani, Sri Hasta; Wijaya, Nurhadi; Wanda, Putra
TEKNOLOGI DITERAPKAN DAN JURNAL SAINS KOMPUTER Vol 7 No 1 (2024): June
Publisher : Universitas Nahdlatul Ulama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study evaluates the performance of Support Vector Machine (SVM) and Naive Bayes algorithms in classifying breast cancer using the Breast Cancer Wisconsin dataset. Both models exhibited high accuracy, with Naive Bayes achieving a slightly higher overall accuracy of 97% and demonstrating a balanced performance between precision and recall. The SVM model showed strong proficiency in detecting positive cases, with an overall accuracy of 95%, though it faced minor challenges in recall for negative cases. These results highlight the effectiveness of both algorithms in breast cancer detection, emphasizing the significance of model selection based on specific diagnostic requirements. Although there are limitations, such as the small sample size and assumptions made in the model, the findings provide useful insights into the use of machine learning in medical diagnostics. This supports the idea that these models have the potential to enhance early detection and treatment results. Future research should focus on utilizing larger, more diverse datasets, exploring advanced feature processing techniques, and integrating additional algorithms to enhance further the accuracy and reliability of breast cancer detection systems.
Implementation of KNN Algorithm for Occupancy Classification of Rehabilitation Houses Nurhadi Wijaya; Joko Aryanto; Kasmawaru Kasmawaru; Anang Faktchur Rachman
International Journal of Informatics and Computation Vol. 4 No. 2 (2022): International Journal of Informatics and Computation
Publisher : University of Respati Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/ijicom.v4i2.36

Abstract

The 2010 eruption of Mount Merapi and the resulting rain lava in Central Java's Kab. Sleman DIY and Magelang Regency damaged homes and infrastructure. According to the Head of BNPB Regulation No. 5, the Community Rehabilitation and Reconstruction and Community-Based Settlement program plan is utilized to repair and rebuild properties damaged by the 2011 Merapi eruption. Two thousand five hundred sixteen residences that will stay in the area have been built permanently due to this initiative. Occupancy rates (permanent occupancy) are used by the World Bank's Key Performance Indicators (KPI) to gauge a program's effectiveness. The database has information on how the software was used and proved successful. Databases, essential tools for introducing new data patterns and revealing previously hidden information, are used in data mining. This study applies the KNN algorithm to classify the house's occupancy status data after Mount Merapi's eruption. The accuracy results obtained from the classification of 82.03%, and the performance of the results through the AUC obtained a value of 0.935.
Implementation of Deep Learning for Classification of Mushroom Using CNN Algorithm Imam Mahfudz I'tisyam; Nurhadi Wijaya; Rike Pradila
International Journal of Informatics and Computation Vol. 5 No. 1 (2023): International Journal of Informatics and Computation
Publisher : University of Respati Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/ijicom.v5i1.42

Abstract

Mushrooms are a type of low-level plant that lacks chlorophyll. One of the advantages of fungi is that they are commonly utilized as food items in the community. This paper discussed the implementation of CNN for the classification of mushrooms. The project aims to develop a robust system that can automate the labor-intensive task of mushroom classification. The CNN model will be trained on a large dataset of annotated mushroom images, learning to extract meaningful features and patterns for accurate categorization. To evaluate the performance of the developed system, a comprehensive set of metrics, including accuracy, precision, recall, and F1 score, will be used. The dataset will be split into training, validation, and testing sets to assess the model's generalization ability to unseen data. Based on the experimental result, the average accuracy rate in the Agaricus Portobello test was % -99.89 %, % -99.89 % in the Amanita Phalloides test, % -99.59 % in the Cantharellus Cibarius test, % -98.89 % in the Gyromitra Esculenta test, % -99.96 % in the Hygrocybe Conica, and % -99.93 % in the Omphalotus Orealius.
Enhancing Heart Disease Detection Using Convolutional Neural Networks and Classic Machine Learning Methods Mulyani, Sri Hasta; Wijaya, Nurhadi; Trinidya, Fike
Journal of Computer, Electronic, and Telecommunication (COMPLETE) Vol. 4 No. 2 (2023): December
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52435/complete.v4i2.394

Abstract

This study addresses the problem of heart disease detection, a critical concern in public health. The research aims to compare the performance of Convolutional Neural Networks (CNN) with conventional machine learning algorithms in diagnosing heart disease using a dataset comprising 14 features. The primary objective is to determine whether CNNs can provide more accurate and reliable results than traditional techniques. The research employs rigorous preprocessing, normalizing relevant features, and splits the dataset into an 80-20 training-testing split. The model is trained for 300 epochs with a batch size of 64, and performance evaluation is conducted using confusion matrices and classification reports. The results reveal that the CNN model achieved a remarkable accuracy of 100%, demonstrating its potential to outperform conventional machine learning algorithms. These findings emphasize the significance of deep learning techniques in improving heart disease diagnostics, although further research is needed to optimize CNN models and address interpretability concerns for practical implementation in healthcare settings.
Stacked Gated Recurrent Units and Indonesian Stock Predictions: A New Approach to Financial Forecasting DIQI, MOHAMMAD; HISWATI, MARSELINA ENDAH; WIJAYA, NURHADI
Jurnal IT UHB Vol 5 No 1 (2024): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/ikomti.v5i1.1106

Abstract

This research paper introduces a novel approach to predicting stock prices using a Stacked Gated Recurrent Unit (GRU) model. The model was trained on historical data from the top 10 companies listed on the Indonesia Stock Exchange, covering the period from July 6, 2015, to October 14, 2021. The performance of the model was evaluated using key metrics, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R2). The results demonstrated promising performance, with average RMSE, MAE, and MAPE values of 0.00592, 0.00529, and 0.01654, respectively, indicating a high level of accuracy in the model's predictions. The average R2 value of 0.97808 further suggests a high degree of predictive power, with the model able to explain a significant proportion of the variance in the stock prices. These findings highlight the effectiveness of the Stacked GRU model in capturing stock price patterns and making accurate predictions. The practical implications of this research are significant, as the model provides a powerful tool for forecasting future stock price trends, which can be utilized in investment decision-making, financial analysis, and risk management. Future research could explore other deep learning architectures, incorporate additional features, or consider different evaluation metrics to enhance the model's performance further.
Identifying Types of Waste as Efforts in Plastic Waste Management Based on Deep Learning Buyung, Irawadi; Munir, Agus Qomaruddin; Wijaya, Nurhadi; Listyalina, Latifah
Telematika Vol 20 No 3 (2023): Edisi Oktober 2023
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v20i3.10804

Abstract

Purpose: This research aims at designing a computer algorithm for automatic waste sorting.Design/methodology/apprach: This research is quantitative and uses secondary data, specifically images of various types of waste. The images will be classified into organic and inorganic waste types with the assistance of a deep learning model. In this research, we propose the EfficientNet method for Waste Type Identification as an Effort in Plastic Waste Management. Experiments were conducted on a secondary dataset from Kaggle.com, which involved classifying various types of waste into 'Plastic' and 'Non-Plastic' categories, showing the effectiveness of the proposed method.Findings/result: The measurement is performed to compute the accuracy of the designed deep learning model in classifying waste images into the appropriate waste types. Based on the research results, our system achieved the highest accuracy of 97% during testing.Originality/value/state of the art: The designed method can perform fast and automatic waste sorting, which is useful in reducing the increasing amount of waste accumulating each year. 
Machine Learning for Environmental Health: Optimizing ConcaveLSTM for Air Quality Prediction Diqi, Mohammad; Hamzah; Ordiyasa, I Wayan; Wijaya, Nurhadi; Martin, Benedicto Reynaka Filio
Jurnal Buana Informatika Vol. 15 No. 01 (2024): Jurnal Buana Informatika, Volume 15, Nomor 01, April 2024
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v15i1.8707

Abstract

This study investigates the optimization of the ConcaveLSTM model for air quality prediction, focusing on the interplay between input sequence lengths and the number of LSTM units to enhance forecasting accuracy. Through the evaluation of various model configurations against performance metrics such as RMSE, MAE, MAPE, and R-squared, an optimal setup featuring 50 input steps and 300 neurons was identified, demonstrating superior predictive capabilities. The findings underscore the critical role of model parameter tuning in capturing temporal dependencies within environmental data. Despite limitations related to dataset representativeness and environmental variability, the research provides a solid foundation for future advancements in predictive environmental modeling. Recommendations include expanding dataset diversity, exploring hybrid models, and implementing real-time data integration to improve model generalizability and applicability in real-world scenarios.