Lasmedi Afuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Interests
Lasmedi Afuan has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
Nurul Hidayat
Department of Informatics, Universitas Jenderal Soedirman, Central Java, Indonesia
4 shared publicationsIpung Permadi
Informatic, Engeneering Faculty, Universitas Jenderal Soedirman
2 shared publications- Ipung Permadi
Department of Informatics, Universitas Jenderal Soedirman, Central Java, Indonesia
2 shared publications - Nurul Hidayat
Universitas Jenderal Soedirman
2 shared publications Swahesti Puspita Rahayu
Informatic, Engeneering Faculty, Universitas Jenderal Soedirman
2 shared publications- Yogiek Indra Kurniawan
Informatika, Fakultas Teknik, Universitas Jenderal Soedirman, Indonesia
2 shared publications
Latest Publications
- Open Access
- 1 September 2026
- Published by Ital Publication in HighTech and Innovation Journal
- Vol. 7 (3) , 1066-1076
A Meta-Calibrated Ensemble Stacking Framework for Reliable Probabilistic Prediction of Intraoperative Hypotension
Accurate prediction of intraoperative hypotension (IOH) is critical for preventing acute organ injury, yet machine learning (ML) models often struggle with highly imbalanced medical datasets, producing overconfident and poorly calibrated risk estimates. This study aims to enhance both the discriminatory performance and the probabilistic reliability of early-warning IOH predictions. We propose a stacking-ensemble architecture integrated with a meta-calibration layer, utilizing a hybrid feature extraction strategy that combines the complex temporal dynamics of MiniROCKET with interpretable time-domain physiological parameters. Evaluated on the retrospective VitalDB dataset, the empirical results demonstrated that the proposed ensemble significantly mitigated confidence bias, achieving an Expected Calibration Error (ECE) of 0.0535 and a Brier score of 0.0775, both statistically superior to baseline models. Concurrently, the architecture maintained exceptional minority-class separability, yielding an Area Under the Receiver Operating Characteristic (AUROC) of 0.9159 and an Area Under the Precision-Recall Curve (AUPRC) of 0.7725. By configuring an operational threshold that prioritizes sensitivity (0.7691) over precision (0.5822) based on the predictive dominance of mean arterial pressure (MAP), the model minimizes the severe clinical cost of false-negative missed detections. Ultimately, this research offers a robust, highly calibrated vigilance-support tool that advances clinical artificial intelligence by shifting the paradigm from mere discriminative accuracy to precise, reliable clinical risk probability estimation in operating room environments.
- 1 September 2026
- Published by Ital Publication in HighTech and Innovation Journal
- Vol. 7 (3) , 1066-1076
Open AccessA Meta-Calibrated Ensemble Stacking Framework for Reliable Probabilistic Prediction of Intraoperative Hypotension
Accurate prediction of intraoperative hypotension (IOH) is critical for preventing acute organ injury, yet machine learning (ML) models often struggle with highly imbalanced medical datasets, producing overconfident and poorly calibrated risk estimates. This study aims to enhance both the discriminatory performance and the probabilistic reliability of early-warning IOH predictions. We propose a stacking-ensemble architecture integrated with a meta-calibration layer, utilizing a hybrid feature extraction strategy that combines the complex temporal dynamics of MiniROCKET with interpretable time-domain physiological parameters. Evaluated on the retrospective VitalDB dataset, the empirical results demonstrated that the proposed ensemble significantly mitigated confidence bias, achieving an Expected Calibration Error (ECE) of 0.0535 and a Brier score of 0.0775, both statistically superior to baseline models. Concurrently, the architecture maintained exceptional minority-class separability, yielding an Area Under the Receiver Operating Characteristic (AUROC) of 0.9159 and an Area Under the Precision-Recall Curve (AUPRC) of 0.7725. By configuring an operational threshold that prioritizes sensitivity (0.7691) over precision (0.5822) based on the predictive dominance of mean arterial pressure (MAP), the model minimizes the severe clinical cost of false-negative missed detections. Ultimately, this research offers a robust, highly calibrated vigilance-support tool that advances clinical artificial intelligence by shifting the paradigm from mere discriminative accuracy to precise, reliable clinical risk probability estimation in operating room environments.
- Open Access
- 1 June 2026
- Published by Ital Publication in HighTech and Innovation Journal
- Vol. 7 (2) , 595-609
Smart Waste Sorting Through Advanced Computer Vision: Optimizing YOLOv11 for High-Accuracy Waste Classification
This research aims to develop a high-accuracy, real-time waste classification system to overcome the inefficiencies and errors associated with manual sorting. The methodology utilizes the advanced YOLO11x-cls architecture, enhanced through transfer learning and optimized using Stochastic Gradient Descent (SGD). Based on the TrashNet dataset containing 2,390 images across five categories (cardboard, glass, metal, paper, and plastic) the study involved rigorous hyperparameter tuning, identifying an optimal initial learning rate of 0.00075. The system was subjected to systematic hyperparameter tuning using a targeted grid search strategy to identify the optimal balance between convergence speed and stability. Key findings demonstrate a superior testing accuracy of 98.16%, an F1-Score of 0.9816, and an inference speed of 35 FPS, proving the system's readiness for real-time applications. Notably, the SGD optimizer provided better stability and generalization than AdamW on this dataset. The novelty of this study lies in being among the first to implement YOLOv11 for waste management, leveraging its new C3K2 and C2PSA blocks to achieve a 1–5% F1-Score improvement over previous YOLO versions while requiring 20% fewer parameters than YOLOv8. This improvement offers a scalable, lightweight solution for edge-computing devices, directly supporting global environmental sustainability goals. The proposed system offers a scalable and hardware-efficient solution for real-time edge deployment in smart waste management infrastructure.
- 1 June 2026
- Published by Ital Publication in HighTech and Innovation Journal
- Vol. 7 (2) , 595-609
Open AccessSmart Waste Sorting Through Advanced Computer Vision: Optimizing YOLOv11 for High-Accuracy Waste Classification
This research aims to develop a high-accuracy, real-time waste classification system to overcome the inefficiencies and errors associated with manual sorting. The methodology utilizes the advanced YOLO11x-cls architecture, enhanced through transfer learning and optimized using Stochastic Gradient Descent (SGD). Based on the TrashNet dataset containing 2,390 images across five categories (cardboard, glass, metal, paper, and plastic) the study involved rigorous hyperparameter tuning, identifying an optimal initial learning rate of 0.00075. The system was subjected to systematic hyperparameter tuning using a targeted grid search strategy to identify the optimal balance between convergence speed and stability. Key findings demonstrate a superior testing accuracy of 98.16%, an F1-Score of 0.9816, and an inference speed of 35 FPS, proving the system's readiness for real-time applications. Notably, the SGD optimizer provided better stability and generalization than AdamW on this dataset. The novelty of this study lies in being among the first to implement YOLOv11 for waste management, leveraging its new C3K2 and C2PSA blocks to achieve a 1–5% F1-Score improvement over previous YOLO versions while requiring 20% fewer parameters than YOLOv8. This improvement offers a scalable, lightweight solution for edge-computing devices, directly supporting global environmental sustainability goals. The proposed system offers a scalable and hardware-efficient solution for real-time edge deployment in smart waste management infrastructure.
- Open Access
- 1 October 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (5) , 3692-3703
Comparative performance analysis of LSTM, GRU, and bidirectional neural networks for political ideology classification
Political ideology classification is crucial for understanding social polarization, monitoring democratic processes, and identifying bias on online platforms. This study compares the performance of long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional GRU (Bi-GRU) neural network models in classifying liberal and conservative political ideologies from social media text data. The Bi-GRU achieved the best results with 88.75% accuracy and 89.16% F1-score, highlighting its strength in contextual analysis. These findings suggest their applicability in areas such as election monitoring and the analysis of political discourse. This study contributes to the field of political text classification by offering a comparative analysis of deep learning architectures. The dataset utilized covers a wide range of issues, including social, political, economic, religious, and racial topics, demonstrating its comprehensive nature. Visualizations using WordCloud and uniform manifold approximation and projection (UMAP) reveal distinct ideological patterns, validating the dataset’s quality for training models. The findings underscore the importance of utilizing advanced bidirectional architectures for nuanced tasks, such as ideology classification, where contextual understanding is crucial. These insights open avenues for future research, such as the application of Bi-GRU in analyzing multilingual political ideologies or real-time sentiment tracking during election campaigns.
- 1 October 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (5) , 3692-3703
Open AccessComparative performance analysis of LSTM, GRU, and bidirectional neural networks for political ideology classification
Political ideology classification is crucial for understanding social polarization, monitoring democratic processes, and identifying bias on online platforms. This study compares the performance of long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional GRU (Bi-GRU) neural network models in classifying liberal and conservative political ideologies from social media text data. The Bi-GRU achieved the best results with 88.75% accuracy and 89.16% F1-score, highlighting its strength in contextual analysis. These findings suggest their applicability in areas such as election monitoring and the analysis of political discourse. This study contributes to the field of political text classification by offering a comparative analysis of deep learning architectures. The dataset utilized covers a wide range of issues, including social, political, economic, religious, and racial topics, demonstrating its comprehensive nature. Visualizations using WordCloud and uniform manifold approximation and projection (UMAP) reveal distinct ideological patterns, validating the dataset’s quality for training models. The findings underscore the importance of utilizing advanced bidirectional architectures for nuanced tasks, such as ideology classification, where contextual understanding is crucial. These insights open avenues for future research, such as the application of Bi-GRU in analyzing multilingual political ideologies or real-time sentiment tracking during election campaigns.
- Open Access
- 17 January 2025
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 605, 03051
A comparative study of machine learning algorithms for fall detection in technology-based healthcare system: Analyzing SVM, KNN, decision tree, random forest, LSTM, and CNN
Fall detection is a major challenge in the development of technology-based healthcare systems, particularly in elderly care. This study aims to compare the performance of six classification algorithms: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest, Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN) in detecting fall incidents using wearable sensor data such as accelerometers and gyroscopes. The research utilizes a dataset consisting of 1,428 training samples and 573 testing samples, evaluated using a 10-fold cross-validation technique. The results show that CNN and LSTM deliver the best performance with accuracies of 94% and 92%, while Random Forest offers a good balance between accuracy and processing time. SVM and KNN exhibit faster processing times but slightly lower accuracies, at 87% and 84%, respectively. The superiority of CNN and LSTM in detecting more complex fall patterns aligns with previous studies emphasizing the capabilities of deep learning models in sensor data classification. The implications of these findings that the selection of fall detection algorithms must consider system priorities, whether focused on high accuracy or processing efficiency. Additionally, this research opens avenues for optimizing deep learning models and leveraging edge computing technologies to reduce response times in wearable device applications.
- 17 January 2025
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 605, 03051
Open AccessA comparative study of machine learning algorithms for fall detection in technology-based healthcare system: Analyzing SVM, KNN, decision tree, random forest, LSTM, and CNN
Fall detection is a major challenge in the development of technology-based healthcare systems, particularly in elderly care. This study aims to compare the performance of six classification algorithms: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest, Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN) in detecting fall incidents using wearable sensor data such as accelerometers and gyroscopes. The research utilizes a dataset consisting of 1,428 training samples and 573 testing samples, evaluated using a 10-fold cross-validation technique. The results show that CNN and LSTM deliver the best performance with accuracies of 94% and 92%, while Random Forest offers a good balance between accuracy and processing time. SVM and KNN exhibit faster processing times but slightly lower accuracies, at 87% and 84%, respectively. The superiority of CNN and LSTM in detecting more complex fall patterns aligns with previous studies emphasizing the capabilities of deep learning models in sensor data classification. The implications of these findings that the selection of fall detection algorithms must consider system priorities, whether focused on high accuracy or processing efficiency. Additionally, this research opens avenues for optimizing deep learning models and leveraging edge computing technologies to reduce response times in wearable device applications.
- Open Access
- 1 December 2024
- Published by Bright Publisher in Journal of Applied Data Sciences
- Vol. 5 (4) , 1738-1753
Sentiment Analysis of the Kampus Merdeka Program on Twitter Using Support Vector Machine and a Feature Extraction Comparison: TF-IDF vs. FastText
Sentiment Analysis of the Kampus Merdeka Program on Twitter Using Support Vector Machine and a Feature Extraction Comparison: TF-IDF vs. FastText
- 1 December 2024
- Published by Bright Publisher in Journal of Applied Data Sciences
- Vol. 5 (4) , 1738-1753
Open AccessSentiment Analysis of the Kampus Merdeka Program on Twitter Using Support Vector Machine and a Feature Extraction Comparison: TF-IDF vs. FastText
Sentiment Analysis of the Kampus Merdeka Program on Twitter Using Support Vector Machine and a Feature Extraction Comparison: TF-IDF vs. FastText
- Open Access
- 3 April 2024
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 5 (2) , 349-356
PATTERN CLASSIFICATION SIGN LANGUAGE USING FEATURES DESCRIPTORS AND MACHINE LEARNING
Sign language is way of communication for the deaf and speech impaired. In Indonesia, the utilization of a standardized language involves the incorporation of American Sign Language (ASL). ASL is employed for various communication needs, ranging from basic alphanumeric fingerspelling (A-Z and numbers) to the more complex SIBI form (comprising gesture vocabulary) in everyday interactions as well as formal contexts. This surge in the digitization of sign language underscores the ongoing advancements in research and development. The challenge in this research lies in the ability to recognize American Sign Language (ASL) with diverse intensities and invariant backgrounds. Therefore, the study emphasis is on proposing a suitable segmentation method comparison for multi-intensity ASL cases. Subsequently, global feature descriptor methods, including Color Histogram, Hu Moments, and Haralick Texture techniques, are applied for feature extraction. The result of the Logistic Regression method versus the supervised Random Forest checks accuracy and suitability in identifying ASL fingerspelling. The findings of this research is predictive value of logistic regression is 48%, with class Y having the highest precision (0.86), class V having the lowest accuracy (0.16), and class L having the highest recall (0.73). The maximum precision in classes B, F, H, I, K, Y, and Z is 1.00, and the lowest in class U is 0.58, while the highest recall is in class G, which is 1.00. The lowest is in class V, while the predictive value from the random forest is 86 percent. Class H has the greatest f1 score (0.99), while class U has the lowest f1 score (0.64). The Random Forest method outperforms the two methods suggested in the paper, according to the comparison.
- 3 April 2024
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 5 (2) , 349-356
Open AccessPATTERN CLASSIFICATION SIGN LANGUAGE USING FEATURES DESCRIPTORS AND MACHINE LEARNING
Sign language is way of communication for the deaf and speech impaired. In Indonesia, the utilization of a standardized language involves the incorporation of American Sign Language (ASL). ASL is employed for various communication needs, ranging from basic alphanumeric fingerspelling (A-Z and numbers) to the more complex SIBI form (comprising gesture vocabulary) in everyday interactions as well as formal contexts. This surge in the digitization of sign language underscores the ongoing advancements in research and development. The challenge in this research lies in the ability to recognize American Sign Language (ASL) with diverse intensities and invariant backgrounds. Therefore, the study emphasis is on proposing a suitable segmentation method comparison for multi-intensity ASL cases. Subsequently, global feature descriptor methods, including Color Histogram, Hu Moments, and Haralick Texture techniques, are applied for feature extraction. The result of the Logistic Regression method versus the supervised Random Forest checks accuracy and suitability in identifying ASL fingerspelling. The findings of this research is predictive value of logistic regression is 48%, with class Y having the highest precision (0.86), class V having the lowest accuracy (0.16), and class L having the highest recall (0.73). The maximum precision in classes B, F, H, I, K, Y, and Z is 1.00, and the lowest in class U is 0.58, while the highest recall is in class G, which is 1.00. The lowest is in class V, while the predictive value from the random forest is 86 percent. Class H has the greatest f1 score (0.99), while class U has the lowest f1 score (0.64). The Random Forest method outperforms the two methods suggested in the paper, according to the comparison.
- Open Access
- 1 January 2024
- Published by Bright Publisher in Journal of Applied Data Sciences
- Vol. 6 (1) , 213-224
Enhanced Fall Detection using Optimized Random Forest Classifier on Wearable Sensor Data
Enhanced Fall Detection using Optimized Random Forest Classifier on Wearable Sensor Data
- 1 January 2024
- Published by Bright Publisher in Journal of Applied Data Sciences
- Vol. 6 (1) , 213-224
Open AccessEnhanced Fall Detection using Optimized Random Forest Classifier on Wearable Sensor Data
Enhanced Fall Detection using Optimized Random Forest Classifier on Wearable Sensor Data
- Open Access
- 1 January 2024
- Published by Coffee Science in Coffee Science
- Vol. 19, 1-12
Analysis of shape features by applying gain ratio and machine learning for coffee bean classification
Coffee is one of the daily consumed beverages in many countries. It is yielded from coffee beans, which have proceeded through several processes. Several common coffee beans have been produced in Indonesia, such as Arabica, Robusta, Liberica, and Excelsa. Nevertheless, many coffee fanatics are unable to distinguish the various coffee bean types visually based on those shapes. Accordingly, it is necessary to classify the types of coffee beans. The work applied training and testing steps. Both involved ROI detection, pre-processing, segmentation, feature extraction, selection, and classification. Image processing was used in ROI detection, pre-processing, and segmentation to simplify the procedure and separate the coffee bean from the background. The feature extraction produced 14 shape features to distinguish the coffee bean’s class, but the proposed method’s performance has yet to reach the optimal result. The gain ratio was used to reduce the features; hence, only 4 features were selected, including aspect ratio, eccentricity, equivalent diameter, and area. These features were utilized as input data for classification using Naive Bayes, Artificial Neural Network (ANN), Support Vector Machine (SVM), C4.5, and decision tree. The proposed method used 4 features and a decision tree classifier. The local dataset has 400 coffee bean photos in four classes of 100 images each. The photos were divided for training and testing using k-fold 10 cross-validation. The accuracy evaluation parameter reached 0.995. Key words: Coffee beans; otsu method; features reduction; cross-validation; decision tree.
- 1 January 2024
- Published by Coffee Science in Coffee Science
- Vol. 19, 1-12
Open AccessAnalysis of shape features by applying gain ratio and machine learning for coffee bean classification
Coffee is one of the daily consumed beverages in many countries. It is yielded from coffee beans, which have proceeded through several processes. Several common coffee beans have been produced in Indonesia, such as Arabica, Robusta, Liberica, and Excelsa. Nevertheless, many coffee fanatics are unable to distinguish the various coffee bean types visually based on those shapes. Accordingly, it is necessary to classify the types of coffee beans. The work applied training and testing steps. Both involved ROI detection, pre-processing, segmentation, feature extraction, selection, and classification. Image processing was used in ROI detection, pre-processing, and segmentation to simplify the procedure and separate the coffee bean from the background. The feature extraction produced 14 shape features to distinguish the coffee bean’s class, but the proposed method’s performance has yet to reach the optimal result. The gain ratio was used to reduce the features; hence, only 4 features were selected, including aspect ratio, eccentricity, equivalent diameter, and area. These features were utilized as input data for classification using Naive Bayes, Artificial Neural Network (ANN), Support Vector Machine (SVM), C4.5, and decision tree. The proposed method used 4 features and a decision tree classifier. The local dataset has 400 coffee bean photos in four classes of 100 images each. The photos were divided for training and testing using k-fold 10 cross-validation. The accuracy evaluation parameter reached 0.995. Key words: Coffee beans; otsu method; features reduction; cross-validation; decision tree.
- Open Access
- 23 December 2023
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 4 (6) , 1535-1540
THE EFFECT OF UNIGRAM AND BIGRAM IN THE NAÏVE BAYES MULTINOMIAL FOR ANALYZING OF COMMENT SENTIMENT OF GOJEK APPLICATION IN GOOGLE PLAY STORE
In sentiment classification systems that use Naïve Bayes Classifier, a commonly used feature extraction method is TF-IDF with unigram and bigram, where the two is used separately. In the reality, most of texts contain single or composed word,so it is needed to use the combination of unigram and bigram to maximize the accuracy of the classification results. In this research, the impact and performance improvement between classification systems using unigram or bigram solely and those using a combination of both are studied. Using 1000 data of reviews with ratings 1 (negative) and 5 (positive) from Gojek users on the Google Play Store, and performing performance validation with K-Fold at K=10, the system that uses the combined TF-IDF feature extraction of unigrams and bigrams achieves the best performance among the three systems with an accuracy of 0.84, however the accuracy of the system that uses unigrams solely has accuracy of 0.83, and 0.7 for the system that uses bigram. From the results of the research, it can be concluded that the use of the combination of unigram and bigram can increase the accuracy of the classification result.
- 23 December 2023
- Published by Infinite Corporation in Jurnal Teknik Informatika (Jutif)
- Vol. 4 (6) , 1535-1540
Open AccessTHE EFFECT OF UNIGRAM AND BIGRAM IN THE NAÏVE BAYES MULTINOMIAL FOR ANALYZING OF COMMENT SENTIMENT OF GOJEK APPLICATION IN GOOGLE PLAY STORE
In sentiment classification systems that use Naïve Bayes Classifier, a commonly used feature extraction method is TF-IDF with unigram and bigram, where the two is used separately. In the reality, most of texts contain single or composed word,so it is needed to use the combination of unigram and bigram to maximize the accuracy of the classification results. In this research, the impact and performance improvement between classification systems using unigram or bigram solely and those using a combination of both are studied. Using 1000 data of reviews with ratings 1 (negative) and 5 (positive) from Gojek users on the Google Play Store, and performing performance validation with K-Fold at K=10, the system that uses the combined TF-IDF feature extraction of unigrams and bigrams achieves the best performance among the three systems with an accuracy of 0.84, however the accuracy of the system that uses unigrams solely has accuracy of 0.83, and 0.7 for the system that uses bigram. From the results of the research, it can be concluded that the use of the combination of unigram and bigram can increase the accuracy of the classification result.
- Open Access
- 17 November 2023
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 448, 02028
Geographic Information System Mapping of Public Works Infrastructure of Kebumen Regency
Geographic Information System (GIS) is an information system that combines graphical (visual) data with text data (attributes) of geographically referenced objects on the Earth's surface. GIS is widely used today in various fields, including analysis, industries, and individual activities such as finding locations or routes to specific destinations. In this research, GIS is used to manage the digitization of infrastructure mapping in Kebumen Regency. The development objective of the GIS is to process and analyze the spatial data of infrastructure locations to generate accurate information. The waterfall method is employed in the development of this system, encompassing stages of analysis, design, implementation, testing, and maintenance using the CodeIgniter framework. The outcome of this research is the Geographic Information System for Mapping Public Works Infrastructure in Kebumen Regency based on Leaflet. The GIS infrastructure of Kebumen Regency facilitates the public in accessing information about the existing infrastructure in the area. The testing results using the black box testing method demonstrate that the system aligns with the defined requirements. The objective of this research is to develop a Geographic Information System (GIS) that can manage and analyze the spatial data of infrastructure in Kebumen Regency, resulting in accurate information. The waterfall method is used in the development of this system, with stages including analysis, design, implementation, testing, and maintenance using the CodeIgniter framework. The outcome of this research is the Geographic Information System for Mapping Public Works Infrastructure in Kebumen Regency based on Leaflet. With the GIS infrastructure of Kebumen Regency, the community can easily access information regarding the infrastructure in the area. This system enables users to visualize the locations of infrastructure and obtain attribute or text data related to those infrastructure objects. Through testing using the black box testing method, the system has been proven to meet the predefined requirements. This indicates that the developed GIS is reliable and provides accurate information about the infrastructure in Kebumen Regency. Thus, the development of this GIS provides significant benefits in managing spatial data of infrastructure and delivering accurate information to the public. This research has successfully achieved its objectives and produced a Geographic Information System that can be utilized as a tool for infrastructure mapping and spatial data analysis in Kebumen Regency.
- 17 November 2023
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 448, 02028
Open AccessGeographic Information System Mapping of Public Works Infrastructure of Kebumen Regency
Geographic Information System (GIS) is an information system that combines graphical (visual) data with text data (attributes) of geographically referenced objects on the Earth's surface. GIS is widely used today in various fields, including analysis, industries, and individual activities such as finding locations or routes to specific destinations. In this research, GIS is used to manage the digitization of infrastructure mapping in Kebumen Regency. The development objective of the GIS is to process and analyze the spatial data of infrastructure locations to generate accurate information. The waterfall method is employed in the development of this system, encompassing stages of analysis, design, implementation, testing, and maintenance using the CodeIgniter framework. The outcome of this research is the Geographic Information System for Mapping Public Works Infrastructure in Kebumen Regency based on Leaflet. The GIS infrastructure of Kebumen Regency facilitates the public in accessing information about the existing infrastructure in the area. The testing results using the black box testing method demonstrate that the system aligns with the defined requirements. The objective of this research is to develop a Geographic Information System (GIS) that can manage and analyze the spatial data of infrastructure in Kebumen Regency, resulting in accurate information. The waterfall method is used in the development of this system, with stages including analysis, design, implementation, testing, and maintenance using the CodeIgniter framework. The outcome of this research is the Geographic Information System for Mapping Public Works Infrastructure in Kebumen Regency based on Leaflet. With the GIS infrastructure of Kebumen Regency, the community can easily access information regarding the infrastructure in the area. This system enables users to visualize the locations of infrastructure and obtain attribute or text data related to those infrastructure objects. Through testing using the black box testing method, the system has been proven to meet the predefined requirements. This indicates that the developed GIS is reliable and provides accurate information about the infrastructure in Kebumen Regency. Thus, the development of this GIS provides significant benefits in managing spatial data of infrastructure and delivering accurate information to the public. This research has successfully achieved its objectives and produced a Geographic Information System that can be utilized as a tool for infrastructure mapping and spatial data analysis in Kebumen Regency.