Hapnes Toba - Academia.edu (original) (raw)

Papers by Hapnes Toba

Lecture notes in networks and systems, 2024

Jurnal Teknik Informatika dan Sistem Informasi

Penerapan Automatic Fare Collection (AFC) pada KA Commuter Line dapat memberikan pengetahuan baru... more Penerapan Automatic Fare Collection (AFC) pada KA Commuter Line dapat memberikan pengetahuan baru dalam melakukan navigasi antar jalur KA Commuter Line dengan data perjalanan Commuter Line secara real. Sistem AFC memungkinkan manajemen untuk memperoleh data rinci dalam jumlah besar mengenai rute setiap komuter setiap hari. Salah satu tantangan yang dihadapi dalam menggunakan big data di AFC adalah ekstraksi data perilaku penumpang angkutan. Perilaku penumpang Commuter Line merupakan faktor yang sangat penting bagi operator untuk mengambil keputusan yang tepat. Penelitian ini menggunakan metode association rules untuk mengekstrak data AFC guna menghasilkan informasi yang baik dan memahami perilaku komuter Jabodetabek. Hasil penelitian menunjukkan bahwa metode association rules dapat mengekstraksi data AFC dan menghasilkan aturan asosiasi yang kuat pada perilaku komuter.

IAES International Journal of Artificial Intelligence (IJ-AI)

The sudden climate change occurring in different places in the world has made disasters more unpr... more The sudden climate change occurring in different places in the world has made disasters more unpredictable than before. In addition, responses are often late due to manual processes that have to be performed by experts. Consequently, major advances in computer vision (CV) have prompted researchers to develop smart models to help these experts. We need a strong image representation model, but at the same time, we also need to prepare for a deep learning environment at a low cost. This research attempts to develop transfer learning models using low-cost masking pre-processing in the experimental building damage (xBD) dataset, a large-scale dataset for advancing building damage assessment. The dataset includes eight types of disasters located in fifteen different countries and spans thousands of square kilometers of satellite images. The models are based on U-Net, i.e., AlexNet, visual geometry group (VGG)-16, and ResNet-34. Our experiments show that ResNet-34 is the best with an F1 sc...

Proceedings of the 1st International Conference on Emerging Issues in Technology, Engineering and Science

Jurnal Teknik Informatika dan Sistem Informasi

During this pandemic, the number of customers of a securities company has increased quite high. T... more During this pandemic, the number of customers of a securities company has increased quite high. This requires securities companies to conduct analysis related to security customer data against transaction data so that the company can find out the segmentation of registered customers and also so that companies can predict the transaction patterns of customers in the company. In processing transaction data, the RFM (Recency, Frequency, Monetary) model can be used as a way to group customers according to their business values. After doing the modeling using RFM, the data is clustered using the K-Means algorithm to find out the segmentation in the RFM model in each group. The RFM model that has been clustered will produce segments based on the RFM group. In this data, a linear regression analysis process is carried out where each group and segment is analyzed and predicted related to variables such as recency, monetary and frequency. The results of data grouping, customer segmentation a...

Jurnal STRATEGI - Jurnal Maranatha, May 20, 2020

Faculty of Information Technology Maranatha Christian University organizes many activities on a r... more Faculty of Information Technology Maranatha Christian University organizes many activities on a regular basis and incidental. One of the major problems is how to avoid conflicting schedules. This research proposes a web calendar application which able to display available time schedules among the participants of an event. The development of the web calendar is based on flexibility by using API. The implementation shows that the calendar system is able to recommend time availabilities of a conflicting timetable by generating minimum remaining values. Our evaluation results show that the web-based calendar application was successfully implemented and interact properly with Google Calendar.

Jurnal STRATEGI - Jurnal Maranatha, Nov 8, 2020

Nowadays, one of the problems that students have to face is financial problems. Therefore, schola... more Nowadays, one of the problems that students have to face is financial problems. Therefore, scholarship opportunities become an important aspect to help students accomplished their study in a university. A special dedicated application is needed in order to know the information about the scholarships and to apply the scholarships as well. Moreover, such application could be useful to facilitate faculties and the Directorate of Students Affairs to manage students scholarship registration and selection process. In order to facilitate those issues, an application is developed which has the main feature to recommend the faculty about students' scholarship candidacy. The developed application employed Analytical Hierarchy Prosess (AHP) method to evaluate scholarship requirements, which supports the faculty to make final decision. Based on the evaluation results, this system shows its flexibility in determining difference scholarship requirements and gives relevant feedback during the decision process.

Jurnal STRATEGI - Jurnal Maranatha, Apr 29, 2019

Jurnal Teknik Informatika dan Sistem Informasi, 2021

This study discusses the analysis of retail store with time series method to obtain information a... more This study discusses the analysis of retail store with time series method to obtain information about sales trend and seasonality by looking at visitor data and total transaction data at a time period. Data in the form of the number of customers who visit are obtained through CCTV video camera recordings placed at retail store X and the total transaction occurred at retail store X. The visitor counting uses the deep learning method with SSD (Single Shot Detector) object detection framework and MobileNet architecture. The library used to count the number of customers visiting the store is OpenCV, Pandas, Numpy, Dlib, and Imutils. The number of customers visiting the store will then be compared to the number of transactions that occur at the same time so that a conversion rate can be obtained. From here, we can see sales trend that occur at any time. Time series analysis is also carried out to determine and analyze the pattern of data obtained based on certain time to predict the thin...

Universitas Kristen Maranatha, 2021

2018 IEEE International Symposium on Multimedia (ISM), 2018

Conventional practices for recording student attendance in a classroom, such as roll-call and sig... more Conventional practices for recording student attendance in a classroom, such as roll-call and sign-in-sheet, are proven to be inefficient in terms of time and staff-workload. In addition, they are also prone to human error and bogus attendance, which introduce inaccuracy in the recorded data. A number of studies have been conducted to improve the way we record class attendance. However, some of the proposed solutions are costly and impractical. Most solutions also fail to address bogus attendance. This paper presents a low cost solution in recording student attendance. Attendance is recorded on class photographs, students' faces are automatically located using a face detection technique, and students then registered their attendance by simply identifying their face on the records. Mobile applications were developed for both students and lecturers as the primary interfaces to interact with the system.

Jurnal STRATEGI - Jurnal Maranatha, Nov 23, 2019

The reporting system at Pasundan Christian Church Bandung have not yet been automated and all inf... more The reporting system at Pasundan Christian Church Bandung have not yet been automated and all information is processed manually. There are several limitations in the manual system, especially the lack of a common format for the reporting process. By the implementation of an automated system it is expected to significantly reduce the current difficulties in reporting process. The automated system has an additional feature in the form of sending notifications to remind the users and minimize delay during reporting. There is also a blocking capability which further restricts the users to immediately collecting reports before all necessary information is reported. If required information is lack, the system will not issue the next month's report since the commission or management cannot legally issues such report during the general meeting. In the next future, this system could facilitate and help all users by increasing their productivity through the modernization of reporting process.

Jurnal STRATEGI - Jurnal Maranatha, May 20, 2020

The Faculty of Information Technology at Maranatha Christian University arranges many activities.... more The Faculty of Information Technology at Maranatha Christian University arranges many activities. The faculty has some difficulties in managing schedules, especially in determining appropriate schedules for all participants. Therefore, a webbased calendar is proposed which could manage the schedule of activities among faculty members. The web application is able to synchronize schedules from all articipants which integrated with Google Calendar. In addition, to ensure web usability, it is also necessary to design attractive user interfaces which comfortable to use and ensure user interaction. This web application is built by utilizing the AngularJS framework, based on MVC-model. The system testing shows that the web application has successfully built and can be used to manage the schedules.

Jurnal STRATEGI - Jurnal Maranatha, Apr 24, 2021

Jurnal STRATEGI - Jurnal Maranatha, Nov 8, 2020

Although Raspberry Pi has a mini size, it can do quite complex computing jobs, such as: digital i... more Although Raspberry Pi has a mini size, it can do quite complex computing jobs, such as: digital image processing to recognize faces. In this research, facial recognition techniques are applied in combination with eigenfaces algorithm. The algorithm is capable to deliver accurate facial recognition with minimal exposure by making black and-white face detection. Other aspects which are investigated in this research is focused on the settings of Raspberry Pi associated with the multimedia system which aim to allow users interacting with camera via Raspberry Pi. The programming language used during the development is Python. The results show that eigenfaces algorithms using Python language is capable to detect faces during login activity on a computer system by combining Raspberry Pi and its camera.

Jurnal STRATEGI - Jurnal Maranatha, Apr 30, 2019

Company X is a newborn company in connecting talents with production houses, advertising agencies... more Company X is a newborn company in connecting talents with production houses, advertising agencies, brands, and content creators. To support the its financial management, X Company needs a system which documents the inflow and outflow money. Based on the problem that occurred the auhtor decided to develop a cash flow system. This cash flow system is developed by using Laravel framework in PHP programming language following the MVC patterns and PostgreSQL database management system. The evaluation shows that the developed system could support the perfomance of Company X.

Jurnal Teknik Informatika dan Sistem Informasi

With the rapid development of new technologies in smartphones, understanding market trends has be... more With the rapid development of new technologies in smartphones, understanding market trends has become an increasingly difficult task. In these circumstances, online product reviews that can reflect consumer sentiment about the product has been a concern for now. Online review analysis can help sellers understand consumer interests and desires prior to launching a new product. The author wants to contribute to seeing the state of the smartphone market by creating a method to find important aspects of a smartphone. The data source comes from the Amazon e-commerce web with 4 predefined smartphone brands. In this study, the authors used topic modeling with the LDA algorithm and sentiment analysis with VADER to find aspects of a smartphone and its sentiment classification. From the 15 scenarios made in this reserach, it is found 3 aspects that always appear, namely the screen, camera, and battery aspects, so it is concluded that these 3 aspects are the most important of a smartphone base...

Jurnal Teknik Informatika dan Sistem Informasi, Dec 20, 2020

This paper presents a cooperation recommendation strategy between higher education institutions. ... more This paper presents a cooperation recommendation strategy between higher education institutions. The recommendation is based on the contents of journals published in a university journal portal. As a case study, we concentrate our approach for the journals with information technology themes. All journals from 10 reputed universities will be compared by using keywords and the contents of the journal themselves. A partnering recommendation list is built by utilizing Latent Semantic Indexing (LSI). LSI technique is used to reduce the curse of dimensionality from the original dataset and to generate topical analysis from all journals as a semantic representation for each journal. Topic modeling is used to calculate the categorical similarity in the dataset of each university journal and a search query. After all categorical similarities have been calculated, an average value of journal topics coherence is used to construct the final recommendation of partner candidates. This approach ensures that the final recommendation is based on the interest of each university rather than the frequencies of matched keywords in each journal.

Lecture notes in networks and systems, 2024

Jurnal Teknik Informatika dan Sistem Informasi

Penerapan Automatic Fare Collection (AFC) pada KA Commuter Line dapat memberikan pengetahuan baru... more Penerapan Automatic Fare Collection (AFC) pada KA Commuter Line dapat memberikan pengetahuan baru dalam melakukan navigasi antar jalur KA Commuter Line dengan data perjalanan Commuter Line secara real. Sistem AFC memungkinkan manajemen untuk memperoleh data rinci dalam jumlah besar mengenai rute setiap komuter setiap hari. Salah satu tantangan yang dihadapi dalam menggunakan big data di AFC adalah ekstraksi data perilaku penumpang angkutan. Perilaku penumpang Commuter Line merupakan faktor yang sangat penting bagi operator untuk mengambil keputusan yang tepat. Penelitian ini menggunakan metode association rules untuk mengekstrak data AFC guna menghasilkan informasi yang baik dan memahami perilaku komuter Jabodetabek. Hasil penelitian menunjukkan bahwa metode association rules dapat mengekstraksi data AFC dan menghasilkan aturan asosiasi yang kuat pada perilaku komuter.

IAES International Journal of Artificial Intelligence (IJ-AI)

The sudden climate change occurring in different places in the world has made disasters more unpr... more The sudden climate change occurring in different places in the world has made disasters more unpredictable than before. In addition, responses are often late due to manual processes that have to be performed by experts. Consequently, major advances in computer vision (CV) have prompted researchers to develop smart models to help these experts. We need a strong image representation model, but at the same time, we also need to prepare for a deep learning environment at a low cost. This research attempts to develop transfer learning models using low-cost masking pre-processing in the experimental building damage (xBD) dataset, a large-scale dataset for advancing building damage assessment. The dataset includes eight types of disasters located in fifteen different countries and spans thousands of square kilometers of satellite images. The models are based on U-Net, i.e., AlexNet, visual geometry group (VGG)-16, and ResNet-34. Our experiments show that ResNet-34 is the best with an F1 sc...

Proceedings of the 1st International Conference on Emerging Issues in Technology, Engineering and Science

Jurnal Teknik Informatika dan Sistem Informasi

During this pandemic, the number of customers of a securities company has increased quite high. T... more During this pandemic, the number of customers of a securities company has increased quite high. This requires securities companies to conduct analysis related to security customer data against transaction data so that the company can find out the segmentation of registered customers and also so that companies can predict the transaction patterns of customers in the company. In processing transaction data, the RFM (Recency, Frequency, Monetary) model can be used as a way to group customers according to their business values. After doing the modeling using RFM, the data is clustered using the K-Means algorithm to find out the segmentation in the RFM model in each group. The RFM model that has been clustered will produce segments based on the RFM group. In this data, a linear regression analysis process is carried out where each group and segment is analyzed and predicted related to variables such as recency, monetary and frequency. The results of data grouping, customer segmentation a...

Jurnal STRATEGI - Jurnal Maranatha, May 20, 2020

Faculty of Information Technology Maranatha Christian University organizes many activities on a r... more Faculty of Information Technology Maranatha Christian University organizes many activities on a regular basis and incidental. One of the major problems is how to avoid conflicting schedules. This research proposes a web calendar application which able to display available time schedules among the participants of an event. The development of the web calendar is based on flexibility by using API. The implementation shows that the calendar system is able to recommend time availabilities of a conflicting timetable by generating minimum remaining values. Our evaluation results show that the web-based calendar application was successfully implemented and interact properly with Google Calendar.

Jurnal STRATEGI - Jurnal Maranatha, Nov 8, 2020

Nowadays, one of the problems that students have to face is financial problems. Therefore, schola... more Nowadays, one of the problems that students have to face is financial problems. Therefore, scholarship opportunities become an important aspect to help students accomplished their study in a university. A special dedicated application is needed in order to know the information about the scholarships and to apply the scholarships as well. Moreover, such application could be useful to facilitate faculties and the Directorate of Students Affairs to manage students scholarship registration and selection process. In order to facilitate those issues, an application is developed which has the main feature to recommend the faculty about students' scholarship candidacy. The developed application employed Analytical Hierarchy Prosess (AHP) method to evaluate scholarship requirements, which supports the faculty to make final decision. Based on the evaluation results, this system shows its flexibility in determining difference scholarship requirements and gives relevant feedback during the decision process.

Jurnal STRATEGI - Jurnal Maranatha, Apr 29, 2019

Jurnal Teknik Informatika dan Sistem Informasi, 2021

This study discusses the analysis of retail store with time series method to obtain information a... more This study discusses the analysis of retail store with time series method to obtain information about sales trend and seasonality by looking at visitor data and total transaction data at a time period. Data in the form of the number of customers who visit are obtained through CCTV video camera recordings placed at retail store X and the total transaction occurred at retail store X. The visitor counting uses the deep learning method with SSD (Single Shot Detector) object detection framework and MobileNet architecture. The library used to count the number of customers visiting the store is OpenCV, Pandas, Numpy, Dlib, and Imutils. The number of customers visiting the store will then be compared to the number of transactions that occur at the same time so that a conversion rate can be obtained. From here, we can see sales trend that occur at any time. Time series analysis is also carried out to determine and analyze the pattern of data obtained based on certain time to predict the thin...

Universitas Kristen Maranatha, 2021

2018 IEEE International Symposium on Multimedia (ISM), 2018

Conventional practices for recording student attendance in a classroom, such as roll-call and sig... more Conventional practices for recording student attendance in a classroom, such as roll-call and sign-in-sheet, are proven to be inefficient in terms of time and staff-workload. In addition, they are also prone to human error and bogus attendance, which introduce inaccuracy in the recorded data. A number of studies have been conducted to improve the way we record class attendance. However, some of the proposed solutions are costly and impractical. Most solutions also fail to address bogus attendance. This paper presents a low cost solution in recording student attendance. Attendance is recorded on class photographs, students' faces are automatically located using a face detection technique, and students then registered their attendance by simply identifying their face on the records. Mobile applications were developed for both students and lecturers as the primary interfaces to interact with the system.

Jurnal STRATEGI - Jurnal Maranatha, Nov 23, 2019

The reporting system at Pasundan Christian Church Bandung have not yet been automated and all inf... more The reporting system at Pasundan Christian Church Bandung have not yet been automated and all information is processed manually. There are several limitations in the manual system, especially the lack of a common format for the reporting process. By the implementation of an automated system it is expected to significantly reduce the current difficulties in reporting process. The automated system has an additional feature in the form of sending notifications to remind the users and minimize delay during reporting. There is also a blocking capability which further restricts the users to immediately collecting reports before all necessary information is reported. If required information is lack, the system will not issue the next month's report since the commission or management cannot legally issues such report during the general meeting. In the next future, this system could facilitate and help all users by increasing their productivity through the modernization of reporting process.

Jurnal STRATEGI - Jurnal Maranatha, May 20, 2020

The Faculty of Information Technology at Maranatha Christian University arranges many activities.... more The Faculty of Information Technology at Maranatha Christian University arranges many activities. The faculty has some difficulties in managing schedules, especially in determining appropriate schedules for all participants. Therefore, a webbased calendar is proposed which could manage the schedule of activities among faculty members. The web application is able to synchronize schedules from all articipants which integrated with Google Calendar. In addition, to ensure web usability, it is also necessary to design attractive user interfaces which comfortable to use and ensure user interaction. This web application is built by utilizing the AngularJS framework, based on MVC-model. The system testing shows that the web application has successfully built and can be used to manage the schedules.

Jurnal STRATEGI - Jurnal Maranatha, Apr 24, 2021

Jurnal STRATEGI - Jurnal Maranatha, Nov 8, 2020

Although Raspberry Pi has a mini size, it can do quite complex computing jobs, such as: digital i... more Although Raspberry Pi has a mini size, it can do quite complex computing jobs, such as: digital image processing to recognize faces. In this research, facial recognition techniques are applied in combination with eigenfaces algorithm. The algorithm is capable to deliver accurate facial recognition with minimal exposure by making black and-white face detection. Other aspects which are investigated in this research is focused on the settings of Raspberry Pi associated with the multimedia system which aim to allow users interacting with camera via Raspberry Pi. The programming language used during the development is Python. The results show that eigenfaces algorithms using Python language is capable to detect faces during login activity on a computer system by combining Raspberry Pi and its camera.

Jurnal STRATEGI - Jurnal Maranatha, Apr 30, 2019

Company X is a newborn company in connecting talents with production houses, advertising agencies... more Company X is a newborn company in connecting talents with production houses, advertising agencies, brands, and content creators. To support the its financial management, X Company needs a system which documents the inflow and outflow money. Based on the problem that occurred the auhtor decided to develop a cash flow system. This cash flow system is developed by using Laravel framework in PHP programming language following the MVC patterns and PostgreSQL database management system. The evaluation shows that the developed system could support the perfomance of Company X.

Jurnal Teknik Informatika dan Sistem Informasi

With the rapid development of new technologies in smartphones, understanding market trends has be... more With the rapid development of new technologies in smartphones, understanding market trends has become an increasingly difficult task. In these circumstances, online product reviews that can reflect consumer sentiment about the product has been a concern for now. Online review analysis can help sellers understand consumer interests and desires prior to launching a new product. The author wants to contribute to seeing the state of the smartphone market by creating a method to find important aspects of a smartphone. The data source comes from the Amazon e-commerce web with 4 predefined smartphone brands. In this study, the authors used topic modeling with the LDA algorithm and sentiment analysis with VADER to find aspects of a smartphone and its sentiment classification. From the 15 scenarios made in this reserach, it is found 3 aspects that always appear, namely the screen, camera, and battery aspects, so it is concluded that these 3 aspects are the most important of a smartphone base...

Jurnal Teknik Informatika dan Sistem Informasi, Dec 20, 2020

This paper presents a cooperation recommendation strategy between higher education institutions. ... more This paper presents a cooperation recommendation strategy between higher education institutions. The recommendation is based on the contents of journals published in a university journal portal. As a case study, we concentrate our approach for the journals with information technology themes. All journals from 10 reputed universities will be compared by using keywords and the contents of the journal themselves. A partnering recommendation list is built by utilizing Latent Semantic Indexing (LSI). LSI technique is used to reduce the curse of dimensionality from the original dataset and to generate topical analysis from all journals as a semantic representation for each journal. Topic modeling is used to calculate the categorical similarity in the dataset of each university journal and a search query. After all categorical similarities have been calculated, an average value of journal topics coherence is used to construct the final recommendation of partner candidates. This approach ensures that the final recommendation is based on the interest of each university rather than the frequencies of matched keywords in each journal.

International Conference on Emerging Issues in Technology, Engineering, and Science, 2021

Breast cancer (BC) is a lethal disease which causes the second largest number of deaths among wom... more Breast cancer (BC) is a lethal disease which causes the second largest number of deaths among women in the world. A diagnosis of biopsy tissue stained with hematoxylin & eosin, commonly named BC histopathological image, is a non-trivial task which requires a specialist to interpret. Recently, the advance in machine learning techniques driven by deep learning techniques and competition datasets has enabled the automation and pre- diction of histopathological images interpretation. Each different competition dataset has its own state-of-the- art technique; therefore, this paper explores an avenue of research by merging popular BC histopathological images research datasets and searching for the best performing models on the unified dataset. The merging process maintains similar classes among the datasets; consequently, the unified dataset has three classes and the prediction problem is cast into multi-class classification problem. We propose a combination of Vahadane preprocessing technique and training method using progressive resizing approach.Our approach demonstrates that both utilizing Vahadane image normalization and utilizing our progressive resizing technique achieve around 99% in F1 score , which is comparable among other state-of-the-art models.The unified dataset is also provided online for advancing research in histopathological images interpretation.