Skip to main content

Heru Ipung

Followers

7

Following

1

Public Views

Interests

Uploads

Papers by Heru Ipung

Design an Agile of Machine Learning to Predictive House Pricing and Targeting Segmented Market

Proceedings of the International Conference on Engineering and Information Technology for Sustainable Industry

Analisis Interaksi Pengguna di Media Sosial Dalam Mencegah Video Hoax dan Model Arsitektur Deteksi Tingkat Tinggi

Jurnal inovasi informatika, Mar 31, 2022

Penyebaran berita hoaks dengan konten video yang berulang pada media sosial merupakan fenomena ya... more Penyebaran berita hoaks dengan konten video yang berulang pada media sosial merupakan fenomena yang sangat luar biasa dan muncul bukan hanya pada kalangan pengguna dewasa saja namun sudah kesegala lapisan usia, Efek yang paling terasa adalah timbulnya perpecahan di masyarakat karena penggunaan video yang sudah pernah tayang atau ada sebelumnya menjadi bukti kuat untuk memvalidasi konten yang dilihatnya. Penting untuk mendeteksi berita hoaks dengan konten video yang berulang dan menghentikan efek negatifnya pada individu dan masyarakat. Pada penelitian ini pembuatan model arsitektur deteksi tingkat tinggi untuk sistem analisis berita hoaks dengan konten video yang digunakan kembali atau berulang pada media sosial di kenalkan, dengan menggunakan deep learning video processing, speech to text dan beberapa fitur content-based dan context-based rancangan model arsitektur ini dibuat. Konten hoaks dengan video yang berulang diharapkan dapat dicegah penyebarannya jika bisa di filter terlebih dahulu sebelum muncul di lini masa. Diharapkan model arsitektur ini dapat menjadi referensi untuk di buat menjadi real system Kata kunci: Hoaks, social media, video processing, speech to text, deep learning, recycle video content

IT strategic planning for finance in PT GMF Aeroasia

Swiss German University, 2018

Mobile Website User Experience (UX) Evaluation on Indonesia's Online Marketplace

Journal of Applied Information, Communication and Technology, Oct 25, 2016

Internet economy is growing in Indonesia, and so is the smartphone usage. The popularity of onlin... more Internet economy is growing in Indonesia, and so is the smartphone usage. The popularity of online marketplace is getting bigger by the day yet the market is not utilized as best as it could. A lot of new smartphone user may not be familiar with the concept of mobile application, yet they browse for products to purchase using their mobile web browser. Therefore, a mobile website User Experience (UX) evaluation on online marketplace in Indonesia is needed. By using User Experience Questionnaire (UEQ), this research hopes to evaluate which aspect of a marketplace's mobile website is looked for by its users. An interview is conducted to 30 people to simulate shopping experience on Tokopedia and Bukalapak using a mobile web browser. The result shows that users prefers shopping without having to register, thus making online shopping quick and easy. In addition, user prefers to have all information they need regarding a product in one page rather than having to perform many action to reveal more information.

Blockchain in Supply Chain: Case Study of Lottemart Ciputat

ACMIT Proceedings, 2019

Current supply chain methods are having difficulties in resolving problems arising from the lack ... more Current supply chain methods are having difficulties in resolving problems arising from the lack of trust in supply chains. The root reason lies in two challenges brought to the traditional mechanism: self-interests of supply chain members and information asymmetry in production processes. Blockchain is a promising technology to address these problems. The key objective of this paper is to present qualitative analysis for blockchain in supply chain as the decision-making framework to implement this new technology. The analysis method used Val IT business case framework, validated by the expert judgements. The further study needs to be elaborated by either the existing organization that use blockchain or assessment by the organization that will use blockchain to improve their supply chain management.

Hadoop Configuration Tuning for Performance Optimization

Journal of Applied Information, Communication and Technology, 2017

Configuration parameter tuning is an essential part of the implementation of Hadoop clusters. Eac... more Configuration parameter tuning is an essential part of the implementation of Hadoop clusters. Each parameter in a configuration plays a role that impacts the ov erall performance of the cluster. Therefore, we need to learn the characteristics of said parameter and understand the impact in hardware utilization in order to achieve optimal configuration. In this paper, we conducted experiments that includes modifying configuration and performed benchmark to find out if there is any performance gain. TeraSort is the program that runs the benchmark, we measure the time needed to complete the sort of the set of data and the CPU utilization during the benchmark. We conclu de that from our experiments we can see significant performance improvements by tuning with the configurations. However, the results may vary between different cluster configuration.

Pengembangan Alternatif Sensor Smartcity: Ujicoba Deteksi Kandungan Air Pada Pasir Dengan Citra Infra Merah Pita Sempit (Narrowband Near Infrared Imaging)

Prosiding Seminar Nasional Pakar

Kandungan air dan kelembaban tanah (Soil Water and Moisture)mempengaruhi iklim lokal di suatu bag... more Kandungan air dan kelembaban tanah (Soil Water and Moisture)mempengaruhi iklim lokal di suatu bagian kota. Di dalam konteks SmartCitydimungkinkan kelembapan permukaan landscape dijaga, dimana diperlukanadanya sensor kelembapan tanah. Saturasi air dalam tanah (Water SaturatedSoil) juga bisa dipakai sebagai indikasi awal bencana yang terkait dengan air(Hazard early Detection). Penelitian ini mengujicobakan awal alternatif murahsensor citra infra merah pita sempit (Narrowband Near Infrared) untuk deteksikeberadaan air yang bisa digunakan di udara (Airborne Sensing) yangmengurangi ketergantungan adanya alat sensor kandungan air di setiap titikyang di amati.

Developing a Scalable and Accurate Job Recommendation System with Distributed Cluster System using Machine Learning Algorithm

Journal of Applied Information, Communication and Technology, 2021

The purpose of this research is to develop a job recommender system based on the Hadoop MapReduce... more The purpose of this research is to develop a job recommender system based on the Hadoop MapReduce framework to achieve scalability of the system when it processes big data. Also, a machine learning algorithm is implemented inside the job recommender to produce an accurate job recommendation. The project begins by collecting sample data to build an accurate job recommender system with a centralized program architecture. Then a job recommender with a distributed system program architecture is implemented using Hadoop MapReduce which then deployed to a Hadoop cluster. After the implementation, both systems are tested using a large number of applicants and job data, with the time required for the program to compute the data is recorded to be analyzed. Based on the experiments, we conclude that the recommender produces the most accurate result when the cosine similarity measure is used inside the algorithm. Also, the centralized job recommender system is able to process the data faster c...

The Influence of Training, Working Displin, and Organizational Commitments to Employee Performance

Detecting Network Security Threats Using Domain Name System and NetFlow Traffic

Proceedings of the 2nd International Conference on Cryptography, Security and Privacy, 2018

With more and more organization in the world rely on the Internet to do their business or activit... more With more and more organization in the world rely on the Internet to do their business or activity, the malicious attackers are always looking for ways to penetrate in organization internal network to achieve their malicious goals. The malicious activities may include spam distribution, denial of service, adware, identity theft and many other security threats. Many of the security perimeter devices only able to detect network security threats from external, organization is left with many undetected or even unknown internal security threats. Many of these network security threats can be detected by monitoring and analyzing network traffic. One of the emerging threats is Domain Name System (DNS) Distributed Denial of Service (DDoS) attack, which flood the authoritative DNS server with large amount of DNS request. We introduce a new method to detect DDoS attack by using Netflow traffic as the early indicator of DDOS attacks and DNS traffic to validate the DNS DDOS attack. We also showed that by measuring statistical entropy of Netflow traffic and statistical values of DNS NXDOMAIN response, our proposed model could be used to detect either low volume or high volume DDoS attack.

Data Integration Readiness Analysis in Merged Telecommunication Company

2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS, 2021

This study conducted analysis of the readiness of data integration in merged telecommunication co... more This study conducted analysis of the readiness of data integration in merged telecommunication company, using the Data Management Body of Knowledge (DAMA-DMBOK) framework and evaluating it with COBIT. Three readiness parameters are evaluated, namely Data Architecture, Data Governance, and Data Quality. The analysis process uses a case in the calculation of revenue and billing collection, which has an impact on the achievement of cash and net income in the company, which is the KPI for the Business Performance of the company. From the Data Architecture Analysis, it was found that some of the business processes were still run manually and had not been integrated. From the Analysis of Data Governance and Data Quality, it is found that there are differences in the interpretation of these two parameters in the company's internal, namely in the expert group of recording revenue compared to the non-expert one, as well as differences in company base employees from companies M and P. Also, it is reviewed from the Data Quality is readier for data integration than when viewed from Data Governance, therefore it requires a lot of improvement. This study aims to uncover that companies should take further systematic and strategic steps before the data integration process is carried out. The DAMA-DMBOK method obtained that Company M had the applicable percentage of 52,98% while Company P had the applicable percentage of 95.00%. Due to the large gap between the perception, further investigation needs to be conducted in possible future studies.

Distributed Denial of Service (DDoS), web vandalism, and

rising of computer violence, such as Distributed Denial of Service (DDoS), web vandalism, and cyb... more rising of computer violence, such as Distributed Denial of Service (DDoS), web vandalism, and cyber bullying are becoming more serious issues when they are politically motivated and intentionally conducted to generate fear in society. These kinds of activity are categorized as cyber terrorism. As the number of such cases increase, the availability of information regarding these actions is required to facilitate experts in investigating cyber terrorism. This research aims to create text classification system which classifies the document using several algorithms including Naïve Bayes, Nearest Neighbor, Support Vector Machine (SVM), Decision Tree, and Multilayer Perceptron. The result shows that SVM outperforms by achieving 100% of accuracy. This result concludes the excellent performance of SVM in handling high dimensional of data.

Core Banking System Scalability Review

ACMIT Proceedings, 2021

In carrying out the digital transformation, bank has to find their optimal routes to exploit the ... more In carrying out the digital transformation, bank has to find their optimal routes to exploit the Open Banking opportunity and minimize or manage any threat. However open Banking models will be making implication on the increasingly hit from the external parties. It will be new and more unpredictable data volumes as third parties request access to the banking system. Bank has to prepare their Banking system on the Enterprise Architecture, and one of the concerns is on the scalability. For the traditional core banking system, the platform of mainframe and other legacy technology could remain the bottleneck to agility and scalability. In this paper, scalability testing and analysis are carried out to verify whether the traditional banking core system running on the power platform can be scalable to support open banking strategy. The results found were that the core banking system could be scalable, but needed a lot of enhancement on the core banking application side, as well as capacit...

Knowledge Capturing and Codifying in Knowledge Management Using Alfresco: A Case Study of Swiss German University

Journal of Applied Information, Communication and Technology, 2015

Knowledge management has become the asset of every organization because every knowledge in each g... more Knowledge management has become the asset of every organization because every knowledge in each group is unique one with another. Two aspects that important in knowledge management is step to capturing theknowledge and codifying the knowledge. Capturing mean to list or create a real documentation of knowledge while codifying is to create a digital version from capturing process so it can be processed or easily manipulated. One of the most growth software to do knowledge management for codifying is alfresco that being established in 2005. Alfresco provide open source so called Alfresco Community Edition that enable developer to create rules in codifying the knowledge. The output of this process is to create functional ECM in a form of a portal where end user can use it to manage a contents or documents.

Object identification and visualization of urban road materials using narrowband near infrared imaging indexes

Journal of emerging technologies and innovative research, 2019

Classification performance analysis was done on selected narrowband near-infrared spectrum to ide... more Classification performance analysis was done on selected narrowband near-infrared spectrum to identify urban road materials. There were five urban road materials to be identified; aggregate, asphalt, carbon organic, clay and concrete. The imaging indexes were selected that proposed a set of narrowband 760nm, 800nm, 850nm, 900nm, 950nm, 980nm with 720nm wide-band spectrum as normalization spectrum. Multilayer perceptron classification method was used. The result was presented where a significant classification performance shown on those five urban road materials with 76.6032 % using 10 fold cross validation on data data samples. A separate test data samples used for further predictions and visualization. Keyword: Imaging indexes, near-infrared, feature classifier, prediction and visualization, multilayer perceptron

Study on Social Media Users and Its Relation to the e-Commerce Activities on Youth in Indonesia

Journal of Applied Information, Communication and Technology, 2016

Internet, Social Media and e-Commerce are three most common thingspeople could find and usually i... more Internet, Social Media and e-Commerce are three most common thingspeople could find and usually interact with nowadays. Internet has beenpart of our basic daily needs: no one can work professionally withoutbeing connected to the network even once in a day. Those people usuallyalso have at least one Social Media accounts; as well know about theexistence of e-Commerce markets. Also, Social Media and e-CommerceChannel nowadays more likely to interact with each other: peoplespreading the word about their commerce in the Social Networks. Basedon that fact, this research purpose is to find out which factors, based onthe Technology Acceptance Model, is playing the huge role on this socalled relations between the interaction of people in the Social Media andtheir activities in the e-Commerce, especially on Indonesian youth. Itturns out, that Voluntariness has 55% contribution towards this relations,as well as Job Relevance, Result Demonstrability and Computer SelfEfficacy with 63%, 60% and ...

Millenial Disruptive Technology: An Assessment on Disrupted Banking Industry

ACMIT Proceedings, 2017

Millennial are new generation that demand a new kind of market expectation and seeks new value on... more Millennial are new generation that demand a new kind of market expectation and seeks new value on how industry interact with its customer. Among assessed industries in the US, Banks are the most vulnerable industry that millennial demands new kind of approach to conduct banking in the past three years facilitated by the increasing influence of digital technology in everyday life. Millennial are the generation that born in 80s and 90s where they see the dying relevant of bank [1]. The survey sees that in US 68% of them think that the way we access our money will be totally different, 70% said that the way we pay for things will be totally different, and even 33% believe that bank will not be needed at all in the next 5 year. However, the key question is what is millennial really needs on the banking services in Indonesia? Is the trend in the US and Europe is catching up soon? Is Indonesia Banks ready from the eyes of Millennial? This research focuses on current level of digital banki...

Urban Road Materials Identification using Narrow Near Infrared Vision System

International Journal of Electrical and Computer Engineering (IJECE), 2017

An urban road materials vision system using narrow band near infrared imaging indexes were propos... more An urban road materials vision system using narrow band near infrared imaging indexes were proposed. This proposed imaging indexes were enhancement for previous work on autonomous multispectral road sensing method. Each urban road material has different near infrared spectral patterns which is as the base of its spectral identification. The new proposed imaging indexes, which using similar formula of NDVI, was normalized with narrow band near infrared spectrum range of 720nm to 1000nm of wavelength, were used to identify concretes, aggregates/sands/rocks, clay, natural dry fibers and bitumen/asphalt that make up most of urban road materials. This paper proposes imaging indexes evaluation from experiment results to identify those urban road materials. There were seven narrow band optical filter sets with the center spectrum at 710nm, 730nm, 750nm, 800nm, 870nm, 905nm and 970nm. Normalization band used was 720nm using high pass optical filter. The proposed multi-spectral imaging index...

Urban Road Materials Identification using Narrow Near Infrared Vision System

International Journal of Electrical and Computer Engineering (IJECE), 2017

An urban road materials vision system using narrow band near infrared imaging indexes were propos... more An urban road materials vision system using narrow band near infrared imaging indexes were proposed. This proposed imaging indexes were enhancement for previous work on autonomous multispectral road sensing method. Each urban road material has different near infrared spectral patterns which is as the base of its spectral identification. The new proposed imaging indexes, which using similar formula of NDVI, was normalized with narrow band near infrared spectrum range of 720nm to 1000nm of wavelength, were used to identify concretes, aggregates/sands/rocks, clay, natural dry fibers and bitumen/asphalt that make up most of urban road materials. This paper proposes imaging indexes evaluation from experiment results to identify those urban road materials. There were seven narrow band optical filter sets with the center spectrum at 710nm, 730nm, 750nm, 800nm, 870nm, 905nm and 970nm. Normalization band used was 720nm using high pass optical filter. The proposed multi-spectral imaging index...

Experiment of Multispectral Sensing Sensor for Urban Road Materials in Outdoor Environment

ICONIET PROCEEDING, 2019

This research is the first attempt to conduct several experiments of multispectralsensing sensor ... more This research is the first attempt to conduct several experiments of multispectralsensing sensor for urban road materials in outdoor environment. This research aims to classifyfive urban road materials that are aggregates, asphalts, concrete, clay, natural fibre includingvegetation and water. There were 9 cameras in the multispectral sensing sensor. Seven cameraattached with narrow band optical filter with the centre spectrum at 710nm, 730nm, 750nm,800nm, 870nm, 905nm and 950nm. One camera attached with 720 nm normalization band useshigh pass optical filter. Another camera attached with UV/IR cut optical filter works as a RGBcamera. The images results, that have been taken, are processed in MATLAB to get the imagingindex results from the multispectral system. Naïve Bayes classifier is used in Weka to classifythe urban road materials with vegetation and water. The first classification and testing thatclassifies five urban road materials with vegetation and water have accuracy results...

Design an Agile of Machine Learning to Predictive House Pricing and Targeting Segmented Market

Proceedings of the International Conference on Engineering and Information Technology for Sustainable Industry

Analisis Interaksi Pengguna di Media Sosial Dalam Mencegah Video Hoax dan Model Arsitektur Deteksi Tingkat Tinggi

Jurnal inovasi informatika, Mar 31, 2022

Penyebaran berita hoaks dengan konten video yang berulang pada media sosial merupakan fenomena ya... more Penyebaran berita hoaks dengan konten video yang berulang pada media sosial merupakan fenomena yang sangat luar biasa dan muncul bukan hanya pada kalangan pengguna dewasa saja namun sudah kesegala lapisan usia, Efek yang paling terasa adalah timbulnya perpecahan di masyarakat karena penggunaan video yang sudah pernah tayang atau ada sebelumnya menjadi bukti kuat untuk memvalidasi konten yang dilihatnya. Penting untuk mendeteksi berita hoaks dengan konten video yang berulang dan menghentikan efek negatifnya pada individu dan masyarakat. Pada penelitian ini pembuatan model arsitektur deteksi tingkat tinggi untuk sistem analisis berita hoaks dengan konten video yang digunakan kembali atau berulang pada media sosial di kenalkan, dengan menggunakan deep learning video processing, speech to text dan beberapa fitur content-based dan context-based rancangan model arsitektur ini dibuat. Konten hoaks dengan video yang berulang diharapkan dapat dicegah penyebarannya jika bisa di filter terlebih dahulu sebelum muncul di lini masa. Diharapkan model arsitektur ini dapat menjadi referensi untuk di buat menjadi real system Kata kunci: Hoaks, social media, video processing, speech to text, deep learning, recycle video content

IT strategic planning for finance in PT GMF Aeroasia

Swiss German University, 2018

Mobile Website User Experience (UX) Evaluation on Indonesia's Online Marketplace

Journal of Applied Information, Communication and Technology, Oct 25, 2016

Internet economy is growing in Indonesia, and so is the smartphone usage. The popularity of onlin... more Internet economy is growing in Indonesia, and so is the smartphone usage. The popularity of online marketplace is getting bigger by the day yet the market is not utilized as best as it could. A lot of new smartphone user may not be familiar with the concept of mobile application, yet they browse for products to purchase using their mobile web browser. Therefore, a mobile website User Experience (UX) evaluation on online marketplace in Indonesia is needed. By using User Experience Questionnaire (UEQ), this research hopes to evaluate which aspect of a marketplace's mobile website is looked for by its users. An interview is conducted to 30 people to simulate shopping experience on Tokopedia and Bukalapak using a mobile web browser. The result shows that users prefers shopping without having to register, thus making online shopping quick and easy. In addition, user prefers to have all information they need regarding a product in one page rather than having to perform many action to reveal more information.

Blockchain in Supply Chain: Case Study of Lottemart Ciputat

ACMIT Proceedings, 2019

Current supply chain methods are having difficulties in resolving problems arising from the lack ... more Current supply chain methods are having difficulties in resolving problems arising from the lack of trust in supply chains. The root reason lies in two challenges brought to the traditional mechanism: self-interests of supply chain members and information asymmetry in production processes. Blockchain is a promising technology to address these problems. The key objective of this paper is to present qualitative analysis for blockchain in supply chain as the decision-making framework to implement this new technology. The analysis method used Val IT business case framework, validated by the expert judgements. The further study needs to be elaborated by either the existing organization that use blockchain or assessment by the organization that will use blockchain to improve their supply chain management.

Hadoop Configuration Tuning for Performance Optimization

Journal of Applied Information, Communication and Technology, 2017

Configuration parameter tuning is an essential part of the implementation of Hadoop clusters. Eac... more Configuration parameter tuning is an essential part of the implementation of Hadoop clusters. Each parameter in a configuration plays a role that impacts the ov erall performance of the cluster. Therefore, we need to learn the characteristics of said parameter and understand the impact in hardware utilization in order to achieve optimal configuration. In this paper, we conducted experiments that includes modifying configuration and performed benchmark to find out if there is any performance gain. TeraSort is the program that runs the benchmark, we measure the time needed to complete the sort of the set of data and the CPU utilization during the benchmark. We conclu de that from our experiments we can see significant performance improvements by tuning with the configurations. However, the results may vary between different cluster configuration.

Pengembangan Alternatif Sensor Smartcity: Ujicoba Deteksi Kandungan Air Pada Pasir Dengan Citra Infra Merah Pita Sempit (Narrowband Near Infrared Imaging)

Prosiding Seminar Nasional Pakar

Kandungan air dan kelembaban tanah (Soil Water and Moisture)mempengaruhi iklim lokal di suatu bag... more Kandungan air dan kelembaban tanah (Soil Water and Moisture)mempengaruhi iklim lokal di suatu bagian kota. Di dalam konteks SmartCitydimungkinkan kelembapan permukaan landscape dijaga, dimana diperlukanadanya sensor kelembapan tanah. Saturasi air dalam tanah (Water SaturatedSoil) juga bisa dipakai sebagai indikasi awal bencana yang terkait dengan air(Hazard early Detection). Penelitian ini mengujicobakan awal alternatif murahsensor citra infra merah pita sempit (Narrowband Near Infrared) untuk deteksikeberadaan air yang bisa digunakan di udara (Airborne Sensing) yangmengurangi ketergantungan adanya alat sensor kandungan air di setiap titikyang di amati.

Developing a Scalable and Accurate Job Recommendation System with Distributed Cluster System using Machine Learning Algorithm

Journal of Applied Information, Communication and Technology, 2021

The purpose of this research is to develop a job recommender system based on the Hadoop MapReduce... more The purpose of this research is to develop a job recommender system based on the Hadoop MapReduce framework to achieve scalability of the system when it processes big data. Also, a machine learning algorithm is implemented inside the job recommender to produce an accurate job recommendation. The project begins by collecting sample data to build an accurate job recommender system with a centralized program architecture. Then a job recommender with a distributed system program architecture is implemented using Hadoop MapReduce which then deployed to a Hadoop cluster. After the implementation, both systems are tested using a large number of applicants and job data, with the time required for the program to compute the data is recorded to be analyzed. Based on the experiments, we conclude that the recommender produces the most accurate result when the cosine similarity measure is used inside the algorithm. Also, the centralized job recommender system is able to process the data faster c...

The Influence of Training, Working Displin, and Organizational Commitments to Employee Performance

Detecting Network Security Threats Using Domain Name System and NetFlow Traffic

Proceedings of the 2nd International Conference on Cryptography, Security and Privacy, 2018

With more and more organization in the world rely on the Internet to do their business or activit... more With more and more organization in the world rely on the Internet to do their business or activity, the malicious attackers are always looking for ways to penetrate in organization internal network to achieve their malicious goals. The malicious activities may include spam distribution, denial of service, adware, identity theft and many other security threats. Many of the security perimeter devices only able to detect network security threats from external, organization is left with many undetected or even unknown internal security threats. Many of these network security threats can be detected by monitoring and analyzing network traffic. One of the emerging threats is Domain Name System (DNS) Distributed Denial of Service (DDoS) attack, which flood the authoritative DNS server with large amount of DNS request. We introduce a new method to detect DDoS attack by using Netflow traffic as the early indicator of DDOS attacks and DNS traffic to validate the DNS DDOS attack. We also showed that by measuring statistical entropy of Netflow traffic and statistical values of DNS NXDOMAIN response, our proposed model could be used to detect either low volume or high volume DDoS attack.

Data Integration Readiness Analysis in Merged Telecommunication Company

2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS, 2021

This study conducted analysis of the readiness of data integration in merged telecommunication co... more This study conducted analysis of the readiness of data integration in merged telecommunication company, using the Data Management Body of Knowledge (DAMA-DMBOK) framework and evaluating it with COBIT. Three readiness parameters are evaluated, namely Data Architecture, Data Governance, and Data Quality. The analysis process uses a case in the calculation of revenue and billing collection, which has an impact on the achievement of cash and net income in the company, which is the KPI for the Business Performance of the company. From the Data Architecture Analysis, it was found that some of the business processes were still run manually and had not been integrated. From the Analysis of Data Governance and Data Quality, it is found that there are differences in the interpretation of these two parameters in the company's internal, namely in the expert group of recording revenue compared to the non-expert one, as well as differences in company base employees from companies M and P. Also, it is reviewed from the Data Quality is readier for data integration than when viewed from Data Governance, therefore it requires a lot of improvement. This study aims to uncover that companies should take further systematic and strategic steps before the data integration process is carried out. The DAMA-DMBOK method obtained that Company M had the applicable percentage of 52,98% while Company P had the applicable percentage of 95.00%. Due to the large gap between the perception, further investigation needs to be conducted in possible future studies.

Distributed Denial of Service (DDoS), web vandalism, and

rising of computer violence, such as Distributed Denial of Service (DDoS), web vandalism, and cyb... more rising of computer violence, such as Distributed Denial of Service (DDoS), web vandalism, and cyber bullying are becoming more serious issues when they are politically motivated and intentionally conducted to generate fear in society. These kinds of activity are categorized as cyber terrorism. As the number of such cases increase, the availability of information regarding these actions is required to facilitate experts in investigating cyber terrorism. This research aims to create text classification system which classifies the document using several algorithms including Naïve Bayes, Nearest Neighbor, Support Vector Machine (SVM), Decision Tree, and Multilayer Perceptron. The result shows that SVM outperforms by achieving 100% of accuracy. This result concludes the excellent performance of SVM in handling high dimensional of data.

Core Banking System Scalability Review

ACMIT Proceedings, 2021

In carrying out the digital transformation, bank has to find their optimal routes to exploit the ... more In carrying out the digital transformation, bank has to find their optimal routes to exploit the Open Banking opportunity and minimize or manage any threat. However open Banking models will be making implication on the increasingly hit from the external parties. It will be new and more unpredictable data volumes as third parties request access to the banking system. Bank has to prepare their Banking system on the Enterprise Architecture, and one of the concerns is on the scalability. For the traditional core banking system, the platform of mainframe and other legacy technology could remain the bottleneck to agility and scalability. In this paper, scalability testing and analysis are carried out to verify whether the traditional banking core system running on the power platform can be scalable to support open banking strategy. The results found were that the core banking system could be scalable, but needed a lot of enhancement on the core banking application side, as well as capacit...

Knowledge Capturing and Codifying in Knowledge Management Using Alfresco: A Case Study of Swiss German University

Journal of Applied Information, Communication and Technology, 2015

Knowledge management has become the asset of every organization because every knowledge in each g... more Knowledge management has become the asset of every organization because every knowledge in each group is unique one with another. Two aspects that important in knowledge management is step to capturing theknowledge and codifying the knowledge. Capturing mean to list or create a real documentation of knowledge while codifying is to create a digital version from capturing process so it can be processed or easily manipulated. One of the most growth software to do knowledge management for codifying is alfresco that being established in 2005. Alfresco provide open source so called Alfresco Community Edition that enable developer to create rules in codifying the knowledge. The output of this process is to create functional ECM in a form of a portal where end user can use it to manage a contents or documents.

Object identification and visualization of urban road materials using narrowband near infrared imaging indexes

Journal of emerging technologies and innovative research, 2019

Classification performance analysis was done on selected narrowband near-infrared spectrum to ide... more Classification performance analysis was done on selected narrowband near-infrared spectrum to identify urban road materials. There were five urban road materials to be identified; aggregate, asphalt, carbon organic, clay and concrete. The imaging indexes were selected that proposed a set of narrowband 760nm, 800nm, 850nm, 900nm, 950nm, 980nm with 720nm wide-band spectrum as normalization spectrum. Multilayer perceptron classification method was used. The result was presented where a significant classification performance shown on those five urban road materials with 76.6032 % using 10 fold cross validation on data data samples. A separate test data samples used for further predictions and visualization. Keyword: Imaging indexes, near-infrared, feature classifier, prediction and visualization, multilayer perceptron

Study on Social Media Users and Its Relation to the e-Commerce Activities on Youth in Indonesia

Journal of Applied Information, Communication and Technology, 2016

Internet, Social Media and e-Commerce are three most common thingspeople could find and usually i... more Internet, Social Media and e-Commerce are three most common thingspeople could find and usually interact with nowadays. Internet has beenpart of our basic daily needs: no one can work professionally withoutbeing connected to the network even once in a day. Those people usuallyalso have at least one Social Media accounts; as well know about theexistence of e-Commerce markets. Also, Social Media and e-CommerceChannel nowadays more likely to interact with each other: peoplespreading the word about their commerce in the Social Networks. Basedon that fact, this research purpose is to find out which factors, based onthe Technology Acceptance Model, is playing the huge role on this socalled relations between the interaction of people in the Social Media andtheir activities in the e-Commerce, especially on Indonesian youth. Itturns out, that Voluntariness has 55% contribution towards this relations,as well as Job Relevance, Result Demonstrability and Computer SelfEfficacy with 63%, 60% and ...

Millenial Disruptive Technology: An Assessment on Disrupted Banking Industry

ACMIT Proceedings, 2017

Millennial are new generation that demand a new kind of market expectation and seeks new value on... more Millennial are new generation that demand a new kind of market expectation and seeks new value on how industry interact with its customer. Among assessed industries in the US, Banks are the most vulnerable industry that millennial demands new kind of approach to conduct banking in the past three years facilitated by the increasing influence of digital technology in everyday life. Millennial are the generation that born in 80s and 90s where they see the dying relevant of bank [1]. The survey sees that in US 68% of them think that the way we access our money will be totally different, 70% said that the way we pay for things will be totally different, and even 33% believe that bank will not be needed at all in the next 5 year. However, the key question is what is millennial really needs on the banking services in Indonesia? Is the trend in the US and Europe is catching up soon? Is Indonesia Banks ready from the eyes of Millennial? This research focuses on current level of digital banki...

Urban Road Materials Identification using Narrow Near Infrared Vision System

International Journal of Electrical and Computer Engineering (IJECE), 2017

An urban road materials vision system using narrow band near infrared imaging indexes were propos... more An urban road materials vision system using narrow band near infrared imaging indexes were proposed. This proposed imaging indexes were enhancement for previous work on autonomous multispectral road sensing method. Each urban road material has different near infrared spectral patterns which is as the base of its spectral identification. The new proposed imaging indexes, which using similar formula of NDVI, was normalized with narrow band near infrared spectrum range of 720nm to 1000nm of wavelength, were used to identify concretes, aggregates/sands/rocks, clay, natural dry fibers and bitumen/asphalt that make up most of urban road materials. This paper proposes imaging indexes evaluation from experiment results to identify those urban road materials. There were seven narrow band optical filter sets with the center spectrum at 710nm, 730nm, 750nm, 800nm, 870nm, 905nm and 970nm. Normalization band used was 720nm using high pass optical filter. The proposed multi-spectral imaging index...

Urban Road Materials Identification using Narrow Near Infrared Vision System

International Journal of Electrical and Computer Engineering (IJECE), 2017

An urban road materials vision system using narrow band near infrared imaging indexes were propos... more An urban road materials vision system using narrow band near infrared imaging indexes were proposed. This proposed imaging indexes were enhancement for previous work on autonomous multispectral road sensing method. Each urban road material has different near infrared spectral patterns which is as the base of its spectral identification. The new proposed imaging indexes, which using similar formula of NDVI, was normalized with narrow band near infrared spectrum range of 720nm to 1000nm of wavelength, were used to identify concretes, aggregates/sands/rocks, clay, natural dry fibers and bitumen/asphalt that make up most of urban road materials. This paper proposes imaging indexes evaluation from experiment results to identify those urban road materials. There were seven narrow band optical filter sets with the center spectrum at 710nm, 730nm, 750nm, 800nm, 870nm, 905nm and 970nm. Normalization band used was 720nm using high pass optical filter. The proposed multi-spectral imaging index...

Experiment of Multispectral Sensing Sensor for Urban Road Materials in Outdoor Environment

ICONIET PROCEEDING, 2019

This research is the first attempt to conduct several experiments of multispectralsensing sensor ... more This research is the first attempt to conduct several experiments of multispectralsensing sensor for urban road materials in outdoor environment. This research aims to classifyfive urban road materials that are aggregates, asphalts, concrete, clay, natural fibre includingvegetation and water. There were 9 cameras in the multispectral sensing sensor. Seven cameraattached with narrow band optical filter with the centre spectrum at 710nm, 730nm, 750nm,800nm, 870nm, 905nm and 950nm. One camera attached with 720 nm normalization band useshigh pass optical filter. Another camera attached with UV/IR cut optical filter works as a RGBcamera. The images results, that have been taken, are processed in MATLAB to get the imagingindex results from the multispectral system. Naïve Bayes classifier is used in Weka to classifythe urban road materials with vegetation and water. The first classification and testing thatclassifies five urban road materials with vegetation and water have accuracy results...