Suryadiputra Liawatimena
@binus.ac.id
Automotive & Robotics Program, Computer Engineering Department/ Faculty of Engineering
BINUS ASO School of Engineering
EDUCATION
Doctor of Computer Science, Bina Nusantara University, 2022
Doctor of Science Education, Curtin University, 2005
PostGraduate Diploma of Applied Science, Edith Cowan University, 1996
RESEARCH INTERESTS
Machine Learning, Computer Vision, Embedded System, Internet of Things, Metaverse, Mind Map
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Richard Medyanto, Nicholas Sanjaya, and Suryadiputra Liawatimena
IEEE
Solar energy is one of the most abundant sources of renewable energy in Indonesia. Solar energy is now typically harnessed using solar panels, but the low efficiency of photovoltaic cells requires the development of other alternatives. The heliostat is a sunlight directing device with mirrors that can be used in a concentrated solar power system. Current heliostats require high capital investment due to their large frames and expensive components. This research was undertaken to develop a lower cost heliostat using a smaller frame, ESP32 microcontroller, servo motor and low-cost components. The position of the sun can be determined using an algorithm based on the National Oceanic and Atmospheric Administration (NOAA) solar calculator, and the mirror is moved to maintain the sun's reflection on a target. The result of this research is a set of heliostat prototypes consisting of the frame and control system. Tests were carried out to test the performance of the designed heliostat and it was found that the heliostat has an accuracy of about 60 cm and can raise temperatures up to 3.41°C. The conclusion is that the heliostat can be used in a concentrated solar power system to heat boilers in solar power towers.
Suryadiputra Liawatimena, Edi Abdurachman, Agung Trisetyarso, Antoni Wibowo, Muhamad Keenan Ario, and Ivan Sebastian Edbert
Universitas Bina Nusantara
Every country in the world needs to report its fish production to the Food and Agriculture Organization of the United Nations (FAO) every year. In 2018, Indonesia ranked top five countries in fish production, with 8 million tons globally. Although it ranks top five, the fisheries in Indonesia are mostly dominated by traditional and small industries. Hence, a solution based on computer vision is needed to help detect and classify the fish caught every year. The research presents a method to detect and classify fish on mobile devices using the YOLOv3 model combined with ResNet18 as a backbone. For the experiment, the dataset used is four types of fish gathered from scraping across the Internet and taken from local markets and harbors with a total of 4,000 images. In comparison, two models are used: SSD-VGG and autogenerated model Huawei ExeML. The results show that the YOLOv3-ResNet18 model produces 98.45% accuracy in training and 98.15% in evaluation. The model is also tested on mobile devices and produces a speed of 2,115 ms on Huawei P40 and 3,571 ms on Realme 7. It can be concluded that the research presents a smaller-size model which is suitable for mobile devices while maintaining good accuracy and precision.
Ivander Ivander, Karunia Agung Mahardini, and Suryadiputra Liawatimena
ACM
PT. XYZ is a company focusing on producing herbal beverages in glass bottles. Inventory level is an important aspect and needs to be controlled by PT. XYZ because it has a strong relationship with the company's cash flow. At this moment, the average inventory level for the glass bottle of PT. XYZ is 32 days, while the target inventory level of the glass bottle must be achieved by PT. XYZ is 14 days. This research will focus on reducing the inventory level of glass bottles in PT. XYZ and ensure the supply sustainability in a high service level. Reduction of inventory level in PT. XYZ can be achieved by implementing the Internet of Things (IoT) and the Vendor Managed Inventory (VMI) method. VMI method implementation will focus on the stock availability with a low inventory level, and the implementation of the Internet of Things will make the inventory level information can be accessed in real-time and resolve this inventory problem. After improvement had been conducted, the service level (vendor performance) of glass bottles increased from 65% to 95%, and the inventory level reduced from 32 days of inventory (DOI) to 9 days.
Ivan William Harsono, Suryadiputra Liawatimena, and Tjeng Wawan Cenggoro
Elsevier BV
Meiryani Meiryani, Hanny Franciska, Rindang Widuri, Suryadiputra Liawatimena, Zaidi Mat Daut, and Hana Ulinnuha
ACM
The development of the increasingly advanced business world will certainly always be related to technological developments, especially in the current 4.0 era. In Indonesia, there are various types of companies such as services, manufacturing, food, and others. The development of the company will cause more and more complex transactions. It is very unlikely that the company has to record all forms of operations with a manual system, especially for large companies with so much data that they need a system to help process data quickly so that all transactions can be processed into reliable information. complete and accurate so that the company's goals can be realized. The purpose of this study was to determine the effectiveness of accurate accounting software for recording sales reports in one of the companies that engaged in food & beverage, namely Bliss Kitchen. The research that the writer did used is a quantitative approach with a survey method. This study finds that Accurate software that applied in Bliss kitchen is effective. Evidence shows the results of the questionnaire from Bliss Kitchen employees is positive about Accurate.
Meiryani Meiryani, Zaidi Mat Daud, Jajat Sudrajat, Tommy Andrian, and Suryadiputra Liawatimena
ACM
This study aims to determine the effect of business strategy on the quality of accounting information, to determine the effect of leadership style on the quality of accounting information and to determine the effect of business processes on the quality of accounting information. This study uses primary data from a population of State-Owned Enterprises throughout Indonesia with a total sample of 61 state-owned enterprises, and is analyzed using a simultaneous equation estimation model or SEM (Structural Equation Modeling), the sample determination is done by purposive sampling. The results showed that (1) leadership style and business processes affect the quality of accounting information systems (2) business strategy has no effect on the quality of accounting information systems on accounting information systems at State-Owned Enterprises in Indonesia.
Meiryani Meiryani, Gisela Gilberta, Risky Arshanty, ASL Lindawati, and Suryadiputra Liawatimena
ACM
This purpose of this study is find empirically The effect of management accounting information systems and decision making on managerial performance. The research method used is quantitative research methods with primary data obtained from questionnaire data which is measured using a likert scale. The result found that management accounting information system and decision making influence managerial performance. The results showed that the smaller the management accounting information system and decision making owned by the company, the smaller the percentage of managerial performance carried out in the company. The higher the management accounting information system, the higher the company's managerial performance.
Meiryani Meiryani, Noviyanti Hanna Uli Pakpahan, Dianka Wahyuningtias, Zaidi Mad Daud, and Suryadiputra Liawatimena
ACM
The rapid development has made financial technology/financial technology's innovations more diverse according to the needs and financial problems that arise. With the existence of financial technology (financial technology) it can also make the financial service process faster, more effective and easier. Because of the development in the field of financial technology with the various solutions offered, this study aims to examine the role of financial technology for the development of MSMEs (Micro and Medium Enterprises), this research also includes aspects of the role of financial inclusion for the development of MSMEs to be able to see how much public knowledge is about financial service products and risk knowledge. The case study in this research is MSMEs in the Tangerang area using quantitative methods. The results of research using multiple linear regression analysis found that the role of financial financial technology for the development of MSMEs has a significant positive effect. Meanwhile, financial inclusion for the development of MSMEs has a positive and insignificant effect on the dependent variable. This study concludes that the use of financial technology for MSME businesses, as well as the high reference to financial products, are important factors in encouraging the development of MSMEs.
Pantri Heriyati and Suryadiputra Liawatimena
IOP Publishing
Abstract This research attempt to propose the development of human mobility monitoring in the pandemic area in Indonesia. Current data on the COVID-19 is still alarming the world of the vast and aggressive spreading and the urgency to call on responsibilities for pandemic preparedness and response. Country answer to COVID-19 is mainly guided by the international situation, with the advice of organizations such as the WHO, investigation, data modeling based on the best available evidence, and the references. The system-wide response plans will have focused on the steadiness of public and vital public services and the stability of the economy, have been improved for COVID-19, based on the best available systematic evidence and guideline. The methodology uses a descriptive approach with mostly desk research. Data is collected from a secondary source and presented as a report format. For Indonesia COVID-19 situation, to monitor the people activity, this system development needs to find a suitable business center to be determined as a government-controlled logistics center. So that people activity can be more effective because transportation is reduced. With the active location feature activated at the user smartphone, then the system at any time can find out how many people are in a specific location. Their mobility is known at any time. This decision as a basis for the implementation of tracing, tracking, and fencing through infrastructure, systems, and telecommunications applications to support Health Surveillance, therefore, require the government reinforcement.
Suryadiputra Liawatimena, Edi Abdurahman, Agung Trisetyarso, Antoni Wibowo, Wiedjaja Atmadja, Fandy Effendi, and Ivan Sebastian Edbert
IOP Publishing
Abstract Convolutional neural networks (ConvNet or CNN) are deep learning algorithms that can process input images, assign meaning to various aspects or objects in the image (biases and learnable weight) and recognize one image from another. The bigger kernel size will take more time to process the input.We present a novelty way to use a 4D rank tensor to improve a convolutional process. At the early stage of the Convolve4D development, the edge detection with 3×3 kernel and The Laplacian of Gaussian (LoG) with 5×5 kernel size was used to demonstrate the convolutional process improvement. The Convolve4D needs more elaboration to be used into a CNN algorithm. The advantage of convolve4D is only need 9 loops to calculate 81 outputs, whereas convolve2D need 9 × 9 × 3 × 1 × 7 × 7 = 11.907 loops. The result is 18.5% shorter when using a 5×5 kernel; it reduces from 0.54 seconds to 0.44 seconds for the edge detection convolution process.
Meiryani -, Monika Sujanto, ASL Lindawati, Arif Zulkarnain, and Suryadiputra Liawatimena
The Science and Information Organization
The purpose of this study is to analyze the auditor’s perception of the implementation of technology transformation such as: blockchain and CAATs that can affect audit quality at the Big Four Public Accounting Firm in Jakarta. This study uses quantitative research methods using a combination of primary and secondary data. The data collection techniques used in this study was questionnaires. The sample was taken using purposive sampling method, which resulted in 60 respondents. Data analysis was carried out with SmartPLS 3.0 and IBM SPSS 26 software which resulted in the conclusion that the auditor’s perception of the implementation of blockchain had a significant positive effect on audit quality, while the auditor’s perception of the implementation of CAATs had no significant positive effect on audit quality.
Suryadiputra Liawatimena, Wiedjaja Atmadja, Bahtiar Saleh Abbas, Agung Trisetyarso, Antoni Wibowo, Erland Barlian, Lilik Tri Hardanto, Natassya Afdalena Triany, Faisal, Jaka Sulistiawan,et al.
IOP Publishing
Abstract It is necessary to study technical factors such as bait used, oceanographic conditions of fishing areas and skipjack tuna trade patterns (Katsuwonus pelamis) as well as other factors in Sulawesi Fisheries. Supporting data to study these technical factors need to be obtained so that it can be improved throughout the year as a skipjack fishing standard with weights taken by the skipjack weights. Therefore, drones and underwater drones with cameras with high-resolution video and images to be fed and processed by computer vision. These drones are operated via Huhate ships which are then used to test efficient technical factors as expected, can be used in determining the size, shape, and colour as well as the analysis of skipjack fish that are in the Fish Aggregating Devices (FADs or Rumpon) in order to manage the management of fisheries managed in Indonesia.
Suryadiputra Liawatimena, Wiedjaja Atmadja, Bahtiar Saleh Abbas, Agung Trisetyarso, Antoni Wibowo, Erland Barlian, Lilik Tri Hardanto, Adi Saputra, Putri Sakinah, Hery Purwoko,et al.
IOP Publishing
Abstract Tuna fishing in Indonesia is excessive and if left unchecked, some types of tuna will become extinct within 3-10 years. There is an urgent need to help MMAF for producing more accurate fish catches data. This paper proposed a system that utilizes computer vision, fuzzy logic and Global Positioning System (GPS) for supporting a sustainableIndonesian fishery by recognizing and measuring fish length, determine fish age and where is the catch location. The system can help authority to manage sustainable fisheries management in Indonesia.
Bagus Wira Pratama, Fabian Glenn, Wiedjaja Atmadja, Suryadiputra Liawatimena, and Rudy Susanto
IOP Publishing
Abstract The purpose of this research is to build artificial grow light using LED for growing leafy vegetables from germination to harvesting (vegetative growth). Plants need to capture photons as energy for photosynthesis in 400nm – 780nm spectrum. Different plant species will respond differently to specific light spectrum. Many studies have been done to find optimal light spectrum for plant growth, but there are still many researches to be done because there are still many combinations of light and plants species to be discovered. Specific light spectra combination is called light recipe. This research will help botanist to discover new light recipe for plant species by mixing 6 light spectra with individual intensity and time control. The developed grow light system has graphical user interface that run in Android tablet, and uses MQTT protocol for communication between android application and grow light system. Light recipe and setting are stored in database and the system also has light sensor to monitor light environmental conditions. Grow light consists of 6 types of 3W high power LED with specific color spectrum: Royal Blue, Deep Red, Ultraviolet, Full Spectrum, Far Red, and Natural White. Testing result shows that the system can produce uniform light distribution across the 50 x 50 cm grow area on average 22.6 µmol m-2s-1 using 60° lens. Germination result of lettuce using grow light shows good results compared to sunlight.
Yuyanto and Suryadiputra Liawatimena
IEEE
Agriculture nowadays deals with numerous factors to support the success of the harvest, such as temperature, air pressure, air humidity, sunlight, soil moisture, rainfall. With so much data that can be collected and analyzed, it is expected to create an early warning system if there are parameters that are already in the critical value and are at risk of causing crop failure. As information technology is developing rapidly, it could be utilized as a tool to support the effort in facing this issue. this study will focus on providing a reliable open data platform which is accessible to relevant stakeholders Google Cloud Platform is selected to serve this purpose to mitigate the risk of maintaining a reliable high availability platform. Google Cloud IoT Core is configured to accept MQTT protocol message sent by sensors. Other google cloud functionality will be configured to store the message into google NoSQL database. Google cloud function will be used to provide data if any request of data to server is being made through REST webservice call. As a result, all the configured Google functionalities are able to synchronize to store and retrieve data.
Mario Nugroho Willyarto, Ulani Yunus, Anggraeni S. Reksodipuro, and Suryadiputra Liawatimena
IEEE
One of the best ways to teach children about road safety in schools is through interactive learning by introducing them to the crossing signs. With the implementation of interactive learning activities regarding the introduction of the crossing signs, is expected to occur for increasing perceptual-motor skills of the research subjects. Perceptual-motor skills are associated with the ability to react quickly to any situations on the street. Through interactive learning activities, the subject research has shown their positive responses and enthusiasm in doing those activities. The research subject is ten preschool students aged 4-5. The process of data collection is conducted through observations, interviews, personal documents of the students, distributing the questionnaire to parents, as well as documentation such as photographs. The research was without IoT. The result of this research found out that the subject research's perceptual motor skills seemed to increase regarding the reaction of speed and correctness from their body movement toward the visual information given. This acquisition appears after the research subject were given some fun and hands-on activities at school especially about an introduction to the crossing signs for preschool children. It was recommended to use IoT for better achievement.
Ivan William Harsono
Universitas Bina Nusantara
Following artificial intelligence implementation in computer vision fields, especially deep learning, many Computer-Aided Diagnosis (CAD) tools are proposed to help to detect lung cancer by the scoring system or by identifying the characteristics of nodules. However, lung cancer is a clinical diagnosis which does not provide detailed information needed by radiologists and clinician to prevent unnecessary invasive diagnostic procedures compared to lung nodule texture detection and classification. Hence, to answer this problem, this research explores the steps needed to implement 3D CNN on raw thorax CT scan datasets and usage of RetinaNet 3D + Inception 3D with transfer learning. The 3D CNN CAD tools can improve the speed, performance, and ability to detect lung nodule texture instead of malignancy status done by previous studies. This study implements 3D CNN on Moscow private datasets acquired from NVIDIA Asia Pacific. The proposed method of data conversion can minimize information loss from raw data to 3D CNN input data. After 100 epoch training, the researchers conclude that the best-proposed model (3D CNN with transfer learning of pretrained LIDC public datasets weight) provides 22.86% of mean average precision (mAP) detection capability and 70.36% of Area Under the Curve (AUC) in Moscow private dataset lung texture detection tasks. It outperforms non-transfer learning 3D CNN model (trained from scratch) and 3D CNN with transfer learning of pre-trained ImageNet weight.