Admin Website UNIKOM

Tag: sinta

  • Inventory Control Cost Reduction for Infusion Using Material Requirement Planning Based on Lot Sizing

    Inventory Control Cost Reduction for Infusion Using Material Requirement Planning Based on Lot Sizing

    Authors: Diana Andriani, Hendry Hardianto, Nugraha

    Abstract

    The purpose of this study is to minimize raw materials’ inventory control cost due to the excess of raw materials from Normal Saline 100 mL and Ringer Lactate 500 mL infusion. The method used in this research were six lot sizing methods such as Fixed Order Quantity, Fixed Period Requirement, Least Unit Cost, Least Total Cost, Part Period Balancing, and Silver Meal Algorithm. The results showed that the Normal Saline 100 mL infusion product used the Least Unit Cost (LUC) method and resulted in the lowest cost with two order periods. The use of LUC method saves a total of IDR 3,425,000. For the Ringer Lactate 500 mL infusion product, it is proven that the LTC and PPB methods produced the least cost. Orders with the LTC and PPB methods are made after two order periods for Sodium Chloride and Calcium Chloride Dihydrate raw materials, four order periods for Sodium Lactate, and five order periods for Potassium Chloride. The savings made using the TLC and PBB methods amounted to IDR 29,675,000. © School of Engineering, Taylor’s University

    Author keywords

    Inventory control costs; Lot sizing; Material requirement planning

    This article can be accessed at https://www.scopus.com/pages/publications/85105040811

  • Implementation of Fuzzy Tsukamoto in Production Planning Decision Support Systems

    Implementation of Fuzzy Tsukamoto in Production Planning Decision Support Systems

    Authors: Riani Lubis, Sri Nurhayati

    Abstract

    The purpose of this research is to implement Fuzzy Tsukamoto in designing production planning decision support systems. Determining the production quantity is one of the important activities in production planning. The production quantity affects the determination of raw material requirements and production costs. Therefore, it is very important to determine the right production quantities. It avoids the accumulation of raw material on the production floor and large production cost. In this research, production planning decision support systems provide recommendation on production quantities. It can be used as a reference for production manager to determine the production quantity for the next production period. Fuzzy Tsukamoto was a method used in this study to determine the production quantities. The result of this research is the production planning decision support system model that applied the Fuzzy Tsukamoto method. Implementation of Fuzzy Tsukamoto can provide a recommendation of production quantities that is used to determine the production quantities and making production schedule. © 2021 Taylor’s University. All rights reserved.

    Author keywords

    Determination; Production amount; Recommendation

    This article can be accessed at https://www.scopus.com/pages/publications/85138270360

  • Elman Recurrent Neural Network for Aspect Based Sentiment Analysis

    Elman Recurrent Neural Network for Aspect Based Sentiment Analysis

    Authors: Nelly Indriani Widiastuti, Maulvi Inayat Ali

    Abstract

    Aspect based sentiment analysis (ABSA) is one of the domains of opinion mining cases which aims to detect the polarity of written text based on certain aspects. The purpose of this study was to determine the accuracy value of Elman RNN in the case of ABSA. The method used is divided into two main processes, namely pre-process and sentiment detection. Before conducting the training, the input data in the form of restaurant reviews in Indonesian went through the preprocessing process. In the data review, case folding, filtering, word normalization, tokenization, stop word removal, the addition of token aspects (price, taste, atmosphere) was carried out, building a word dictionary, and forming one-hot encoding. In the polarity detection process, training and testing use the ERNN algorithm. The data used were 1584 sentences of Indonesian restaurant reviews and were tested on 422 data. Based on the test results, Elman RNN got the best accuracy of 81.22% and an f1 score of 82.78%. For the social analytic system developer, these results show evidence that the ERNN is promising to be used in detecting the polarity of a restaurant review. © School of Engineering, Taylor’s University

    Author keywords

    Aspect based sentiment analysis; Indonesian language; Preprocessing; Recurrent neural network; Semantic evaluation

    This article can be accessed at https://www.scopus.com/pages/publications/85108833617

  • Development of UX Orbit Design Online Courses Platform in the field of User Interface (UI) and User Experience (UX)

    Development of UX Orbit Design Online Courses Platform in the field of User Interface (UI) and User Experience (UX)

    Authors: Leonardi Paris Hasugian, Dalih Rusmana

    Abstract

    The purpose of this research is to provide a User Interface (UI) and User Experience (UX) learning solution for the community so that the distribution of good quality learning content can be properly and easily conveyed to the public. To achieve this goal, an online course platform that specifically focuses on the UI and UX fields which meets community’s preferences was created. It addresses problems such as issues in finding learning resources and mentors, as well as the lack of distribution of good quality learning content. This research used prototyping model from analysing the existing system until developing a prototype system. The created online course platform is expected to help people, both technophiles and non-technophiles to increase their knowledge and abilities, especially in the fields of UI and UX. © School of Engineering, Taylor’s University.

    Author keywords

    Course; Platform; User experience; User interface

    This article can be accessed at https://www.scopus.com/pages/publications/85109564413

  • Study of Hybrid Flood Forecasting Approach Combining Multiplicate Seasonal Arima and Hybrid-Neuro Fuzzy Based on Long-Term Time Series

    Study of Hybrid Flood Forecasting Approach Combining Multiplicate Seasonal Arima and Hybrid-Neuro Fuzzy Based on Long-Term Time Series

    Authors: Sri Supatmi, Irfan Dwiguna Sumitra, Rongtao Hou

    Abstract

    This research proposes a modern hybrid method to forecast the flood employing an approach combining Multiplicative Seasonal Autoregressive Moving Average (MSARIMA) and Hybrid-Neuro Fuzzy Inference System (HN-FIS) based on long-term time series. This proposed method is called Hybrid Flood Forecasting System Technology (Hybrid-FFST). This research aims to improve three previous types of research on flood forecasts, such as flood prediction using HNFIS and flood forecasting using MSARIMA and rainfall prediction using Multiplicative Seasonal Autoregressive Moving Average Subsequence Aggregate (MSARIMASA). This research has taken place in Bandung West Java Province, Indonesia. The performance of flood event forecasting improving by using the hybrid approaches method using both MSARIMA and two levels of HN-FIS. This proposed method employs six parameters: rainfall, temperature, population density, large watershed, the altitude of the area, and slop of the land to predict the flood event. The performance of this method is generated and fitting well using the Hybrid-FFST approach and the verified by Mean Absolute Percentage Error (MAPE), Root Means Square Percentage Error (RMSPE), and Mean Forecast Error (MFE) to identify the best-fitted model of the proposed model. The proposed model’s performance is compared using MAPE, RMSPE, and MFE with MSARIMA, HN-FIS, and MSARIMASA model. The confidence performance of the proposed method obtains more significant than 97% according to the MAPE, RMSE, and MFE values. The proposed model results indicate better performance than the MSARIMA, HN-FIS, and MSARIMASA models to forecast the flood event. The impact of this research is the flood can be predicted before occurred in someplace. © School of Engineering, Taylor’s University.

    Author keywords

    Flood; Flood forecasting system; Hybrid approach; Prediction

    This article can be accessed at https://www.scopus.com/pages/publications/85111844671

  • Wind Load on Temporary Air Rib Inflated Pneumatic Building Structure

    Wind Load on Temporary Air Rib Inflated Pneumatic Building Structure

    Author: Salmon Priaji Martana

    Abstract

    This study aims to provide an example of calculating the wind load in an air rib inflated structure. The method used was an architectural simulation in which building criteria were created and then realized in a CAD-generated iconic model. The building is divided into several segments, analysed mathematically using a calculation method adapted from conventional rigid structure calculations. The lift and drag force results obtained in this study can be used to determine how the air-inflated rib structure builds up against these forces so that each rib element remains anchored on the ground when facing the external forces. To tackle the lift up force is then the next issue of finding the correct foundation in a specific surface material to bind the structure to the ground. This study’s calculation model is expected to open the possibilities to develop safer air rib inflated structure application to stand the strong wind. © School of Engineering, Taylor’s University

    Author keywords

    Air inflated structure; Air rib structure; Pneumatic architecture; Pneumatic structure

    This article can be accessed at https://www.scopus.com/pages/publications/85111182516

  • Development of Class Library in Domain of Scrolling Shooter Game

    Development of Class Library in Domain of Scrolling Shooter Game

    Authors: Adam Mukharil Bachtiar, Dian Dharmayanti, Rakhmat Sabarudin

    Abstract

    The purpose of this research is to develop a Class Library in the domain of Scrolling Shooter games. The built of this Class Library will be used to develop Scrolling Shooter games as the result of this research. In software engineering, there is a reuse concept that is used to reuse functional systems. One application of this concept is the class library. With the class library, programmers can directly call the functions they need without building them from scratch. This study also used the class library concept for the domain of the shooter scrolling game case. The development of a Class Library is done through seven phases, Domain Analysis, Frozenspot Analysis, Hotspot Analysis, Modelling Class Library, Implementation Class Library, Unit Testing, and Integration Testing, and those will be the main discussion of this research. Furthermore, this research’s conclusion is expected to help game programmers develop Scrolling Shooter games without making the whole system functional from scratch. This research also contributes to software engineering concepts, namely: Reusable code, abstraction, and class design. © 2021 Taylor’s University. All rights reserved.

    Author keywords

    Class library; Domain analysis; Frozenspot analysis; Game scrolling shooter; Hotspot analysis

    This article can be accessed at https://www.scopus.com/pages/publications/85118679668

  • Student Attendance Monitoring System Using Fingerprint and Whatsapp

    Student Attendance Monitoring System Using Fingerprint and Whatsapp

    Authors: Rahmatya M. D, Wicaksono M. F

    Abstract

    This study aims at creating a student attendance monitoring system using fingerprint and WhatsApp. It is due to the tight activity of parents or guardians which make them difficult to monitor their children’s attendance at school. The system approach and development method used were object oriented and waterfall. The waterfall method consists of requirements, design, and implementation. The study results present that the system can send messages about students’ attendance via WhatsApp. The system can help the teacher in managing student attendance data as well as informing parents or guardians of students about the date and time when students enter and leave the school. Other than that, it can also help in informing students’ presence on that day so that parents or guardians know that the student is attending school. The system also provides summary of student attendance data in one semester via WhatsApp number of parents or guardians. © 2021 Taylor’s University. All rights reserved.

    Author keywords

    Attendance; Fingerprints; Monitoring system; School; WhatsApp

    This article can be accessed at https://www.scopus.com/pages/publications/85117191896

  • Min-Cost Flow Network to Detect Text Line on Certificate

    Min-Cost Flow Network to Detect Text Line on Certificate

    Authors: Indra Rianto, Ednawati Rainarli

    Abstract

    This study aims to use the Min-Cost Flow network to obtain text lines in the character detection that process on the certificate. Determining the text line is part of the text detection process before the word recognition process. Detection of the text that appears on the certificate is part of the process for automatically extracting information. The diversity of colour, font types and sizes, and the complexity of the certificate background make the scanner text detection more complex than other optical character detections. This study used the Tesseract tool to get character candidates and added merging characters into a text line using the Min-Cost Flow method. To improve the quality of the image, we used smoothing techniques with integral images. After the thresholding and segmentation process, the result is the input to Tesseract. The Tesseract detects the candidates of character. The test varies the confidence score, the threshold value for the vertical length of the two components, horizontal width, and font size difference. The best results are the confident score of at least 50, the horizontal width of less than 2, the vertical length of less than 0.2, and a difference in size between letters less than 2 with an F-Score of 62%. Even though the F-score is less than 70%, we found that the Min-Cost Flow method can select objects other than text detected by the Tesseract result, such as signatures and logos. Using the Min-Cost Flow, we can combine character candidates into one text line for later processing on text recognition. © 2021 Taylor’s University. All rights reserved.

    Author keywords

    Candidate components; Certificates; Min-Cost flow; Text detection; Text line

    This article can be accessed at https://www.scopus.com/pages/publications/85117332547

  • Min-Cost Flow Network to Detect Text Line on Certificate

    Authors: Indra Rianto, Ednawati Rainarli

    Abstract

    This study aims to use the Min-Cost Flow network to obtain text lines in the character detection that process on the certificate. Determining the text line is part of the text detection process before the word recognition process. Detection of the text that appears on the certificate is part of the process for automatically extracting information. The diversity of colour, font types and sizes, and the complexity of the certificate background make the scanner text detection more complex than other optical character detections. This study used the Tesseract tool to get character candidates and added merging characters into a text line using the Min-Cost Flow method. To improve the quality of the image, we used smoothing techniques with integral images. After the thresholding and segmentation process, the result is the input to Tesseract. The Tesseract detects the candidates of character. The test varies the confidence score, the threshold value for the vertical length of the two components, horizontal width, and font size difference. The best results are the confident score of at least 50, the horizontal width of less than 2, the vertical length of less than 0.2, and a difference in size between letters less than 2 with an F-Score of 62%. Even though the F-score is less than 70%, we found that the Min-Cost Flow method can select objects other than text detected by the Tesseract result, such as signatures and logos. Using the Min-Cost Flow, we can combine character candidates into one text line for later processing on text recognition. © 2021 Taylor’s University. All rights reserved.

    Author keywords

    Candidate components; Certificates; Min-Cost flow; Text detection; Text line

    This article can be accessed at https://www.scopus.com/pages/publications/85117332547