Admin Website UNIKOM

Tag: kampus entrepreneur digital

  • Travel Route Recommendation System Based on 

    Weather Prediction and Geolocation Technology

    Authors: Eko Budi Setiawan; Gradiyanto Putera Husein; Angga Setiyadi

    DOI: 10.1109/INCITEST59455.2023.10395920

    Abstract

    Information regarding weather conditions is quite challenging to obtain and predict. People who in their daily lives have to travel to a destination, such as workers or traveling salesman, cannot predict the weather they will encounter during their journey. The impact is that people often experience some losses when traveling. This research produces an Android-based application used by the general public to avoid travel losses caused by weather. The application provides travel recommendation information in the form of routes obtained from the Google Directions API and weather predictions obtained from the Dark Sky API. This application helps users predict weather predictions on their path to reduce the risk of rain loss. The results of black-box testing and user acceptance found that Android-based applications managed to get a level of 84% in providing travel recommendations, achieving 80.6% success in predicting the weather and obtaining 76.6% in reducing rain risk. © 2023 IEEE.

    Author keywords

    Geolocation; Recommendation; Route; Travel; Weather

    Indexed keywords

    Engineering controlled terms

    Acceptance tests; Android (operating system); Application programming interfaces (API); Black-box testing; Weather forecasting

    Engineering uncontrolled terms

    Condition; Daily lives; Geolocations; Recommendation; Route; Travel; Travel routes; Weather; Weather prediction; Workers’

    Engineering main heading

    Rain

    This article can be accessed at https://www.scopus.com/pages/publications/85185198321

  • Optimizing Bankruptcy Prediction Through Filterbased Feature Selection

    Authors: Nelly Indriani Widiastuti, Ednawati Rainarli, Kania Evita Dewi

    DOI: 10.1109/INCITEST64888.2024.11121476

    Abstract

    Predicting corporate bankruptcy is a critical task in the financial world. Artificial intelligence techniques have become a promising solution for predicting a company’s condition. One of the crucial phases in the bankruptcy prediction process is feature selection. It is the procedure for choosing from a data set the variables that will be most useful in a prediction model. This study examines and evaluates the important feature selection for machine learning-based bankruptcy prediction. A Taiwan Stock Exchange public dataset, which includes 95 financial ratio features, was used in the study. Several filtering feature selection methods, such as Analysis of Variance (ANOVA), Kendall Tau correlation coefficient (KT), and Mutual Information (MI), were used to identify relevant features. The methods of bankruptcy classification applied were Logistic Regression and Random Forest. According to the test results, ANOVA produces the highest recall value for the Taiwan Stock Exchange dataset, both with the Logistic Regression (LR) and Random Forest (RF). Using 61% of the available features or 58 features, the bankruptcy prediction model with Random Forest performed well without compromising accuracy, precision, recall, or F1 score. © 2024 IEEE.

    Author keywords

    ANOVA; bankruptcy prediction; feature selection; filtering methods; financial ratios

    This article can be accessed at https://www.scopus.com/pages/publications/105015829493

  • Optimizing Bankruptcy Prediction Through Filterbased Feature Selection

    Authors: Nelly Indriani Widiastuti, Ednawati Rainarli, Kania Evita Dewi

    DOI: 10.1109/INCITEST64888.2024.11121476

    Abstract

    Predicting corporate bankruptcy is a critical task in the financial world. Artificial intelligence techniques have become a promising solution for predicting a company’s condition. One of the crucial phases in the bankruptcy prediction process is feature selection. It is the procedure for choosing from a data set the variables that will be most useful in a prediction model. This study examines and evaluates the important feature selection for machine learning-based bankruptcy prediction. A Taiwan Stock Exchange public dataset, which includes 95 financial ratio features, was used in the study. Several filtering feature selection methods, such as Analysis of Variance (ANOVA), Kendall Tau correlation coefficient (KT), and Mutual Information (MI), were used to identify relevant features. The methods of bankruptcy classification applied were Logistic Regression and Random Forest. According to the test results, ANOVA produces the highest recall value for the Taiwan Stock Exchange dataset, both with the Logistic Regression (LR) and Random Forest (RF). Using 61% of the available features or 58 features, the bankruptcy prediction model with Random Forest performed well without compromising accuracy, precision, recall, or F1 score. © 2024 IEEE.

    Author keywords

    ANOVA; bankruptcy prediction; feature selection; filtering methods; financial ratios

    This article can be accessed at https://www.scopus.com/pages/publications/105015829493

  • Design of Public Service Administrative Information System

    Authors: Herry Saputra, Nizar Rabbi Radliya, Eddy Soeryanto Soegoto, Fadhil Fadhilah Ilham

    DOI: 10.1109/INCITEST64888.2024.11121522

    Abstract

    The sub-district office is one of the government agencies in charge of carrying out population administration services at the village level. However, in the implementation of these administrative services, there are still obstacles that must be addressed, such as the process of making certificates and filing documents, which are still too complicated and timeconsuming. To help solve these problems, we need an information system website that can help speed up the administrative service process. This study aims at designing an administrative information system called SIAPIK, which is based on the website at the Tagaraja Sub-district office, Riau, Indonesia. Descriptive analysis method with a qualitative approach was used in this study to determine the needs of the system to be built. In the system development process, we used the concept of an object-oriented approach with a prototype development method. The results showed that the development of this information system could provide convenience in supporting the role and function of the sub-district office in carrying out the population service administration process. In conclusion, the existence of this online administration system will help solve various problems at the sub-district office. This information system used an online system that allows residents to make certificate via desktop or smartphone devices regardless of time and place without having to come directly to the sub-district office. © 2024 IEEE.

    Author keywords

    information system; public service administrative; SIAPIK

    This article can be accessed at https://www.scopus.com/pages/publications/105015848206

  • Analysis and Monitoring System of Train Generator Sets Based on Internet of Things (IoT)

    Authors: Henny; Agus Heri Setya Budi; Arjuni Budi Pantjawati; Mochamad Ilham Alwi Rifa; Iyan Andriana

    DOI: 10.1109/INCITEST59455.2023.10396896

    Abstract

    This research aims to create a reliable and monitoring system for train generator sets based on the Internet of Things (IoT) using the Research and Development (R&D) method. The main objective of this research is to obtain a system that can provide real-time information about power factor changes in the generator set and improve the power factor through reactive power compensation by determining the value of capacitors that should be installed to achieve a target power factor of 0,9. The research stages include designing and developing the system using relevant hardware and software components. The system is designed based on components such as PZEM-004T, CT, LM2596 SIM 800L, and ESP32 microcontroller to collect data from the sensors and send it to the server through the internet. Next, the system stores parameter data in the Firebase database. Then, an algorithm is created to recommend capacitor values to improve the power factor with a target of 0.9. Finally, a website is built using ReactJS to display all parameter data and capacitor recommendations. Testing the PZEM-004T sensor showed an error rate of 0.8% to 1.5% in the generator set parameters. From this research, it can be concluded that the reliability and monitoring system for train generator sets based on the Internet of Things (IoT) have been successfully developed. The system can provide real-time information about the power factor and offer capacitor value recommendations with a target power factor of 0,9. © 2023 IEEE.

    Author keywords

    capacitor; generator sets; internet of things (IoT); power factor

    This article can be accessed at: https://www.scopus.com/pages/publications/85185196384

  • Computational Calculation on the Shell and Tube-Type Heat Exchanger for Lanthanum Oxide (La2O3) Nanoparticle Production Process for Energy-Related Material Application

    Authors: Asep Bayu Dani Nandiyanto ; Irine Sofianty ; Adani Gina Puspita Sari ; Rofi Fadilah Madani ; Fitri Febrianti ; Risti Ragadhita ; Teguh Kurniawan ; Rizky Jumansyah ; Eddy Soeryanto Soegoto ; Senny Luckyardi ; Muhammad Aziz

    DOI: 10.18280/mmep.100243

    Abstract

    This paper introduced a design of a heat exchanger to get an optimum heat transfer enhancement technique that can be used for the production of lanthanum oxide (La2O3). The shell and tube type was selected since this type is one of the effective types for making excellent heat transfer, which was then compared to the Tubular Exchanger Manufacturers Association (TEMA) standard to obtain the dimensional specifications of the heat exchanger device. Several parameters were calculated to evaluate the performance of the designed heat exchanger. Numerical calculation obtained from the heat exchanger containing 138 tubes can be used to maintain the temperature in the reactor (prospective temperature can change from 40 to 60°C with rapid heating) using heating liquid (controlling by transferring heat from 100 to 70°C) with the effective value of 96%. This study can be used as a reference for supporting information in the current issue of the need for the large production of La2O3 particles © 2023, Mathematical Modelling of Engineering Problems.All Rights Reserved.

    Author keywords

    heat exchanger; La2O3; nanoparticles; shell and tube

  • Integration of Failure Mode and Effect Analysis with Fuzzy Analytical Hierarchy Process for Risk Prioritization in Machining Processes

    Authors: Gabriel Sianturi, Agus Riyanto, M. Yani Syafei, Julian Robecca, Alam Santosa, Adi Lukman Nurhakim

    DOI: 10.1109/INCITEST64888.2024.11121517

    Abstract

    This paper develops a Failure Mode and Effect Analysis (FMEA) method integrated with the Fuzzy Analytical Hierarchy (FAHP) method to prioritize the risk in the autoclave bolt machining processes. FMEA is applied to identify and evaluate the failure modes, while FAHP is utilized to determine the weights of risk factors so that the weights are not taken the same as in the traditional FMEA approach, but it is based on the decision maker’s judgment. The incorporation of fuzzy set theory into FAHP can overcome the problems of uncertainty and vagueness faced by decision makers during the evaluation process. The result of the research shows that the severity has the highest weight, followed by detection and occurrence. In addition, the diameter is not accurate in the failure mode with the highest Risk Priority Number (RPN) among all failure modes. © 2024 IEEE.

    Author keywords

    FMEA; Fuzzy AHP; machining process

    This article can be accessed at https://www.scopus.com/pages/publications/105015745069

  • Implementation of Science Learning Application Two Seasons Weather Change Material Based of multimedia For Deaf Students

    Authors: Diana Effendi; Beri Noviansyah; Sri Ela Dinasti; Delviola Cancerina

    DOI: 10.1109/INCITEST59455.2023.10397027

    Abstract

    This research is a continuation of previous research, namely the Design of Multimedia Based Two Season Weather Change Science Learning Application For Deaf Students Part B for Deaf. This study will discuss how to implement programs that have been made into applications that can be used by user with prototype approach. In addition, a measurement of user satisfaction with the application was carried out. To measure user satisfaction with the application, descriptive and quantitative methods were used, using a questionnaire distributed to seven respondents, namely six students of grade VI and one science teacher at SLBN Cicendo Bandung, with seven questions. From the results of the questionnaire distribution, the satisfaction level of the respondents was 95%, which means that the user is satisfied with the multimedia application, where this application can help in the process of teaching science, especially the material of two seasons weather change. The results of this research contribute to how the learning model is more interesting for deaf students and makes it easier for teachers to explain the material compared to conventional teaching methods. © 2023 IEEE.

    Author keywords

    multimedia; science; two season weather change

    This article can be accessed at: https://www.scopus.com/pages/publications/85185194326

  • Feature Classification Based on Heterogenous Data 

    Using Hybrid Machine Learning: A Review

    Authors: Agus Nursikuwagus ; Heri Purwanto ; Deshinta Arrova Dewi

    DOI: –

    Abstract

    Heterogeneous data is a dataset with various types including data type and data source. Classification of heterogeneous data is still becoming a discussion in research in the field of intelligence artificial especially in learning classification. Based on data and machine development classification, then study this still relevant done. Machine classification that is still trending now is a hybrid engine known as the collaboration technique such as a fuzzy technique and neural network. The aim of this review paper is to find opportunity research on hybrid machine learning that perform classification on heterogeneous data with multi-class targets. There are several challenges on heterogeneous data such as 1)determining algorithm normalization and text processing as Step beginning from the input layer, 2) function formation variable linguistics for every case allow existence opportunity study for linguistic processes, 3) A membership function algorithm that can adapt of the dataset used can as opportunity research, 4) finding method shaper fuzzy rule as machine inference from a neural network, 5) Process structure of every task, 6) performance like efficiency memory for processing ( management memory ), complexity (process time), and validation architecture (accuracy, precision, recall, f-measure, specification, true prediction, false prediction). The result of the research obtained is the existence opportunity for improving or developing a hybrid classification machine that can handle heterogeneous data with multi-class targets. © 2023 Little Lion Scientific.

    Author keywords

    Classification; Feature; Fuzzy; Heterogenous Data; Neural Network

    This article can be accessed at https://www.scopus.com/pages/publications/85174975477

  • Development of Innovative Model for Waste Management System Using Internet of Things (IoT) and Machine Learning

    Development of Innovative Model for Waste Management System Using Internet of Things (IoT) and Machine Learning

    Authors: Dimas Akmarul Putera, Ansarullah Lawi, Filmada Ocky Saputra, Sri Handayani, Yun Arifathul Fatimah, Ivan Muhammad Reza, Sholikun, Zainal Arifin Hasibuan, Alvendo Wahyu Aranski

    DOI: 10.1109/ICIC64337.2024.10957619

    Abstract

    Effective and efficient waste management system is a significant challenge in coastal areas. This research proposes the development of innovative model for waste management system using IoT and machine learning. The system consists of hardware such as cameras and image sensors installed in coastal locations to monitor the volume and types of waste. The image data collected from these devices is stored and analyzed using image processing techniques. The YOLO (You Only Look Once) algorithm is used to identify and classify the types of waste. The identified data is then used to train a machine learning model, which allows for the prediction of future waste volume and types. These predictions are used to optimize waste collection schedules, reduce operational costs, plan the types of waste processing, and minimize environmental impact. With this holistic approach, the system is expected to enhance the efficiency and sustainability of waste management, providing an innovative solution to waste management issues in coastal areas. © 2024 IEEE.

    Keywords: Environment; Image Processing; IoT; Machine Learning; Waste Management

    This article can be accessed at https://www.scopus.com/pages/publications/105004578932