Admin Website UNIKOM

Tag: UNIKOM computer science research

  • Application of The Thinking Design Method in UI/UX Design of The Lawn Mowing Service Application

    Authors: Muhammad Faiz Islami, Hanhan Maulana

    DOI: 10.1109/INCITEST64888.2024.11121521

    Abstract

    People in Bangkinang have difficulty accessing effective lawn mowing services. Lack of information and traditional ordering methods prevent service providers from expanding their market reach. A digital solution is needed to overcome this problem. In Bangkinang City, many people are engaged in lawn mowing services, but ordering for this service traditionally done through brochures and word of mouth recommendations. This study focuses on developing a lawn mowing service application using design thinking. English This methodology consists of five steps: empathize, define, ideate, prototype, and test, which are used to understand user needs, generate ideas, develop prototypes, and test solutions. The research results in the form of a prototype mobile application for service providers in Bangkinang City, tested using the system usability ladder (SUS) method with an average score of 80.66 for the service user application and 81.5 for the service provider application, indicating that the application is easy to use and well received by users. This research is expected to improve the effectiveness and efficiency of the lawn mowing servise booking process and contribute significantly to the development of information technology in the community. This research aims to design a lawn mowing service application using design thinking, to give users a good experience and can efficiently order services. © 2024 IEEE.

    Author keywords

    Design thinking; system usability scale; usability

    This article can be accessed at https://www.scopus.com/pages/publications/105015889965

  • Optimizing Forest Fire Detection Using PSO, Neural Networks, 

    and k-Fold Cross-Validation

    Authors: Nina Kurnia Hikmawati; Yudi Ramdhani; Doni Purnama Alamsyah

    DOI: 10.1109/ICIC64337.2024.10956756

    Abstract

    Preventing Forest fires by identifying events based on specific criteria using the Neural Network (NN) algorithm. To ensure result stability, test and training data are divided using k-fold cross-validation with variations k-5, k-10, and k-20. The NN algorithm performed significantly better after being optimized with Particle Swarm Optimization (PSO), with the average accuracy value going from 97% to 98.78% and the AUC value increasing from 0.997 to 0.999. A weight study of PSO reveals variability in values for each attribute, with Day and Month having no significant effect on classification. The results of the Paired Two-sample t-test for Means show that using PSO improves accuracy significantly. The merging of PSO with Neural Networks has a considerable positive influence on forest fire prediction and is suggested for applications requiring high accuracy. © 2024 IEEE.

    Author keywords

    Forest Fires; Machine Learning; Neural Networks; Particle Swarm Optimization

    Indexed keywords

    Engineering controlled terms

    Stability criteria

    Engineering uncontrolled terms

    Forest fire detection; Forest fires; K fold cross validations; Machine-learning; Neural networks algorithms; Neural-networks; Particle swarm; Particle swarm optimization; Particle swarm optimization-neural networks; Swarm optimization

    Engineering main heading

    Particle swarm optimization (PSO)

    This article can be accessed at https://www.scopus.com/pages/publications/105004579202

  • Comparative Analysis of Interactive Map Data Loading Using the GeoJSON Method for West Java New Entrepreneurs

    Authors: Angga Setiyadi; Eko Budi Setiawan

    DOI: 10.1109/INCITEST59455.2023.10396976

    Abstract

    The purpose of this study is to analyze interactive maps using the GeoJSON method and without using GeoJSON for new entrepreneurs in West Java. The flow of the stages of this research consists of three parts, namely analyzing the code, implementing the code, and testing the code that has been created using GeoJSON and without GeoJSON. The results obtained in this study are using GeoJSON to display data on an interactive map faster than without using GeoJSON. The downside of using GeoJSON on an interactive map is that the app developer is more likely to write down the source code on loading the interactive map. © 2023 IEEE.

    Author keywords

    Comparative Analysis; GeoJSON; Interactive Map; New Entrepreneurs

    This article can be accessed at: https://www.scopus.com/pages/publications/85185197883

  • K-Means Clustering for Crime Cluster Analysis in District Prosecution Office of Indramayu

    K-Means Clustering for Crime Cluster Analysis in District Prosecution Office of Indramayu

    Author: Aditya Erlangga, Rizky Bani Asmara E.M., Raudatussholihat Amalia, Estiko Rijanto

    DOI: 10.1109/INCITEST59455.2023.10396984

    Abstract

    Crime is a criminal behavior that often causes problems in society with a variety of crimes that often occur such as murder, assault, rape, theft, fraud, embezzlement, narcotics and. In Article 35 paragraph (1) letter K of Law No. 16 of 2004 concerning the Attorney General of the Republic of Indonesia as amended in Law No. 11 of 2021 states that the Prosecution Office is a government institution whose function is related to judicial power to prosecute and other power abide by law. K-Algorithm Means is a non-hierarchical clustering algorithm that has capability to group data in large quantity, quickly and efficiently. In this paper, data from 217 cases tested from Indramayu District Attorney during January 2022 until December 2022. K-Means algorithm was successful to classify relationship between criminal cases and which prosecutors whom handling them. The result using optimal K=3 formed three cluster which consists of Cluster C1 = 9 types of cases, Cluster C2 = 9 types of cases Cluster C3 = 9 types cases with members C2 and C3 have the Global Unique, Domination, and Share characteristics within each cluster. © 2023 IEEE.

    Keywords: clustering; crime; K-Means; prosecutor

    This article can be accessed at https://www.scopus.com/pages/publications/85185198398

  • Leveraging Internet of Things and Blockchain for Improved Air Quality Monitoring Systems

    Authors: Irawan Afrianto, Fikri Muhamad Fauzi, Sufa Atin

    DOI: 10.1109/INCITEST64888.2024.11121510

    Abstract

    The objective of this research is to develop an air quality monitoring system based on the Internet of Things (IoT) and blockchain technology. The application of the two technologies is considered a very suitable solution to provide air quality information in a fast and accurate manner and has resistance to data manipulation, reliable and trustworthy. The research includes problem identification, data collection, system analysis and design. In addition, implementation and testing of the system that has been developed. IoT is used as an input media that supports air data such as CO and CO2. Data from IoT is acquired by the system, and stored in a blockchain network through smart contracts to maintain the integrity of the data. Data from the blockchain network then used as information that can be utilized by users to determine the condition of air quality in the environment. The results showed that the air quality monitoring system that integrates IoT and blockchain technology was successfully developed. System performance testing based on success ratio and failure variables send rate, latency, and throughput shows that the developed system can produce a good performance to handle large IoT data and can maintain the integrity of IoT data in the blockchain network. The contribution resulting from this research shows that a system that integrates IoT and blockchain technology can increase and improve the quality and performance of the air quality monitoring system. © 2024 IEEE.

    Author keywords

    air quality; blockchain technology; internet of things (IoT); monitoring system

    This article can be accessed at https://www.scopus.com/pages/publications/105015869404

  • Application of Backend and Frontend Systems on 

    Go-Baby Application in Bandung City

    Authors: Fenny Syafariani R. ; Andri Sahata Sitanggang ; Andino Maseleno

    DOI: –

    Abstract

    The purpose of this research is that researchers build basic applications in solving problems that occur in housewives and career women, namely GO-BABY Application that provides facilities to find a place in caring for children, and can provide security, education, health and comfort for a child. Applications are built from 2 parts, namely the first part in the society side such as housewives / career women and the second part is the side of the provider of child care services. The application that is built will integrated between applications that are applied in the society and service providers through an Android-based application and web based application. The results of this study will have a direct impact on both housewives/career women, in providing child care solutions that can be trusted while for child care services provider, provide convenience in the administration of child care services. Based on the function of the application, there are 2 parts that are given, namely to providers of child care services by providing an easy function of administrative data processing, including registration of child care services through online or offline, providing ease in processing data on children’s facilities, ease of payment report on income of child care services. Whereas for the community is the ease in the process of online registration and booking of child care services quickly and reliably. © BEIESP.

    Author keywords

    Android; Application; GO-BABY; Web

    This article can be accessed at https://www.scopus.com/pages/publications/85066755171

  • Traffic Congestion Tracking Application Using Object Detection and Geolocation Technology

    Traffic Congestion Tracking Application Using Object Detection and Geolocation Technology

    Authors: Eko Budi Setiawan, Megianto Adi Saputra, Budi Herdiana

    Abstract

    Traffic congestion occurs when traffic does not move smoothly and may even reach a standstill. This congestion is frequently caused by a lack of information regarding current traffic conditions, leading to excess vehicles beyond the road’s capacity in terms of length and width. Various efforts have been made by the traffic management sector, such as the Area Traffic Control System (ATCS). This research aims to create an Android application that offers real-time traffic updates for the streets of Bandung city in Indonesia, particularly for drivers. This research produces a mobile Android application that can track traffic jams from the results of the CCTV ATCS object detection process using Tensorflow, Realtime traffic jam reports from drivers and geolocation technology. The research methodology employed descriptive research and the waterfall model approach for software development. The study’s results showed that 94% of users found the application helpful in obtaining traffic information and route recommendations. Object detection technology on CCTV allowed for an 88% accuracy in determining the congestion level. The application facilitated Bandung City Transportation Department (DISHUB) in acquiring traffic information with an effectiveness of 91.33% and successfully provided weather prediction support for 94.67% of the surveyed routes. Further research is needed to maximize the object detection computing process using cloud computing technology. © 2024 Taylor’s University. All rights reserved.

    Keywords: Area traffic control system; CCTV; Global positioning system; Mobile Android; Traffic congestion tracking

    This article can be accessed at https://www.scopus.com/pages/publications/85203605984

  • Comparative Study of K-Means and Mean Shift Clustering Algorithms for Waste Data in West Java Province

    Authors: Rony Setyawan, Geraldi Catur Pamuji

    Abstract

    This study presents a comprehensive comparative analysis of the k-Means and Mean Shift clustering algorithms, utilizing waste data collected from West Java Province’s final disposal site spanning 2016 to 2021, with the primary objective of evaluating their performance and applicability for waste management practices; the analysis encompasses several critical parameters, including the number of clusters generated, variable uniformity, evaluation metrics employed, divergence measures, and processing time efficiency, revealing that k-Means, which formed three clusters, excels in rapid processing and provides finer cluster division, while Mean Shift, yielding two clusters, offers nuanced insights into data patterns, leading to the recommendation that the choice between the two algorithms should be driven by specific project requirements and considerations such as urgency of waste management needs and the depth of understanding desired for effective decision-making, thereby offering a tailored approach to waste data organization that optimizes categorization and contributes to more efficient and sustainable waste disposal practices in the future. © School of Engineering, Taylor’s University.

    Keywords: k-means clustering; Mean shift clustering; Waste data

    This article can be accessed at https://www.scopus.com/pages/publications/85197577372