J-Icon : Jurnal Komputer dan Informatika

GOOGLE TEACHABLE MACHINE: PEMANFAATAN MACHINE LEARNING BERBASIS CNN UNTUK IDENTIFIKASI CEPAT BATUAN MINERAL KALSIT, KUARSA DAN MAGNETIT

Albert Zicko Johannes, Minsyahril Bukit, Agustinus D D Betan, Jonshon Tarigan — Thu, 31 Oct 2024 13:24:32 +0000

Google Teachable Machine is a web-based application that allows users to create a machine learning model without the need for coding. The application utilizes Convolutional Neural Networks (CNN) in its process. In this study, Teachable Machine was utilized to create a machine learning model capable of identifying specific mineral rocks, particularly magnetite, calcite, and quartz. The research procedure was conducted through several stages: Sample Collection, Sample Classification (Dataset), Model Training, and Evaluation Process. Sample data in the form of mineral rock images were obtained and downloaded from Google. The data was then divided into three mineral classes: magnetite, calcite, and quartz, which were used as inputs in the Teachable Machine. Model training in Teachable Machine used input epochs of 100, batch size of 64, and learning rate of 0.0001. The results of the Teachable Machine modeling were then evaluated, showing that the obtained model could recognize magnetite, calcite, and quartz minerals with an average accuracy, precision, recall, specificity, and F1-score of 91.11% (86.67%), 87.30%, 86.67%, 93.33%, and 86.50% respectively. This research indicates that the utilization of Teachable Machine assists in quick, accurate, and easy identification, thereby contributing to speeding up the process of mineral rock analysis, decision-making, and exploration strategy development. Additionally, these results demonstrate the potential for broader development of this application in various fields of study.

Detection Model of Microalgae Spirulina platensis and Chlorella vulgaris Based on Convolutional Neural Network YOLOv8

Zahra Cahya Ramadhani, Dimas Firmanda Al Riza — Thu, 31 Oct 2024 14:49:40 +0000

Microalgae are unicellular microscopic organisms that live in various water. Microalgae such as Spirulina platensis and Chlorella vulgaris are grown due to their potential as bioenergy source. During cultivation, typically, hemocytometers are used to manually count the cells and that is time-consuming and prone to human error. This research aims to develop microalgae detection model based on microscopic images and Convolutional Neural Network using YOLOv8 architecture. The methodology includes sample preparation (dilution and optical density measurement), best density determination, image acquisition, annotation, creation of datasets, YOLOv8 model training, and model performance evaluation. Best density determines good microscopic images. Image acquisition was done using binocular microscope and acquired 560 images which were then annotated. The YOLOv8n, YOLOv8s, and YOLOv8m models were trained using default hyperparameters on Google Collaboratory to determine the augmentation effect on model accuracy. Model performance evaluation was done on selected YOLOv8 models. The results showed the augmentation (crop, brightness, blur) get the highest mAP train and test on YOLOv8m model, which are 0.945 and 0.913. The YOLOv8m model was retrained with various hyperparameters and it was found that the best configuration was SGD optimizer, epoch 50, and learning rate 0.01 with mAP train and test are 0.934 and 0.925. However, 29 epochs yielding a better model with accuracy of 0.8535, minimising overfitting and resource wastage. This research can facilitate the more efficient and automatic counting for microalgae-related research and industry.

Pengembangan Dashboard Penjualan Tiket di Kaldera Toba Nomadic Escape

Riyanthi Angrainy Sianturi, Daniel Alex Candra Simamora — Thu, 31 Oct 2024 14:53:17 +0000

Lake Toba has been designated as one of Indonesia's Super Priority Tourism Destinations (DPSP). The Kaldera Toba Nomadic Escape is a tourist attraction within the Lake Toba DPSP area, managed by the Lake Toba Authority (BPODT). Visitors to the Toba Caldera tourist area often face challenges, particularly those from outside the region who cannot book tickets online. Additionally, ticket sales data at Caldera is still managed manually using traditional bookkeeping methods, which prevents immediate compilation and accurate reporting of sold tickets. There are two categories of ticket bookings available at the Toba Caldera: entry tickets for general tourist access and event tickets, which are only available when events are organized at the Kaldera Toba Nomadic Escape. To facilitate easier management of ticket bookings at the Kaldera Toba Nomadic Escape, a web-based system has been developed, enabling visitors to book tickets online. This system includes a dashboard that allows for real-time transaction recapitulation. The system development follows the Waterfall model, which consists of several stages: Communication, Planning, Modeling, Construction, and Deployment. In developing the ticket sales dashboard, a comparative analysis of several previous studies was also conducted to enhance the visual details and functionality of the ticket sales dashboard. As a result of this research, a web-based ticket booking system and sales dashboard were developed. The ticket booking system allows visitors to easily purchase tickets, while the sales dashboard enables the Kaldera Toba Nomadic Escape management to monitor important statistics, such as the number of visitors, ticket sales, and the availability of tickets in real-time.

APPLICATION TO ASSESS SERVICE QUALITY AT ZHAHIRA LAUNDRY APPLYING SERVQUAL DIMENSIONS

Ari Tri Pirganta, Diana Diana — Thu, 31 Oct 2024 14:55:53 +0000

Zhahira Laundry is a business that provides laundry services. However, the quality of Zhahira Laundry services provided is not always in accordance with consumer expectations, there are obstacles that affect the quality of laundry services. To overcome these problems, Zhahira Laundry requires the Zhahira Laundry Assessment Application (APZAL). An application created to display a web-based questionnaire that will be assessed by customers. In this study, the quality of service that is the main thing in solving problems can be measured by Service Quality (Servqual) which consists of service quality factors such as tangible, dependability, responsibility, assurance and empathy. There is a purpose of measurement based on the Servqual is to determine the value of the gap between expectations and perceptions that occur regarding the services provided through the five dimensions of Servqual tangible, response, dependable, assurance, and empathy. This application can be accessed online by scanning the barcode listed using only Android. This application can identify gaps (GAP) in the Servqual dimension indicators. The GAP value is the result of reducing the scale of very satisfying expectations 5.00 and the service quality score for each Servqual dimension is calculated through ranking in each question indicator based on the GAP value from the highest to the lowest. Based on the GAP value after being implemented and used by customers, what is the GAP and ranking produced, so it can be concluded that customers are satisfied.

ANALYSIS QUALITY SERVICE INTERNET NETWORK OF WIRELESS LAN

Robertus Aman, Putu Wida Gunawan, I Nyoman Bernadus — Thu, 31 Oct 2024 15:03:46 +0000

Educational institutions certainly have the same hope of establishing a good internet service system in order to realize mutual satisfaction in the academic environment. In reality, not all educational institutions have achieved this, of the many institutions Tunas Daud School is one of them. Results of observations that have been carried out previously are problems that often occur today, complaints about internet network disruptions are still often experienced at certain times when downloading or uploading data. The aim of the research is to analyze the Quality of Service (QoS) on the Tunas Daud School internet network. The results of this research will describe the customer satisfaction index (CSI) method, also known as the customer satisfaction index, which means the weight of school internet user satisfaction with a total average satisfaction index of 61.93% (quite satisfied), with a value for each throughput parameter of 76.52% (satisfied), delay 40.85% (dissatisfied), packet loss 52.31% (quite satisfied), jitter 69.14% (satisfied), and bandwidth 37% (dissatisfied).

MAPPING OF COBIT 5 DOMAIN GOVERNANCE IN THE IMPLEMENTATION OF LMS E-LEARNING ITB STIKOM BALI

Ni Made Rai Masita Dewi, Dian Pramana, I Gede Putra Mas Yusadara — Thu, 31 Oct 2024 15:10:00 +0000

The implementation of e-Learning at ITB STIKOM Bali represents a significant support for online learning. The Learning Management System (LMS) called e-Learning ITB STIKOM Bali, based on Moodle LMS, is used to conduct lectures online. e-Learning is integrated with SINAK (Academic Information System), SID (Lecturer Information System), and SION (Online Information System) for both students and lecturers, including course registration and enrollment of students and lecturers. This system is used for both fully online lectures (Asynchronous Learning) and blended learning lectures in all study programs. However, proper maintenance and management of this system are necessary. Therefore, evaluation and analysis in IT governance related to the used LMS are required. In order to measure the maturity level of the e-Learning LMS implementation, measurement based on mapping and measuring the level of capability or gaps is needed. This measurement is conducted using the Process Assessment Model (PAM) within the COBIT 5 framework. Measurement activities will be based on several domains within COBIT 5, with process mapping based on business goals and institutional objectives. Based on the process mapping using PAM, domains strongly related to institutional IT goals focusing on customers and internal aspects are identified: MEA01 (Monitor and Evaluate Performance and Conformance), DSS 03 (Manage Security Services), APO13 (Manage Security), EDM 03 (Ensure Risk Optimization), BAI 07 (Manage Change Acceptance and Transitioning).

APPLICATION OF DATA MINING FOR PREDICTION OF FISHERY CULTIVATION HARVEST RESULTS FROM HARVEST PARTNERS USING THE SUPPORT VECTOR REGRESSION ALGORITHM

Thu, 31 Oct 2024 15:13:38 +0000

PT. Adma Digital Solusi is a company that serves as a harvest partner for cultivators in the fields of agriculture, animal husbandry and fisheries which is used for planning and controlling supply chain results. Planning and controlling PT fishery supply chain results. Adma Digital Sousi in the digital era needs to utilize various technologies and information systems. This aims to ensure that planning and controlling fish resources fulfill aspects of effectiveness and efficiency in decision making. In this research, a machine learning method will be implemented using the Support Vector Regression (SVR) algorithm to predict the harvest results of PT's fishery cultivation partners. Adma Digital Solutions. The SVR algorithm is a theory used to solve a regression classification problem using a Support Vector Machine (SVM). The SVR forecasting process uses the SVR() model by filling in the parameters, namely the kernel using polynomials, C is filled with the value 100, gamma is filled with auto, degree is filled with the value three, epsilon is filled with the value 0.1, and finally coef0 is filled with the value one. Then, using the fit function to train the model using x train and y train data to produce a MAPE error rate value of 0.12865018182566176 and an R2 value of 0.9998831470091238 with very good and accurate prediction capabilities. By knowing the estimated harvest results of aquaculture, the benefits obtained by harvest partners are adjusting production and marketing strategies to maximize profits. And can help harvest partners in managing risks, because they can prepare themselves well for situations where harvest results do not match estimates.

GREENHOUSE MONITORING WITH BLYNK CLOUD APPLICATION IN SEMI-ARID CLIMATE

Thu, 31 Oct 2024 00:00:00 +0000

Monitoring temperature and humidity during growth plants are very important Because impact significant on speed growth, productivity, and quality plant. Optimal temperature influences photosynthesis, transpiration, and development flower / fruit. Humidity tall help absorption of water and nutrients, reducing risk damage consequence change temperature extreme. Monitoring temperature and humidity also help detect and resolve problem plant. Study This aim For designing system IoT- based for monitor temperature and humidity plants at home glass. Study This test performance system as IoT tools for observation. Device design involve preparation equipment and manufacture code Arduino source (C++) for Arduino, which is connected through jumper cables to the DHT11 sensor and NodeMCU ESP8266. Blynk configuration allows Android devices with application the For display data, include temperature and humidity House glass. By Simultaneous, monitoring daily take notes change temperature moment apply devices at home glass hydroponics in Kupang City, East Nusa Tenggara Province. Research result show that system consists from device IoT hardware ( NodeMCU ESP8266 and Sensor DHT11) and components device software (Arduino IDE and Blynk), everything works with effective. Testing tool with a hygrometer and micrometre produce difference average temperature / humidity in the house glass of 1.33%, and humidity amounting to 2.17%. The error average temperature is 1.40%, with humidity of 2.35%.

EFFECTIVENESS OF COMMUNITY-BASED E-COMMERCE PLATFORM IN IMPROVING DIGITAL MARKETING FOR UMKM IN WEST SULAWESI

Musyrifah Musyrifah, Asmawati Saal — Thu, 31 Oct 2024 15:24:24 +0000

This study aims to measure the effectiveness of a community-based e-commerce platform in enhancing digital marketing for UMKM in West Sulawesi. UMKM often face significant challenges in reaching wider markets, mainly due to limitations in infrastructure, technology access, and digital marketing knowledge. DiKe, a community-based e-commerce application, was developed to address these issues by providing an integrated, accessible, and community-based marketing solution. The research methodology includes analyzing UMKM needs through surveys and interviews, developing the application using an iterative approach, and testing and evaluating the platform's effectiveness. The initial stage of the research involved an in-depth analysis of the needs and challenges faced by UMKM in West Sulawesi. The analysis results indicated that the majority of UMKM have limitations in market access and digital technology usage. Based on these findings, the DiKe application was developed, offering features such as online store creation, social media integration, and analytics tools for sales performance monitoring. The application trial was conducted for six months involving 50 UMKM as respondents. Effectiveness evaluation was done by measuring changes in sales, market reach, and user satisfaction. The study results show that the use of the DiKe platform significantly increased the market reach and sales of UMKM products. About 85% of users reported increased sales with an average increase of 30%. Additionally, 90% of users stated that this application made it easier for them to conduct digital marketing, especially in terms of product promotion and customer interaction. Furthermore, interactions and collaborations among community members also increased. The community features in the application allow users to share experiences, marketing tips, and engage in business collaborations, thereby creating a more solid ecosystem that supports local business growth. The study also found that UMKM actively participating in the community tend to experience higher business performance improvements compared to those that are not active. Thus, this community-based e-commerce platform has proven effective in supporting digital marketing for UMKM in West Sulawesi. This success indicates the potential for adoption in other regions with similar characteristics, thereby providing broader benefits for UMKM development nationally. This research significantly contributes to the literature on community-based e-commerce and offers a model that can be implemented in various regional contexts.

RICE QUALITY CLASSIFICATION USING ANDROID-BASED CONVOLUTIONAL NEURAL NETWORK

Muhammad Yusuf, Reinhard Ruimassa, Anisa Iriani Tawainella, Devi Maharani — Thu, 31 Oct 2024 00:00:00 +0000

The importance of rice as a food commodity in Asia, especially in Indonesia, lies not only in its role as a major source of carbohydrates, but also in its quality that affects the selling value, nutritional aspects, and consumer satisfaction. In this context, research on rice quality becomes essential, with an emphasis on shape and color as the main factors affecting rice quality. Rice that is whiter, cleaner, and intact tends to have better quality, making the assessment of the level of whiteness and cleanliness of rice crucial in the food industry. To evaluate rice quality, this study utilizes Deep Learning technology with a focus on developing an Android application. The model used is the Convolutional Neural Network (CNN) with VGG-16 architecture. The application of the Extreme Programming development method in creating this application shows an adaptive and responsive approach to changing user needs. In essence, this application aims to provide a smart and efficient solution in classifying rice quality based on its physical characteristics. Through rice image analysis, the application can assess the level of whiteness and cleanliness, while the area analysis of the rice object is used to evaluate the level of integrity. Thus, this application is expected to be a tool that can help food industry players, farmers, and consumers in assessing and selecting rice that meets the desired quality standards. This research opens up opportunities to improve understanding related to rice quality evaluation by utilizing advances in Deep Learning technology.

Selection of Superior Rice Seeds by Applying Fuzzy Method and K-Means Clustering

Bedi Suprapty, Rheo Malani, Achmad Fanany Onnilta Gaffar — Sun, 03 Nov 2024 10:50:23 +0000

This study aims to develop a superior rice seed selection method using a Fuzzy and K-Means Clustering approach, with a case study in Kutai Kartanegara Regency, East Kalimantan Province, one of Indonesia's major rice-producing regions. The Fuzzy method is used to handle uncertainties in assessing seed characteristics, allowing each seed attribute (such as plant height, amylose content, grain weight, and yield) to have a membership value within specific categories. This fuzzification process provides flexibility in evaluating seed quality in stages, which is then converted through defuzzification to obtain a final score determining seed quality. K-Means Clustering plays a role in grouping seeds based on characteristics that have been assigned membership values. This algorithm divides seed data into several clusters, such as low, medium, and high quality, by calculating the distance between seed characteristics and each cluster's centroid. This iterative process yields seed groups with similar characteristics, simplifying recommendations for superior varieties. The evaluation was conducted using clustering accuracy metrics and silhouette score validation to ensure cluster cohesion and separation. The study results demonstrate that this method effectively identifies high-quality rice seeds with high accuracy. Recommended varieties include standard rice seeds like Mengkongga and Ciherang, as well as superior varieties like Inpari 32, Inpari 48, Padjajaran Agritan, Inpari IR Nutri Zinc, and Pamera, which are well-suited to Kutai Kartanegara’s specific conditions. Implementing this method is expected to assist farmers in selecting high-quality seeds, thereby supporting increased crop productivity in the study area.

ANALYSIS OF SERVICE QUALITY TOWARDS VISITOR SATISFACTION AT STIKOM UYELINDO LIBRARY

Semlinda Juszandri Bulan — Thu, 07 Nov 2024 00:57:33 +0000

The library has an important role in improving the learning process to prepare quality academic individuals. The level of library visitor satisfaction can be used as an indicator to assess the quality of intangible services. The purpose of this study was to analyze five aspects of service quality in the STIKOM Uyelindo library towards visitor satisfaction. These aspects include tangible evidence, reliability, responsiveness, assurance, and empathy. Respondents in this study were 253 students and lecturers of STIKOM Uyelindo. The method used for data analysis was Partial Least Square (PLS) and was run with SmartPLS software version 3.0. The results showed that reliability, responsiveness, assurance and empathy positively influenced library visitor satisfaction. For libraries to be able to complete book collections with the latest books that are in accordance with the needs of the latest curriculum and expand library space and add facilities such as chairs and computers because the number of students is increasing.