Jurnal Media Computer Science

Implementation Of Ratcliff/Obershelp And Cosine Similarity Methods On Image For Detection

2025-06-12T08:24:24+00:00

Image is a tool for communicating in conveying certain messages from the image maker, so that images can be used as language in the technical field. Important pictures are stored by the user on a storage medium. The problem that occurs is that an image can be copied for personal gain, for example forging scanned images on important documents that can be misused. This study uses the Ratcliff/Obershelp and Cosine Similarity methods to detect similarities and differences in image images. So that with the implementation of the Ratcliff/Obershelp and Cosine Similarity methods for detecting similarities and differences in images, the image similarities can be known.

Effectiveness And Efficiency Of LLM Models Vs Traditional Machine Learning In Sentiment Analysis Of Indonesian Language Product Reviews

2025-07-05T08:07:30+00:00

This research aims to conduct a comparative analysis of the performance and efficiency of several machine learning models in the task of sentiment analysis on Indonesian language customer reviews. In the digital business era, a quick and accurate understanding of customer opinions is a strategic asset for making decisions, from product development to marketing strategy. Four models were evaluated: two Transformer-based models (agufsamudra/indo-sentiment-analysis and ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa), Naive Bayes, and K-Nearest Neighbors (KNN) on a dataset of 5,400 product reviews. The evaluation metrics used are Accuracy, Precision, Recall, and F1-Score. The results show that the Naive Bayes model and the Transformer model 'agufsamudra/indo-sentiment-analysis' achieve the highest performance with an F1-Score and accuracy of around 95%, significantly outperforming other Transformer models (90%) and KNN (47%). The crucial finding of this research is that the performance of the classical Naive Bayes model is equivalent to the state-of-the-art Transformer model. From an accounting and business perspective, this implies that solutions with much higher computational efficiency (Naive Bayes) can provide a more optimal Return on Investment (ROI) for large-scale implementation of customer sentiment monitoring systems.

Fuzzy Tsukamoto Method in Service Satisfaction Assessment at the Village Office Tanjung Aur 1

2025-07-07T02:08:24+00:00

IKM analysis must always be carried out periodically so that it can be seen that public satisfaction with the services provided, especially at the Tanjung Aur 1 Village Office. But in reality, so far the Tanjung Aur 1 Village Office has not had a benchmark that is used as a forum for knowing public satisfaction with these services.The application of the Fuzzy Tsukamoto Method in assessing service satisfaction at the Tanjung Aur 1 Village Office can assist in managing the results of the Community Satisfaction assessment of Services at the Tanjung Aur 1 Village Office, and can provide information on the results of measuring the level of community satisfaction with services at the Tanjung Aur 1 Village Office as an evaluation material to improve service quality. The application of the Fuzzy Tsukamoto Method in assessing service satisfaction at the Tanjung Aur 1 Village Office is built web-based using the PHP programming language and MySQL database which can be accessed online via the link https://kepuasandesatanjungaur1.site/, where there are 2 interface access rights in the application, namely Administrators and Villagers of Tanjung Aur 1. Based on the 2024 service satisfaction assessment data with 9 respondents who have been inputted into the web-based application, the results of the service satisfaction assessment that have been analysed through the Fuzzy Tsukamoto Method are Very Satisfied 44.44%, Satisfied 22.22%, Quite Satisfied 33.33%, Dissatisfied 0% and Very Dissatisfied 0%. Based on the results of the demo programme that has been carried out, 9 respondents have successfully provided service satisfaction assessments on the application online and also the operator can see the output of the satisfaction assessment results which will be given to the Village Head for evaluation.

Designing a Virtual Lan Network Using Manageable Switches at Smkn 3 Bengkulu City

2025-07-07T06:20:00+00:00

This study aims to design a VLAN network using a manageable switch at SMKN 3 Kota Bengkulu. The research method used in this study is the PPDIOO method. The hardware used in the configuration of the Virtual LAN network design is a Mikrotik Haplite Rb941 4 port and a D-link manageable switch, while the software used for the configuration is the Windows 10 operating system and a web browser. Data collection was carried out by observation, laboratory studies, and literature studies. The results showed that the quality of the VLAN network was better than the actual network as measured by the parameters of throughput, packet loss, delay, and jitter. The throughput value on the actual network was 198 Kb (poor) and increased on the VLAN network by 1367 kb (good). The actual network delay value was 3.56 ms (moderate) and decreased on the VLAN network by 2.53 ms (good). The jitter value also decreased from 8.30 ms (moderate) to 7.45 ms (good). Meanwhile, the packet loss value on the actual network and VLAN are both 0% (very good). In addition, the performance of file transfer speed between PCs using VLAN networks is better than the actual network, which is 10.9 MB/s for the actual network and 11 MB/s for the VLAN network. The use of VLAN networks can also improve network security because it can separate teacher and administration PCs as evidenced by the two PCs not being connected when the ping test was carried out.

Implementation of Multi-Objective Optimisation Method On The Basis Of Ratio Analysis for Finalist Selection of Putra Putri Kampus Bengkulu Province

2025-07-07T08:03:35+00:00

The Executive Board of the Campus Putra Putri Association (IPPK) of Bengkulu Province has utilised computers in the data processing process both registration data and assessment data. The implementation of the Multi-Objective Optimization Method On The Basis Of Ratio Analysis in the selection of finalists for the Putra Putri Kampus of Bengkulu Province was built using the PHP programming language with a MySQL database which can be accessed online via the link https://ppkbengkulu.online/. The implementation of the Multi-Objective Optimisation On The Basis Of Ratio Analysis method can simplify the data management process and provide information in the form of recommendations for the selection of finalists for the campus princess in Bengkulu Province. Based on tests that have been carried out using sample data from the registration of the 2024 campus princess son participants as many as 40 participants divided into 20 boys and 20 girls, the results of recommendations through the Moora Method are the best 15 boys and the best 15 girls as the Finalists of the Putra Putri Kampus Bengkulu Province. Based on the results of Black Box testing, it shows that the application functions properly and is able to recommend the best finalists for the Putra Putri Kampus Bengkulu Province Selection using the Multi-Objective Optimization On The Basis Of Ratio Analysis Method.

Analysis Of Electrostatic Precipitator (Esp) Performance Based On Changes In Reference Voltage And Temperature In The Coal Boiler At Pt. Chandra Asri So Puloampel

2025-07-07T08:05:09+00:00

This study aims to gain an in-depth understanding of various factors that influence the performance of electrostatic precipitator (ESP) systems in industrial environments. An experimental method with a quantitative approach was used to analyze the effects of reference voltage and temperature on ESP performance. The research process involved data collection through observation, efficiency calculations using the Deutch-Anderson equation, and direct system testing. A monitoring system based on Arduino Uno WiFi R3 and ESP8266 was designed to track voltage, current, and sparking activity in real-time via the Blynk application. Flowcharts were used to illustrate the stages of analysis and the development of the monitoring tool as part of the overall research process. The findings indicate that the performance of the electrostatic precipitator (ESP) is significantly influenced by the settings of reference voltage and current, temperature, and compartment environmental conditions. Efficiency reached only 75% when the feedback voltage was 42kV with a current of 100mA, highlighting the need for simultaneous adjustment of voltage and current to achieve the optimal 99.5% efficiency. The highest resistance value of 9.13 GΩ at a temperature of 69.4°C demonstrates the importance of maintaining cleanliness and humidity to reduce the risk of sparking. The monitoring system based on Arduino Uno WiFi R3 and ESP8266 successfully displayed real-time data via Blynk, despite an error margin of ±6%. Additionally, the safety indicator system functioned effectively in detecting disturbances and supporting the safe operation of the ESP.

Expert System For Diagnosing Eardrum (Tympanic Membrane) Diseases Using Certainty Factor Method

2025-07-07T08:06:11+00:00

Dr. M. Yunus Regional General Hospital Bengkulu is one of the hospitals in Bengkulu City that provides health service facilities. The current problem at the M. Yunus Regional General Hospital is the limited time available at the ENT Polyclinic and the delay in examining eardrum disease. So patients must go directly to the ENT Specialist Doctor who treats eardrum disease. The limited time of the Specialist Doctor who treats eardrum disease at the Hospital is also one of the causes of the delay in handling patients with eardrum disease. The expert system for diagnosing eardrum disease (tympanic membrane) using the certainty factor method at the M Yunus Regional General Hospital, Bengkulu City can be used as a container to help determine the diagnosis of eardrum disease based on the symptoms felt, and can make it easier for users to consult online via the link https://spakarmembrantimpanicf.site/. The expert system for diagnosing eardrum disease (tympanic membrane) using the certainty factor method at the M Yunus Regional General Hospital, Bengkulu City was created using the PHP programming language and MySQL database, which can be accessed online. Based on the black box method testing that has been carried out, it can be concluded that the functionality of the application has run well and this expert system can provide consultation results for the diagnosis of eardrum disease (tympanic membrane) through the Certainty Factor method stages based on the symptoms selected by the user during the consultation. Based on the alpha testing method testing that has been carried out, it can be concluded that this expert system is quite helpful for users in consultations and provides early detection information for the diagnosis of eardrum disease from the symptoms felt.

Application Of K-Means Method In Grouping Horticultural Commodity Production Results In The Department Of Food Crops Horticulture And Plantations Of Bengkulu Province

2025-07-07T08:07:11+00:00

The Department of Agriculture, Food Crops, Horticulture and Plantations of Bengkulu Province is a government agency whose task is to collect data on horticultural commodities in the Bengkulu Province. In the Department of Agriculture, Food Crops, Horticulture and Plantations of Bengkulu Province, there is no specific system used to group data on horticultural commodity production results, so it is difficult to obtain information on horticultural commodities that fall into high, medium, and low production levels in Bengkulu Province. The application of the k-means method in grouping horticultural commodity production results at the Department of Food Crops, Horticulture and Plantations of Bengkulu Province can help the department obtain information on the results of grouping horticultural commodity data in Bengkulu Province, and can help determine planning programs and provide counseling to farmers in horticultural commodities, especially those in the low production group to increase their production results. Based on the data used in 2023 with 3 categories of horticultural commodities, the results of the grouping in the vegetable category cluster C1 were 3 commodities, cluster C2 was 9 commodities, cluster C3 was 13 commodities, in the fruit category cluster C1 was 4 commodities, cluster C2 was 7 commodities, cluster C3 was 20 commodities, in the medicinal plants and spices category cluster C1 was 2 commodities, cluster C2 was 1 commodity, cluster C3 was 13 commodities. In the vegetable horticultural commodity category that includes high production results are Large Chili (Group), Cabbage, Eggplant, the fruit horticultural commodity category that includes high production results is Durian, Orange (Group), Siamese Orange/Tangerine, Banana, and the vegetable horticultural commodity category that includes low production results is Ginger, Rhizome (Group).

Sentiment Analysis on the Application of Tabungan Perumahan Rakyat (TAPERA) Policy in Indonesia

2025-07-07T08:08:08+00:00

Tapera is a program provided by the Indonesian government to provide poor people with decent housing, by charging all working classes with salaries above the Regional Minimum Wage of 3% for Tapera contributions. Even though it seems that this program aims to help poor people, this has given rise to a new polemic, which can be seen from some people who don't like this, as can be seen from several negative comments on social media, one of which is X or Twitter. This paper aims to determine whether public sentiment toward the TAPERA policy is positive or negative among Indonesians affected by it, regardless of whether the sentiment analysis results are predominantly positive or negative. This research is conducted by collecting data from Twitter and then processing it in such a way that, later will be checked for sentiment analysis with the Naive Bayes method. Out of 742 analyzed tweets (filtered from an initial 1,680), 651 expressed negative sentiment, while 91 were positive, indicating significant public dissatisfaction with the TAPERA policy.

Implementation Of Weighted Product Method In Cadre Selection At Sawah Lebar Community Health Center Bengkulu

2025-07-07T08:09:03+00:00

Sawah Lebar Health Center Bengkulu faces challenges in selecting health cadres who have the right qualifications and abilities to support health programs in the community. Selecting the right cadres is an important factor in improving the quality of health services at the basic level. One method that can be used to assist in this selection process is the Weighted Product (WP) method. This method is used to perform objective calculations and assessments based on predetermined criteria, such as education level, work experience, communication skills, and commitment to health programs.The purpose of this study was to implement the Weighted Product method in selecting cadres at Sawah Lebar Health Center Bengkulu and to evaluate the most relevant criteria in selecting the right cadres. In addition, this study aims to test the effectiveness of the system built using the WP method in providing optimal cadre recommendations.The method used in this study is to collect data on cadre candidates, then assess each candidate based on the weight and criteria that have been determined. The results of the system test show that the use of the WP method can produce objective cadre selection, reduce subjectivity in decision making, and increase transparency in the selection process. In the system testing, this system successfully provided results that were in accordance with the expectations and priorities of the Health Center in selecting cadres.In conclusion, the application of the Weighted Product method can improve the accuracy and objectivity in selecting cadres at the Sawah Lebar Bengkulu Health Center. The system that was built has also proven effective in providing recommendations for cadres that are in accordance with the established criteria, so that it can support the success of health programs in the region.

Utilization of Generative Pre-trained Transformer Model for Automatic Evaluation and Feedback on Scientific Manuscripts

2025-07-07T22:44:45+00:00

This study aims to explore the use of the Generative Pre-trained Transformer (GPT) model in the automatic evaluation of scientific papers, with a focus on the conformity of the feedback provided with the applicable academic writing guidelines. In this study, GPT was used to analyze manuscripts published in accredited scientific journals and to provide feedback on errors in grammar, spelling, citation format, use of academic terms, content organization, and quality of argument. The results showed that the GPT was highly effective in detecting and correcting technical errors in the manuscripts, with high correction rates for spelling and grammar errors (95% and 93%, respectively). In addition, the GPT also provided relevant suggestions for correcting formatting errors, such as citation and bibliography formats, with an improvement rate of 90%. The model also successfully provided suggestions to improve content organization and argument strengthening in scientific papers. Although GPT is effective in correcting technical errors and providing structural feedback, human editing is still required to improve substantial and in-depth aspects of scientific papers. This study concludes that GPT can be used as an effective tool in the process of automatic evaluation of scientific papers, but the role of human editors is still needed for optimal results. This study also suggests further development in fine-tuning GPT to improve substantial analysis and strengthening of argument quality in scientific writing.

Implementation Of Apriori Algorithm To Analyze Sales Data Of Goods At Izza Aquarium Shop

2025-07-07T22:46:12+00:00

Toko Izza Aquarium is a business that sells animal feed and aquarium equipment. This research analyzes the sales data of Toko Izza Aquarium by applying the Apriori algorithm with the aim of providing data-based strategic recommendations to increase sales and customer satisfaction. This research is also expected to contribute in the field of sales data analysis in small and medium enterprises. The application of data mining to analyze the sales data of the Izza Aquarium Store is to provide information. The results of the analysis of Monthly sales data for the Izza Aquarium Store. Can be used as a parameter for inventory management at the Izza Aquarium Store and also provides information about the best-selling items at the Izza Aquarium Store. In analyzing sales data, the Apriori method is applied, so that the final result stage of the analysis passes the Apriori Method stage by meeting the Minimum Support and Minimum Confidence that has been determined. Based on the results of tests carried out on a data sample of 20 transactions in August 2024, the sales products that are most in demand by the public meet Minimum Support of 15% and Confidence 90% It turns out that Misster Puss Salmon and Chat Choice Green.

Implementation of Convolutional Neural Network for Soil Type Category Detection in a Web-Based Plant Recommendation System

2025-07-07T23:05:18+00:00

The growth of the agricultural sector in Indonesia is highly dependent on soil fertility, as soil is an important factor in the agricultural sector. However, conventional identification of soil types often takes a long time and requires high costs. To overcome this problem, this research develops a soil classification system using an optimized Convolutional Neural Network (CNN) model to improve soil classification accuracy. The results of this classification become the basis for a Content-Based Filtering (CBF) based recommendation system, in order to provide suggestions for crop types that are suitable for soil types. This research was conducted through several main stages, namely soil image data collection, data preprocessing, CNN model training and CBF-based recommendation system implementation. The CNN model is used to recognize soil texture and color patterns, while CBF is used to match soil characteristics with suitable plant species. System evaluation is conducted using confusion matrix to assess the accuracy of the classification model as well as the effectiveness of the recommendation system. The soil type classification process using CNN with MobileNetV2 architecture achieved an accuracy rate of 96%. This result shows that the architecture is effective in recognizing soil types precisely and can be used to provide appropriate crop recommendations. Thus, this system has the potential to support increased agricultural productivity, both on a small and large scale.

Pengelolaan Brand Awereness Aplikasi Ezurance PT Jasaraharja Putera Semarang Melalui Strategi Public Relation

2025-07-07T23:06:56+00:00

This Public relations strategy plays a strategic role in building corporate image and increasing brand awareness, especially in the context of digital services such as the Ezurance application owned by PT Jasaraharja Putera Semarang Branch. This study aims to analyze the implementation of communication strategies carried out by the company in promoting Ezurance to the public. The approach used is PDCA (Plan, Do, Check, Action), which is applied in stages starting from the planning, implementation, evaluation, to corrective action. The strategies implemented include digital promotion through social media, participation in local events, dissemination of information through booths, and use of print media. In addition, the utilization of brand ambassadors that match the company's image is an innovative step to expand audience reach and increase campaign appeal. The results of the study indicate that the PR strategies implemented by the company have gradually succeeded in increasing brand awareness, although challenges remain due to the low level of digital literacy among the public in understanding insurance. Therefore, continuous public education and periodic evaluation are needed to ensure that the PR strategy implemented remains relevant to the development of digital trends and the changing needs of the audience

Deep Learning-based Sentiment Analysis of Public Comments on Military Education Using RoBERTa Algorithm and Rule-Based Hybird Parameters

2025-07-10T01:14:01+00:00

Social media such as Instagram has become an important digital public space for people to voice opinions on various policy issues, including the military education policy, which has recently become highly debated, especially in West Java and even outside Java. The purpose of this research is to develop a sentiment analysis model for public comments on Instagram regarding military education policy using a deep learning approach. m The RoBERTa model was trained and tested using classification performance metrics such as accuracy, precision, recall, and f1-score. The test results show that the model achieved an accuracy of 97%, with the highest f1-score value in the positive category at 0.98. The results show that RoBERTa can effectively classify sentiment based on public opinion on social media. This method can not only provide an overview of public responses, but can also be used as a tool in the decision-making process or public policy evaluation based on real-time digital opinion analysis.

Decision Support System for Prioritising the Use of Village Funds in Improving Local Infrastructure Using the Analytic Hierarchy Process (AHP) Method

2025-07-10T01:15:03+00:00

This study discusses the development of a Decision Support System (DSS) to assist the Karya Bakti Village government in determining priorities for the use of Village Funds for local infrastructure development. The background of this research stems from a common problem in villages, namely suboptimal fund allocation due to subjective and conventional decision-making processes. The objective of this research is to design a DSS based on the Analytic Hierarchy Process (AHP) method so that decision-making becomes more objective, measurable, and in line with the urgent needs of the community. The benefits of this research are expected to assist the village in determining infrastructure development priorities and serve as a scientific reference for academics or researchers in similar fields. The results of this research are a web-based system that has been successfully developed and tested using the black box method, with all features functioning as intended. This system facilitates the comparison process between criteria and infrastructure project alternatives using AHP, and produces clearer and more measurable development priorities. In conclusion, the application of this DSS has proven effective in improving transparency and efficiency in decision-making at the village level, and has the potential to be applied to other villages with adjustments to local characteristics.

Analisis Faktor-Faktor Keterlambatan Pada Pelaksanaan Pekerjaan Proyek Modernisasi Gedung Serba Guna Pt Pusri Palembang

2025-07-11T01:50:08+00:00

Construction project delays often result in financial losses and schedule disruptions. This study analyzes the factors causing delays in the modernization project of the Multi-Purpose Building of PT Pupuk Sriwidjaja (Pusri) Palembang using Structural Equation Modeling (SEM). The findings reveal that ineffective communication is the dominant factor, contributing 39.9% to project delays. Inefficient execution accounts for 37.5%, while insufficient workforce skills significantly contribute 33.2%. Additionally, the interaction among these three variables exacerbates the impact of delays. This study highlights the importance of improving coordination among project stakeholders, enhancing project execution efficiency, and developing workforce capacity. These measures are crucial to preventing similar delays in future projects.

Application Of Data Mining In Grouping Data On The Need For Social Welfare Services (Ppks) At The Dharma Guna Center In Bengkulu

2025-07-11T02:02:40+00:00

Sentra Dharma Guna Bengkulu is an institution under the auspices of the Ministry of Social Affairs of the Republic of Indonesia that provides social rehabilitation services for people with disabilities, including therapy (physical therapy and occupational therapy) and training. At Sentra Dharma Guna Bengkulu, data collection is carried out on PPKS (Social Welfare Service Recipients) every month to determine the development of the PPKS based on 5 (five) assessment aspects, namely physical aspects, spiritual aspects, psychological aspects, social aspects, and vocational aspects. Every month the development of PPKS Mentally Disabled (PDM) is assessed against 5 assessment aspects to determine whether PPKS is in the severe, moderate or mild group. The application of data mining in grouping data on Social Welfare Service Recipients (PPKS) at the Dharma Guna Bengkulu Center can help collect data and assess the development of PPKS, especially People with Mental Disabilities (PDM), can help analyze and group PPKS data, especially People with Mental Disabilities (PDM), and can provide information on the results of grouping PPKS data, especially People with Mental Disabilities (PDM) every month. From the test data used, namely PPKS data for People with Mental Disabilities (PDM) in October 2024 as many as 49 PPKS, the results of data grouping were obtained using the K-Means Clustering Method which has been divided into 3 groups. The number of Cluster C1 data (Severe Group) consists of 9 PPKS data, Cluster C2 (Moderate Group) consists of 26 PPKS data, and Cluster C3 (Light Group) consists of 14 PPKS data.

Decision Support System, SAW Method, Best Journalist Selection, Harian Rakyat Bengkulu, Multi-Criteria Decision Making

2025-07-11T02:06:15+00:00

The development of information technology has a significant impact on the world of journalism, including in efforts to improve the professionalism of journalists. PT. Rakyat Semarak Bengkulu Permai (Rakyat Bengkulu) as a press company continues to innovate, one of which is through periodic assessment of the best journalists. However, the assessment process that has been running so far still faces the obstacle of subjectivity and has not been supported by an objective and measurable system. This study aims to develop a web-based Decision Support System (DSS) using the Simple Additive Weighting (SAW) method to help the journalist assessment process more efficiently and objectively. This system is built using the PHP programming language and MySQL database, and is specifically designed so that it can only be accessed by the Editor-in-Chief. The test results show that the system is able to improve efficiency, objectivity, and accuracy in the process of assessing the best journalists in the company environment

Personal Data Protection Law And Information Security Risk Management In Higher Education Institutions

2025-07-11T02:20:18+00:00

Technological advancements have increased the risk of personal data breaches, including within academic environments. This research analyzes the implementation of Law No. 27 of 2022 on Personal Data Protection in information security risk management within higher education institutions. The method used is Design Science Research Methodology, comprising four stages: observation, interviews, BPMN annalysis, and stakeholder evaluation. The results indicate a persistent gap between regulation and practical implementation, as well as significant risks of data breaches. A new BPMN model is proposed to enhance compliance and data security. Evaluation demonstrates that this model can support higher education institutions in complying with the PDP Law.

Comparative Study of MySQL and MongoDB Performance on Node.js REST API Using Chinook Database

2025-07-11T03:13:54+00:00

Kebutuhan akan sistem manajemen basis data (Database Management System) yang efisien dan optimal semakin penting, terutama dalam pengembangan aplikasi berbasis REST API. Penelitian ini bertujuan untuk mengevaluasi dan membandingkan performa dua jenis DBMS yang umum digunakan, yaitu MySQL (relasional) dan MongoDB (non-relasional), ketika diimplementasikan dalam REST API berbasis Node.js. Pengujian dilakukan di lingkungan server nyata untuk mencerminkan kondisi operasional sesungguhnya, menggunakan alat Apache JMeter dengan empat parameter utama, yaitu processed requests, response time, throughput, dan error rate. Data yang digunakan bersumber dari Chinook Database yang telah diperbanyak hingga mencapai 10.000 entri, dan diuji dengan beban pengguna virtual sebanyak 50 dan 100 pengguna selama 120 detik, dengan skenario yang telah diatur. Hasil penelitian menunjukkan bahwa MySQL unggul pada hampir seluruh parameter, dengan processed requests tertinggi (64.098 permintaan), response time terendah (135 ms), dan throughput terbesar (532 permintaan/detik), serta tanpa error. Sebaliknya, MongoDB mencerminkan karakteristik arsitektur non-relasional yang lebih dinamis, namun menunjukkan performa yang lebih rendah pada skenario pengujian ini. Kesimpulan dari penelitian ini menyatakan bahwa pemilihan DBMS harus disesuaikan dengan kebutuhan aplikasi, di mana MySQL lebih cocok untuk pengolahan data yang terstruktur dan konsisten, sedangkan MongoDB lebih sesuai untuk data semi-terstruktur atau tidak terstruktur yang berkembang secara dinamis.

Executive Information System For Decision Making In Radio Management In Indonesia

2025-07-11T03:15:07+00:00

The advancement of information technology has encouraged media organizations, including radio stations, to adopt data-driven approaches in decision-making. However, radio stations often lack well-managed and systematic data, resulting in underutilization of information to support decisions through visual insights. This study aims to design an Executive Information System (EIS) dashboard capable of presenting strategic information to radio management for understanding programming and listener behavior. The dashboard design employs the Prototyping method, adopting the Spiral model principles. This approach enables iterative and responsive development aligned with stakeholder needs. The design process involves identifying information requirements, creating visual prototypes, and validating the design through display and data readability evaluations. The resulting dashboard provides visual representations of listener demographics, popular broadcast programs, and time slots with the highest engagement levels. The dashboard is recognized for assisting radio management in formulating data-driven content and promotional strategies. Furthermore, this study highlights the effectiveness of the Prototyping method in producing adaptive, communicative, and business-relevant dashboard designs.

Web Based Cloud Hosting Service Using Xcode Hoster

2025-07-11T03:16:04+00:00

Demand for efficient, reliable, and easily accessible cloud hosting services continues to increase. Xcodehoster is a web-based cloud hosting platform designed to meet these needs. This research aims to evaluate the adoption process of Xcodehoster as a cloud hostingservices at an organizational scale. This was done by identifying key user needs, analyzing Xcodehoster’s features and advantages, and comparing it with other cloud hosting platforms. The methods used in this research include a literature review and direct testing of Xcodeshoster. The result of this research indicate that Xcodehoster has significant potential in improving operational efficiency and reducing IT infrastructer costs. Furthermore, its ease of use and reliable technical support make Xcodehoster an attractive option for organizations.

Create An E-Raport Application Using The Laravel Framework And Mysql

2025-07-11T03:17:10+00:00

Learning outcome reports are written evidence of student learning progress over time. The data recorded in the student learning outcome report can be used to track student progress, identify student strengths and weaknesses in several subjects. This research aims to develop a web-based E-Raport application using the Laravel Framework and MySQL. This research was conducted at SD Negeri 33 Seluma. Located in Lubuk Betung Village, Semidang Alas Maras District, Seluma Regency, Bengkulu Province from October to November 2024. The result of this research is the creation of an E-Raport application that has features of managing student data, inputting grades, calculating grades, and making report cards.

Application Of Vision Transformer For Identifying Indonesian Herbal Plants Based On Visual Images

2025-07-11T04:07:11+00:00

Indonesia has vast biodiversity, including herbal plants that have been used for generations as traditional medicinal ingredients. However, the many types of herbal plants that have similar shapes, colors, and textures often make it difficult for people to identify them accurately. To overcome this challenge, this research develops a visual image-based herbal plant identification system using the Vision Transformer (ViT) model, an artificial intelligence approach that is able to understand visual patterns more effectively than conventional methods. This research went through several stages, including the collection of herbal plant image datasets from public platforms, data preprocessing and image dimension adjustment, and training of the ViT model. The model was evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure optimal performance. The results show that the ViT model is able to identify herbal plants with an accuracy of 92% and consistent performance of other evaluation metrics. This system is also implemented into the web, thus helping users in recognizing herbal plants quickly and accurately

Implementation of Lean Methodology in IoT-Based Smart Water Dispenser for Real-Time Monitoring and Notification

2025-07-11T04:09:38+00:00

This research develops an Internet of Things (IoT)-based Smart Water Dispenser using the Lean Methodology approach to create a real-time monitoring and notification system that is responsive to user needs. The system consists of a load cell, temperature sensor, and ultrasonic sensor integrated into a Firebase-based mobile application. Tests on 35 respondents showed an average volume sensor error of 1.89% (standard deviation 0.62%), an average notification delay of 0.92 seconds (standard deviation 0.15 seconds), and a user satisfaction score of 4.5/5. The main innovation of this research is the integration of multi-sensors with a Lean-based mobile notification system, which has proven to increase the efficiency of drinking water monitoring in public facilities. The results of this research are recommended for large-scale development and implementation in public environments. The consistent performance demonstrates that the system is highly feasible for implementation in large-scale public facilities.

Sistem Pencatatan dan Monitoring Pelanggaran Karyawan PT Pasar Kuota Berbasis Web

2025-07-11T04:11:30+00:00

Kedisiplinan karyawan merupakan faktor penting dalam menjaga produktivitas dan profesionalisme di lingkungan perusahaan. PT Pasar Kuota sebagai perusahaan digital yang berkembang pesat membutuhkan sistem yang terstruktur untuk mencatat dan memantau pelanggaran yang dilakukan oleh karyawan. Penelitian ini bertujuan untuk merancang dan membangun sistem pencatatan dan monitoring pelanggaran karyawan berbasis web guna meningkatkan efisiensi, transparansi, dan akuntabilitas dalam pengelolaan data pelanggaran. Metode pengembangan yang digunakan adalah metode Waterfall, dimulai dari tahap analisis kebutuhan, desain sistem, implementasi menggunakan Laravel Framework, hingga tahap pengujian sistem. Sistem ini memungkinkan admin dan HRD untuk mencatat pelanggaran, menetapkan poin pelanggaran, serta mengelola kategori pelanggaran secara terstruktur. Fitur utama yang dikembangkan meliputi manajemen data karyawan, input pelanggaran, rekap laporan, serta notifikasi otomatis kepada karyawan melalui WhatsApp gateway pihak ketiga ketika terjadi pelanggaran. Hasil pengujian menunjukkan bahwa sistem berjalan dengan baik sesuai kebutuhan pengguna, mampu mempercepat proses pencatatan pelanggaran, dan memudahkan pemantauan data pelanggaran secara real-time. Dengan sistem ini, diharapkan proses pembinaan dan evaluasi karyawan dapat dilakukan secara lebih objektif dan terintegrasi.

Application Of Mamdani Fuzzy Logic To Predict Rice Pest Attacks On Bp3 Bingin Kuning

2025-07-11T04:14:35+00:00

The Agricultural and Fisheries Extension Centre (BP3) Bingin Kuning is an agricultural extension centre that carries out activities related to agricultural extension preparation, evaluation, management, and development across various sectors. Every year, BP3 Bingin Kuning collects data on temperature, humidity, rainfall, and the number of attacks by each type of pest that occurs. The application of Mamdani fuzzy logic to predict rice pest infestations at BP3 Bingin Kuning can help in obtaining information on rice pest infestations each year, serve as a basis for evaluating measures to address future pest infestations, and assist farmers in addressing potential pest infestations earlier, thereby supporting BP3 Bingin Kuning in its agricultural extension activities. Based on test data under conditions of 24°C temperature, 90% relative humidity, and 295 mm rainfall in 2024, the pest type with the highest predicted attack frequency is the Keong Mas pest. Based on the system testing conducted, it can be concluded that the functionality of the Mamdani fuzzy logic application for predicting rice pest attacks at BP3 Bingin Kuning is functioning well and capable of displaying pest attack prediction results in accordance with the stages of the Mamdani fuzzy logic system.

Implementation Of Data Mining In Forecasting Herbal Medicine Sales At Cv. Anugerah Alam Indonesia Using The Linear Regression Method

2025-07-11T08:01:34+00:00

CV. Anugerah Alam Indonesia is a company engaged in the production and sale of herbal medicines. The main issue faced by the company is the inaccuracy in estimating production quantities, which often leads to either overstocking or stock shortages. This research aims to develop a sales forecasting application for herbal products using the simple linear regression method as part of data mining techniques. The sales data used in this study spans from 2020 to 2025 and focuses on ten selected herbal products. The application is web-based, developed using the PHP programming language and Laravel framework, with MySQL as the database. The forecasting process involves calculating regression constants and coefficients based on historical sales data and evaluating the prediction results using the Mean Absolute Percentage Error (MAPE) metric. The test results show that the forecasting model demonstrates varying levels of accuracy, ranging from very good to acceptable, depending on the product. By implementing this system, the company can optimize its production and distribution processes, avoid resource waste, and improve operational efficiency.