ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
PERBANDINGAN ALGORITMA YOLOV3 DAN YOLOV4 DALAM PENGELOMPOKAN UKURAN TELUR AYAM SECARA REAL TIME
Get PDFThe common problem currently faced by MSMEs producing chicken eggs is the difficulty in calculating the number of eggs and grouping egg sizes where everything is still done manually so that errors often occur and many entrepreneurs often experience losses. To improve and strengthen productivity, management, and marketing in this business, technological innovation is needed. This study aims to detect the number of eggs and group egg sizes based on their type using the Yolov3 and Yolov4 algorithms. Based on the results of the tests carried out, it shows that the Yolov3 and Yolov4 algorithms are able to detect chicken eggs in real time with the best accuracy value obtained by the Yolov3 algorithm. The comparison was carried out using 10 epoch tests with an F1-Score value of 0.89 where the F1-Score value approaching 1 indicates that the system performance has been running well. The results of this classification can be used to create a real time egg calculation application that can help calculate the number of eggs every day by each MSME
PELATIHAN KOMUNIKASI EFEKTIF PADA KARYAWAN RSU ANNA MEDIKA
Get PDFThe hospital is an organizer service health in a way plenary. Communication become a very important thing in the giving process of service health. Interaction between officers at home become a basic thing for everyone to do services provided to patient can done optimally. Communication effectively not only between officers with patients but also between officers at home sick. Communication effectively at home sick will minimize doubt in the patient regarding a series of treatment processes so that the patient will obey what is informed or recommended by the officer of health and so on no direct can increase the quality of home service. The purpose of the activity devotion public is to give importance to understanding officer health-related communication effective in giving service health good communication officer to patients between officer health at home sick. Activity training there are several suite activities among them offering material communication effective SBAR method and 7C formula, administration evaluation consisting of the pre-test and post-test, and roleplay for each case. Results of activities training enhanced understanding by participants related to communication effective besides That activity this is also a reminder return about material communication effective ever obtained moment lectures. There is an enhancement in the average pre-test score is 5.12 and the average post-test score is 9.06 on the SBAR method and there are increase in understanding of communication effective use 7C formula (pretest mean score of 5.25 and post-test mean score of 9.25)
PEMANFAATAN TEKNOLOGI INFORMASI PADA SEKOLAH MENENGAH ATAS DI BELINYU
Get PDFThe implementation of infrastructure and development of information technology (IT) services in educational environments such as schools and campuses plays an important role in supporting quality learning experiences. Regarding the introduction of IT infrastructure and service development in the educational environment. IT infrastructure covers various aspects such as providing hardware and software to meet educational needs, providing a reliable communications network, and ensuring data and information security. Services provided include training for teachers in the use of learning technology, technical support for students and staff, as well as implementation of related policies. With the right infrastructure, students and lecturers can access learning resources efficiently and interact in a technology-integrated learning environment. This service also plays an important role in increasing the technological literacy of students and teachers and ensuring the smooth operation of systems in educational environments. The services provided at schools can have a positive impact on improving the quality of education, preparing students to face the challenges of the digital world, and creating an inclusive and innovative learning environment. A holistic and coordinated implementation approach and ongoing support from all stakeholders will be key to achieving this goal
PELATIHAN PEMIKIRAN BERBASIS RISIKO MENGGUNAKAN TEKNOLOGI KOMPUTER UNTUK MENINGKATKAN AKUNTABILITAS KANTOR DISTRIK NAVIGASI PALEMBANG
Get PDFWith its strategic role, the Palembang Navigation District Office has made substantial efforts to improve the quality of its services, particularly by conducting initiatives to develop Standard Operating Procedures for the many types of services it offers. One of the main activities in this series of activities is providing training entitled Risk-Based Thinking - Identifying Risk Aspects in Processes that can support Accounting and Management Information Systems. The author explains to the participants using three methods: the Lecture Method, the Question-and-Answer Method, and the Case Study Discussion Method, all of which are conducted face-to-face and divided into five sessions, beginning with the opening session, material presentation session, illustration session, question and answer session, and closing session. It is hoped that by participating in this training activity, participants will gain a better understanding of the concept and application of risk-based thinking, as well as skills in using various types of tools, techniques and computer technology commonly used in risk management, which will be integrated into the process of developing the new service procedures. According to the results of the post-activity interview, the Head of the Palembang Navigation Office was satisfied with the training results and his team's absorption of the content
TREND ANALYSIS AND CORRELATION OF TOURIST, RESTAURANT AND HOTEL VISITS IN KUNINGAN REGENCY
Get PDFThis study conducts an in-depth analysis of the tourism sector in Kuningan Regency, focusing specifically on hotel stays, tourist arrivals, and restaurant visits. Utilizing forecasting models and correlation analyses, the research aims to uncover trends and interdependencies within the sector. The primary objective is to identify actionable insights that can inform data-driven decision-making. The study employs the FBProphet algorithm for forecasting future trends and conducts Kendall correlation analysis to examine relationships among key variables. Data collected spans a time series of 84 months, from January 2016 to December 2022. FBProphet accurately predicts trends in hotel stays, while variations exist in predictions for tourist arrivals and restaurant visits. Mean values for hotel stays, tourist arrivals, and restaurant visits are 21,098.67, 135,647.33, and 130,660.83, respectively. Kendall correlation analysis reveals a moderate positive correlation (0.214, p-value = 0.004) between tourist arrivals and restaurant visits, a strong positive correlation (0.324, p-value = 1.291e-05) between tourist arrivals and hotel stays, and a weaker positive correlation (0.176, p-value = 0.019) between restaurant visits and hotel stays. These findings underscore the intricate dynamics of Kuningan Regency's tourism sector, providing stakeholders with critical insights for strategic planning. The research contributes significantly to sustainable growth initiatives by guiding stakeholders in leveraging the interconnected elements of tourism and making well-informed decisions
EMPOWERING STRAWBERRY CULTIVATION: HARNESSING THE POTENTIAL OF IOT-BASED TECHNOLOGY IN SMART FARMING
Get PDFAgro-tourism is a form of tourism that uses agricultural land or related facilities to attract tourists. One popular agro-tourism site in Rasau Jaya Tiga is the Inspirasi Strawberry Park. Until now, the manual watering has been a common practice for strawberry plants. The Problem in watering strawberry plants manually is that inconsistent watering schedules often lead to overwatering or underwatering, affecting plant health and yield. Therefore, there is a necessity for an automated system to ensure precise and consistent watering, optimizing plant growth, water efficiency, and overall crop quality. By developing an Internet of Things (IoT) integrated irrigation system for strawberry plants, strawberry plants can be watered automatically and controlled through the Internet or mobile devices, using soil moisture sensors, air temperature, and intelligent decision-making. The results of this study indicate that the automatic watering system is able to accurately collect real-time data on temperature, humidity, time, and date of data collection. Additionally, the automatic scheduling system for watering plants and lighting system can operate as intended. With the implementation of an IoT-based automatic irrigation system for strawberry cultivation, labor costs are reduced, and crop yields are increased, contributing to enhanced agricultural productivity and economic sustainability
E-GOVERNMENT MATURITY ANALYSIS USING THE LAYNE AND LEE, HILLER AND BELANGER, AND SPBE MODELS
Get PDFThis research aims to analyze the level of e-government maturity in Kupang City using the Layne and Lee and Hiller and Belanger models and combine them with the SPBE model to provide a more comprehensive approach. The method used to develop an audit model involves a literature study to understand the e-government maturity model, identification of specific objectives for analysis of the Kupang City Population and Civil Registration Service (DUKCAPIL) website, determination of scope based on the SPBE model, determination of design audit criteria and benchmarks, collection and data synthesis from the Kupang City DUKCAPIL e-Government site, as well as analysis of audit findings, and using the GT Metrix tool for performance analysis and evaluation of the Kupang City DUKCAPIL website. The research results show that the lowest rating is F out of six, which indicates poor service performance. The Layne and Lee Model assessment gives a score of 18, indicating the technology's lack of integration and complexity. Hiller and Belanger's Model assessment gives a value of 13, indicating an immature level. These findings highlight significant gaps between the models evaluated. Recommendations based on research are to increase citizen participation by improving the Kupang City DUKCAPIL website based on a maturity model and the need for regular audits and ongoing evaluations to improve public services in Kupang City in e-government maturity. In conclusion, this research provides a new contribution to the field of e-government by highlighting the need for audits using several e-government maturity models to improve public services in Kupang City
MODEL OF INDONESIAN CYBERBULLYING TEXT DETECTION USING MODIFIED LONG SHORT-TERM MEMORY
Get PDFCyberbullying, in its essence, refers to the deliberate act of exploiting technological tools to inflict harm upon others. Typically, this offensive conduct is perpetuated repeatedly, as the perpetrator takes solace in concealing their true identity, thereby avoiding direct exposure to the victim's reactions. It is worth noting that the actions of the cyberbully and the responses of the individual being cyberbullied share an undeniable interconnection. The main objective of this study was to identify and analyze Instagram comments that contain bullying words using a model of WLSTML2 which is an optimization of a long short-term memory network with word-embedding and L2 regularization. This experiment using dataset with negative labels as many as 400 data and positive as many as 400 data. In this study, a comparison of 70% training data and 30% testing data was used. Based on experimental results, the WLSTMDR model obtained 100% accuracy at the training stage and 80% accuracy at the testing stage. The WLSTML2 model received an accuracy of 99.25% at the training stage and an accuracy of 83% at the testing stage. The WLSTML1 model obtained an accuracy of 97.01% at the training stage and an accuracy of 80% at the testing stage. Based on the experimental results, the WLSTML2 model gets the best accuracy at the training and testing stages. At the testing stage of 132 data, it was found that the positive label data predicted to be correct was 56 data and the negative label data that was predicted to be correct was 53 data
IMPLEMENTATION OF FISHER-YATES SHUFFLE ALGORITHM IN ANDROID-BASED JAVANESE BATIK CULTURE EDUCATION GAME
Get PDFBatik, as one of Indonesia's precious cultural heritages, has a variety of motifs in the art of batik in this country. The preservation of batik is important and the success of educational games in supporting this goal has been proven. Understanding the complex meaning and philosophy of batik is difficult given the variety of motifs. Therefore, this research creates an Android game that incorporates elements of batik culture to introduce the meaning and philosophy of Indonesian batik to the next generation. Android technology makes learning more flexible, allowing unrestricted access to information. By following the Game Development Life Cycle (GDLC) method and integrating the Fisher-Yates Shuffle algorithm and Finite State Machine (FSM), this game takes players on an adventure against Non-Playable Character (NPC) characters using the FSM model. The Fisher-Yates Shuffle algorithm is used to randomize 10 questions, making each game session unique. The algorithm test results showed an average question execution time of about 35.6 microseconds, indicating stable performance despite variations in each trial. The alpha test results showed an average score of 87%, covering aspects of information readability, responsiveness, player motivation, combat experience, educational benefits, as well as satisfaction, and game design that showed good performance. Thus, this research succeeded in creating an educational game that is entertaining and educational, as well as helping to maintain and introduce batik cultural heritage to the next generation
OPTIMASI KINERJA LINEAR REGRESSION, RANDOM FOREST REGRESSION DAN MULTILAYER PERCEPTRON PADA PREDIKSI HASIL PANEN
Get PDFRice yield prediction is a significant challenge in the context of climate uncertainty and farmland variation. Erratic weather factors, along with land differences, make this prediction more complex. This research aims to address these issues using a machine learning approach. The method used involves three machine learning models namely Linear regression, Random Forest Regression, and ANN with MultiLayer Perceptron algorithm as well as the evaluation matrix RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and MAPE (Mean Absolute Percentage Error). This research focuses on testing the accuracy of the three models in the face of uncertain seasonal conditions and variations in agricultural land. The results showed that the MultiLayer Perceptron prediction model gave the best results with an error value of 0.094. The random forest regression method ranks second with an error value of 0.510, followed by Linear regression with an error value of 0.281. The importance of outlier testing in the model development process can be seen from the significant improvement in the performance of the MultiLayer Perceptron model. This research contributes to the development of a more reliable and dependable rice yield prediction system, especially in the midst of uncertain climatic conditions. Machine learning models, particularly MultiLayer Perceptron, can be an effective solution to increase agricultural productivity and reduce risks associated with weather changes and land variations