ejournal.nusamandiri.ac.id (STMIK Nusa Mandiri)
Not a member yet
1504 research outputs found
Sort by
DEVELOPMENT A DAILY NUTRITIONAL ADEQUACY BALANCE IDENTIFICATION SYSTEM AS AN EFFORT TO PREVENT MALNUTRITION
Get PDFMalnutrition is a deficiency, excess or imbalance in a person's energy and nutritional intake. Malnutrition can occur when a person has too much or too little food and important nutrients in their body. The Ministry of Health, Indonesia, has campaigned for food consumption that complies with balanced nutrition guidelines under the slogan "Isi Piringku". However, the guidelines regarding this matter are still not properly understood by the public. Even if implemented, the nutritional levels contained in one portion of food consumed cannot yet be measured. Thus, to identify the fulfillment of balanced nutritional, a device is needed to easily detect how much calories is consumed. Therefore, this research aims to develop a system which can identify whether the portion of food consumed meets balanced nutrition or not. It is developed in Django framework, Python programming language, and MySQL database. It has been evaluated using black box testing, white box testing, and system usability scales. The result shows that all system requirements have been run well. Meanwhile, system usability testing result shows that the identification system has been tested with a score of 82 and categorized in Excellent
BRAIN TUMOR CLASSIFICATION USING INCEPTIONRESNET-V2 AND TRANSFER LEARNING APPROACH
Get PDFBrain, a highly intricate organ within the central nervous system, plays a fundamental role in information processing, cognition, motor control, and consciousness. Brain tumors pose severe threats to brain function and overall human well-being. Timely detection of these tumors is imperative for life-saving interventions. A dataset comprising four categories: no tumors, meningioma tumors, glioma tumors, and pituitary tumors was regarded in this research. The employed of the InceptionResNet-V2 architecture combined with Transfer Learning and data augmentation proposed to obtain optimal results on brain tumor classification types. Transfer learning act as fine tuning, enabling the model to acquire fundamental low-level image features from a comprehensive dataset. It then leverages higher-level features to become more tailored to the specific training data. This method is employed to improve the model's adaptability to the training data. The InceptionResNet-V2 architecture utilized in the evaluation using test data, in Scenario 1, achieved 94.18% accuracy. Scenario 2, which combined augmentation with InceptionResNetV2, showed an improvement in accuracy to 95.10%. Furthermore, in Scenario 3, the combination of InceptionResNetV2 with Transfer Learning and augmentation resulted in an impressive accuracy of 96.63%, demonstrating its effectiveness in brain tumor classification. Transfer learning aligns the model by acquiring low-level image features and utilizing higher-level features to improve adaptability to the training data
PERANCANGAN APLIKASI INFORMASI PENDAKIAN GUNUNG DI INDONESIA BERBASIS ANDROID DENGAN MENGGUNAKAN METODE PROTOTYPE
Get PDFNowadays, more and more teenagers and adults are interested in mountain climbing. Climbers are keen to find information about the routes and mountains they will be climbing. However, many mountaineers complain that the information they get about climbing routes is not accurate or complete. The information currently available is only general information and does not have accurate data such as coordinate points, mountain profiles, transportation facilities, and other facilities that help climbing. To solve this problem, Object Oriented Design (OOD) and Prototype system development methods were used to create an Android-based Indonesian mountaineering information application. The application was developed using Android Studio and designed to provide comprehensive information for mountaineers, including paths to the mountain, photo galleries, current news about the mountain to be climbed, climbing posts, and geographical locations. The study resulted in contributions in various aspects that can improve the safety and comfort of mountaineers in Indonesia. With more accurate and complete information and the utilization of modern technology, this application supports mountaineering activities significantly. Climbers not only get better guidance but also feel safer and more comfortable in pursuing their hobby
PENINGKATAN DAYA SAING DAN KESEJAHTERAAN KT. KOMPITU HIJAU SEBAGAI GARDEN CITY MELALUI DIGITAL MARKETING
Get PDFKT Kompitu Hijau faces challenges in marketing fresh agricultural products only through Whatsapp Group. Marketing of derivative products such as vegetable chips, healthy vegetable juice, dawet spinach, instant herbal medicine is limited to certain events organized by the Department. As well as less than optimal production management related to less attractive product packaging and water and electricity problems. The solution to overcome these problems requires training and mentoring in Digital Marketing as well as training and mentoring in production management. The method used in the training and mentoring of Digital Marketing and Production Management is the Participatory Rural Appraisal (PRA) approach which involves the community in the development process. As well as the FGD method to determine the right marketing strategy. The results after carrying out community empowerment activities are KT. Kompitu can market and sell products online through GrabMart E-Commerce, Instagram and WhatsApp Business Toko Kompitu Sehat. The results of assistance and training in production management of KT Kompitu Hijau are able to produce products that are packaged and have an attractive logo. As well as having optimal waters to produce the best products. KT Kompitu Hijau won 1st place in the Yogyakarta City Vegetable Landscape Competition which was attended by 34 farmer groups in Yogyakarta City. The evaluation results show that digital literacy has increased. This community empowerment activity was organized as a contribution to increasing the competitiveness and welfare of KT. Kompitu Hijau
FASILITATOR PEMBELAJARAN DIGITAL BAGI TENAGA PENGAJAR PADA MADRASAH TSANAWIYAH NEGERI 1 KOTA LHOKSEUMAWE
Get PDFPendidikan merupakan proses yang vital bagi pengembangan individu, dengan guru memainkan peran sentral dalam menentukan kualitas pendidikan. Kompetensi guru, meliputi kemampuan pedagogik, kepribadian, sosial, dan profesional, sangat penting untuk menciptakan lingkungan pembelajaran yang efektif. Seiring dengan perkembangan teknologi, pemanfaatan media pembelajaran digital telah menjadi metode yang inovatif untuk meningkatkan kualitas pendidikan. Namun, hal ini masih jarang dilakukan oleh guru di dalam proses pembelajaran kepada peserta didiknya. Maka dari itu, penelitian ini berfokus pada kegiatan pengabdian masyarakat yang bertujuan untuk memperkenalkan dan mengaplikasikan media pembelajaran digital kepada guru di Madrasah Tsanawiyah Negeri 1 Kota Lhokseumawe. Muatan materi yang diberikan kepada peserta kegiatan juga merupakan hasil observasi dan wawancara yang diberikan oleh pihak mitra berdasarkan kebutuhan sekolah. Kegiatan dimulai dari persiapan kegiatan, pelaksanaan kegiatan, serta evaluasi kegiatan. Kegiatan ini dilaksanakan selama tiga hari, dari 6 hingga 8 Agustus 2024 dan meliputi presentasi materi, diskusi, serta praktik langsung. Selama tiga hari pelatihan, guru diberikan materi mengenai perkembangan teknologi informasi, pengelolaan kelas secara interaktif, serta media dan game pembelajaran interaktif. Materi yang diberikan antara lain adalah perkembangan teknologi informasi dalam pembelajaran digital, pengelolaan kelas secara interaktif dan media pembelajaran digital, serta media pembelajaran dan game pembelajaran dengan memanfaatkan beberapa perangkat lunak, seperti produk Google (GForm, Classroom, Drive), Wordwall, dan Quizizz. Hasil evaluasi menunjukkan tingkat pengetahuan peserta meningkat signifikan, dengan 89,5% berhasil menjawab soal evaluasi dengan benar dan 100% peserta mengumpulkan tugas yang diberikan
ANALISIS PENGARUH HARGA TERHADAP KEPUTUSAN PEMBELIAN DI WARUNG GOCENG DEPOK: STUDI KASUS
Get PDFThis research was conducted due to the challenges faced by Warung Goceng in Depok, such as inconsistent product quality, price competition, and customer service issues, which motivated this study. The aim of this study is to evaluate the influence of price on customer purchasing decisions. Using a quantitative approach, 60 customers of Warung Goceng in Depok City participated as research participants. Data were obtained through the distribution of questionnaires and observation, and hypothesis testing was conducted using SPSS. The findings of the study indicate that the majority of consumer purchasing decisions are significantly influenced by price factors, and there is a direct relationship between Warung Goceng's prices and consumer purchasing decisions Bonus dan promosi menarik adalah salah satu daya tarik utama Indohoki77. Platform ini menawarkan berbagai jenis bonus seperti bonus selamat datang, bonus deposit, dan cashback . Therefore, Warung Goceng can improve its pricing strategy to better suit consumer preferences and enhance its competitiveness in the culinary industr
PREDICTION OF BIODIESEL FUEL PRICES USING MULTIPLE LINEAR REGRESSION ALGORITHMS
Get PDFBiodiesel is a fuel derived from palm oil and a type of fuel that is an alternative to renewable energy, can be renewed and has the potential to become a substitute for fossil sources that are used non-stop. The utilize of biodiesel can be an arrangement for Indonesia to diminish reliance on imported diesel fuel since biodiesel does not contain sulfur and is demonstrated to be ecologically inviting. The price of biodiesel-type biofuels can increase, decrease, or remain constant due to factors that influence it, including the price of biodiesel competitors, palm oil, and world crude oil. For this reason, it is necessary to have a method that can predict the price of biodiesel-type fuel so that in the future, the price of biodiesel-type biofuel does not decrease or become unable to compete with its competitors. Prediction of biodiesel fuel prices can be done by implementing a multiple linear regression algorithm, one of the data mining algorithms. RMSE results obtained in this study were 0.003 with a standard deviation of +/- 0.000 so it can be concluded that this algorithm is quite accurate in predicting the price of biodiesel-type biofuels. A comparison of the results of manual calculations with the implementation of RapidMiner in the study obtained the same results because there was a causal relationship between attributes. The use of the multiple linear regression algorithm in this research is useful in planning the right strategy and making decisions to maintain biodiesel market price stability in the future
INTEGRATION OF BLOCKCHAIN TECHNOLOGY IN DIGITAL LIBRARIES: A SOFTWARE ENGINEERING DESIGN
Get PDFThis research aims to design software engineering that integrates blockchain technology in digital libraries to improve system security and reliability. This integration is expected to overcome challenges related to data security, service reliability, and efficiency in digital library management. The research methodology involves collecting data through literature, expert interviews, and observations, on the implementation of blockchain technology in digital libraries, then analyzing data to support data design such as etherum, smart contracts, address, node.js, solidity, metamask, and sublime text, then using the Agile Extreme Programming (XP) method for software development. The research results include the design of a decentralized blockchain architecture, the use of smart contracts, and the application of cryptographic techniques to enhance security. Immutability testing in the context of blockchain involves verifying data consistency, validating the process of adding data, testing the ability to delete data, testing against attacks, and activities on immutable data. These tests were conducted using the Truffle framework. The results show that the system is able to maintain data integrity well
SENTIMENT ANALYSIS USING CONVOLUTIONAL NEURAL NETWORK (CNN) AND PARTICLE SWARM OPTIMIZATION ON TWITTER
Get PDFOver time, social media has always changed quickly. People can voice their ideas on various topics and communicate with each other through social media. One social media platform that allows users to express their ideas through tweets is Twitter. Sentiment is the route via which each person can express their ideas on a variety of subjects. The sentiment can be positive or negative. Sentiment analysis can be used to determine how Twitter users feel about particular subjects. Sentiment analysis on popular subjects in 2023, specifically the 2024 presidential contenders, will be done in this research. The dataset used in this research consists of 37,391 entries with 5 keywords. The research aims to understand how Twitter users respond and express their sentiments towards the presidential candidate through the use of deep learning classification techniques with Convolutional Neural Network (CNN), feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) method, and feature expansion with Word2Vec. Furthermore, this study employs Particle Swarm Optimization as an optimization technique to enhance the sentiment analysis model's performance. The test's results demonstrate a high degree of accuracy, offering a comprehensive picture of Twitter users' sentiments and perspectives toward the 2024 presidential contenders. This research helps to understand the dynamics of public opinion in the political context. Based on the evaluation results of the research, it yielded an accuracy of 78.2%, showcasing an improvement of 10.07% compared to the baseline
XGBOOST HYPERPARAMETER OPTIMIZATION USING RANDOMIZEDSEARCHCV FOR ACCURATE FOREST FIRE DROUGHT CONDITION PREDICTION
Get PDFClimate change and increasing global temperatures have increased the frequency and intensity of forest fires, making fire risk evaluation increasingly important. This study aims to improve the accuracy of predicting forest fuel drought conditions (Drought Code) by using the XGBoost algorithm optimized with RandomizedSearchCV. The research methods include collecting data related to forest fires, preprocessing data to ensure quality and consistency, and using RandomizedSearchCV for XGBoost hyperparameter optimization. The results showed that the optimized XGBoost model resulted in a decrease in Mean Squared Error (MSE) and an increase in R-squared value compared to the default model. The optimized model achieved an MSE of 0.0210 and R2 of 0.9820 on the test data, indicating significantly improved prediction accuracy for forest fuel drought conditions. These findings emphasize the importance of hyperparameter optimization in improving the accuracy of predictive models for forest fire risk assessment