Jurnal Teknologi dan Rekayasa Sistem Komputer (TEKNOKOM)
Not a member yet
85 research outputs found
Sort by
SISTEM OTOMATISASI PEMANAS AIR MENGGUNAKAN SENSOR DHT11 BERBASIS ARDUINO UNO
Get PDFHeat water is part of our needs in our daily life. With its variety of uses, a tool is needed to heat the water. In this study, a system will be designed so that the heat water can turn off automatically whenever the water is boiling. The methods used will include literacy studies from previous research journals, component selection based on literacy studies, and system design. The results obtained will be in the form of division of experimental water based on the set of temperature points on programming as a benchmark. From the experimental data, it can be concluded that the relationship between the amount of water and the temperature value for the set point in the programming will affect the water produced at the end of the experiment greatly. The more the amount of water, the higher the set point must be given
ANALISIS SENTIMEN PRODUCT TOOLS & HOME MENGGUNAKAN METODE CNN DAN LSTM
Get PDFSentiment analysis is gaining popularity as the number of internet users increases. Internet users often express their opinions through reviews on websites. The customer opinions expressed have a huge impact on sellers and customer numbers, as many consumers rely on online reviews as a reference when purchasing products. In order to quickly understand sentimental views and tendencies towards a product or event, a text sentiment analysis is performed on the opinions expressed by users. Sentiment analysis focuses on understanding the sentiments contained in the text. One common approach in sentiment analysis is to use Deep Learning (DL) models. This study aims to analyze product sentiment in the Tools & Home category from Amazon using models such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). The CNN model is used to extract features from words that reflect short-term sentiment dependencies, while LSTM is used to establish long-term sentiment relationships between words. CNN and LSTM are sophisticated DL models, capable of efficiently processing text data and recognizing relationships and patterns that exist at various levels of abstraction. The purpose of this study is to understand the differences in the performance of the DL model in conducting sentiment analysis, it is hoped that it can also be a reference for those who plan to apply other DL models
PERBANDINGAN BERBAGAI MODEL MACHINE LEARNING UNTUK MENDETEKSI DIABETES
Get PDF
Diabetes mellitus, often known as diabetes, is a significant metabolic illness that has a negative impact on living organisms. It causes high blood sugar levels by either creating inadequate insulin or using it inefficiently. Diabetes that is not effectively treated raises the risk of heart attacks, retinopathy, vision loss, skin disorders, and other ailments. Early detection is critical for guiding essential actions. In this setting, machine learning (ML) has emerged as a potent tool. We used Python data manipulation tools to develop ML techniques for discovering patterns and risk factors in the Pima Indian diabetes dataset in our study. We correctly identified patients as diabetes or non-diabetic using K-Nearest Neighbors (KNN), AdaBoost, Logistic Regression (LR), Light Gradient Boosting, Random Forest (RF), dan Support Vector Machine (SVM). Notably, we used the Synthetic Minority Over-sampling Technique (SMOTE) to solve class imbalance, which enhanced model performance. By efficiently utilizing ML and SMOTE in diabetes categorization, our work greatly adds to the scientific area. We suggest studying cutting-edge technology and undertaking external validation and clinical studies to assure trustworthy and generalized models for diabetic patient care in the future. With diabetes's increasing prevalence, such improvements have enormous promise for improving early identification and management, eventually leading to better health outcomes
A NODEMCU INTERNET OF THINGS-BASED FIRE AUTOMATION DESIGN WITH BLYNK APPS NOTIFICATIONS
No full textThe impact of fires causes quite large losses, often even causing fatalities. The method used in the system is monitoring the fire sensor which is used to detect a fire, the buzzer as a notification output in the form of sound, and the water pump as a fire extinguisher which will function after the fire sensor is on. detecting the presence of fire. to detect fire in realtime and 9 in the event of a fire with a research and development. Monitoring approach on fire sensors used to detect the presence of fire, buzzers as output notifications in the form of sound, and water pumps as a tool to extinguish fires which will function after the fire sensor detect the presence of fire
IMPLEMENTATION OF FUZZY LOGIC ON SPEED PREDICTION ON INCLUDING ROADS
Get PDFGoing through a road with a high slope has a risk of an accident due to a miscalculation by the driver. Therefore, detecting the speed limit to pass it is the solution. The aim of this research is to create a precise and minimal error system that predicts the uphill speed that must be used by the driver. By using fuzzy logic, of course you can predict what speed should be used. For tilt detection, a gyroscope is used and speed detection is being used using a GPS sensor. For the fuzzy inference system itself, it uses the Takagi Sugeno-Kang, method with a linear and constant output. In addition, the calculation of the crisp value is carried out using the manual calculation method and using a simulation application, namely MATLAB. The results of subsequent calculations are compared to calculate the precision value of the system in detecting uphill speed. The calculation uses MAPE. So the results of this study are speed detection systems that must be used on inclines that predict precisely. The implication of this research is that driving safety on high-slope roads can be improved and accidents that occur can be minimized. In addition, the driver can estimate the speed that must be used
PENDEKATAN INTERNET OF THINGS UNTUK PREDIKSI BIAYA PENGGUNAAN LISTRIK RUMAH PADA APLIKASI ANDROID
Get PDFTechnology is currently growing rapidly and of course, in this era electrical energy has become a necessity for carrying out activities. Therefore, the Smart Watt Meter system can be interpreted as a tool that can monitor and predict costs for home electricity use using the Android application, so that all these devices and systems can be connected to one another. Only by connecting to a smartphone, users can monitor electricity usage and can predict home electricity costs that will be incurred every month using an Android application remotely in real time. Due to the large amount of electricity used in homes that is difficult to control, the aim of designing a Smart Watt Meter system is to reduce excess electricity usage by providing predictions of electricity user costs. This Smart Watt Meter is composed of Wemos D1R1 as the microcontroller in the main system, where when the PZEM 004T V3 sensor reads the value of electricity usage, an output will be produced in the form of a value on the application that has been made and also an OLED display. The results of this study found that voltage, current, power, frequency, power loss, energy consumption, the cost of using electricity per month can be measured. One of the suggestions from this study is to make a dashboard that can be accessed on any device, such as making a dashboard that can be opened on websites and also on smartphones
STORAGE ROOM TEMPERATURE AND HUMIDITY MONITORING IOT- BASED MEDICINE
Get PDFThis research is important as it portrays a notable advancement in current internet technology known as the Internet of Things (IoT), which facilitates advanced services through the interconnection of physical and virtual objects. One crucial aspect of everyday life is air quality, especially indoors, as indoor air pollution differs from outdoor air pollution. An important indicator to determine the cleanliness of a room is its humidity level. In this context, this research holds significant relevance as it can help ensure the effectiveness and safety of stored medications under appropriate temperature and humidity conditions. Therefore, this study designed a drug storage room that requires a tool to measure the humidity value of the room in real time and the humidity conditions in the room. The solution to this problem can be overcome using Internet of Things technology. In this project, a hygrometer, or humidity meter, based on Internet of Things technology is made. Humidity is measured by the DHT-11 sensor, which is integrated on the NodeMCU ESP8266 board. Humidity measurement data can be observed via the Blynk IoT platform available on smartphones. With this tool, humidity can be observed in real time, even from a distance. The results of this study are that the tool can measure the temperature and humidity of the medicine room, and the tool can send humidity and temperature measurement data to the Blynk IoT and MIT APP Inventor servers. On the Blynk IoT website, the dashboard can display temperature, humidity, and drug safety measurement data in real time
ANALYSIS OF SOLAR ENERGY POTENTIAL IN THE PT. SUMEDANG TELEVISI UTAMA BUILDING AS AN ALTERNATIVE ENERGY SOURCE
Get PDFIndonesia is a tropical region with significant solar energy potential, where the average daily sunlight reaches 4.5 - 4.8 kWh/m²/day. This makes solar energy one of the promising forms of renewable energy worthy of development. The instability of electricity supply from the national grid (PLN) is a prevalent issue across various regions. PT. Sumedang Televisi Utama (SMTV), a television broadcasting company, frequently encounters disruptions in TV broadcasts due to power supply issues originating from PLN. Hence, this research holds the urgency to explore alternatives that can provide electricity supply during interruptions in the PLN power distribution. The contribution of this study lies in the development of a practical and applicable Photovoltaic Solar Power Plant (PLTS) module. With the implementation of this module, it is anticipated that PT. Sumedang Televisi Utama (SMTV) and other entities can have a backup electricity supply source, mitigating the impact of power supply disturbances from PLN. Suggesions for further research include delving deeper into the efficiency and performance assessment of the designed PLTS module under various environmental conditions and weather patterns that are typical in Indonesia. Furthermore, subsequent research could focus on integrating a more effective energy storage system with the PLTS module, thereby maximizing solar energy utilization even during periods of limited sunlight. This endeavor would enhance the resilience and availability of alternative power supply during instances of disruptions in the national grid (PLN) distribution
DIGITAL HERITAGE PORTAL BASED ON PROGRESSIVE WEB APP: EFFORTS FOR THE DEVELOPMENT OF CULTURAL HERITAGE AND TOURISM IN LAMPUNG
Get PDFAccording to Undang-undang No. 11 Th. 2010 regarding Cultural Heritage, preservation involves dynamic efforts to safeguard the existence and values of Cultural Heritage through protection, development, and utilization. Despite rapid technological progress, there is currently no dedicated digital platform designed to promote and preserve cultural heritage in Lampung Province. The diverse cultural legacies could be better harnessed and developed, as they hold significant potential for attracting tourists to the region. This research aims to design a Progressive Web App-based Digital Heritage Portal to foster cultural heritage and tourism in Lampung Province. Digital Heritage employs technology to understand and conserve cultural legacies. As an innovative approach, the information system is crafted using Progressive Web App technology for easy user access online or offline, without requiring prior app installation. The system is anticipated to aid in the promotion, preservation, and advancement of cultural heritage and tourism in Lampung. The research follows the Waterfall method with these stages: 1) Problem analysis, (2) Data collection, (3) System requirement analysis, (4) Coding, (5) Deployment, and (6) System testing. The research yields an application design functioning as an informative platform for historical and cultural heritage tourism in Lampung Province. The application operates smoothly across platforms and offline. Test results affirm proper menu functionality aligned with stipulated system requirements
WEB-BASED LPG DISTRIBUTION MANAGEMENT INFORMATION SYSTEM AT PT BOY BAGUS WINDI
Get PDFPT Boy Bagus Windi is one of the LPG distributors in the Langkat Regency. Because Microsoft Excel is still used to hold distribution data, financial data, sales and purchase data, and personnel data, PT. Boy Bagus Windi faces a number of difficulties managing his data. The problem that businesses run into is that when they need to look for data, it takes a while since they have to access each folder or page in Microsoft Excel individually. Due to the current rapid growth of information technology, many businesspeople conduct their everyday activities online. In order to administer its business management information system, a company is compelled to adopt a web-based information system. Therefore, PT. Web-based Boy Bagus Windi developed a management information system. This system is intended to make it simpler for businesses to search data and handle human, financial, and products data management in one web for a more streamlined and orderly arrangement.