Jurnal Rekayasa Elektrika
Not a member yet
345 research outputs found
Sort by
Toddler Stunting Consulting Chatbot using Rasa Framework
Full text linkChatbots are artificial intelligence software that can communicate with users to assist them in certain tasks or provide information. They can reduce the need for human interaction and make processes more efficient. However, when it comes to more specific tasks related to handling the problem of stunting in toddlers these services are usually unable to provide an appropriate response. Chatbots were created with the help of the Rasa framework, which was designed to adapt the various components of natural language understanding (NLU). This adjustment allows him to understand more complex questions from respondents such as those related to healthy feeding of toddlers. This research explained the use of the Rasa framework to enhance their capabilities, describe the testing and evaluation process, and present the performance results of the chatbot model in addressing the issue of stunting in toddlers. The model is then tested using a confusion matrix, precision, accuracy, and F1 score, which measures how accurate the chatbot's responses are to the user's input. The model had a precision, accuracy, and F1 score of 0.928, 0.932 and 0.930, respectively
The Duration of the Cycle to Get the P Amplitude on A Discrete Electrocardiogram
Full text linkThe P amplitude value for each cycle has not been carried out even though it is related to indications of atrial hypertrophy. The basic interpretation of the maximum P amplitude under normal conditions is 2.5 small squares on electrocardiogram (ECG) paper which is equivalent to 2.5 mV. Apart from these interpretations, an amplitude value is required that corresponds to the amount of depolarization of the atrial muscle cells. The difficulty faced by researchers is the lack of discrete ecg data available for experiments, so it only depends on amplitude data as a function of Physionet output time. An ECG is produced using discrete data but there is no electrocardiograph that displays discrete data yet. This study aims to obtain the P amplitude value based on discrete electrocardiogram data. The cycle duration value obtained from R to R is used to obtain the initial position of the cycle (sc) with the formula RN+1-1.5dR for each cycle. The P amplitude value can be obtained by filtering the maximum amplitude value between the sc and RN positions. The results of research on 10 physionet samples and 10 RSSA samples showed that all samples had an amplitude R, cycle duration and P amplitude value in each cycle
Optimization of Fuzzy Social Force Model Adaptive Parameter using Genetic Algorithm for Mobile Robot Navigation Control
Full text linkThe Social Force Model (SFM) is a popular navigation technique for mobile robots that is primarily used to simulate pedestrian movement. The SFM method's drawback is that several parameter values, such as gain, k, and impact range, , must be determined manually. The reaction of the SFM is frequently inappropriate for certain environmental circumstances as a result of this manual determination. In this paper, we propose employing the Fuzzy Inference System (FIS), whose rules are optimized using a Genetic Algorithm (GA) to manage the value of the gain, k, parameter adaptive. The relative distance, d, and relative angle, , concerning the robot's obstacle are the inputs for the FIS. The test results using a 3-D realistic CoppeliaSim demonstrated that the learning outcomes of FIS rules could provide adaptive parameter values suitable for each environmental circumstance, allowing the robot to travel smoothly is represented using the robots heading deviation which decreasing by and reaching the goal 1.6 sec faster from the starting point to the goal, compared to the SFM with the fixed parameter value. So that the proposed method is more effective and promising when deploying on the real robot implementation
Perancangan dan Implementasi Alat Pendeteksi Dini Penyakit Jantung Koroner
Full text linkPenyakit jantung koroner merupakan penyebab kematian tertinggi di Indonesia setelah stroke dengan persentase sebesar 12,9%. Penyakit jantung koroner terjadi akibat penumpukan plak yang disebabkan oleh tingginya kadar kolesterol serta meningkatnya tekanan darah dalam jangka panjang. Dibutuhkan sistem yang dapat memantau kesehatan jantung secara berkala. Pada penelitian ini menyajikan sistem yang mampu melakukan deteksi dini penyakit jantung koroner yang terdiri dari kategori risiko rendah, sedang, dan tinggi berdasarkan tiga parameter yaitu kolesterol, tekanan darah, dan detak jantung. Pengukuran kolesterol dilakukan secara non-invasif menggunakan LED sebagai transmitter dan photodioda sebagai receiver. Pengukuran tekanan darah menggunakan sensor MPX5100DP dengan metode osilometri, dan pengukuran detak jantung menggunakan sensor MAX30102. Data dari sensor dan informasi tambahan berupa jenis kelamin, usia, dan status perokok akan diolah dengan metode K-Nearest Neighbor untuk mengetahui hasil klasifkasi penyakit jantung koroner. Dari keseluruhan pengukuran, akurasi rata-rata untuk pengukuran kolesterol adalah 97,9%, pengukuran tekanan darah sistolik adalah 96,3%, tekanan darah diastolik 92,7%, dan pengukuran detak jantung adalah 98,8%. Klasifikasi penyakit jantung koroner pada 15 responden menggunakan metode K-Nearest Neighbor memiliki perbedaan sekitar 20% dengan perhitungan menggunakan tabel Framingham Risk Score yang dilakukan oleh dokter
Alat Pendeteksi Kadar Glukosa pada Urine dengan Metode Naive Bayes
Full text linkDiabetes Melitus (DM) adalah penyakit kronis yang ditandai dengan kadar glukosa darah yang melebihi batas normal yang disebabkan oleh tidak berfungsinya pankreas dalam memproduksi insulin yang cukup. Ketika glukosa berlebih, gula akan dikeluarkan melalui urine yang disebut glukosuria. Sehingga tujuan dari penelitian ini adalah untuk membuat alat pendeteksi kadar glukosa dari urine menggunakan sensor warna dan sensor gas dengan metode naive bayes. Untuk mengetahui jumlah kadar glukosa melalui urin dapat menggunakan larutan benedict. Dari percampuran antara sample urine dan larutan benedict akan dihasilkan perubahan warna yang dapat diukur dengan sensor warna TCS3200. Selain menggunakan sensor warna, digunakan juga sensor gas yaitu MQ-135, dimana cara kerja dari sensor ini adalah mendeteksi bau / kadar amonia dalam sample urine. Data dari kedua sensor akan diolah oleh metode nave bayes untuk mengetahui hasil klasifikasi dan juga menggunakan metode regresi linier untuk menghitung kadar glukosa darah. Hasil dari penelitian ini dengan menggunakan 16 sample, untuk metode nave bayes diperoleh akurasi sebesar 93,75%
Adaptasi Model CNN Terlatih pada Aplikasi Bergerak untuk Klasifikasi Citra Termal Payudara
Full text linkThe model development for breast thermal image classification can be done using deep learning methods, especially the convolutional neural network (CNN) architecture. This article focuses on adapting a trained CNN (trained model) on a mobile application for binary classification of breast thermal images into normal and abnormal classes. The CNN model applied in this study was based on ShuffleNet, called BreaCNet, with a learning weight of 1028 filters generated from training on images downloaded from the Database for Mastology Research (DMR) and a model size of 22 MB. The model must be converted into a mobile application to enable a trained model to be adapted into a mobile platform. The BreaCNet model was built using MatLab; thus, the stages in the adaptation process consisted of converting the model into ONNX file format, converting ONNX files into Tensorflow files, and Tensorflow files into Tensorflow Lite format. However, not all nodes are fully supported by MATLAB. The shuffle node on ShuffleNet cannot be fully exported using ExportToOnnx, so it needs to be re-defined with a placeholder named MATLAB PLACEHOLDER. In addition to the model conversion process, this article describes the user interaction process with the application using UML diagrams and application feature menu designs. The application was also tested on 20 thermal images of the breast. The testing results show that the application can perform the image classification process on mobile devices in less than 1 second with an accuracy rate of 85%. Finally, the breast thermal image screening application has been successfully built by directly interpreting the thermal image of the breast on a mobile device to keep the user data private
Analisis Perbandingan Kinerja Sensor Jarak HC-SR04 dan GP2Y0A21YK Dengan Menggunakan Thingspeak dan Wireshark
No full textUntil now, Internet of Things (IoT) is a very interesting topic to research. This is due to the wide role that IoT can play in human life. This study aims to compare the performance of two sensors in an IoT-based distance detection system with the focus of the parameters being tested: sensor readings, Qos of data transmission, and power requirements. The two sensors that are the subject of comparison are HC-SR04 and GP2YA21YK. As an analytical tool, this research uses two tools, namely Thingspeak and Wireshak. The performance test results show that in terms of accuracy in determining distance, the HC-SR04 has a much better performance than the GP2YA21YK. On HC SR04, the average reading error is 0.82 cm, while on GP2YA21YK it is 14.40 cm. Meanwhile, in terms of QoS parameters, the two sensor systems show almost commensurate performance, the packet loss is both 0%, the throughput value is 37.01 kbps on HC-SR04 and 38.12 kbps on GP2YA21YK. As for the delay, the HC-SR04 sensor gives a value of 33.55 ms, and on GP2YA21YK it is 26.1 ms. Furthermore, based on power requirements, sensor systems using the HC-SR04 consume 14.36% less power than the system that use GP2YA21YK. By referring to the results of measurements and visualizations using Wireshark and Thingspeak, it can be concluded that the distance detection system using the HC-SR04 sensor is better than the system with the GP2YA21YK
Rancang Bangun AirMouse Menggunakan Sarung Tangan Bersensor Berbasis ESP32
Full text linkDigital interactions are still commonly using indirect media such as mouse and keyboard to provide user input in the form of two-dimensional data. Therefore, to provide intuition in virtual interactions, it is possible to add media that can draw directly in the air or a flat surface that will track hand movements and overall finger position. In this research, we try to track hand movements in real time by capturing the position of the hand and finger curvature using a wearable sensor equipped with an Inertial Measurement Unit (IMU) sensor and a flex sensor installed by the user. Then the system will identify the position of the user's finger bending. and the location indicated by the sensors installed to move the cursor on the screen and simulate left-click and right-click hand movements as with a traditional mouse. By using this system, users can interact with the computer more naturally and get the accuracy of cursor movement with the accuracy of finger movement translation reaching more than 85% and the translation of hand movements to mouse cursor movements is on average 73% for shapes that use straight lines. and 23.4% on curved lines such as circles and other shapes
An Implementation of Measurement System Analysis for IoT-Based Waste Management Development
Full text linkA measurement system is a process that consists of standards, employees, and methods for measuring particular quality characteristics. Measurement System Analysis (MSA) attempts to evaluate a measuring system's precision, accuracy, and consistency so that clients receive high-quality goods. The previous study implements the MSA for machinery and industrial lines, electronics manufacturing, agricultural and poultry, aviation, and even employee monitoring and inspection. Elsewhere, waste management has problems, especially with capacity measurement instruments and weight sensors. This study aims to: (i) build an IoT-based waste management system; and (ii) evaluate the developed system by implementing the MSA technique, focusing on measurement equipment. The Gauge Repeatability and Reproducibility (GRR) Study Type 1, the (GRR) Study, and the Analysis of Variance (ANOVA) are conducted to evaluate the measurement instrument of the waste management system. The study findings that the total variance of the GRR is 20.95 %, and the distinct categories are 6. Thus, as the Automotive Industry Action Group (AIAG) GRR recommendation, the measuring system is marginal (acceptable in certain conditions). Moreover, the ANOVA result indicates that interaction and operators did not affect measurement outcomes because the blue dots remain inside the acceptable range
Classification of Koilonychia, Beaus Lines, and Leukonychia based on Nail Image using Transfer Learning VGG-16
Full text linkHuman nail disease is usually ignored since it does not reveal clinical signs that are harmful to one's health. Nail disease, on the other hand, can be an early sign of a health issue. Some types of nail disease can cause infection, injury, or even the loss of the nail itself. It can reduce a person's aesthetics and beauty. Nail disease is very varied, so it is often difficult for clinicians to diagnose because several types have high similarities. Therefore, an automatic nail disease classification method based on nail photos was proposed in this study. The proposed method was based on the VGG-16 neural network architecture with an Adam optimizer. Nail diseases including Koilonychia, Beaus Lines, Leukonychia have been classified in this study. The model in this study is simulated in Python programming. The simulation results show that the highest classification accuracy is 96%, achieved with epoch-10. The transfer learning method based on a neural network simulated in this study is expected to support the clinical diagnosis of nail disease