IJEIS (Indonesian Journal of Electronics and Instrumentation Systems)
Not a member yet
300 research outputs found
Sort by
Sistem Deteksi Orang Jatuh Dengan Menggunakan Sensor Kamera Kinect Dengan Metode AdaBoost
Get PDFFall cases of elderly people aged 65 or above put their health at risk because it could lead to hip bone fracture, concussion, even death. Immediate help is needed if fall happened which is why an automatic and unobtrusive fall detection system is needed. There are three approaches in fall detection system; wearable, ambience, and vision-based. Wearable approach has the drawback of its obtrusive nature while ambience approach is prone to high false positive value. Vision-based approach is chosen because its unobtrusive nature and low false positive value. This study uses Kinect camera because of its ability on extracting skeletal data. The methods that are used in the fall detection system are AdaBoost method and joint velocity thresholding method. Thresholding method is used as a comparison to AdaBoost method. Both methods use skeletal data from the subject recorded by the Kinect camera. AdaBoost method compares the skeletal data with model that was made before while thresholding method compares the joint velocity value with the threshold value. System test is done using training data, test data, and real-time data. The average accuracy obtained from the system test with AdaBoost method is 91.75% and with thresholding method is 68.22%
Development of Automated "Hexagonal Obstacle Test" in Sports Agility Measurement
Get PDFThe measurement of agility in sports using the "hexagonal obstacle test" which used a stopwatch with human assistance as a tester is believed to be less objective. In general, this research aims to develop an agility measurement instrument "Hexagonal Obstacle Test" which is able to measure a person's agility electronically and more objectively. Specifically, this research aims to: (1) replace conventional agility measurement, because this measuring instrument will work electronically; (2) developing a hexagonal obstacle test that works electronically by utilizing Infrared (IR)/ Laser Diode and Real-Time Clock (RTC) technology so that it is processed by a microcontroller so that the test is carried out automatically; (3) developing a hexagonal obstacle test that is more modern, practical, effective, objective and efficient. This study uses a research and product development approach which consists of several steps, namely observation, planning and design, experimentation and testing, and analysis. The results of data analysis showed that the product validity value was 0.975146897 and the product reliability value was 0.995983936. We conclude that the hexagonal obstacle test automation product is valid and reliable for measuring agility
Klasifikasi Curah Hujan Menggunakan Neuro-Fuzzy System Melalui Citra Radar Cuaca
Get PDFRainfall intensity can be measured one of them through the reading of the reflectivity of raindrops on the weather radar. Reflectivity values are represented through colors in the visualization of two-dimensional radar images. Based on several approaches to the classification of weather conditions through radar data that has been successfully carried out, a system is designed to classify rainfall according to weather conditions in an area by utilizing weather radar imagery.The system implementation is carried out in several stages, namely pre-processing, feature extraction and labeling, and classification. Pre-processing is done to visualize radar data from Yogyakarta Climatology Station into a two-dimensional image. After capturing features using the RGB and HSV methods and labeling the rain class, classification is performed using the Neuro-fuzzy algorithm with the Adaptive Neuro-fuzzy Inference System (ANFIS) architecture. The results showed that the Neuro-fuzzy System algorithm was able to classify rainfall better on the RGB feature with an accuracy of 85.02% and a precision of 86.19%, while for the HSV feature the accuracy was 82.68%, 86.67% precision
Design of Medium Power AC-DC Flyback LED Driver
Get PDFLED lighting market share shows an ever increasing trend. This is driven by some of the LED advantages, such as higher efficiency, wide range of colors, and longer lifetime. LED is a DC device, and to power it from AC supply, like in household or street lightings, a driver is required to convert AC to DC supply. In addition, LED driver is preferred to operate in constant current mode in order to avoid LED thermal runaway. Also the driver has to have high efficiency, low THD (total harmonic distortion), and comply with electromagnetic emission limits. In this paper, a prototype of primary-side-regulated AC-DC flyback LED driver has been implemented. It has a constant output current of 0.990A 0.012A across the output voltage 15.59V – 42.80V. Measurement results show that the achieved efficiency is up to 88.55%, current harmonics comply with IEC 61000-3-2, and conducted emission levels comply with CISPR 15
Analisis Hasil Elektroforesis DNA dengan Image Processing Menggunakan Metode Gaussian Filter
Get PDFDNA gel electrophoresis plays an important role in the development of science. However, the process of manually analyzing DNA size is still relatively difficult, time-consuming, and often results an error. This study proposed electrophoresis process using image processing with Gaussian Filter method. Gaussian Filter is used to improve the quality of the image which makes the image clearer. The method was applied using python programming and then embedded into Raspberry pi 3 module. This modul processed images taken by Raspberry pi V1 camera. To realize these taken images, tracking mouse was used. All the images which had been processed were displayed on LCD touchscreen 5 inch. The result shows that the study using Gaussian Filter indicates good performance. This is proved by the lowest error percentage of 0,20% . In addition, compared to previous studies, the largest error percentage is still relatively smaller at 12.41%
Pendeteksian Lubang Pada Jalanan Menggunakan Metode SSD-MobileNet
Get PDFThe rapid advancement of technology following the number of potholes on the streets that need to be inspected have led people to develop technology that can inspect pothole using a detection system. Digital image processing is a method used by some people to detect potholes by using its colour as the main extracted feature, after that the field of machine learning and deep learning approaches have been studied and developed in terms of detection, one of which is the ssd-mobilenet. In this study three types of dataset were used, they were obtained secondarily from various sources, namely the normal dataset, the dashboard dataset, and the closeup dataset. These three datasets will also be combined and varied in the amount of the training data with an increment of 500 data train so that various model results are obtained. The results obtained are the detection bounding boxes and also the confusion matrix score of each model dataset, where the normal dataset gets an accuracy score of 56%, the dashboard dataset gets 50% and the closeup dataset gets 76%
Sistem Pendeteksi Viabilitas Benih Kacang Tanah Berdasarkan Luas Area HSV Color
Get PDFPeanut seed tetrazolium test evaluation is usually by eye and a microscope. This method has a weaknesses in the accuracy of reading the color intensity, and is more subjective. The seeds was observed one by one so that the observation is not effective. To make observations more accurate, efficient, and effective, digital image processing can be applied to the seed viability evaluation. The method can be used was the detection of the Hue, Saturation, and Value color area in reading the red color pattern resulting from tetrazolium test.The result is the system can detect a maximum of 25 seeds with an operational time of 22-25 seconds in one detection. Seed classification is the seeds are predicted to normal, abnormal, and dead. The process of classifying seeds is identified based on the red color pattern resulting from the detection of the area of 4 HSV color ranges, namely red (175,100,20:180,255,255), pink (160, 100,20 : 174,150,255), white 1 (175,0,0 : 180,100,255), and white 2 (0,0,0 : 100,255,255). The results show that the accuracy of the system in reading the total number of seeds is 100% with the detection error of HSV color area is 1.54%
Sistem Deteksi Kemurnian Minyak Goreng Dengan Menggunakan Metode Gelombang Ultrasonik
Get PDFBulk cooking oil is a food ingredient that is widely used by the public. The seller uses used bulk cooking oil to be mixed with new bulk cooking oil or even mixes it with harmful ingredients. Lab tests are needed to determine the quality of cooking oil, but the lab test requires a long time and can also damage the content of the cooking oil so it cannot be reused. The focus of this research is the creation of a system that can detect the purity of cooking oil by utilizing the wave velocity measurement method without damaging the shape and nature of the cooking oil.Wave velocity measurements are carried out by propagating ultrasonic waves on objects with a wave frequency of 40 kHz. The value of the duration of the wave propagation time at a distance of 19.4 cm is sampled and used for the calculation of wave velocity. The results of these wave velocity calculations are used to determine the purity level of cooking oil. Then the results of the purity level obtained were analyzed with an approach to the value of fluid viscosity. The results of the wave velocity values show that the waves propagate faster if the purity level of cooking oil is higher and produces a positive correlation with R2=0.9784. The results of the analysis conducted with the approach to fluid viscosity also showed a positive correlation with R2= 0.9999. The average wave velocity in pure bulk cooking oil is 1174.90 m/s
Analisa Karakteristik Single Board Computer sebagai Streaming Video Server
Get PDF Development in image processing is just not focused on the camera sensor and the software. Furthermore, the supporting tools has to be concerned. IP-based cameras are used widely today. Unfortunately, IP Camera has its own limitation. We cannot modificate the system as we want. This paper has introduced a system which has the same function of IP Camera but also can be modificate as we like. The system consists of Odroid XU4 and webcam as a streaming video server. Also, the test result is included in Local network which connected to 31 clients. The result shows that the video has 21,46 fps average on each client. The packet loss is only 1,20%. This means the system works properly and categorized as “very good”
Deteksi Kesalahan Pengucapan Huruf Jawa Carakan dengan Jaringan Syaraf Tiruan Perambatan Balik
Get PDFJavanese is an Indonesian culture which needs to be preserved, but many Javanese students make mistakes in the pronunciation of Javanese letters and find it difficult to analyze errors by human teachers because of the limited time and subjective assessment, so a system is needed to detect incorrect pronunciation of Javanese letters. Mispronunciation detection system has been widely applied in foreign languages, but the system has not been implemented for Javanese carakan letters. This research develops the Javanese letters mispronunciation detection system using Back-Propagation Artificial Neural Networks (BP-ANN). The dataset is obtained from the recorded pronunciation of hanacaraka texts by 24 speakers with 5 repetitions. ALNS method then used to automatically segment the signal into syllables. ANN-PB use statistical value of Mel-Frequency Cepstral Coefficient (MFCC) method with 7 and 14 coefficients. 10-Fold Cross Validation is used to validate and test the system. The Javanese mispronunciation detection using 7MFCC coefficients produces the highest accuracy of 80,07%. While the Javanese mispronunciation detection using 14 MFCC coefficients produces an accuracy of 82.36% at the highest