Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)

Deteksi Puncak Amplitudo dan Durasi Gelombang QRS Elektrokardiogram Menggunakan Discrete Data Setiawidayat Sabar; Aviv Yuniar Rahman; Ratna Hidayati
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 3 (2020): Juni 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (858.697 KB) | DOI: 10.29207/resti.v4i3.1658

Abstract

In each cycle of the Heart on the Electrocardiogram there are generally P waves as a presentation of Atrial Muscle Depolarization, QRS waves as a presentation of Ventricular Muscle Depolarization and T waves as a presentation of Ventricular Muscle Repolarization. Some types of electrocardiographs only represent wave morphology and some other types of electrocardiographs are equipped with duration and amplitude information but are limited. This limitation of information is calculated manually using small boxes on ecg paper measuring 40 ms for duration and 1 mV for amplitude. The consequences of this manual calculation will require time and accuracy of the calculation results. This study aims to obtain the QRS wave duration along with the amplitude value in each cycle of cardiac examination results. Discrete data from the sampling results of the ECG continuous signal in the maximum filter amplitude to get peak R values. The position of integer peak R with the next peak R is the duration of the cycle. PQRST algorithm is used to obtain peak Q and peak S, so the duration of QS can be obtained by subtracting the position of integer peak S with integer position Q. 10 samples of discrete ecg Sinus Rhythm data from Physionet and 5 samples from ECG-UWG were used in this study. The results showed that all sample data in 3 cycles had a value of QRS duration and peak amplitude values ​​Q, R and S. Peak amplitude R max values ​​and R min physionet sample records were obtained in record 16273 which was 3,485 mV and record 16795 was 0.805 mV. The QRS duration for Bradicardia and Tachicardia is shown in record 16483 which is 40 ms and record 17052 which is 144 ms.
Pengurangan Noise Pada RTL-SDR Menggunakan Least Mean Square Dan Recursive Least Square Aviv Yuniar Rahman; Mamba’us Sa’adah; Istiadi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 2 (2020): April 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1828.55 KB) | DOI: 10.29207/resti.v4i2.1667

Abstract

Noise reduction is an important process in a communication system, one of which is radio communication. In the process of broadcasting radio Frequency Modulation (FM) often encountered noise so that listeners find it difficult to understand the information provided. In the past, noise reduction used traditional filters that were only able to filter certain frequencies. However, for future technologies an adaptive filter is needed that can dynamically reduce noise effectively. Register Level-Software Defined Radio (RTL-SDR) can capture signals with a very wide frequency range but has a less clear sound quality. So it needs to be done noise reduction. In this study, two methods are used, namely Least Mean Square (LMS) and Recursive Least Square (RLS). The data used five radio stations in Malang. The results showed that the LMS algorithm is stable but has a slow convergence speed, whereas the RLS algorithm has poor stability but has a high convergence speed. From the test, it can be concluded that the performance of RLS is better than LMS for noise reduction in RTL-SDR. The best performance is the reduction of White Noise using RLS on the Oryza radio station with an Normalized Weight Differences (NWD) value of -13.93 dB.
Klasifikasi Citra Burung Lovebird Menggunakan Decision Tree dengan Empat Jenis Evaluasi Aviv Yuniar Rahman
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 4 (2021): Agustus 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (445.559 KB) | DOI: 10.29207/resti.v5i4.3210

Abstract

Lovebird is a pet that many people in Indonesia have known. The diversity of species, coat color, and body shape gives it its charm. As well in this lovebird bird has its uniqueness of various rare colors. However, many ordinary people have difficulty distinguishing the types of lovebirds. This research is needed to improve previous study performance in classifying lovebird images using the Decision Tree J48 algorithm with 4 types of evaluation. In this case, also to reduce the stage of feature extraction to speed up the computational process. Based on available comparisons, the results obtained at the same split ratio with a comparison of 60:40 in Decision Tree J48 have the precision of 1,000, recall of 1,000, f-measure of 1,000, and accuracy value of 100%. Then the Artificial Neural Network with a split ratio of 60:40 has a precision of 0.854, recall of 0.843, f-measurement of 0.841, and an accuracy value of 84.25%. These results prove that by testing the first-level extraction on color features, Decision Tree J48 is superior in classifying images of lovebird species, and Decision Tree J48 can improve performance and produce the best accuracy.
Klasifikasi Kualitas Biji Kopi Menggunakan MultilayerPerceptron Berbasis Fitur Warna LCH Ilhamsyah Ilhamsyah; Aviv Yuniar Rahman; Istiadi Istiadi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 6 (2021): Desember 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (509.835 KB) | DOI: 10.29207/resti.v5i6.3438

Abstract

Coffee is one of Indonesia's foreign exchange earners and plays an important role in the development of the plantation industry. In previous studies, coffee bean quality research has been carried out using the ANN method using color features. RGB and GLCM. However, the results carried out in the study only had an accuracy value of up to 47%. Therefore, this study aims to improve the performance of coffee bean quality classification using four machine learning methods and 7 color features. From the results obtained, it shows that MultilayerPerceptron is better starting with RGB color with an accuracy of 38% split ratio 90:10. HSV has an accuracy of 57% split ratio 90:10. CMYK has an accuracy of 63% split ratio 90:10. LAB has a 58% curation split ratio of 90:10. The YUV type has an accuracy of 58% split ratio 90:10. Furthermore, the HSI color type has an accuracy of 42% split ratio 90:10. The HCL color type has an accuracy of 65% split ratio 90:10 and LCH has an accuracy of 78% split ratio 90:10. In testing, it can be concluded that the MultilayerPerceptron method is better than other methods for the coffee bean classification process.
Temu Kembali Kemiripan Motif Citra Tenun Menggunakan Transformasi Wavelet Diskrit Dan GLCM Anderias Bai Seran; Aviv Yuniar Rahman; Istiadi Istiadi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 5 (2021): Oktober2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (559.458 KB) | DOI: 10.29207/resti.v5i5.3484

Abstract

Indonesia is a country with cultural diversity. One of the famous cultural heritages in Indonesia is Woven Fabrics. East Nusa Tenggara Province, especially South Central Timor, is an area that also produces weaving. There are 3 types of woven fabric motifs, namely the Buna, Lotis, and Futus motifs which were inherited from their ancestors. Woven cloth is unique because it is made through a ritual process and is used for traditional ceremonies, weddings, funerals, and so on. However, along with the development of technology, ordinary people increasingly forget the motifs of woven fabrics and have difficulty distinguishing the motifs. The function of this research is to improve the performance of previous studies in the process of finding the similarity of weaving image motifs using discrete wavelet transforms and GLCM. The results are known, calculations using a confusion matrix on discrete wavelet transformation feature extraction and GLCM, comparisons on discrete wavelet transformations produce an accuracy rate of 70% Minkowski matrix, 60% Manhattan matrix, 60% Canberra matrix, 20% Euclidean matrix. Comparison of feature extraction calculations on GLCM produces an average quality of the Minkowski matrix of 90% and the lowest level of accuracy on the Euclidean, Manhattan, and Canberra matrices of 80%.