Claim Missing Document
Check
Articles

Comparison of resting electroencephalogram coherence in patients with mild cognitive impairment and normal elderly subjects Sugondo Hadiyoso; Inung Wijayanto; Suci Aulia
International Journal of Electrical and Computer Engineering (IJECE) Vol 12, No 2: April 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v12i2.pp1558-1564

Abstract

Mild cognitive impairment (MCI) was a condition beginning before more serious deterioration, leading to Alzheimer’s dementia (AD). MCI detection was needed to determine the patient's therapeutic management. Analysis of electroencephalogram (EEG) coherence is one of the modalities for MCI detection. Therefore, this study investigated the inter and intra-hemispheric coherence over 16 EEG channels in the frequency range of 1-30 Hz. The simulation results showed that most of the electrode pair coherence in MCI patients have decreased compared to normal elderly subjects. In inter hemisphere coherence, significant differences (p<0.05) were found in the FP1-FP2 electrode pairs. Meanwhile, significant differences (p<0.05) were found in almost all pre-frontal area connectivity of the intra-hemisphere coherence pairs. The electrode pairs were FP2-F4, FP2-T4, FP1-F3, FP1-F7, FP1-C3, FP1-T3, FP1-P3, FP1-T5, FP1-O1, F3-O1, and T3-T5. The decreased coherence in MCI patients showed the disconnection of cortical connections as a result of the death of the neurons. Furthermore, the coherence value can be used as a multimodal feature in normal elderly subjects and MCI. It is hoped that current studies may be considered for early detection of Alzheimer’s in a larger population.
Geometric and Grayscale Template Matching for Saudi Arabian Riyal Paper Currency Recognition Suci Aulia; Bagus Budhi L.; Angga Rusdinar; Yuyun Siti R.
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 6: December 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v8i6.pp4230-4238

Abstract

Detecting the authenticity of paper currencies using automated based Paper Currency Recognition (PCR) with image processing techniques was still a hot topic of discussion, due to the circulation of counterfeit currency that was still overwhelming in some countries. There was a downside along with this advancement in technology in the field of color printing, duplication, and scanning, because it was became one of the supporting factors of the increasing crime rate in production of counterfeit money. Our system has performed a PCR approach based on image processing techniques. In this study, the SAR banknote was the object to be recognized and detected its authenticity with the development of the previous method, which was incorporating the Geometric Template Matching and Grayscale Template Matching. In addition to the pattern recognition process, the classification process on 1 SAR, 2 SAR, 5 SAR, and 10 SAR was also performed. From PCR test up to 100 sample data, for each tested banknote value obtained the average value of the best accuracy level from incorporating GeoMatchingScore and GrayMatchingScore for the classification process was 95.25%. While the average level of system accuracy in recognizing counterfeit money on each banknote obtained a maximum value of 100%.
Hand gesture recognition using discrete wavelet transform and hidden Markov models Erizka Banuwati Candrasari; Ledya Novamizanti; Suci Aulia
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 5: October 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i5.13725

Abstract

Gesture recognition based on computer-vision is an important part of human-computer interaction. But it lacks in several points, that was image brightness, recognition time, and accuracy. Because of that goal of this research was to create a hand gesture recognition system that had good performances using discrete wavelet transform and hidden Markov models. The first process was pre-processing, which done by resizing the image to 128x128 pixels and then segmented the skin color. The second process was feature extraction using the discrete wavelet transform. The result was the feature value in the form of a feature vector from the image. The last process was gesture classification using hidden Markov models to calculate the highest probability of feature matrix which had obtained from the feature extraction process. The result of the system had 72% of accuracy using 150 training and 100 test data images that consist five gestures. The newness thing found in this experiment were the effect of acquisition and pre-processing. The accuracy had been escalated by 14% compared to Sebastien’s dataset at 58%. The increment effect propped by brightness and contrast value.
FPGA-based implementation of speech recognition for robocar control using MFCC Bayuaji Kurniadhani; Sugondo Hadiyoso; Suci Aulia; Rita Magdalena
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 4: August 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i4.12615

Abstract

This research proposes a simulation of the logic series of speech recognition on the MFCC (Mel Frequency Spread Spectrum) based FPGA and Euclidean Distance to control the robotic car motion. The speech known would be used as a command to operate the robotic car. MFCC in this study was used in the feature extraction process, while Euclidean distance was applied in the feature classification process of each speech that later would be forwarded to the part of decision to give the control logic in robotic motor. The test that has been conducted showed that the logic series designed was precise here by measuring the Mel Frequency Warping and Power Cepstrum. With the achievement of logic design in this research proven with a comparison between the Matlab computation and Xilinx simulation, it enables to facilitate the researchers to continue its implementation to FPGA hardware.
Automatic face and VLP’s recognition for smart parking system Reivind P. Persada; Suci Aulia; Burhanuddin D.; Sugondo H.
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 4: August 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i4.11746

Abstract

One of the concerning issues regarding smart city is Smart Parking. In Smart Parking, some researchers try to provide solutions and breakthroughs on several research topics among security systems, the availability of single space, an IoT framework, etc. In this study, we proposed a security system on Smart Parking based on face recognition and VLP’s (Vehicle License Plates) identification. In this research, SSIM (Structural Similarity) method as part of IQA has been applied due to its reliability and simple computation for face detection and recognition process. From the test results of 30 data, obtained the highest SSIM value 0.83 with the highest accuracy rate of 76.67%. That level of accuracy still has not reached the implementation standard of 99.9%. So that it still needs to be improved in the future studies, especially in the filtering noise section.
Hand gesture recognition using discrete wavelet transform and convolutional neural network Muhammad Biyan Priatama; Ledya Novamizanti; Suci Aulia; Erizka Banuwati Candrasari
Bulletin of Electrical Engineering and Informatics Vol 9, No 3: June 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (753.476 KB) | DOI: 10.11591/eei.v9i3.1977

Abstract

Public services are available to all communities including people with disabilities. One obstacle that impedes persons with disabilities from participating in various community activities and enjoying the various public services available to the community is information and communication barriers. One way to communicate with people with disabilities is with hand gestures. Therefore, the hand gesture technology is needed, in order to facilitate the public to interact with the disability. This study proposes a reliable hand gesture recognition system using the convolutional neural network method. The first step, carried out pre-processing, to separate the foreground and background. Then the foreground is transformed using the discrete wavelet transform (DWT) to take the most significant subband. The last step is image classification with convolutional neural network. The amount of training and test data used are 400 and 100 images repectively, containing five classes namely class A, B, C, # 5, and pointing. This study engendered a hand gesture recognition system that had an accuracy of 100% for dataset A and 90% for dataset B.
Multipoint to Point EKG Monitoring Berbasis ZigBee Sugondo Hadiyoso; Suci Aulia
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2014
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pada penelitian sebelumnya, telahdirealisasikan perangkat monitoring EKG berbasis Wifidan ZigBee namun masih bersifat point to point sehinggatidak dapat digunakan untuk memonitor banyak pasiendalam satu perangkat display. Sistem point to pointmenjadi tidak efisien ketika digunakan pada beberapapasien yang memerlukan pemantauan secara bersamaan.Oleh karena itu diperlukan konfigurasi multipoint to pointuntuk mengatasi permasalahan tersebut. Pada penelitianini telah direalisasikan suatu sistem monitoring EKG yangmengaplikasikan konfigurasi jaringan multipoint to pointmenggunakan perangkat ZigBee sebagai modultransceiver. Sebagai penelitian awal, direalisasikan sistemmonitoring untuk tiga (3) perangkat EKG pada sisi pasiendan satu perangkat penerima sebagai penampil data sinyalEKG. Sistem ini kita sebut 3 to 1 EKG monitoring system.Perangkat EKG pada proyek ini menggunakan tekniksadapan bipolar lead berbasis segitga Einthoven dengansadapan lead II sebagai standar monitoring EKG.
Safety Helmet Implementation with Centralized Information System on Remote Monitoring Applications Alvinas Deva Sih Illahi; Anatasya Bella; Sugondo Hadiyoso; Suci Aulia
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 9, No. 1 April 2018
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (460.92 KB) | DOI: 10.24843/LKJITI.2018.v09.i01.p01

Abstract

Personal Protective Equipment (PPE) is standard equipment that required to ensure safety of workers. PPE equipment that used during work such as: Safety helmet, safety glass, and ear plug. PPE that being used by workers doesn’t informative yet, only serve as personal protective so evacuation prevention still looks difficult to do prior accident happened. In this research, Safety Helmet Project has been implemented with pulse sensor, temperature sensor, carbon monoxide gas sensor, and transmission media which able transmitting data to control and monitoring center. The system also supports multiuser monitoring applications that can be accessed simultaneously through the internet network. Based on test results, the comparison of measurement gap with standard tool has been obtained as temperature sensor is 0,07%, heart sensor is ± 4%. Accuracy level for temperature sensor and heart rate are 99,67% and 95,45% by various condition of test. Another test is delay of the transmitting sensor data to the website around ± 10 seconds and controlling around ± 5 seconds.
SISTEM KEAMANAN BERBASIS ALARM IP CAMERA DENGAN PASSIVE INFRARED RECEIVER (PIR) SENSOR DAN SMS GATEWAY Hafiidh As Syahidulhaq; Hafiddudin Hafiddudin; Suci Aulia
Jurnal Elektro dan Telekomunikasi Terapan (e-Journal) Vol 3 No 2: JETT Desember (2016)
Publisher : Direktorat Penelitian dan Pengabdian Masyarakat, Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (700.306 KB) | DOI: 10.25124/jett.v3i2.300

Abstract

Penelitian mengenai security sytem sekarang ini sedang ramai diperbincangkan. Beberapa diantaranya adalah dengan menggunakan CCTV, dengan adanya rekaman CCTV ini sangat memudahkan bagi para penyelidik untuk mengetahui tindak kejahatan yang terjadi, namun penggunaan CCTV untuk merekam secara terus menerus selama waktu tertentu umtuk mendapat visualisasi kejadian yang lengkap membutuhkan kapasitas memori yang besar sehingga tidak efisien. Pada penelitian ini diimplementasikan sistem keamanan alarm CCTV network atau biasa disebut dengan Kamera IP dengan menggunakan PIR (Passive Infrared Receiver) sebagai sensor untuk mendeteksi gerak manusia sehingga CCTV hanya akan merekam pada saat terjadi pergerakan manusia dengan mendeteksi perubahan suhu disekitarnya, pada saat terdeteksi adanya pergerakan manusia yang tertangkap di kamera IP akan membunyikan alarm dan mengirimkan notifikasi pesan singkat ke ponsel genggam pemilik CCTV menggunakan SMS Gateway dan terekam oleh CCTV sehingga dapat dilihat melalui aplikasi pada smartphone atau PC. secara realtime. Penelitian dilakukan dengan cara memasang kamara IP dan SMS gateway di kamar kost dan PC serta smart pendeteksi dilakukan di kampus. Dari hasil pengukuran, sensor PIR dapat mendeteksi suhu dengan jarak terjauh 4 meter.Lamanya buzzer menyala adalah 50.67 detik. Apabila buzzer aktif, maka sms akan terkirim secara otomatis pada smartphone, adapun delay ratarata pengiriman notifikasi sms adalah 5.2 detik. Parameter QoS yang terukur yaitu,  packet loss sebesar 0,2%, delay 0,0038 second/packet, dan throughput sebesar 2,028 Mbit/sec.
PENGENALAN TULISAN TANGAN KARAKTER HIRAGANA MENGGUNAKAN DCT, DWT, DAN K-NEAREST NEIGHBOR Suci Aulia; Arif Setiawan
Jurnal Elektro dan Telekomunikasi Terapan (e-Journal) Vol 4 No 1: JETT Juli 2017
Publisher : Direktorat Penelitian dan Pengabdian Masyarakat, Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (4121.163 KB) | DOI: 10.25124/jett.v4i1.993

Abstract

Research to recognize hiraga na character based image processing has been widely practiced and even the accuracy level is close to 100%. However, the input image that used is still in the form of japanese characters print - out while the handwriting has not been studied. So in this stu dy tested the recognition of hiragana letters derived from handwriting format. Jpeg. Of the several related studies, the most commonly used compression approach for JPEG images is the DCT and DWT algorithms, so both algorithms are used in this study to be tested and compared their performance. In the system tested 45 images of 3 people handwriting hiragana character with KNN - based classification where previously 45 different images of the 3 people are trained by each DWT and DCT algorithms. The result is ba sed on the distance parameters that exist in the KNN algorithm, the DWT algorithm is superior to the DCT algorithm. The achievement of the maximum accuracy level obtained for each DWT - DCT algorithm is on the cityblock distance parameter 82.61% (DWT) and co rrelation distance 58.70% (DCT).