Harun Sumbul

Harun Sumbul


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2020 in IRBM
Verified
Journal Article
Closed access
AYA.H. Yüzer
A.H. Yüzer
HSHarun Sumbul
Harun Sumbul
Kemal PolatKemal Polat
Kemal Polat

14 January 2022 in Medical & Biological Engineering & Computing
Verified
Journal Article
Closed access
PDF file
HSHarun Sumbul
Harun Sumbul
AYAhmet Hayrettin Yüzer
Ahmet Hayrettin Yüzer
KSKazim Sekeroglu,
Kazim Sekeroglu,

22 August 2024 in IEEE Access
Verified
Journal Article
Open access
HSHarun Sumbul
Harun Sumbul
This article presents a wearable glove mounted flex sensors and a MEMS-based accelerometer array for detecting hand movements to sign language recognition. The functionality and performance of the glove were extensively evaluated for repeatability across different hand gestures (numbers 1-5 and 10 American Sign Language figures) while obtaining real-time raw data. The multilayer perceptron feed-forward neural network (MLPFFNN) was chosen as the specific artificial neural network (ANN) algorithm to determine the gestures. To create a comprehensive database of hand movements, both flex sensor and accelerometer data were used to generate PWM values, which served as input to the model. A total of 5204 data points, including acceleration (ACC) and flex sensor values, were recorded for model training and movement detection (with 75% of the data used for training and 25% for testing). The predicted values of the model were compared with the actual values and analyzed statistically. The output data from the model were then transferred to a developed robotic hand platform to test the accuracy, and the movements were observed. It was found that the original hand movements and the model-generated robotic hand movements were quite similar. When compared with existing methods, the proposed method was observed to improve the accuracy of sign language recognition and enhance the tracking of hand movements. This article presents statistical results with a classification accuracy of 99.67% based on measured test data for various recognition scenarios.

1 November 2015
Verified
Conference Paper
Closed access
HSHarun Sumbul
Harun Sumbul
AYA. Hayrettin Yuzer
A. Hayrettin Yuzer
With the development of technology, in the diagnosis of many diseases, electrical signals measured from different points on the human body, offered to doctors by making meaningful with the help of different algorithms. This is quite important for both safer for the patient to be diagnosed more quickly. This paper presents a data acquisition system which has ability to measure and record the movement of diaphragm. The developed measuring device was connected on the five patients whose have different features (age, tall, weight) and the diaphragm movements were monitored. It is showed that the shape of recorded data by the developed system is similar to shape of recorded data by using industrial spirometer instrument. Besides breathing signal, some parameters (FVC, TVC) that play an important role in the detection of some diseases such as COPD also has been obtained and shared at the measurement results section. As a results, our developed system seems to measure and record the breathing movements and some respiratory parameters with great reliability and inexpensive, portable, easy to use.

31 July 2021 in Demiryolu Mühendisliği
Verified
Journal Article
Closed access
PDF file
HSHarun Sumbul
Harun Sumbul
ABAhmet Bogrek
Ahmet Bogrek
ATAbdurrahman Tunçer
Abdurrahman Tunçer
Bu çalışmada, demiryollarında güvenli yolculuk için deray anını tespit ederek makiniste bilgi veren bir sistemin kavramsal tasarımı gerçekleştirilmiş olup sistem aynı zamanda bir bilgisayar programı ile simüle edilmiştir. Buna göre bir elektronik devre çizim programı (Proteus ISIS Labcenter Electronics 7.7 SP2) yardımı ile kavramsal tasarıma ait bir devre çizilmiştir. Devre üzerinde, treni temsilen sinyal üreteci; titreşimlerin ve kapasitif değerlerin algılandığını temsil eden butonlar, alınan sinyallerin yükseltildiği opamplı yükselteç devresi, iki algılayıcıdan da alınan verilere göre makiniste bilgi gönderilmesine karar verecek olan bir karşılaştırıcı (VE kapısı), sinyallerin izlendiği dijital osiloskop ve deray algılandığında makinist uyarımında kullanılacak sesli/ışıklı uyarım sistemi (buzzer) bulunmaktadır. Demiryolu titreşimleri ve oluşan frekans aralıkları için ilgili literatür göz önüne alınarak simülasyon devresinde sinyal üreteci frekansı 1,5KHz ve genliği ise 5v üçgen dalga DC şeklinde ayarlanmıştır. Eşik değer olarak 2.5v seçilmiştir. Buna göre karşılaştırıcı çıkışındaki değer, her iki algılayıcıdan da bilgi alındığı anda aktif olmuştur. Simülasyona göre deray 300 ms sürmüş ve 1/3 saniye gibi kısa bir sürede tespit edilerek çıkış birimleri aktif edilmiştir. Simülasyon sonuçlarına göre önerilen kavramsal modelin gerçek hayatta başarılı bir şekilde kullanılabileceği ve böylece deray kaynaklı tren kazalarının önüne geçebileceği öngörülmüştür. Bunun neticesi olarak da ölümlü / yaralanmalı / maddi kayıplı kazaları engellenerek ülkemize tren ile güven ile ulaşım konusunda yeni bir literatür kazandırılacağına inanılmaktadır.

27 July 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
HSHarun Sumbul
Harun Sumbul
AYAhmet Hayrettin Yüzer
Ahmet Hayrettin Yüzer