Dinsel, Emir Ali

Profile URL:
Job Title:Arş. Gör. Uzm.
Email Address:eadinsel@ktun.edu.tr
Main Affiliation:10.01. Department of Computer Engineering
Status: Current Staff
Website: https://www.ktun.edu.tr/tr/Universite/PersonelBilgi/?prsnl=dYNBkyjGvKpXazkCTm6PFgPD8XcAtKrycPjbS9UBFspAbQaCIjwgXvsm4zJ+TM/8JGuhvXabHBhWje2wR+jUgQ==
ORCID:ORCID Profile0000-0002-2180-5882
Scopus ID:Scopus Profile60645259200
YÖK Akademik: BB5EFDF9C456E64D
Web of Science ID:Web of Science ProfileQKZ-6101-2026
Name Variants:
Dinsel, E. Ali Dinsel, E. A.
Full item page
Author of Publication: search.filters.isAuthorOfPublication.1783d7a0-eaab-4f6c-ac75-834aa613694d

Scholarly Output Search Results

Now showing 1 - 2 of 2
  • Article
    A Lightweight and Robust Parallel CNN–LSTM Network with Random Crop Augmentation for Single-Lead Raw ECG Arrhythmia Classification
    (Elsevier B.V., 2026-07-01) Kodaz, Halife; Dinsel, Emir Ali
    Cardiovascular diseases remain one of the leading causes of mortality worldwide, creating a strong need for continuous and reliable electrocardiogram (ECG) monitoring systems. Although recent deep learning methods have achieved high arrhythmia classification accuracy, many of them are computationally demanding and less suitable for wearable or edge-oriented applications. In addition, single-lead ECG recordings may exhibit temporal misalignment, segment variability, and noise, which can reduce model robustness in practical monitoring scenarios. To address these challenges, this study proposes a lightweight parallel CNN-LSTM framework for raw single-lead ECG arrhythmia classification, together with a Random Crop augmentation strategy designed to improve robustness to temporal variability. The proposed method was evaluated on the MIT-BIH Arrhythmia Database and the INCART Database under an intra-patient 5-fold cross-validation protocol. Three classification settings were considered: MIT-BIH NSVFQ, MIT-BIH NLRAV, and INCART NSV. The proposed parallel CNN-LSTM consistently outperformed CNN-only and LSTM-only baselines across all tasks. It achieved 99.34% accuracy and 95.59% macro F1-score on MIT-BIH NSVFQ, 99.58% accuracy and 98.63% macro F1-score on MIT-BIH NLRAV, and 99.74% accuracy and 97.22% macro F1-score on INCART NSV. Additional ablation results showed that Random Crop generally improved performance when combined with CNN-based and parallel feature learning, while its effect on LSTM-only modeling was more limited and task-dependent. To further assess practical applicability, input-length sensitivity, class-wise confusion-matrix analysis, and noise robustness experiments were also performed. The results showed that the selected input lengths of 340 samples for MIT-BIH and 240 samples for INCART provide effective heartbeat-centered context, and that the proposed framework remains highly stable under mild-to-moderate Gaussian and EMG-like noise. Grad-CAM visualizations further indicated that the model primarily attends to clinically meaningful waveform regions, especially around the QRS complex and class-dependent morphological transitions. In addition to predictive performance, computational efficiency was analyzed in terms of parameter count, FLOPs, and inference latency. The proposed model contains 2,070,917 parameters for the MIT-BIH configuration and 1,865,603 parameters for the INCART configuration, while maintaining real-time inference capability with CPU runtime below 1 ms per beat in both settings. These findings suggest that the proposed framework provides an effective and computationally practical solution for intra-patient single-lead ECG arrhythmia classification in wearable monitoring scenarios.
  • Article
    A Lightweight 1D-CNN for Bark and Howl Classification from Raw Audio Waveforms Under Controlled Additive Noise
    (MDPI, 2026) Kodaz, Halife; Dinsel, Emir Ali
    Automatic classification of dog vocalizations can support bioacoustic monitoring and animal welfare, but many systems require spectral or cepstral preprocessing. This study evaluates a lightweight one-dimensional convolutional neural network (1D-CNN) for Bark and Howl classification directly from raw waveforms under controlled additive noise. The dataset comprised 46 Bark and 57 Howl recordings. Audio was converted to mono, resampled to 16 kHz, and standardized to 2.0 s. The network contains 7130 trainable parameters, occupies 27.85 KB with 32-bit weights, and requires 18.35 MFLOPs. The complete five-fold cross-validation procedure was repeated ten times with independently generated run-specific seeds and newly shuffled partitions. Under the no-added-noise condition, mean accuracy was 93.40 ± 2.62%, and macro F1-score was 93.20 ± 2.75%. Performance remained within run-to-run variability between 30 and 5 dB SNR for Gaussian and uniform additive noise, whereas mean accuracy decreased to 79.42% at 0 dB. In the seed-42 reference ablation, removing noise augmentation preserved no-added-noise accuracy but reduced 5 dB accuracy by approximately 20 percentage points. The findings provide preliminary recording-level evidence for efficient Bark and Howl classification under controlled conditions. Generalization to unseen dogs and field recordings remains unverified.
No research topics data found.

Sustainable Development Goals

SDG data is not available
Documents

2

Citations

0

h-index

0

Go to Scopus profile
Documents

2

Citations

0

Go to WoS profile
No records found in other affiliations.
JournalCount
Applied Sciences1
Engineering Science and Technology, an International Journal1
Current Page: 1 / 1
Scholarly Output

2

Articles

2

Views / Downloads

0/0

Supervised MSc Theses

0

Supervised PhD Theses

0

WoS Citation Count

0

Scopus Citation Count

0

Patents

0

Projects

0

WoS Citations per Publication

0.00

Scopus Citations per Publication

0.00

Open Access Source

2

Supervised Theses

0

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud