A. Enis Cetin

A. Enis Cetin

University of Illinois at Chicago

H-index: 55

North America-United States

About A. Enis Cetin

A. Enis Cetin, With an exceptional h-index of 55 and a recent h-index of 27 (since 2020), a distinguished researcher at University of Illinois at Chicago, specializes in the field of Signal processing, Image and Video Processing, Speech and Sound Processing, Biomedical signal and image processing, Wavelets.

His recent articles reflect a diverse array of research interests and contributions to the field:

The Blind Normalized Stein Variational Gradient Descent-Based Detection for Intelligent Massive Random Access

Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets

A Probabilistic Hadamard U-Net for MRI Bias Field Correction

Electroencephalogram Sensor Data Compression Using an Asymmetrical Sparse Autoencoder with a Discrete Cosine Transform Layer

Stein variational gradient descent-based detection for random access with preambles in mtc

Wildfire detection via transfer learning: a survey

Domain Generalization with fourier Transform and soft thresholding

A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression

A. Enis Cetin Information

University

University of Illinois at Chicago

Position

.

Citations(all)

11565

Citations(since 2020)

3763

Cited By

9538

hIndex(all)

55

hIndex(since 2020)

27

i10Index(all)

201

i10Index(since 2020)

97

Email

University Profile Page

University of Illinois at Chicago

A. Enis Cetin Skills & Research Interests

Signal processing

Image and Video Processing

Speech and Sound Processing

Biomedical signal and image processing

Wavelets

Top articles of A. Enis Cetin

The Blind Normalized Stein Variational Gradient Descent-Based Detection for Intelligent Massive Random Access

Authors

Xin Zhu,Ahmet Enis Cetin

Journal

arXiv preprint arXiv:2403.18846

Published Date

2024/3/8

The lack of an efficient preamble detection algorithm remains a challenge for solving preamble collision problems in intelligent massive random access (RA) in practical communication scenarios. To solve this problem, we present a novel early preamble detection scheme based on a maximum likelihood estimation (MLE) model at the first step of the grant-based RA procedure. A novel blind normalized Stein variational gradient descent (SVGD)-based detector is proposed to obtain an approximate solution to the MLE model. First, by exploring the relationship between the Hadamard transform and wavelet transform, a new modified Hadamard transform (MHT) is developed to separate high-frequencies from important components using the second-order derivative filter. Next, to eliminate noise and mitigate the vanishing gradients problem in the SVGD-based detectors, the block MHT layer is designed based on the MHT, scaling layer, soft-thresholding layer, inverse MHT and sparsity penalty. Then, the blind normalized SVGD algorithm is derived to perform preamble detection without prior knowledge of noise power and the number of active devices. The experimental results show the proposed block MHT layer outperforms other transform-based methods in terms of computation costs and denoising performance. Furthermore, with the assistance of the block MHT layer, the proposed blind normalized SVGD algorithm achieves a higher preamble detection accuracy and throughput than other state-of-the-art detection methods.

Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets

Authors

Hongyi Pan,Emadeldeen Hamdan,Xin Zhu,Salih Atici,Ahmet Enis Cetin

Journal

IEEE Transactions on Neural Networks and Learning Systems

Published Date

2024/4/22

In this article, we propose a set of transform-based neural network layers as an alternative to the $3\ttimes3$ Conv2D layers in convolutional neural networks (CNNs). The proposed layers can be implemented based on orthogonal transforms, such as the discrete cosine transform (DCT), Hadamard transform (HT), and biorthogonal block wavelet transform (BWT). Furthermore, by taking advantage of the convolution theorems, convolutional filtering operations are performed in the transform domain using elementwise multiplications. Trainable soft-thresholding layers, that remove noise in the transform domain, bring nonlinearity to the transform domain layers. Compared with the Conv2D layer, which is spatial-agnostic and channel-specific, the proposed layers are location-specific and channel-specific. Moreover, these proposed layers reduce the number of parameters and multiplications significantly while …

A Probabilistic Hadamard U-Net for MRI Bias Field Correction

Authors

Xin Zhu,Hongyi Pan,Yury Velichko,Adam B Murphy,Ashley Ross,Baris Turkbey,Ahmet Enis Cetin,Ulas Bagci

Journal

arXiv preprint arXiv:2403.05024

Published Date

2024/3/8

Magnetic field inhomogeneity correction remains a challenging task in MRI analysis. Most established techniques are designed for brain MRI by supposing that image intensities in the identical tissue follow a uniform distribution. Such an assumption cannot be easily applied to other organs, especially those that are small in size and heterogeneous in texture (large variations in intensity), such as the prostate. To address this problem, this paper proposes a probabilistic Hadamard U-Net (PHU-Net) for prostate MRI bias field correction. First, a novel Hadamard U-Net (HU-Net) is introduced to extract the low-frequency scalar field, multiplied by the original input to obtain the prototypical corrected image. HU-Net converts the input image from the time domain into the frequency domain via Hadamard transform. In the frequency domain, high-frequency components are eliminated using the trainable filter (scaling layer), hard-thresholding layer, and sparsity penalty. Next, a conditional variational autoencoder is used to encode possible bias field-corrected variants into a low-dimensional latent space. Random samples drawn from latent space are then incorporated with a prototypical corrected image to generate multiple plausible images. Experimental results demonstrate the effectiveness of PHU-Net in correcting bias-field in prostate MRI with a fast inference speed. It has also been shown that prostate MRI segmentation accuracy improves with the high-quality corrected images from PHU-Net. The code will be available in the final version of this manuscript.

Electroencephalogram Sensor Data Compression Using an Asymmetrical Sparse Autoencoder with a Discrete Cosine Transform Layer

Authors

Xin Zhu,Hongyi Pan,Shuaiang Rong,Ahmet Enis Cetin

Published Date

2024/4/14

Electroencephalogram (EEG) data compression is necessary for wireless recording applications to reduce the amount of data that needs to be transmitted. In this paper, an asymmetrical sparse autoencoder with a discrete cosine transform (DCT) layer is proposed to compress EEG signals. The encoder module of the autoencoder has a combination of a fully connected linear layer and the DCT layer to reduce redundant data using hard-thresholding nonlinearity. Furthermore, the DCT layer includes trainable hard-thresholding parameters and scaling layers to give emphasis or de-emphasis on individual DCT coefficients. Finally, the one-by-one convolutional layer generates the latent space. The sparsity penalty-based cost function is employed to keep the feature map as sparse as possible in the latent space. The latent space data is transmitted to the receiver. The decoder module of the autoencoder is designed …

Stein variational gradient descent-based detection for random access with preambles in mtc

Authors

Xin Zhu,Hongyi Pan,Salih Atici,Ahmet Enis Cetin

Published Date

2024/4/14

Traditional preamble detection algorithms have low accuracy in the grant-based random access scheme in massive machine-type communication (mMTC). We present a novel preamble detection algorithm based on Stein variational gradient descent (SVGD) at the second step of the random access procedure. It efficiently leverages deterministic updates of particles for continuous inference. To further enhance the performance of the SVGD detector, especially in a dense user scenario, we propose a normalized SVGD detector with momentum. It utilizes the momentum and a bias correction term to reduce the preamble estimation errors during the gradient descent process. Simulation results show that the proposed algorithm performs better than Markov Chain Monte Carlo-based approaches in terms of detection accuracy.

Wildfire detection via transfer learning: a survey

Authors

Ziliang Hong,Emadeldeen Hamdan,Yifei Zhao,Tianxiao Ye,Hongyi Pan,Ahmet Enis Cetin

Journal

Signal, Image and Video Processing

Published Date

2024/2

This paper presents a comprehensive survey of publicly available neural network models specifically designed for detecting wildfires using regular visible-range cameras positioned on hilltops or forest lookout towers. The surveyed models are first pre-trained on the ImageNet-1K dataset and then fine-tuned on a custom wildfire dataset to enhance their performance. Evaluations are conducted on diverse wildfire images, enabling a thorough assessment of their capabilities. The survey findings provide valuable insights for individuals interested in leveraging transfer learning techniques for wildfire detection. Among the examined models, Swin Transformer-tiny achieves the highest area under the curve value, indicating strong overall performance in distinguishing wildfire events. However, ConvNext-tiny stands out for its exceptional ability to detect all instances of wildfires while maintaining the lowest false alarm rate …

Domain Generalization with fourier Transform and soft thresholding

Authors

Hongyi Pan,Bin Wang,Zheyuan Zhang,Xin Zhu,Debesh Jha,Ahmet Enis Cetin,Concetto Spampinato,Ulas Bagci

Published Date

2024/4/14

Domain generalization aims to train models on multiple source domains so that they can generalize well to unseen target domains. Among many domain generalization methods, Fourier-transformbased domain generalization methods have gained popularity primarily because they exploit the power of Fourier transformation to capture essential patterns and regularities in the data, making the model more robust to domain shifts. The mainstream Fouriertransform-based domain generalization swaps the Fourier amplitude spectrum while preserving the phase spectrum between the source and the target images. However, it neglects background interference in the amplitude spectrum. To overcome this limitation, we introduce a soft-thresholding function in the Fourier domain. We apply this newly designed algorithm to retinal fundus image segmentation, which is important for diagnosing ocular diseases but the neural …

A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression

Authors

Xin Zhu,Daoguang Yang,Hongyi Pan,Hamid Reza Karimi,Didem Ozevin,Ahmet Enis Cetin

Journal

Engineering Applications of Artificial Intelligence

Published Date

2024/1/1

The lack of an efficient compression model remains a challenge for the wireless transmission of gearbox data in non-contact gear fault diagnosis problems. In this paper, we present a signal-adaptive asymmetrical autoencoder with a transform domain layer to compress sensor signals. First, a new discrete cosine Stockwell transform (DCST) layer is introduced to replace linear layers in a multi-layer autoencoder. A trainable filter is implemented in the DCST domain by utilizing the multiplication property of the convolution. A trainable hard-thresholding layer is applied to reduce redundant data in the DCST layer to make the feature map sparse. In comparison to the linear layer, the DCST layer reduces the number of trainable parameters and improves the accuracy of data reconstruction. Second, training the autoencoder with a sparsifying DCST layer only requires a small number of datasets. The proposed method is …

Adc/dac-free analog acceleration of deep neural networks with frequency transformation

Authors

Nastaran Darabi,Maeesha Binte Hashem,Hongyi Pan,Ahmet Cetin,Wilfred Gomes,Amit Ranjan Trivedi

Journal

IEEE Transactions on Very Large Scale Integration (VLSI) Systems

Published Date

2024/3/18

The edge processing of deep neural networks (DNNs) is becoming increasingly important due to its ability to extract valuable information directly at the data source to minimize latency and energy consumption. Although pruning techniques are commonly used to reduce model size for edge computing, they have certain limitations. Frequency-domain model compression, such as with the Walsh–Hadamard transform (WHT), has been identified as an efficient alternative. However, the benefits of frequency-domain processing are often offset by the increased multiply-accumulate (MAC) operations required. This article proposes a novel approach to an energy-efficient acceleration of frequency-domain neural networks by utilizing analog-domain frequency-based tensor transformations. Our approach offers unique opportunities to enhance computational efficiency, resulting in several high-level advantages, including array …

A hybrid quantum-classical approach based on the hadamard transform for the convolutional layer

Authors

Hongyi Pan,Xin Zhu,Salih Furkan Atici,Ahmet Cetin

Published Date

2023/7/3

In this paper, we propose a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing. It implements the regular convolutional layers in the Hadamard transform domain. The idea is based on the HT convolution theorem which states that the dyadic convolution between two vectors is equivalent to the element-wise multiplication of their HT representation. Computing the HT is simply the application of a Hadamard gate to each qubit individually, so the HT computations of our proposed layer can be implemented on a quantum computer. Compared to the regular Conv2D layer, the proposed HT-perceptron layer is computationally more efficient. Compared to a CNN with the same number of trainable parameters and 99.26% test accuracy, our HT network reaches 99.31% test accuracy with 57.1% MACs reduced in the MNIST dataset; and in our ImageNet-1K experiments, our HT-based ResNet-50 exceeds the accuracy of the baseline ResNet-50 by 0.59% center-crop top-1 accuracy using 11.5% fewer parameters with 12.6% fewer MACs.

0537 incident hypertension prediction in obstructive sleep apnea using machine learning

Authors

Omid Halimi Milani,Tu Nguyen,Ankit Parekh,Ahmet Enis Cetin,Bharati Prasad

Journal

Sleep

Published Date

2023/5/1

Introduction Obstructive sleep apnea (OSA) is associated with hypertension due to intermittent hypoxia and sleep fragmentation. Due to the complex pathogenesis of hypertension, it is difficult to predict incident hypertension associated with OSA. A Machine Learning (ML) model to predict incident hypertension identified up to five years after the diagnosis of OSA by polysomnography developed. Methods Polysomnography provides time-series data on multiple physiological signals. We used the sleep heart health study (SHHS) cohort, where 4,797 participants had OSA. After excluding participants with pre-existing hypertension at baseline, the sample size was 2,652. 1,814 participants with follow-up data at 5 years were included (911/1,814, 50% with incident hypertension). In addition to clinical data (i.e. age and race), features extracted from polysomnography (heart rate …

IIHP: Intelligent Incident Hypertension Prediction in Obstructive Sleep Apnea

Authors

Omid Halimi Milani,Ahmet Enis Cetin,Prasad Bharati

Journal

bioRxiv

Published Date

2023

Obstructive sleep apnea (OSA) increases the risk of hypertension, mainly attributed to intermittent hypoxia and sleep fragmentation. Given the multifaceted pathogenesis of hypertension, accurately predicting incident hypertension in individuals with OSA has posed a considerable challenge. In this study, we leveraged Machine Learning (ML) techniques to develop a predictive model for incident hypertension up to five years after OSA diagnosis by polysomnography. We used data from the Sleep Heart Health Study (SHHS), which included 4,797 participants diagnosed with OSA. After excluding those with pre-existing hypertension and Apnea Hypopnea Index (AHI) values below 21 per hour, we had 671 participants with five-year follow-up data. We adopted two distinct methodologies. We first implemented adaptive convolution layers to extract features from the signals and combined them into a 2D array. The 2D array was further processed by a 2D pre-trained neural network to take advantage of transfer learning. Subsequently, we delved into feature extraction from full-length signals across various temporal frames, resulting in a 2D feature array. We studied the use of various 2D networks such as MobileNet, EfficientNet, and a family of RESNETs. The best algorithm achieved an average area under the curve of 72%. These results suggest a promising approach for predicting the risk of incident hypertension in individuals with OSA, providing tools for practice and public health initiatives.

AggregateNet: A deep learning model for automated classification of cervical vertebrae maturation stages

Authors

Salih Furkan Atici,Rashid Ansari,Veerasathpurush Allareddy,Omar Suhaym,Ahmet Enis Cetin,Mohammed H Elnagar

Journal

Orthodontics & Craniofacial Research

Published Date

2023/12

Objective A study of supervised automated classification of the cervical vertebrae maturation (CVM) stages using deep learning (DL) network is presented. A parallel structured deep convolutional neural network (CNN) with a pre‐processing layer that takes X‐ray images and the age as the input is proposed. Methods A total of 1018 cephalometric radiographs were labelled and classified according to the CVM stages. The images were separated according to gender for better model‐fitting. The images were cropped to extract the cervical vertebrae automatically using an object detector. The resulting images and the age inputs were used to train the proposed DL model: AggregateNet with a set of tunable directional edge enhancers. After the features of the images were extracted, the age input was concatenated to the output feature vector. To have the parallel network not overfit, data augmentation was used. The …

Classification of the Cervical Vertebrae Maturation (CVM) Stages Using the Tripod Network

Authors

Salih Atici,Hongyi Pan,Mohammed H Elnagar,Veerasathpurush Allareddy,Omar Suhaym,Rashid Ansari,Ahmet Enis Cetin

Published Date

2023/6/4

We present a novel deep learning method for fully automated detection and classification of the Cervical Vertebrae Maturation (CVM) stages. The deep convolutional neural network consists of three parallel networks (TriPodNet) independently trained with different initialization parameters. They also have a built-in set of novel directional filters that highlight the Cervical Vertebrae edges in X-ray images. Outputs of the three parallel networks are combined using a fully connected layer. 1018 cephalometric radiographs were labeled, divided by gender, and classified according to the CVM stages. Resulting images, using different training techniques and patches, were used to train TripodNet together with a set of tunable directional edge enhancers. Data augmentation is implemented to avoid overfitting. TripodNet achieves the state-of-the-art accuracy of 81.18% in female patients and 75.32% in male patients. The …

Robust Array Signal Processing Using L1-Kernel-Based Principal Component Analysis

Authors

Hongyi Pan,Erdem Koyuncu,Ahmet Enis Cetin

Published Date

2023/10/9

In this paper, we present a set of efficient dimensionality reduction methods for array signal processing using Kernel-based multiplication-free PCA ( -MF-PCA) techniques. Our proposed -MF-PCA methods utilize -norm kernels, which enhance the robustness of the approach compared to classical -PCA. Additionally, we demonstrate that the MF-PCA methods are energy-efficient, reducing the number of multiplication operations significantly. Multiplication operations are known to be costly in terms of energy consumption in many processors. Furthermore, we extend the -MF - PCA methods into the complex-valued versions for the direction of arrival (DOA) estimation task. We experimentally show that the proposed methods are robust to outliers and outperform traditional approaches in terms of accuracy and efficiency. Our results demonstrate the potential of the proposed -MF - PCA methods …

Hybrid Binary Neural Networks: A Tutorial Review

Authors

Ahmet Enis Cetin,Hongyi Pan

Published Date

2023/4/24

In this article, we review neural networks which have neurons with binary operations or networks that use binary transforms such as the Walsh-Hadamard transform (WHT). Neural networks with binary neurons or binary layers can be used in edge applications and/or applications requiring energy-efficient decision-making. WHT-based network is as accurate as the regular neural networks in the CIFAR-10 and the Tiny ImageNet image databases.

Real-time wireless ecg-derived respiration rate estimation using an autoencoder with a dct layer

Authors

Hongyi Pan,Xin Zhu,Zhilu Ye,Pai-Yen Chen,Ahmet Enis Cetin

Published Date

2023/6/4

In this paper, we present a wireless ECG-derived Respiration Rate (RR) estimation using an autoencoder with a DCT Layer. The wireless wearable system records the ECG data of the subject and the respiration rate is determined from the variations in the baseline level of the ECG data. A straightforward Fourier analysis of the ECG data obtained using the wireless wearable system may lead to incorrect results due to uneven breathing. To improve the estimation precision, we propose a neural network that uses a novel Discrete Cosine Transform (DCT) layer to denoise and decorrelates the data. The DCT layer has trainable weights and soft-thresholds in the transform domain. In our dataset, we improve the Mean Squared Error (MSE) and Mean Absolute Error (MAE) of the Fourier analysis-based approach using our novel neural network with the DCT layer.

Electromagnetically unclonable functions generated by non-Hermitian absorber-emitter

Authors

Minye Yang,Zhilu Ye,Hongyi Pan,Mohamed Farhat,Ahmet Enis Cetin,Pai-Yen Chen

Journal

Science Advances

Published Date

2023/9/8

Physically unclonable functions (PUFs) are a class of hardware-specific security primitives based on secret keys extracted from integrated circuits, which can protect important information against cyberattacks and reverse engineering. Here, we put forward an emerging type of PUF in the electromagnetic domain by virtue of the self-dual absorber-emitter singularity that uniquely exists in the non-Hermitian parity-time (PT)–symmetric structures. At this self-dual singular point, the reconfigurable emissive and absorptive properties with order-of-magnitude differences in scattered power can respond sensitively to admittance or phase perturbations caused by, for example, manufacturing imperfectness. Consequently, the entropy sourced from inevitable manufacturing variations can be amplified, yielding excellent PUF security metrics in terms of randomness and uniqueness. We show that this electromagnetic PUF can be …

High-resolution time-frequency representation with generative adversarial networks

Authors

Zeynel Deprem,A Enis Cetin

Journal

Signal, Image and Video Processing

Published Date

2023/4

Signal representation in time-frequency (TF) domain is valuable in many applications including radar imaging and inverse synthetic aperture radar. TF representation allows us to identify signal components or features in a mixed time and frequency plane. There are several well-known tools, such as Wigner–Ville Distribution (WVD), short-time Fourier transform and various other variants for such a purpose. The main requirement for a TF representation tool is to give a high-resolution view of the signal such that the signal components or features are identifiable. A commonly used method is the reassignment process which reduces the cross-terms by artificially moving smoothed WVD values from their actual location to the center of the gravity for that region. In this article, we propose a novel reassignment method using the conditional generative adversarial network (CGAN). We train a CGAN to perform the …

GazeGNN: A Gaze-Guided Graph Neural Network for Disease Classification

Authors

Bin Wang,Hongyi Pan,Armstrong Aboah,Zheyuan Zhang,Ahmet Cetin,Drew Torigian,Baris Turkbey,Elizabeth Krupinski,Jayaram Udupa,Ulas Bagci

Journal

arXiv preprint arXiv:2305.18221

Published Date

2023/5/29

The application of eye-tracking techniques in medical image analysis has become increasingly popular in recent years. It collects the visual search patterns of the domain experts, containing much important information about health and disease. Therefore, how to efficiently integrate radiologists' gaze patterns into the diagnostic analysis turns into a critical question. Existing works usually transform gaze information into visual attention maps (VAMs) to supervise the learning process. However, this time-consuming procedure makes it difficult to develop end-to-end algorithms. In this work, we propose a novel gaze-guided graph neural network (GNN), GazeGNN, to perform disease classification from medical scans. In GazeGNN, we create a unified representation graph that models both the image and gaze pattern information. Hence, the eye-gaze information is directly utilized without being converted into VAMs. With this benefit, we develop a real-time, real-world, end-to-end disease classification algorithm for the first time and avoid the noise and time consumption introduced during the VAM preparation. To our best knowledge, GazeGNN is the first work that adopts GNN to integrate image and eye-gaze data. Our experiments on the public chest X-ray dataset show that our proposed method exhibits the best classification performance compared to existing methods.

See List of Professors in A. Enis Cetin University(University of Illinois at Chicago)

A. Enis Cetin FAQs

What is A. Enis Cetin's h-index at University of Illinois at Chicago?

The h-index of A. Enis Cetin has been 27 since 2020 and 55 in total.

What are A. Enis Cetin's top articles?

The articles with the titles of

The Blind Normalized Stein Variational Gradient Descent-Based Detection for Intelligent Massive Random Access

Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets

A Probabilistic Hadamard U-Net for MRI Bias Field Correction

Electroencephalogram Sensor Data Compression Using an Asymmetrical Sparse Autoencoder with a Discrete Cosine Transform Layer

Stein variational gradient descent-based detection for random access with preambles in mtc

Wildfire detection via transfer learning: a survey

Domain Generalization with fourier Transform and soft thresholding

A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression

...

are the top articles of A. Enis Cetin at University of Illinois at Chicago.

What are A. Enis Cetin's research interests?

The research interests of A. Enis Cetin are: Signal processing, Image and Video Processing, Speech and Sound Processing, Biomedical signal and image processing, Wavelets

What is A. Enis Cetin's total number of citations?

A. Enis Cetin has 11,565 citations in total.

What are the co-authors of A. Enis Cetin?

The co-authors of A. Enis Cetin are Metin N. Gurcan, Orhan Arikan, Rengul Cetin Atalay, Omer Nezih Gerek, Uğur Güdükbay, Behçet Uğur Töreyin.

    Co-Authors

    H-index: 43
    Metin N. Gurcan

    Metin N. Gurcan

    Wake Forest University

    H-index: 37
    Orhan Arikan

    Orhan Arikan

    Bilkent Üniversitesi

    H-index: 37
    Rengul Cetin Atalay

    Rengul Cetin Atalay

    Orta Dogu Teknik Üniversitesi

    H-index: 29
    Omer Nezih Gerek

    Omer Nezih Gerek

    Anadolu Üniversitesi

    H-index: 29
    Uğur Güdükbay

    Uğur Güdükbay

    Bilkent Üniversitesi

    H-index: 25
    Behçet Uğur Töreyin

    Behçet Uğur Töreyin

    Istanbul Teknik Üniversitesi

    academic-engine

    Useful Links