Sami Arica
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sami Arica has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Ahmed H. Tewfik
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, USA
5 shared publications- Ahmed H. Tewfik
Department of Electrical & Computer Engineering, University of Minnesota, Minneapolis, MN 55455, USA
4 shared publications N.F. Ince
Dept. of Electr. & Electron. Eng., Cukurova Univ., Turkey
4 shared publications- Nuri Firat Ince
University of Minnesota Twin Cities, Electrical & Computer Engineering, 4–174 Keller Hall, 200 Union St SE, Minneapolis, MN 55455, USA
4 shared publications A. Tewfik
3 shared publicationsNuri F. Ince
Brain Sciences Center, VA Health Care System, Minneapolis, Minnesota, United States of America
3 shared publications
Latest Publications
- 20 January 2025
- Published by Turkish Journal of Engineering in Turkish Journal of Engineering
- Vol. 9 (1) , 1-11
Application of Convolutional Neural Networks for Watermelon Detection in UAV Aerial Images: A Case Study
Although human dependence on agriculture decreases with developing technology, it continues. As many resources are increasingly restricted due to various climatic reasons, the importance of studies in this field increases. Applications using deep learning models are frequently encountered in the agricultural field. In particular, there are applications where deep learning models are used as a tool for optimum planting, land use, yield improvement, production/disease/pest control, and other activities.In this study, watermelons in an aerial view of a watermelon field were detected by utilizing the Alexnet deep learning architecture. To obtain yield, watermelons in watermelon fields should be specified and then counted. Aerial images are used for this application. The field image was divided into 50% overlapping sub-images, and each was classified as watermelon, leaf, and soil. Consequently, watermelon regions on the field image were specified. After training the Alexnet and Vgg19 network structure with the dataset, watermelons were to be identified by segmenting the images. It was observed that the Vgg19 network achieved 97.78% accuracy. The results of the experimental applications show that the Vgg19 can be applied for watermelon fruit and yield detection applications.
- 20 January 2025
- Published by Turkish Journal of Engineering in Turkish Journal of Engineering
- Vol. 9 (1) , 1-11
Application of Convolutional Neural Networks for Watermelon Detection in UAV Aerial Images: A Case Study
Although human dependence on agriculture decreases with developing technology, it continues. As many resources are increasingly restricted due to various climatic reasons, the importance of studies in this field increases. Applications using deep learning models are frequently encountered in the agricultural field. In particular, there are applications where deep learning models are used as a tool for optimum planting, land use, yield improvement, production/disease/pest control, and other activities.In this study, watermelons in an aerial view of a watermelon field were detected by utilizing the Alexnet deep learning architecture. To obtain yield, watermelons in watermelon fields should be specified and then counted. Aerial images are used for this application. The field image was divided into 50% overlapping sub-images, and each was classified as watermelon, leaf, and soil. Consequently, watermelon regions on the field image were specified. After training the Alexnet and Vgg19 network structure with the dataset, watermelons were to be identified by segmenting the images. It was observed that the Vgg19 network achieved 97.78% accuracy. The results of the experimental applications show that the Vgg19 can be applied for watermelon fruit and yield detection applications.
- 2 November 2023
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 49 (5) , 6695-6705
Categorization of Breast Carcinoma Histopathology Images by Utilizing Region-Based Convolutional Neural Networks
- 2 November 2023
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 49 (5) , 6695-6705
Categorization of Breast Carcinoma Histopathology Images by Utilizing Region-Based Convolutional Neural Networks
- 29 December 2021
- Published by Cukurova Universitesi Muhendislik-Mimarlik Fakultesi Dergisi in Çukurova Üniversitesi Mühendislik Fakültesi Dergisi
- Vol. 36 (4) , 997-1004
Yarım Bant Nyquist Filtre ile Sinyallerin Ayrıştırılması ve Gürültünün Giderilmesi Üzerine Bir Araştırma
Medical signal processing is often used for analyzing and detecting diseases from bio-signals. Segmentation, filtering, and noise removal are application examples in this area. The segmentation or decomposition of signals is investigated in this study. Each branch of two band quadrature-mirror orthogonal filter bank structure (analysis and synthesis parts are cascaded) is a half band Nyquist filter when down-up samplers are removed. To perform partitioning, one branch of the filter bank was adapted to a component of input signal to suppress the other element and filter out the target part of the signal. This was done by obtaining the filter-tap weights, which minimize - norm of error at the output. This goal was achieved by employing the exhaustive search method. The filter performance was tested for three scenarios: filtering with and without down-up samplers and wavelet de-noising using one-level decomposition. The comparison was done with Daubechies and Symlet filters. The approach was run and tested for separating synthetically generated evoked potential from noise, and the results show that the designed filter achieves lower total absolute error than the classical wavelet filters.
- 29 December 2021
- Published by Cukurova Universitesi Muhendislik-Mimarlik Fakultesi Dergisi in Çukurova Üniversitesi Mühendislik Fakültesi Dergisi
- Vol. 36 (4) , 997-1004
Yarım Bant Nyquist Filtre ile Sinyallerin Ayrıştırılması ve Gürültünün Giderilmesi Üzerine Bir Araştırma
Medical signal processing is often used for analyzing and detecting diseases from bio-signals. Segmentation, filtering, and noise removal are application examples in this area. The segmentation or decomposition of signals is investigated in this study. Each branch of two band quadrature-mirror orthogonal filter bank structure (analysis and synthesis parts are cascaded) is a half band Nyquist filter when down-up samplers are removed. To perform partitioning, one branch of the filter bank was adapted to a component of input signal to suppress the other element and filter out the target part of the signal. This was done by obtaining the filter-tap weights, which minimize - norm of error at the output. This goal was achieved by employing the exhaustive search method. The filter performance was tested for three scenarios: filtering with and without down-up samplers and wavelet de-noising using one-level decomposition. The comparison was done with Daubechies and Symlet filters. The approach was run and tested for separating synthetically generated evoked potential from noise, and the results show that the designed filter achieves lower total absolute error than the classical wavelet filters.
- Open Access
- 11 October 2021
- Published by Brieflands in Iranian Journal of Radiology
- Vol. 18 (4)
Use of Histogram Analysis in Diffusion-Weighted Magnetic Resonance Imaging for Differentiation of Renal Tumor Subgroups
Background: The histopathological differentiation of renal neoplasms can be challenging via imaging. Objectives: To evaluate differences in histogram parameters on apparent diffusion coefficient (ADC) maps and to investigate the efficacy of histogram analysis in differentiation of oncocytomas from malignant renal neoplasm (MRN) subgroups. Patients and Methods: In this cross-sectional, retrospective study, the texture parameters of diffusion-weighted magnetic resonance images (DW-MRI) were evaluated in 65 patients with renal tumors (nine cases of oncocytoma and 59 cases of MRN) for a histological analysis. Results: A total of 68 lesions from 50 male and 15 female patients, with a median age of 55.4 years, were examined in this study. There were significant differences in the mean, median, and peak ADC values, as well as ADC percentiles, between the oncocytoma and MRN subgroups. Regarding the histopathological features of the lesions, 9 (11.5%) cases of oncocytomas, 23 (29.5%) cases of clear cell renal carcinoma (ccRCC), 14 (17.9%) cases of papillary renal cell carcinoma (pRCC), 12 (15.4%) cases of chromophobe renal cell carcinoma (chRCC), and 10 (12.8%) other tumors (including four cases of transitional cell carcinoma, four cases of non-Hodgkin’s lymphoma, and two cases of primitive neuroectodermal tumor) were identified. Significant differences were found in the mean and median ADC values between the oncocytoma, pRCC, chRCC, and other MRN subgroups. Moreover, significant differences were found in the mean and median ADC values between the ccRCC, pRCC, and chRCC subgroups. There were also significant differences in the percentiles of mean and median ADCs between oncocytomas and pRCC, chRCC, and other MRN subgroups. However, there were no significant differences in the mean and median ADCs (including the percentile histogram analysis) or the peak ADC between the oncocytoma and ccRCC groups. The mean, median, and percentile of ADC for renal masses were superior to kurtosis, skewness, and entropy. Conclusion: Although differentiation between ccRCC and oncocytoma was not possible by only measuring the mean, median, and peak ADC values, the histogram analysis of ADCs may improve differentiation between the MRN subgroups. Clearly, ADC cannot be used to differentiate between oncocytomas and MRNs.
- 11 October 2021
- Published by Brieflands in Iranian Journal of Radiology
- Vol. 18 (4)
Open AccessUse of Histogram Analysis in Diffusion-Weighted Magnetic Resonance Imaging for Differentiation of Renal Tumor Subgroups
Background: The histopathological differentiation of renal neoplasms can be challenging via imaging. Objectives: To evaluate differences in histogram parameters on apparent diffusion coefficient (ADC) maps and to investigate the efficacy of histogram analysis in differentiation of oncocytomas from malignant renal neoplasm (MRN) subgroups. Patients and Methods: In this cross-sectional, retrospective study, the texture parameters of diffusion-weighted magnetic resonance images (DW-MRI) were evaluated in 65 patients with renal tumors (nine cases of oncocytoma and 59 cases of MRN) for a histological analysis. Results: A total of 68 lesions from 50 male and 15 female patients, with a median age of 55.4 years, were examined in this study. There were significant differences in the mean, median, and peak ADC values, as well as ADC percentiles, between the oncocytoma and MRN subgroups. Regarding the histopathological features of the lesions, 9 (11.5%) cases of oncocytomas, 23 (29.5%) cases of clear cell renal carcinoma (ccRCC), 14 (17.9%) cases of papillary renal cell carcinoma (pRCC), 12 (15.4%) cases of chromophobe renal cell carcinoma (chRCC), and 10 (12.8%) other tumors (including four cases of transitional cell carcinoma, four cases of non-Hodgkin’s lymphoma, and two cases of primitive neuroectodermal tumor) were identified. Significant differences were found in the mean and median ADC values between the oncocytoma, pRCC, chRCC, and other MRN subgroups. Moreover, significant differences were found in the mean and median ADC values between the ccRCC, pRCC, and chRCC subgroups. There were also significant differences in the percentiles of mean and median ADCs between oncocytomas and pRCC, chRCC, and other MRN subgroups. However, there were no significant differences in the mean and median ADCs (including the percentile histogram analysis) or the peak ADC between the oncocytoma and ccRCC groups. The mean, median, and percentile of ADC for renal masses were superior to kurtosis, skewness, and entropy. Conclusion: Although differentiation between ccRCC and oncocytoma was not possible by only measuring the mean, median, and peak ADC values, the histogram analysis of ADCs may improve differentiation between the MRN subgroups. Clearly, ADC cannot be used to differentiate between oncocytomas and MRNs.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Partition of medical signals with a two band adaptive filter bank
Medical signal processing is often used to detect diseases. Segmentation, filtering, categorization are basic operations in this field. In this study; a two-band quadrature mirror orthogonal filter bank structure is used to emphasize and extract signals like QRS wave from electrocardiography, evoked potential from electroencephalography signal. One branch of the filter bank is adopted to filter out a target signal. This is done by minimizing error energy at the output of the filter bank system. The approach is run and tested for a QRS signal and a synthetic evoked potential signal. The common orthogonal wavelet filters (Daubechies, Symlet, Coiflet) and designed filter are compared in terms of mean squared error (MSE). The designed filter attains the target signal with the minimum MSE and outperforms common classical wavelet filters.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Partition of medical signals with a two band adaptive filter bank
Medical signal processing is often used to detect diseases. Segmentation, filtering, categorization are basic operations in this field. In this study; a two-band quadrature mirror orthogonal filter bank structure is used to emphasize and extract signals like QRS wave from electrocardiography, evoked potential from electroencephalography signal. One branch of the filter bank is adopted to filter out a target signal. This is done by minimizing error energy at the output of the filter bank system. The approach is run and tested for a QRS signal and a synthetic evoked potential signal. The common orthogonal wavelet filters (Daubechies, Symlet, Coiflet) and designed filter are compared in terms of mean squared error (MSE). The designed filter attains the target signal with the minimum MSE and outperforms common classical wavelet filters.
- 13 March 2018
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 12 (6) , 1181-1188
Familiar/unfamiliar face classification from EEG signals by utilizing pairwise distant channels and distinctive time interval
- 13 March 2018
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 12 (6) , 1181-1188
Familiar/unfamiliar face classification from EEG signals by utilizing pairwise distant channels and distinctive time interval
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Detection of Exudates from Digital Fundus Images of Diabetic Retinopathy Patients
Diabetes is a condition where the body does not produce enough insulin to convert sugar to energy, leading to a build up of sugar in the blood. This leads to a number of problems, including diabetic retinopathy. Diabetic retinopathy is a complication of diabetes that causes damage to the blood vessels of the retina that allowing you to see fine detail. It causes progressive damage to the retina. This paper proposes a simple yet an efficient approach for automatic detection of the exudates of the Diabetic Retinopathy. The detection of exudates of diabetic retinopathy is composed of eight steps: 1. RGB to gray conversion. 2. Moving mean to 0.5 3. Max Filter 4. Threshold specification 5. Optic disk removal 6. Remove of objects which is not exudates 7. Thresholding original image using the specified exudate regions 8. Computing statistical measures.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Detection of Exudates from Digital Fundus Images of Diabetic Retinopathy Patients
Diabetes is a condition where the body does not produce enough insulin to convert sugar to energy, leading to a build up of sugar in the blood. This leads to a number of problems, including diabetic retinopathy. Diabetic retinopathy is a complication of diabetes that causes damage to the blood vessels of the retina that allowing you to see fine detail. It causes progressive damage to the retina. This paper proposes a simple yet an efficient approach for automatic detection of the exudates of the Diabetic Retinopathy. The detection of exudates of diabetic retinopathy is composed of eight steps: 1. RGB to gray conversion. 2. Moving mean to 0.5 3. Max Filter 4. Threshold specification 5. Optic disk removal 6. Remove of objects which is not exudates 7. Thresholding original image using the specified exudate regions 8. Computing statistical measures.
- 13 June 2017
- Published by Springer Nature
- p. 1101-1104
A Simple Approach to Detect Alcoholics using Electroencephalographic Signals
- 13 June 2017
- Published by Springer Nature
- p. 1101-1104
A Simple Approach to Detect Alcoholics using Electroencephalographic Signals
- 13 June 2017
- Published by Springer Nature
- p. 414-417
Automatic Segmentation of Computed Tomography Images of Liver Using Watershed and Thresholding Algorithms
- 13 June 2017
- Published by Springer Nature
- p. 414-417
Automatic Segmentation of Computed Tomography Images of Liver Using Watershed and Thresholding Algorithms
- Open Access
- 1 January 2017
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 25 (4) , 3342-3354
Classification of EEG signals of familiar and unfamiliar face stimuli exploiting most discriminative channels
- 1 January 2017
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 25 (4) , 3342-3354
Open AccessClassification of EEG signals of familiar and unfamiliar face stimuli exploiting most discriminative channels