Zekeriya Balci
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zekeriya Balci has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- İsMail Yabanova
Department of Electrical Engineering, Manisa Celal Bayar University 3 , Manisa
4 shared publications - Mehmet Yumurtaci
Afyon Kocatepe Universitesi
3 shared publications - Ahmet Mert
Department of Mechatronics Engineering, Bursa Technical University, Yildirim, Bursa, Turkey
2 shared publications - Semih Ergin
Department of Electrical and Electronics Engineering Eskisehir Osmangazi University Eskisehir Türkiye
2 shared publications A. Mert
Bursa Technical University
1 shared publicationF.S. Kaya
1 shared publication
Latest Publications
- Open Access
- 12 October 2026
- Published by Ankara University Faculty of Agriculture in Tarım Bilimleri Dergisi
- Vol. 32 (4) , 953-966
Dynamic Weighing Signal Denoising Approach Based on Convolutional Denoising Autoencoders: A Novel Rapid Weight Determination for Egg Sorting Machines
With the increasing scale of industrial egg production, rapid and precise weight classification has become a technical necessity. While dynamic weighing systems are employed to maintain high production speeds, load cell signals in these systems are significantly corrupted by mechanical vibrations and environmental noise, compromising measurement accuracy. This study proposes a Convolutional Denoising Autoencoder (CDAE)-based approach to effectively filter these dynamic weighing signals and ensure accurate classification. The performance of the proposed method was evaluated and compared against traditional filtering techniques, specifically Discrete Wavelet Transform (DWT) and Moving Average Filter (MAF). The results demonstrate that the CDAE-based model provides superior noise reduction, enabling faster and more stable weight determination compared to conventional methods. By addressing the limitations of traditional filters in high-speed environments, this study offers a robust artificial intelligence-based solution to the precision dynamic weighing challenges encountered in the food industry.
- 12 October 2026
- Published by Ankara University Faculty of Agriculture in Tarım Bilimleri Dergisi
- Vol. 32 (4) , 953-966
Open AccessDynamic Weighing Signal Denoising Approach Based on Convolutional Denoising Autoencoders: A Novel Rapid Weight Determination for Egg Sorting Machines
With the increasing scale of industrial egg production, rapid and precise weight classification has become a technical necessity. While dynamic weighing systems are employed to maintain high production speeds, load cell signals in these systems are significantly corrupted by mechanical vibrations and environmental noise, compromising measurement accuracy. This study proposes a Convolutional Denoising Autoencoder (CDAE)-based approach to effectively filter these dynamic weighing signals and ensure accurate classification. The performance of the proposed method was evaluated and compared against traditional filtering techniques, specifically Discrete Wavelet Transform (DWT) and Moving Average Filter (MAF). The results demonstrate that the CDAE-based model provides superior noise reduction, enabling faster and more stable weight determination compared to conventional methods. By addressing the limitations of traditional filters in high-speed environments, this study offers a robust artificial intelligence-based solution to the precision dynamic weighing challenges encountered in the food industry.
- 15 September 2025
- Published by Taylor & Francis in British Poultry Science
- Vol. 67 (2) , 224-232
An acoustic signal-to-image conversion integrated convolutional neural network model for egg crack detection
1. The presence of fractures or cracks in eggshells represent a significant risk in terms of food safety. Bacteria and viruses are likely to enter through these cracks, which increases the risk of food poisoning. Furthermore, deformations in the shell can compromise the integrity of the protective shell, rendering the egg more susceptible to environmental damage and accelerating deterioration.2. In order to mitigate these risks, a convolutional neural network (CNN) integrated into an acoustic signal to image conversion was developed as a crack detection system. Mechanical and electronic sub-systems were designed to generate non-destructive acoustic excitation on the eggshell and capture the resulting sound with a high-sensitivity microphone.3. The recorded 1 × 731-sample signals from 120 intact or cracked eggs were subjected to variational mode decomposition (VMD) to extract intrinsic mode functions (IMF). Subsequently, IMF were converted to greyscale images and classified using the proposed acoustic signal-to-image conversion and the lightweight CNN.4. The proposed model showed the capability (100%) to distinguish between intact and cracked eggs, including invisible micro-cracks.
- 15 September 2025
- Published by Taylor & Francis in British Poultry Science
- Vol. 67 (2) , 224-232
An acoustic signal-to-image conversion integrated convolutional neural network model for egg crack detection
1. The presence of fractures or cracks in eggshells represent a significant risk in terms of food safety. Bacteria and viruses are likely to enter through these cracks, which increases the risk of food poisoning. Furthermore, deformations in the shell can compromise the integrity of the protective shell, rendering the egg more susceptible to environmental damage and accelerating deterioration.2. In order to mitigate these risks, a convolutional neural network (CNN) integrated into an acoustic signal to image conversion was developed as a crack detection system. Mechanical and electronic sub-systems were designed to generate non-destructive acoustic excitation on the eggshell and capture the resulting sound with a high-sensitivity microphone.3. The recorded 1 × 731-sample signals from 120 intact or cracked eggs were subjected to variational mode decomposition (VMD) to extract intrinsic mode functions (IMF). Subsequently, IMF were converted to greyscale images and classified using the proposed acoustic signal-to-image conversion and the lightweight CNN.4. The proposed model showed the capability (100%) to distinguish between intact and cracked eggs, including invisible micro-cracks.
- 1 August 2025
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 96 (8)
Photoacoustic signal to image based convolutional neural network for defect detection
In this paper, we propose a novel photoacoustic (PA) signal to image conversion based convolutional neural network (CNN) model for defect detection in materials. A low-cost computer aided PA triggering and acquisition device has been developed, and then, PA signals are stored for four types of defected and intact materials. Variational mode decomposition is applied to the dataset to extract intrinsic mode functions to convert PA signals to images as the first step of the feature extraction, and then, a lightweight CNN architecture is trained and tested using converted grayscale PA images to detect as defected or intact material. The proposed model is performed on the PA signals of aluminum, iron, wood, and plastic depending on the within-class and all-class evaluation strategies. The mean accuracy levels of 0.977 (up to 1.0) for within-class (material dependent) and 0.942 (up to 0.955) for all-class (material independent) are yielded.
- 1 August 2025
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 96 (8)
Photoacoustic signal to image based convolutional neural network for defect detection
In this paper, we propose a novel photoacoustic (PA) signal to image conversion based convolutional neural network (CNN) model for defect detection in materials. A low-cost computer aided PA triggering and acquisition device has been developed, and then, PA signals are stored for four types of defected and intact materials. Variational mode decomposition is applied to the dataset to extract intrinsic mode functions to convert PA signals to images as the first step of the feature extraction, and then, a lightweight CNN architecture is trained and tested using converted grayscale PA images to detect as defected or intact material. The proposed model is performed on the PA signals of aluminum, iron, wood, and plastic depending on the within-class and all-class evaluation strategies. The mean accuracy levels of 0.977 (up to 1.0) for within-class (material dependent) and 0.942 (up to 0.955) for all-class (material independent) are yielded.
- Open Access
- 3 March 2024
- Published by Journal of Materials and Mechatronics: A in Journal of Materials and Mechatronics: A
- p. 1-13
Farklı Katı Malzemelerde Görgül Kip Analizi Tabanlı Foto Akustik Sinyal İşleme ile Kusur Tespiti
Bu çalışmada, görgül kip ayrışımı (GKA) ve makine öğrenimi algoritması kullanılarak malzeme kusurlarının tespiti için bir fotoakustik (FA) sinyal işleme çerçevesi önerilmiştir. Zaman ve zaman-frekans düzleminde çıkarılan özellikler ve gelişmiş sinyal işleme yöntemlerinin yardımıyla kusurların başarılı bir şekilde tespit edilmesini sağlamıştır. Lazer, mikrofon ve veri toplama kartı tabanlı bir FA sistem kullanılarak alüminyum, demir ve ahşap malzemelerden FA sinyallerinden oluşan veritabanı elde edilmiştir. Her bir malzeme grubundan toplam 240 örnek (120 sağlam örnek ve 120 kusurlu örnek) ve toplam 720 örnek, GKA uygulandıktan sonra zaman ve zaman-frekans düzlemi özelliklerini çıkarmak için kullanılmıştır. Daha sonra k-en yakın komşu sınıflandırıcısı veri tabanındaki kusurlu ve sağlam malzemelerin tespiti için çıkarılan 14 özellik kullanılarak eğitilmiş ve test edilmiştir. Materyaller özelinde ve materyaller arası sınıflandırma yapılmış ve doğruluk oranları sırasıyla %100 ve %97.77 olarak elde edilmiştir.
- 3 March 2024
- Published by Journal of Materials and Mechatronics: A in Journal of Materials and Mechatronics: A
- p. 1-13
Open AccessFarklı Katı Malzemelerde Görgül Kip Analizi Tabanlı Foto Akustik Sinyal İşleme ile Kusur Tespiti
Bu çalışmada, görgül kip ayrışımı (GKA) ve makine öğrenimi algoritması kullanılarak malzeme kusurlarının tespiti için bir fotoakustik (FA) sinyal işleme çerçevesi önerilmiştir. Zaman ve zaman-frekans düzleminde çıkarılan özellikler ve gelişmiş sinyal işleme yöntemlerinin yardımıyla kusurların başarılı bir şekilde tespit edilmesini sağlamıştır. Lazer, mikrofon ve veri toplama kartı tabanlı bir FA sistem kullanılarak alüminyum, demir ve ahşap malzemelerden FA sinyallerinden oluşan veritabanı elde edilmiştir. Her bir malzeme grubundan toplam 240 örnek (120 sağlam örnek ve 120 kusurlu örnek) ve toplam 720 örnek, GKA uygulandıktan sonra zaman ve zaman-frekans düzlemi özelliklerini çıkarmak için kullanılmıştır. Daha sonra k-en yakın komşu sınıflandırıcısı veri tabanındaki kusurlu ve sağlam malzemelerin tespiti için çıkarılan 14 özellik kullanılarak eğitilmiş ve test edilmiştir. Materyaller özelinde ve materyaller arası sınıflandırma yapılmış ve doğruluk oranları sırasıyla %100 ve %97.77 olarak elde edilmiştir.
- 30 June 2022
- Published by Sakarya University Journal of Science in Sakarya University Journal of Science
- Vol. 26 (3) , 579-589
Artificial Intelligence Based Determination of Cracks in Eggshell Using Sound Signals
Although the egg is a cheap food source, it is one of the valuable nutritional sources for people because of its rich nutritional values. It is also among the most consumed foods in daily nutrition. With the increase in egg production, it is very difficult to collect them with the human power in the egg production farms, to classify them according to their weights and to separate the defective (dirty and broken) eggs. Therefore, the mechanization has become a necessity in large capacity production farms. Cracks and fractures may occur in the egg shell as a result of exposure to external factors such as the transportation of eggs. The cracks or fractures that are formed leave the egg vulnerable to disease-causing micro-organisms. Before the egg sorting and packing, the broken and cracked eggs must be separated. This process is commonly carried out with manpower by which it is very difficult to obtain the necessary efficiency. In this study, the egg crack detection was performed by using Support Vector Machines (SVM) and Artificial Neural Network (ANN). As a result of the application of studied methods, the accuracy values of crack detection process were 0.99 for ANN and 1 for SVM. In addition, a data acquisition and processing program was developed in LABVIEW environment to detect cracks in real time.
- 30 June 2022
- Published by Sakarya University Journal of Science in Sakarya University Journal of Science
- Vol. 26 (3) , 579-589
Artificial Intelligence Based Determination of Cracks in Eggshell Using Sound Signals
Although the egg is a cheap food source, it is one of the valuable nutritional sources for people because of its rich nutritional values. It is also among the most consumed foods in daily nutrition. With the increase in egg production, it is very difficult to collect them with the human power in the egg production farms, to classify them according to their weights and to separate the defective (dirty and broken) eggs. Therefore, the mechanization has become a necessity in large capacity production farms. Cracks and fractures may occur in the egg shell as a result of exposure to external factors such as the transportation of eggs. The cracks or fractures that are formed leave the egg vulnerable to disease-causing micro-organisms. Before the egg sorting and packing, the broken and cracked eggs must be separated. This process is commonly carried out with manpower by which it is very difficult to obtain the necessary efficiency. In this study, the egg crack detection was performed by using Support Vector Machines (SVM) and Artificial Neural Network (ANN). As a result of the application of studied methods, the accuracy values of crack detection process were 0.99 for ANN and 1 for SVM. In addition, a data acquisition and processing program was developed in LABVIEW environment to detect cracks in real time.
- 28 June 2022
- Published by Anadolu Universitesi Bilim ve Teknoloji Dergisi-A: Uygulamali Bilimler ve Muhendislik in Eskişehir Technical University Journal of Science and Technology A - Applied Sciences and Engineering
- Vol. 23 (2) , 161-172
THE DETECTION OF EGGSHELL CRACKS USING DIFFERENT CLASSIFIERS
Chicken eggs, which are widely consumed in daily life due to their rich nutritional values, are also used in many products. The increasing need for eggs must be met quickly for various circumstances. Eggs are subjected to various impacts and shaken from production to packaging. In some cases, these effects cause an eggshell to crack. While these cracks are sometimes visible, they are sometimes micro-sized and cannot be seen. The cracks on the egg allow harmful micro-organisms to spoil the egg in a short time. In this study, acoustic signals generated by a mechanical effect to the eggs were recorded for 0.2 seconds at 50 kHz sampling frequency using a microphone. To determine the active part in the collected acoustic signal data, a clipping process was implemented by a thresholding process. Thus, the exactly correct moment of mechanical contact on the eggshell was easily detected. After passing the determined threshold value, statistical parameters such as min, max, difference, mean, standard deviation, skewness and kurtosis were extracted from the data obtained, and 7-dimensional feature vectors were created. Finally, the Common Vector Approach (CVA) is applied on the extracted feature vectors, 100% success rate has been achieved for the test data set. The ANN and SVM classifiers in where the same feature vectors are treated were used for the comparison purpose, and exactly the same classification rates are attained; however, the less number of eggs are tested with the ANN and SVM classifiers in the same amount of time. With the proposed mechanical system and classification methodology, it takes about 0.2008 seconds to determine whether the shells of eggs are cracked/intact. Therefore, the proposed combination of the feature vectors based on statistical features and CVA as a classifier for the detection of cracks on eggshells is notably appropriate especially for industrial applications in terms of speed and accuracy aspects.
- 28 June 2022
- Published by Anadolu Universitesi Bilim ve Teknoloji Dergisi-A: Uygulamali Bilimler ve Muhendislik in Eskişehir Technical University Journal of Science and Technology A - Applied Sciences and Engineering
- Vol. 23 (2) , 161-172
THE DETECTION OF EGGSHELL CRACKS USING DIFFERENT CLASSIFIERS
Chicken eggs, which are widely consumed in daily life due to their rich nutritional values, are also used in many products. The increasing need for eggs must be met quickly for various circumstances. Eggs are subjected to various impacts and shaken from production to packaging. In some cases, these effects cause an eggshell to crack. While these cracks are sometimes visible, they are sometimes micro-sized and cannot be seen. The cracks on the egg allow harmful micro-organisms to spoil the egg in a short time. In this study, acoustic signals generated by a mechanical effect to the eggs were recorded for 0.2 seconds at 50 kHz sampling frequency using a microphone. To determine the active part in the collected acoustic signal data, a clipping process was implemented by a thresholding process. Thus, the exactly correct moment of mechanical contact on the eggshell was easily detected. After passing the determined threshold value, statistical parameters such as min, max, difference, mean, standard deviation, skewness and kurtosis were extracted from the data obtained, and 7-dimensional feature vectors were created. Finally, the Common Vector Approach (CVA) is applied on the extracted feature vectors, 100% success rate has been achieved for the test data set. The ANN and SVM classifiers in where the same feature vectors are treated were used for the comparison purpose, and exactly the same classification rates are attained; however, the less number of eggs are tested with the ANN and SVM classifiers in the same amount of time. With the proposed mechanical system and classification methodology, it takes about 0.2008 seconds to determine whether the shells of eggs are cracked/intact. Therefore, the proposed combination of the feature vectors based on statistical features and CVA as a classifier for the detection of cracks on eggshells is notably appropriate especially for industrial applications in terms of speed and accuracy aspects.
- 30 June 2021
- Published by Bilecik Seyh Edebali Universitesi Fen Bilimleri Dergisi in Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi
- Vol. 8 (1) , 125-135
Yumurta Kabuğundan Alınan Akustik Sinyalin Dalgacık Paket Dönüşümü ve Entropiye Dayalı Olarak İşlenmesi ve Yapay Sinir Ağlarıyla Çatlağın Belirlenmesi
Endüstride birçok üründe ve evlerimizde, vitaminler ve mineraller bakımından zengin olmasından dolayı yumurta yaygın olarak tüketilmektedir. Artan ihtiyacın hızlı bir şekilde karşılanması için tavuk çiftliklerinde yumurtaların toplanması, ağırlıklarına göre sınıflandırılması, sağlam/çatlak olanların ayrılması, paketlenmesi vb. işlemler için otomasyona geçiş yapılmıştır. Kabuğun çatlak olması durumunda içerisine zararlı mikroorganizmalar kolaylıkla girebileceği gibi yumurta içinin havayla temasından dolayı kısa sürede bozulmasına yol açacaktır. Çatlaklar gözle görülebilecek kadar büyük olabildiği gibi bazen de mikro boyutta olmakta insan gözüyle tespit edilememektedir. Bu çalışmada yumurta kabuğunun çatlak/sağlam olması durumunun sinyal işleme ve makine öğrenme tabanlı tespiti gerçekleştirilmiştir. Mekanik sistem vasıtasıyla kabuğa yapılan darbe neticesindeki oluşan akustik sinyal sistemdeki mikrofonla 50kHz örnekleme frekansında 0.2 sn süresince kayıt altına alınmaktadır. Kabuğu sağlam ve çatlak olan ayrı ayrı 50 yumurta verisi düzenekle kayıt altına alınıp veri seti oluşturulmuştur. Yumurta kabuğuna darbenin uygulanma anından sönümlenene kadarki zamanın tespiti için 0.74V eşik değeri kullanılıp bu değerden sonraki 680 veri alınmıştır. Bu verilere db4 ana dalgacığı ile 2. seviyeden Dalgacık Paket Dönüşümü (DPD) uygulanarak farklı frekanslı detay ve yaklaşım bileşenleri çıkartılmıştır. Her bir bileşenin entropi değeri hesaplanarak 1x4 boyutunda özellik vektörü elde edilmiştir. Çıkartımı yapılan özellik vektörünün yumurta kabuğundaki çatlağın tespitindeki etkinliğini belirlemek için Yapay Sinir Ağı (YSA) kullanılmıştır. %100 başarım elde edilmiş olup bir yumurtanın kabuk çatlak/sağlam belirleme süresi yaklaşık olarak 0.216sn’dir.
- 30 June 2021
- Published by Bilecik Seyh Edebali Universitesi Fen Bilimleri Dergisi in Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi
- Vol. 8 (1) , 125-135
Yumurta Kabuğundan Alınan Akustik Sinyalin Dalgacık Paket Dönüşümü ve Entropiye Dayalı Olarak İşlenmesi ve Yapay Sinir Ağlarıyla Çatlağın Belirlenmesi
Endüstride birçok üründe ve evlerimizde, vitaminler ve mineraller bakımından zengin olmasından dolayı yumurta yaygın olarak tüketilmektedir. Artan ihtiyacın hızlı bir şekilde karşılanması için tavuk çiftliklerinde yumurtaların toplanması, ağırlıklarına göre sınıflandırılması, sağlam/çatlak olanların ayrılması, paketlenmesi vb. işlemler için otomasyona geçiş yapılmıştır. Kabuğun çatlak olması durumunda içerisine zararlı mikroorganizmalar kolaylıkla girebileceği gibi yumurta içinin havayla temasından dolayı kısa sürede bozulmasına yol açacaktır. Çatlaklar gözle görülebilecek kadar büyük olabildiği gibi bazen de mikro boyutta olmakta insan gözüyle tespit edilememektedir. Bu çalışmada yumurta kabuğunun çatlak/sağlam olması durumunun sinyal işleme ve makine öğrenme tabanlı tespiti gerçekleştirilmiştir. Mekanik sistem vasıtasıyla kabuğa yapılan darbe neticesindeki oluşan akustik sinyal sistemdeki mikrofonla 50kHz örnekleme frekansında 0.2 sn süresince kayıt altına alınmaktadır. Kabuğu sağlam ve çatlak olan ayrı ayrı 50 yumurta verisi düzenekle kayıt altına alınıp veri seti oluşturulmuştur. Yumurta kabuğuna darbenin uygulanma anından sönümlenene kadarki zamanın tespiti için 0.74V eşik değeri kullanılıp bu değerden sonraki 680 veri alınmıştır. Bu verilere db4 ana dalgacığı ile 2. seviyeden Dalgacık Paket Dönüşümü (DPD) uygulanarak farklı frekanslı detay ve yaklaşım bileşenleri çıkartılmıştır. Her bir bileşenin entropi değeri hesaplanarak 1x4 boyutunda özellik vektörü elde edilmiştir. Çıkartımı yapılan özellik vektörünün yumurta kabuğundaki çatlağın tespitindeki etkinliğini belirlemek için Yapay Sinir Ağı (YSA) kullanılmıştır. %100 başarım elde edilmiş olup bir yumurtanın kabuk çatlak/sağlam belirleme süresi yaklaşık olarak 0.216sn’dir.