Mehmet Erkan Yuksel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mehmet Erkan Yuksel has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Eyyüp Yıldız
Erzincan Binali Yildirim Universitesi
4 shared publications - Selcuk Sevgen
Department of Computer Engineering, Faculty of Engineering, Istanbul University-Cerrahpaşa, Istanbul 34320, Türkiye
3 shared publications - Hüseyin Fidan
Department of Industrial Engineering, Burdur Mehmet Akif Ersoy University, Burdur, Turkey
2 shared publications - Arif Koyun
Süleyman Demirel Üniversitesi
1 shared publication - Asım Sinan Yüksel
Süleyman Demirel University
1 shared publication - Doğukan Özeren
Burdur Mehmet Akif Ersoy University
1 shared publication
Latest Publications
- Open Access
Gateway-Driven Hybrid Adaptive Power Management for Energy-Harvesting LPWAN IoT Nodes Using Fuzzy Logic
Low-Power Wide-Area Network (LPWAN)-based Internet of Things (IoT) deployments require energy management strategies that adapt to dynamic operating conditions without increasing the processing burden on energy-harvesting nodes. These nodes must coordinate data reporting with mandatory local services within a finite energy budget. Conventional fixed duty-cycling and synchronization policies do not jointly account for node energy availability, network traffic, and environmental factors influencing energy harvesting. This study presents hybrid adaptive power management (HA-PM), a framework combining gateway-based reporting-period adaptation with node-side scheduling and power-mode selection. A gateway fuzzy logic controller (FLC) evaluates supercapacitor state of charge (SoC), network traffic, and weather/control context to adjust the reporting period. The node selects the feasible plan with the lowest estimated total node energy from a finite catalog, subject to mandatory service and timing requirements. The reporting period specifies data-reporting requirements, while the local schedule determines available low-power intervals. Simulations compare HA-PM with fixed-period baselines across representative deployment, workload, harvesting, and adverse-condition scenarios. Results indicate that HA-PM reduces communication-related energy consumption, increases low-power-mode residency, and improves supercapacitor-level operational continuity under the evaluated conditions. Stress tests further demonstrate adaptive responses to adverse harvesting and traffic scenarios. These findings support HA-PM as a practical, context-aware energy management strategy for energy-harvesting LPWAN IoT applications, although the reported results are contingent on the specified simulation models, parameters, and operating scenarios.
Open AccessGateway-Driven Hybrid Adaptive Power Management for Energy-Harvesting LPWAN IoT Nodes Using Fuzzy Logic
Low-Power Wide-Area Network (LPWAN)-based Internet of Things (IoT) deployments require energy management strategies that adapt to dynamic operating conditions without increasing the processing burden on energy-harvesting nodes. These nodes must coordinate data reporting with mandatory local services within a finite energy budget. Conventional fixed duty-cycling and synchronization policies do not jointly account for node energy availability, network traffic, and environmental factors influencing energy harvesting. This study presents hybrid adaptive power management (HA-PM), a framework combining gateway-based reporting-period adaptation with node-side scheduling and power-mode selection. A gateway fuzzy logic controller (FLC) evaluates supercapacitor state of charge (SoC), network traffic, and weather/control context to adjust the reporting period. The node selects the feasible plan with the lowest estimated total node energy from a finite catalog, subject to mandatory service and timing requirements. The reporting period specifies data-reporting requirements, while the local schedule determines available low-power intervals. Simulations compare HA-PM with fixed-period baselines across representative deployment, workload, harvesting, and adverse-condition scenarios. Results indicate that HA-PM reduces communication-related energy consumption, increases low-power-mode residency, and improves supercapacitor-level operational continuity under the evaluated conditions. Stress tests further demonstrate adaptive responses to adverse harvesting and traffic scenarios. These findings support HA-PM as a practical, context-aware energy management strategy for energy-harvesting LPWAN IoT applications, although the reported results are contingent on the specified simulation models, parameters, and operating scenarios.
- Open Access
- 28 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (19) , 9625
Domain Adaptation of LLaMA-2-7B for Veterinary and Livestock Question Answering: A Lexical, Semantic, Statistical and Expert-Based Evaluation
Large Language Models (LLMs) have demonstrated substantial capabilities in natural language processing, yet their adaptation to specialized domains such as veterinary medicine and livestock production remains comparatively underexplored. This study adapted LLaMA-2-7B to the veterinary and livestock domain using a domain-specific corpus comprising 24,182 records and 19,904,874 LLaMA-2 tokens. Domain adaptation was performed using Low-Rank Adaptation (LoRA)-based parameter-efficient fine-tuning. Model performance was evaluated on 100 veterinary and livestock-related questions using veterinarian-prepared reference responses, lexical metrics (BLEU, ROUGE, and METEOR), BERTScore, veterinary expert assessment, question-level paired statistical analyses, and selected general capability benchmarks (ARC-Challenge, HellaSwag, WinoGrande, and MMLU). Question-level paired analyses showed that METEOR increased significantly from 0.1741 to 0.2156 (Holm-adjusted p < 0.001), whereas BLEU, ROUGE-1, and ROUGE-2 showed no significant differences after multiple-comparison correction. ROUGE-L decreased from 0.1236 to 0.1096 (adjusted p = 0.0403), while BERTScore showed a small but significant decrease from 0.8442 to 0.8373 (adjusted p = 0.0113). Veterinary expert assessment of the LoRA-adapted model yielded an overall question-level score of 7.1960 ± 1.4589 across five qualitative dimensions. Agreement between the two complete domain-expert assessment streams showed a moderate-to-good reliability profile across complementary agreement statistics. General capability evaluation showed modest improvements on ARC-Challenge and HellaSwag and modest decreases on WinoGrande and MMLU. Overall, LoRA-based domain adaptation produced measurable but metric-dependent effects rather than uniform improvements. These findings emphasize the importance of multidimensional evaluation and provide a methodological foundation for the development and assessment of specialized LLMs for veterinary medicine and livestock production. The findings characterize model behavior within a controlled veterinary and livestock question-answering setting and should not be interpreted as evidence of clinical safety or readiness for autonomous veterinary decision support.
- 28 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (19) , 9625
Open AccessDomain Adaptation of LLaMA-2-7B for Veterinary and Livestock Question Answering: A Lexical, Semantic, Statistical and Expert-Based Evaluation
Large Language Models (LLMs) have demonstrated substantial capabilities in natural language processing, yet their adaptation to specialized domains such as veterinary medicine and livestock production remains comparatively underexplored. This study adapted LLaMA-2-7B to the veterinary and livestock domain using a domain-specific corpus comprising 24,182 records and 19,904,874 LLaMA-2 tokens. Domain adaptation was performed using Low-Rank Adaptation (LoRA)-based parameter-efficient fine-tuning. Model performance was evaluated on 100 veterinary and livestock-related questions using veterinarian-prepared reference responses, lexical metrics (BLEU, ROUGE, and METEOR), BERTScore, veterinary expert assessment, question-level paired statistical analyses, and selected general capability benchmarks (ARC-Challenge, HellaSwag, WinoGrande, and MMLU). Question-level paired analyses showed that METEOR increased significantly from 0.1741 to 0.2156 (Holm-adjusted p < 0.001), whereas BLEU, ROUGE-1, and ROUGE-2 showed no significant differences after multiple-comparison correction. ROUGE-L decreased from 0.1236 to 0.1096 (adjusted p = 0.0403), while BERTScore showed a small but significant decrease from 0.8442 to 0.8373 (adjusted p = 0.0113). Veterinary expert assessment of the LoRA-adapted model yielded an overall question-level score of 7.1960 ± 1.4589 across five qualitative dimensions. Agreement between the two complete domain-expert assessment streams showed a moderate-to-good reliability profile across complementary agreement statistics. General capability evaluation showed modest improvements on ARC-Challenge and HellaSwag and modest decreases on WinoGrande and MMLU. Overall, LoRA-based domain adaptation produced measurable but metric-dependent effects rather than uniform improvements. These findings emphasize the importance of multidimensional evaluation and provide a methodological foundation for the development and assessment of specialized LLMs for veterinary medicine and livestock production. The findings characterize model behavior within a controlled veterinary and livestock question-answering setting and should not be interpreted as evidence of clinical safety or readiness for autonomous veterinary decision support.
- 9 July 2026
- Published by Elsevier in Neurocomputing
- Vol. 700
A Single-Image GAN Framework with Adversarially Learned Inference
- 9 July 2026
- Published by Elsevier in Neurocomputing
- Vol. 700
A Single-Image GAN Framework with Adversarially Learned Inference
- 26 December 2025
- Published by Isparta Uygulamali Bilimler Universitesi in Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi
- Vol. 9 (2) , 194-205
A COMPARATIVE EVALUATION OF CNN ARCHITECTURES FOR SINGLE-IMAGE GANS
Generative Adversarial Networks (GANs) have achieved remarkable success in image synthesis, enabling the generation of photorealistic and diverse visual content. While most generative models depend on large datasets to capture visual variability, single-image GANs such as SinGAN demonstrate that rich generative behavior can emerge from the internal patch statistics of a single natural image. However, the effect of convolutional neural network (CNN) backbones on single-image generative performance remains underexplored. This study presents a comparative analysis of five CNN architectures—Inception, ResNet, DenseNet, CBAM, and MobileNet—integrated into the SinGAN framework to investigate their influence on image quality, diversity, and computational efficiency. Each architecture was trained under identical multi-scale SinGAN settings using 15 natural images, and evaluated with Single-Image Fréchet Inception Distance (SIFID), Multi-Scale Structural Similarity (MS-SSIM), and Learned Perceptual Image Patch Similarity (LPIPS), complemented by qualitative visual assessment. The results reveal consistent trade-offs among backbones: ResNet best preserves global structural coherence; DenseNet maximizes fine-detail diversity through dense feature reuse; CBAM enhances perceptual realism via attention module; Inception provides balanced multi-scale feature representation; and MobileNet achieves strong diversity and quality with favorable computational efficiency. These findings demonstrate that architectural design fundamentally governs generative behavior in single-image GANs. The study provides empirical insights and practical guidelines for selecting CNN backbones based on trade-offs between quality, diversity, and efficiency-supporting the design of data-efficient generative models for real-world and resource-constrained applications.
- 26 December 2025
- Published by Isparta Uygulamali Bilimler Universitesi in Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi
- Vol. 9 (2) , 194-205
A COMPARATIVE EVALUATION OF CNN ARCHITECTURES FOR SINGLE-IMAGE GANS
Generative Adversarial Networks (GANs) have achieved remarkable success in image synthesis, enabling the generation of photorealistic and diverse visual content. While most generative models depend on large datasets to capture visual variability, single-image GANs such as SinGAN demonstrate that rich generative behavior can emerge from the internal patch statistics of a single natural image. However, the effect of convolutional neural network (CNN) backbones on single-image generative performance remains underexplored. This study presents a comparative analysis of five CNN architectures—Inception, ResNet, DenseNet, CBAM, and MobileNet—integrated into the SinGAN framework to investigate their influence on image quality, diversity, and computational efficiency. Each architecture was trained under identical multi-scale SinGAN settings using 15 natural images, and evaluated with Single-Image Fréchet Inception Distance (SIFID), Multi-Scale Structural Similarity (MS-SSIM), and Learned Perceptual Image Patch Similarity (LPIPS), complemented by qualitative visual assessment. The results reveal consistent trade-offs among backbones: ResNet best preserves global structural coherence; DenseNet maximizes fine-detail diversity through dense feature reuse; CBAM enhances perceptual realism via attention module; Inception provides balanced multi-scale feature representation; and MobileNet achieves strong diversity and quality with favorable computational efficiency. These findings demonstrate that architectural design fundamentally governs generative behavior in single-image GANs. The study provides empirical insights and practical guidelines for selecting CNN backbones based on trade-offs between quality, diversity, and efficiency-supporting the design of data-efficient generative models for real-world and resource-constrained applications.
- Open Access
- 30 August 2025
- Published by International Journal of 3D Printing Technologies and Digital Industry in International Journal of 3D Printing Technologies and Digital Industry
- Vol. 9 (2) , 247-262
PERFORMANCE COMPARISON OF VISION-LANGUAGE MODELS IN IMAGE CLASSIFICATION
Vision-Language Models (VLMs) have introduced a new paradigm shift in image classification by integrating visual and textual modalities. While these models have demonstrated strong performance on multimodal tasks, their effectiveness in purely visual classification remains underexplored. This study presents a comprehensive, metric-driven comparative analysis of eight state-of-the-art VLMs—GPT-4o-latest, GPT-4o-mini, Gemini-flash-1.5-8b, LLaMA-3.2-90B-vision-instruct, Grok-2-vision-1212, Qwen2.5-vl-7b-instruct, Claude-3.5-sonnet, and Pixtral-large-2411—across four datasets: CIFAR-10, ImageNet, COCO, and the domain-specific New Plant Diseases dataset. Model performance was evaluated using accuracy, precision, recall, F1-score, and robustness under zero-shot and few-shot settings. Quantitative results indicate that GPT-4o-latest consistently achieves the highest performance on typical benchmarks (accuracy: 0.91, F1-score: 0.91 on CIFAR-10), substantially surpassing lightweight models such as Pixtral-large-2411 (accuracy: 0.13, F1-score: 0.13). Near-perfect results on ImageNet and COCO likely reflect pre-training overlap, whereas notable performance degradation on the New Plant Diseases dataset underscores domain adaptation challenges. Our findings emphasize the need for robust, parameter-efficient, and domain-adaptive fine-tuning strategies to advance VLMs in real-world image classification.
- 30 August 2025
- Published by International Journal of 3D Printing Technologies and Digital Industry in International Journal of 3D Printing Technologies and Digital Industry
- Vol. 9 (2) , 247-262
Open AccessPERFORMANCE COMPARISON OF VISION-LANGUAGE MODELS IN IMAGE CLASSIFICATION
Vision-Language Models (VLMs) have introduced a new paradigm shift in image classification by integrating visual and textual modalities. While these models have demonstrated strong performance on multimodal tasks, their effectiveness in purely visual classification remains underexplored. This study presents a comprehensive, metric-driven comparative analysis of eight state-of-the-art VLMs—GPT-4o-latest, GPT-4o-mini, Gemini-flash-1.5-8b, LLaMA-3.2-90B-vision-instruct, Grok-2-vision-1212, Qwen2.5-vl-7b-instruct, Claude-3.5-sonnet, and Pixtral-large-2411—across four datasets: CIFAR-10, ImageNet, COCO, and the domain-specific New Plant Diseases dataset. Model performance was evaluated using accuracy, precision, recall, F1-score, and robustness under zero-shot and few-shot settings. Quantitative results indicate that GPT-4o-latest consistently achieves the highest performance on typical benchmarks (accuracy: 0.91, F1-score: 0.91 on CIFAR-10), substantially surpassing lightweight models such as Pixtral-large-2411 (accuracy: 0.13, F1-score: 0.13). Near-perfect results on ImageNet and COCO likely reflect pre-training overlap, whereas notable performance degradation on the New Plant Diseases dataset underscores domain adaptation challenges. Our findings emphasize the need for robust, parameter-efficient, and domain-adaptive fine-tuning strategies to advance VLMs in real-world image classification.
- 9 August 2024
- Published by Bursa Technical University in Journal of Innovative Science and Engineering
Investigating the effect of loss functions on single-image GAN performance
Loss functions are crucial in training generative adversarial networks (GANs) and shaping the resulting outputs. These functions, specifically designed for GANs, optimize generator and discriminator networks together but in opposite directions. GAN models, which typically handle large datasets, have been successful in the field of deep learning. However, exploring the factors that influence the success of GAN models developed for limited data problems is an important area of research. In this study, we conducted a comprehensive investigation into the loss functions commonly used in GAN literature, such as binary cross entropy (BCE), Wasserstein generative adversarial network (WGAN), least squares generative adversarial network (LSGAN), and hinge loss. Our research focused on examining the impact of these loss functions on improving output quality and ensuring training convergence in single-image GANs. Specifically, we evaluated the performance of a single-image GAN model, SinGAN, using these loss functions in terms of image quality and diversity. Our experimental results demonstrated that loss functions successfully produce high-quality, diverse images from a single training image. Additionally, we found that the WGAN-GP and LSGAN-GP loss functions are more effective for single-image GAN models.
- 9 August 2024
- Published by Bursa Technical University in Journal of Innovative Science and Engineering
Investigating the effect of loss functions on single-image GAN performance
Loss functions are crucial in training generative adversarial networks (GANs) and shaping the resulting outputs. These functions, specifically designed for GANs, optimize generator and discriminator networks together but in opposite directions. GAN models, which typically handle large datasets, have been successful in the field of deep learning. However, exploring the factors that influence the success of GAN models developed for limited data problems is an important area of research. In this study, we conducted a comprehensive investigation into the loss functions commonly used in GAN literature, such as binary cross entropy (BCE), Wasserstein generative adversarial network (WGAN), least squares generative adversarial network (LSGAN), and hinge loss. Our research focused on examining the impact of these loss functions on improving output quality and ensuring training convergence in single-image GANs. Specifically, we evaluated the performance of a single-image GAN model, SinGAN, using these loss functions in terms of image quality and diversity. Our experimental results demonstrated that loss functions successfully produce high-quality, diverse images from a single training image. Additionally, we found that the WGAN-GP and LSGAN-GP loss functions are more effective for single-image GAN models.
- 15 November 2023
- Published by Omer Halisdemir Universitesi in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
An Unconditional Generative Model with Self-Attention Module for Single Image Generation
Generative models have recently become a prominent research topic in the field of artificial intelligence. Among these models, Generative Adversarial Networks (GAN) have revolutionized the field of deep learning by enabling the production of high-quality synthetic data that is very similar to real-world data. However, the effectiveness of GANs largely depends on the size and quality of training data. In many real-world applications, collecting large amounts of high-quality training data is impractical, time-consuming, and expensive. Accordingly, in recent years, there has been intense interest in the development of GAN models that can work with limited data. These models are particularly useful in scenarios where available data is sparse, such as medical imaging, or in creative applications such as creating new works of art. In this study, we propose a GAN model that can learn from a single training image. Our model is based on the principle of multiple GANs operating sequentially at different scales. At each scale, the GAN learns the features of the training image in different dimensions and transfers them to the next GAN. Samples produced by the GAN at the finest scale are images that have the characteristics of the training image but have different realistic structures. In our model, we utilized a self-attention module to increase the realism and quality of the generated images. Additionally, we used a new scaling method to increase the success of the model. The quantitative and qualitative results we obtained from our experimental studies show that our model performs image generation successfully. In addition, we demonstrated the robustness of our model by testing its success in different image manipulation applications. As a result, our model can successfully produce realistic, high-quality, diverse images from a single training image, providing short training time, memory efficiency, and good training stability. Our model is flexible enough to be used in areas where limited data needs to be worked on.
- 15 November 2023
- Published by Omer Halisdemir Universitesi in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
An Unconditional Generative Model with Self-Attention Module for Single Image Generation
Generative models have recently become a prominent research topic in the field of artificial intelligence. Among these models, Generative Adversarial Networks (GAN) have revolutionized the field of deep learning by enabling the production of high-quality synthetic data that is very similar to real-world data. However, the effectiveness of GANs largely depends on the size and quality of training data. In many real-world applications, collecting large amounts of high-quality training data is impractical, time-consuming, and expensive. Accordingly, in recent years, there has been intense interest in the development of GAN models that can work with limited data. These models are particularly useful in scenarios where available data is sparse, such as medical imaging, or in creative applications such as creating new works of art. In this study, we propose a GAN model that can learn from a single training image. Our model is based on the principle of multiple GANs operating sequentially at different scales. At each scale, the GAN learns the features of the training image in different dimensions and transfers them to the next GAN. Samples produced by the GAN at the finest scale are images that have the characteristics of the training image but have different realistic structures. In our model, we utilized a self-attention module to increase the realism and quality of the generated images. Additionally, we used a new scaling method to increase the success of the model. The quantitative and qualitative results we obtained from our experimental studies show that our model performs image generation successfully. In addition, we demonstrated the robustness of our model by testing its success in different image manipulation applications. As a result, our model can successfully produce realistic, high-quality, diverse images from a single training image, providing short training time, memory efficiency, and good training stability. Our model is flexible enough to be used in areas where limited data needs to be worked on.
- 1 April 2020
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 45 (4) , 2865-2882
A Novel Short Text Clustering Model Based on Grey System Theory
- 1 April 2020
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 45 (4) , 2865-2882
A Novel Short Text Clustering Model Based on Grey System Theory
- Open Access
A Decision Support System Using Text Mining Based Grey Relational Method for the Evaluation of Written Exams
Grey relational analysis (GRA) is a part of the Grey system theory (GST). It is appropriate for solving problems with complicated interrelationships between multiple factors/parameters and variables. It solves multiple-criteria decision-making problems by combining the entire range of performance attribute values being considered for every alternative into one single value. Thus, the main problem is reduced to a single-objective decision-making problem. In this study, we developed a decision support system for the evaluation of written exams with the help of GRA using contextual text mining techniques. The answers obtained from the written exam with the participation of 50 students in a computer laboratory and the answer key prepared by the instructor constituted the data set of the study. A symmetrical perspective allows us to perform relational analysis between the students’ answers and the instructor’s answer key in order to contribute to the measurement and evaluation. Text mining methods and GRA were applied to the data set through the decision support system employing the SQL Server database management system, C#, and Java programming languages. According to the results, we demonstrated that the exam papers are successfully ranked and graded based on the word similarities in the answer key.
Open AccessA Decision Support System Using Text Mining Based Grey Relational Method for the Evaluation of Written Exams
Grey relational analysis (GRA) is a part of the Grey system theory (GST). It is appropriate for solving problems with complicated interrelationships between multiple factors/parameters and variables. It solves multiple-criteria decision-making problems by combining the entire range of performance attribute values being considered for every alternative into one single value. Thus, the main problem is reduced to a single-objective decision-making problem. In this study, we developed a decision support system for the evaluation of written exams with the help of GRA using contextual text mining techniques. The answers obtained from the written exam with the participation of 50 students in a computer laboratory and the answer key prepared by the instructor constituted the data set of the study. A symmetrical perspective allows us to perform relational analysis between the students’ answers and the instructor’s answer key in order to contribute to the measurement and evaluation. Text mining methods and GRA were applied to the data set through the decision support system employing the SQL Server database management system, C#, and Java programming languages. According to the results, we demonstrated that the exam papers are successfully ranked and graded based on the word similarities in the answer key.
- 12 March 2019
- Published by Bitlis Eren Universitesi Fen Bilimleri Dergisi in Bitlis Eren Üniversitesi Fen Bilimleri Dergisi
- Vol. 8 (1) , 234-242
Türkçe Karakter Destekli Genişletilmiş Kayan Polybius Karesi ile Şifrelenmiş Veriyi Gömme
The security of a message transmitted from one peer to another is a matter of many studies over centuries. Today, with digital communication, billions of data are transmitted from one point to another every milisecond. That is why data security has become one of the most studied topics. In this study, an ancient encryption method called Polybius square which has been a source of inspiration for today's encryption methods is introduced. In addition an expanded version of Polybius square was developed adding Turkish character support. An encryption key has also been added to the Polybius cipher. The entire message can be encrypted with a key or with different keys in each character of the message. The encrypted message is hidden within the pixels of the picture files using the LSB algorithm. Thus, when the message is transmitted to the other side, it is encrypted with a private key, hidden inside a cover data, and has become unsuspicious. To measure the change in cover data; MSE, PSNR and SSIM measurement methods are used. The method proposed in the study is coded with a visual programming language. The developed software has been introduced and its results are shown.
- 12 March 2019
- Published by Bitlis Eren Universitesi Fen Bilimleri Dergisi in Bitlis Eren Üniversitesi Fen Bilimleri Dergisi
- Vol. 8 (1) , 234-242
Türkçe Karakter Destekli Genişletilmiş Kayan Polybius Karesi ile Şifrelenmiş Veriyi Gömme
The security of a message transmitted from one peer to another is a matter of many studies over centuries. Today, with digital communication, billions of data are transmitted from one point to another every milisecond. That is why data security has become one of the most studied topics. In this study, an ancient encryption method called Polybius square which has been a source of inspiration for today's encryption methods is introduced. In addition an expanded version of Polybius square was developed adding Turkish character support. An encryption key has also been added to the Polybius cipher. The entire message can be encrypted with a key or with different keys in each character of the message. The encrypted message is hidden within the pixels of the picture files using the LSB algorithm. Thus, when the message is transmitted to the other side, it is encrypted with a private key, hidden inside a cover data, and has become unsuspicious. To measure the change in cover data; MSE, PSNR and SSIM measurement methods are used. The method proposed in the study is coded with a visual programming language. The developed software has been introduced and its results are shown.