Umut Altinişik

Regression testing in continuous integration (CI) helps preserve delivered software value by exposing regressions early, but limited feedback windows make test order consequential. This study evaluates a leakage-safe dynamic test case prioritization framework that reconstructs job–build–commit provenance, combines strictly prior-build history with change–test similarity, applies class-conditional conformal calibration, and evaluates an operator-level deep Q-network (DQN). The primary held-out evaluation contains 273 failure-bearing jobs and 45,774 job–test rows from four Java projects. Pretrained history–semantic fusion achieved an equal-project macro failing-test-entity APFD surrogate (FTE-APFD surrogate) of 0.8840, compared with 0.8689 for history-only and 0.7023 for pretrained semantic-only ranking; the fusion–history difference did not survive Holm correction. A train-only TF–IDF control reached 0.7502 for semantic-only ranking and 0.8871 when fused with history in a seed-averaged diagnostic, so the benchmark does not establish unique superiority of the pretrained representation. A protocol-aligned RETECS reimplementation achieved 0.8296 ± 0.0111 FTE-APFD surrogate across five seeds. Adaptive conformal calibration reduced the candidate fraction from 0.3171 to 0.2598 while retaining 0.9058 failing-test coverage. The candidate-informed gated DQN remained below strong deterministic fusion rankings at 10%, 25%, and 50% budgets; five-seed, short-budget, hyperparameter, pre-execution-budget, and project-exclusion sensitivities did not establish a consistent DQN advantage. An additional three-project operational analysis containing 444 passing test jobs showed high failing-row coverage but strongly project-dependent candidate burden. Overall, the evidence favors strong leakage-safe deterministic rankings with explicit uncertainty control, while the evaluated reinforcement-learning design remains a local negative result rather than a general conclusion about reinforcement learning.

Transportation is among the daily routines of many people and a large part of human life is spent in transportation. In a process where transportation has gained so much importance, it is important to regularly perform maintenance and repair of vehicles for comfortable, safe and fast transportation. In this study, it is aimed to improve the maintenance and repair times of Kocaeli Metropolitan Municipality tram operation. Therefore, Maintenance Repair Data Model is designed by applying K-NN (K-nearest neighbors) classification, Decision Trees and Deep Learning algorithms from Data Mining algorithms.Thus, the warranty periods of the trams are extended and the trams operate with maximum performance by looking at the mean time between failures and the length of maintenance work periods.Quantitative findings revealed that the K-NN algorithm achieved the highest performance with an accuracy rate of 87.6%, outperforming the Decision Tree 85.95% and Deep Learning 70.66% models. Moreover, the K-NN model demonstrated the most balanced classification performance, with a precision of 0.716, recall of 0.637, and an F1-score of 0.652. In contrast, the Deep Learning algorithm exhibited lower performance, with an F1-score of only 0.355, indicating its limited effectiveness when applied to structured maintenance data. These results suggest that in cases where the dataset is structured and relatively small in scale, simpler non-parametric models such as K-NN may offer more efficient and practical solutions for predicting maintenance durations.

Throughout the ages, safely preserving and transmitting data that have extraordinary importance for humanity has increased its importance with rapid advances in computer technology. Steganography stores hidden data within the files, which are unnoticed by third parties, so it provides secure transmission of data to the receiver. In this study, a steganography-based GUI design has been carried out, which ensures that the agricultural data is safely stored and communicated to the other party. We used LSB one-bit, two-bit, three-bit substitution and PVD algorithms with GUI for stages of agricultural data hiding and extracting at cover images. We also provided extra security using the embedded key and shifting operations on the hidden data before hiding data the cover image. In short, we confused the hidden data in the cover image so that malicious people can't understand. In experimental studies, performance analysis was evaluated by comparing various criteria as similarity ratio (Structural Similarity Index Measure, SSIM), stego image quality (Peak Signal-to-Noise Ratio, PSNR) and data hiding capacity (Payload).

The goals of image steganography are to simultaneously reach maximum embedding capacity, enhanced embedding efficiency, better image quality, and more security. We present a two-step data hiding method that improves image quality, capacity, and embedding efficiency, and also provides stego security. In the first step of the proposed method, the hidden data are encrypted with the key words and shifting method to provide security. In the second stage, we propose adaptive least-significant-bit (LSB)+3 type I and adaptive LSB+3 type II methods to hide encrypted data in the cover image. The image quality of the stego image obtained from the proposed adaptive LSB+3 method is better than the traditional three-bit LSB methods. When maximum data are embedded in the cover image, a peak signal-to-noise ratio (PSNR) greater than 41 dB is reached. Experimental studies show that adaptive LSB+3 type I and adaptive LSB+3 type II methods are higher PSNR values (3.48% and 5.73%) than the standard three-bit LSB substitution methods.

In this article, a new method is presented by adding bit shift of encrypted data in LSB method (SED-LSB). The message to be embedded in the cover image is encrypted by the key received from the user. Then, secret data are obtained by bit shifting operation using this encrypted text. Finally, the secret data is hidden inside the cover image using the LSB method. SED-LSB is performed by preparing GUI in MATLAB. The quality of the cover image is measured by Peak Signal-to-Noise Ratio (PSNR), besides the similarity between the cover and stego image is determined by the Structural Similarity Index (SSIM). The 512 x 512 size of colored images as Lena, Peppers, Fruits and Baboon are used to hide 87373 byte data. PSNR values are between 51.615 – 51.656 and SSIM values are between 0.99937 – 0.99982. In the proposed method, when data are hidden at a higher capacity, stage image is found not only secure but also high quality.

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

In this study, nuts are determined using image processing techniques and classified by k‐means and k‐means++ methods in rapid time. Firstly, pixel area (PA) and square area (SA) features are extracted by an image processing technique. Then, the obtained data are classified by the k‐means and k‐means++ clustering methods. We present a new method called the pixel area and square area method (PASAM), which is realized by clustering feature selection of PA and SA values. Our proposed method is applied on numerous real RGB images of nuts for different cases. Experimental results show that k‐means++ clustering based on PASAM is more efficient than other techniques such as k‐means and k‐means++ clustering based on PA and SA. The nuts in the working environment are determined and classified with 100% accuracy by PASAM.Practical applications: The proposed research distinguishes small, medium and big nuts based on image processing and PASAM. This method is appropriate to use to separate all vegetables and fruits for which classification is important.

Yapılan çalışmada, ortamda bulunan nesnelerin gerçek zamanlı olarak tespit edilmesi, sınıflandırılması ve elde edilen sonuçlar sunulmaktadır. Önerilen yönteme ait deneysel çalışmaların gerçekleştirilmesinde fındık meyvesi kullanılmaktadır. Çalışma ortamında bulunan fındıklara ait görüntü, kamera ile alındıktan sonra görüntü işleme teknikleri kullanılarak işlenmektedir. Fındıkların görüntü düzlemi üzerinde kapladıkları boyut ve alan verileri hesaplanmaktadır. Elde edilen veriler değerlendirilerek, fındıklar gerçek zamanlı olarak üç sınıfa ayrılmaktadır. Bu işlem ortalama tabanlı sınıflandırma ve K-means kümeleme yöntemleri kullanılarak gerçekleştirilmektedir. Küme merkezlerinin belirlenmesi ve sınıflandırma işlemi fındık meyvesi verilerinden elde edilen bilgi veritabanı kullanılarak sağlanmaktadır. Çalışma ortamında bulunan fındık meyveleri, görüntü işleme teknikleri kullanılarak %100 başarımla tespit edilmektedir. Fındık meyvelerinin, ortalama tabanlı ve K-means kümeleme yöntemleri kullanılarak sınıflandırılması karşılaştırılmıştır. Karşılaştırma sonucunda, gerçeklenen iki yöntemin %90 ila %100 başarım oranında benzeştiği gözlenmiştir.