Skin cancer has emerged as a grave health concern leading to significant mortality rates. Diagnosis of this disease traditionally relies on specialist dermatologists who interpret dermoscopy images using the ABCD rule. However, the integration of computer-aided diagnosis technologies is gaining popularity as a means to assist clinicians in accurate skin cancer diagnosis, overcoming potential challenges associated with human error. The objective of this research is to develop a robust system for the detection of skin cancer by employing machine learning algorithms for skin lesion classification and detection. The proposed system utilizes Convolutional Neural Network (CNN), a highly accurate and efficient deep learning technique well-suited for image classification tasks. By using the power of CNN, this system effectively classifies various skin diseases in dermoscopic images associated with skin cancer The MNIST HAM10000 dataset, comprising 10015 images, serves as the foundation for this study. The dataset encompasses seven distinct skin diseases falling within the realm of skin cancer. In this study, diverse transfer learning methods were used and evaluated to enhance the performance of the system. By comparing and analyzing these approaches the highest accuracy rate was obtained using the MobileNetV2 model with a rate of 80.79% accuracy.

The production of electric and hybrid vehicles on land and at sea is now widely used to reduce carbon emissions. While charging the batteries of electric vehicles can be done manually, studies to automate this process are increasing. Recently, many studies based on computer vision have been carried out to provide real-time and more accurate detection of charging systems. For automatic charging, the position and distance of the socket on the ship approaching the shore can be determined by processing the image taken by the camera. For this purpose, in this study, an interface has been developed for the detection system of electrical charging system sockets by using classical image processing and the YOLO technique, which is one of the deep learning methods. With the developed interface, the socket's position can be detected and monitored in real-time through the image taken from the camera. Thus, automatic charging can be performed successfully.

Hazelnut (Corylus avellana L.) is a significant global agricultural product due to its high economic and nutritional worth. The traditional methods used to measure the hazelnut kernel percentage for quality assessment are often time-consuming, expensive, and prone to human errors. Inaccurate measurements can adversely impact the market value, shelf life, and industrial applications of hazelnuts. This research introduces a novel system for calculating hazelnut kernel percentage utilizing a non-destructive X-ray imaging technique along with deep learning methods to assess hazelnut quality more efficiently and reliably. An image dataset of hazelnut kernels has been developed using X-ray technology, and defective areas are identified employing YOLOv7 architecture. Additionally, a novel bounding box regression technique called DCIoU and an algorithm for Neighborhood Relationship have been introduced to enhance object detection capabilities and to improve the selection of the target box with greater precision, respectively. The performance of these proposed methods has been evaluated using both the created hazelnut dataset and the COCO-128 dataset. The results indicate that the system can serve as a valuable tool for measuring hazelnut kernel percentages by accurately identifying defects in hazelnuts.

This study aims to enhance organizational processes and support decision-making for managers by conducting an automated analysis of employee feedback through text classification. Employee satisfaction and motivation are critical factors that directly impact sustainability and efficiency goals. To overcome the challenges of manual feedback analysis, the study employs Temporal Convolutional Network (TCN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bidirectional Encoder Representations from Transformers (BERT) algorithms. The dataset comprises feedback collected from meeting notes, internal surveys, and manager-employee interviews, with data synthesis and preprocessing steps including text cleaning, tokenization, and modelling. The study's findings reveal that the CNN algorithm achieved the best performance, with an accuracy of 99.12%, a test loss of 0.0609, precision of 0.9912, recall of 0.9912, and an F1 score of 0.9911. This research demonstrates the valuable contribution of automated classification models in effectively and efficiently analysing employee feedback.

Open‐source large language models (LLMs) have significantly advanced natural language processing (NLP), particularly for English. However, their performance in Arabic has remained limited due to the scarcity of high‐quality datasets and the high computational cost of full fine‐tuning. To address this challenge, we curated and prepared a diverse collection of Arabic‐specific datasets covering translation, summarization, storytelling, dialogue generation, and Classical–Modern Arabic bridging. Building on these resources, we developed ArGemma, an Arabic‐adapted version of the Gemma model, fine‐tuned using Supervised Fine‐Tuning (SFT) with Low‐Rank Adaptation (LoRA) to enable efficient adaptation with reduced computational overhead. A hybrid approach integrating SFT, Retrieval‐Augmented Generation (RAG), and few‐shot prompting was also employed to enhance contextual understanding and performance—particularly for tasks requiring nuanced reasoning across different forms of Arabic. ArGemma's performance was evaluated using both quantitative metrics (BLEU, ROUGE) and qualitative assessments by native speakers and language experts to measure fluency, coherence, and contextual accuracy. Results demonstrate that LoRA‐based fine‐tuning, supported by carefully prepared datasets and retrieval‐augmented techniques, can significantly enhance Arabic NLP performance while remaining computationally efficient. This work, which was awarded third place in the 2025 Google—Unlock Global Communication with Gemma Kaggle competition, demonstrates how parameter‐efficient fine‐tuning (PEFT) combined with targeted dataset preparation can effectively expand LLM support for underrepresented languages like Arabic.

A new digital image watermarking method based on dual-tree complex wavelet transform is proposed. The proposed method is shown to be robust to geometric and non-geometric modifications performed on the watermarked image. The complex wavelet domain for watermark insertion gives rise to robustness for non-geometric modifications, while the image normalization provides robustness against geometric modifications. First, the original image is normalized. Then, a watermark is generated such that the capacity is more than one bit according to the properties of the human visual system, and it is added to the three detail subbands coefficients of the normalized image at the first decomposition level in the complex wavelet domain. Finally, successive applications of the inverse complex wavelet transform and the inverse normalization give the watermarked image. Computer simulations show that the method is robust to numerous image manipulations and is superior to the existing digital image watermarking approaches. However, the implementation of the complex wavelet transform is computationally costly. Hence, dual tree implementation is used to reduce computational complexity in the experiments.