Abstract: As artificial intelligence (AI) systems become increasingly complex and pervasive, the need for transparency and interpretability has never been more critical. Explainable AI (XAI) addresses this need by providing methods and techniques to make AI decisions more understandable to humans. This paper explores the core principles of XAI, highlighting its importance for trust, accountability, and ethical AI deployment. We examine various XAI techniques, including interpretable models and post-hoc explanation methods, and discuss their strengths and limitations. Additionally, we present case (...) studies demonstrating the practical applications of XAI across diverse domains such as healthcare, finance, and autonomous systems. The paper also addresses the ongoing challenges and outlines future research directions aimed at enhancing the effectiveness and applicability of XAI. By bridging the gap between complex AI systems and human understanding, XAI plays a pivotal role in fostering more reliable and responsible AI technologies. (shrink)

Abstract. This study explores the use of convolutional neural networks (CNNs) for classifying different pineapple varieties, specifically pineapples and mini pineapples. By using a dataset of pineapple images, the research demonstrates the effectiveness of a pre-trained VGG16-based CNN model in accurately classifying these fruit categories. The model achieved over 99% accuracy on both the training and validation sets. The performance of the CNN was compared to traditional machine learning algorithms to highlight the advantages of deep learning in image classification tasks. (...) The results underscore the model’s ability to generalize well to the classification task, offering insights into feature extraction from complex image datasets. (shrink)

Abstract: Accurate identification of marine species is critical for effective fishery management, biodiversity conservation, and the aquaculture industry. Traditional methods of fish identification rely on expert knowledge and manual labor, making them time- consuming, expensive, and error-prone. In this research, we explore a machine learning-based approach to automate the classification of nine fish species using image recognition techniques. The fish species under study include Black Sea Sprat, Gilt- Head Bream, Horse Mackerel, Red Sea Bream, Shrimp, Trout, Striped Red Mullet, Sea (...) Bass, and Red Mullet. We collected 1000 images per species, yielding a total of 9000 images, with 750 used for training and 250 reserved for testing. We utilized convolutional neural networks (CNNs) pre-trained on the ImageNet dataset and fine-tuned them to perform fish species classification. Preliminary experiments showed that CNNs, particularly transfer learning models like VGG16 and ResNet50, achieved accuracy rates as high as 98.6% on the test set. This research highlights the potential of deep learning in automating marine species identification, enabling faster, more reliable monitoring. (shrink)

Abstract: Vegetables that are popular and versatile over the world are peppers. Precise categorisation of pepper cultivars is vital for multiple uses, such as assessing market trends, regulating quality, and conducting genetic research. Classifying peppers using traditional methods can be subjective and time-consuming. This research proposes an automated pepper variety classification method based on deep learning. A deep convolutional neural network (CNN) model was trained on a dataset of 2,368 photos of peppers. With the purpose of accurately classifying the pepper (...) photos, the CNN was built to extract essential features from them. The trained model demonstrated its efficacy in differentiating between pepper varieties with an astounding accuracy of 100% on a held-out test set. Deep learning has the capacity to classify peppers accurately and efficiently, as this study shows. The suggested strategy can help the food processing, quality control, and agriculture sectors advance. (shrink)

Abstract. This study investigates the application of convolutional neural networks (CNNs) to the task of classifying male and female eyes. Using a dataset of eye images, the research explores the potential of deep learning to accurately distinguish between the genders based solely on eye features. The proposed CNN model achieved 94% accuracy on the training set and 91% on the validation set. The study addresses the challenges and limitations in feature extraction from eye images and compares the proposed model with (...) traditional machine learning approaches. The results demonstrate the model's robustness, providing significant insights into gender recognition through partial facial analysis. (shrink)

Abstract: Abstract: The classification of nuts is crucial for food security; nevertheless, accurate and swift identification continues to be a challenge in numerous areas due to insufficient infrastructure. The rise in smartphone utilization, along with advancements in computer vision driven by deep learning, has facilitated smartphone-assisted nut classification. We trained a deep convolutional neural network to categorize five distinct nut types (Chestnut, Hazelnut, Nut Forest, Nut Pecan, and Walnut) using a public dataset of 2,850 photos gathered under controlled conditions. The (...) model attained an accuracy of 98.37% on a reserved test set, illustrating the viability of this method. This approach offers a viable avenue for large-scale smartphone-assisted nut categorization. (shrink)

Abstract: In modern agriculture, ensuring the quality of crops plays a vital role in enhancing production and minimizing waste. This research focuses on the classification of lemon plants into two categories: good quality and bad quality, using deep learning techniques. We employ convolutional neural networks (CNN) to develop a classification model that can accurately predict plant quality based on images. Through a structured pipeline involving data collection, preprocessing, model design, and evaluation, we demonstrate the effectiveness of CNNs in performing quality (...) assessments. This paper discusses the experimental results in applying deep learning to agricultural tasks. (shrink)

Abstract: This research focuses on the classification of nine varieties of dates using deep learning techniques. The study aims to develop an accurate and efficient model capable of identifying different types of dates based on images. A Convolutional Neural Network (CNN) was employed, trained on a dataset comprising thousands of date images, processed to enhance classification performance. The model was evaluated on multiple metrics, achieving high accuracy rates, demonstrating the feasibility of using deep learning in date classification. This approach can (...) significantly aid in automating the identification process, which is crucial for the agricultural industry. The results indicate that deep learning techniques offer a robust solution for the classification of date varieties, with potential applications in quality control and market sorting. (shrink)