International Journal of Intelligent Computing Systems

Abstract:

Credit card fraud detection continues to be a major challenge in the financial industry due to extreme class imbalance, where fraudulent transactions occur far less frequently than legitimate ones. Traditional machine learning models often perform poorly on such imbalanced datasets, resulting in inadequate fraud detection rates. This paper introduces a sophisticated fraud detection framework that utilizes Variational Autoencoders (VAEs) for generating synthetic data and the Synthetic Minority Over-sampling Technique (SMOTE) to balance the minority class. Our hybrid approach generates realistic synthetic fraudulent samples while mitigating overfitting and loss of information associated with traditional oversampling techniques.

We evaluated multiple classification models, including XGBoost, Deep Neural Networks (DNN), AdaBoost, and CatBoost, using an augmented dataset and conducted a comparative analysis with conventional oversampling techniques. Extensive experiments demonstrate that our hybrid augmentation strategy significantly enhances fraud detection performance by increasing recall and F1-score while reducing false positives. We also discuss the trade-offs between different synthetic data generation techniques and their impact on classifier performance. Furthermore, we explore adversarial training techniques and their potential for real-time fraud detection deployment.

Abstract:

Small object detection in remote sensing images is essential for urban planning, environmental monitoring, disaster relief operations, and defence. Detecting small objects is still challenging because of sparse pixel representation, class imbalance, and complex background. The conventional object detection models, such as Faster R-CNN and RetinaNet, have difficulty preserving fine-grained spatial information, and the detection accuracy is lower. In this paper, we apply YOLOv8, a cutting-edge deep learning model, to improve detection of small objects. The model is trained and tested on the DIOR data set, which consists of diverse aerial images with horizontal bounding boxes. Preprocessing operations involve parsing XML annotations, translating bounding box coordinates to YOLO format, and performing data augmentation to enhance generalization. The performance of the model is measured using mean Average Precision (mAP), Precision, Recall, and Accuracy. Experimental results show that YOLOv8 obtains a mAP@50 of 73.4% on training and 71.0% on testing, and a mAP@50-95 of 50.3% and 48.5%, respectively. The model also obtains high Precision and Accuracy, better than the previous versions of YOLO and conventional detectors. In comparison with transformer-based models such as DETR, YOLOv8 provides the best speed-accuracy trade-off for real-time applications. This work forms an effective basis for detecting small objects, allowing scalable and automated surveillance systems for high-resolution satellite images in remote sensing applications.

Abstract:

Text-to-image generation has seen remarkable progress with the emergence of deep learning models like Stable Diffusion.These models allow for high-quality and customized image creation. However, conventional approaches often require extensive computational resources and subject-specific fine- tuning, limiting their scalability and accessibility. Instant Imager eliminates this need by leveraging in-context learning, enabling the model to replicate the capabilities of numerous subject-specific expert models. This innovation allows for the instant creation of high-flexibility and creative potential. The framework’s efficiency is evident in its ability to generate customized images 10 times faster than the conventional optimization methods, while delivering user specific number of images with superior quality. Evolutions on stable-diffusion- v1-5 and stable-diffusion-sdxl-turbo datasets highlight its performance, consistency outperforming existing models as confirmed by generation process. In addition to speed and quality, Instant Imager streamlines the image generation process, making it an essential tool for artists, designers, and content creators.

Abstract:

Object detection plays a crucial role in the development of intelligent and efficient traffic management systems, allowing authorities to effectively monitor, analyze, and regulate traffic flow. This paper introduces the design and implementation of a real-time object detection system powered by YOLOv8 (You Only Look Once), a cutting-edge deep learning model recognized for its high speed and accuracy in object detection tasks. The proposed system can identify and classify various vehicle types—such as cars, trucks, buses, motorcycles, and bicycles—from live traffic surveillance footage. Experimental results indicate that YOLOv8 delivers high detection accuracy alongside real-time processing, making it highly viable for practical deployment in traffic monitoring and law enforcement applications. By integrating object detection with speed and surveillance features, the system offers a holistic solution to modern traffic management issues. This research underscores the potential of YOLOv8-based systems in supporting automated and Intelligent Transportation Systems (ITS), contributing to safer and more efficient urban mobility. Future enhancements may involve incorporating multi-object tracking (MOT) for persistent vehicle tracking and extending the system’s functionality to operate under nighttime or low-visibility conditions.

Abstract:

AI is revolutionizing fashion by automating clothing categorization and trend identification. This project classifies outfits into casual, sports, and formal categories using TensorFlow, ensuring accurate classification while identifying key attributes like gender, color, and outfit type. Convolutional Neural Networks (CNNs) enhance pattern recognition, improving classification accuracy. The model refines fashion suggestions, facilitates product filtering on e-commerce platforms, and provides tailored outfit recommendations, leading to an improved shopping experience and higher customer satisfaction. Retailers benefit from optimized inventory management and better demand forecasting. As AI continues to evolve, its role in fashion innovation will expand, enabling more precise style predictions and enhanced personalization. This paper highlights how machine learning transforms fashion by streamlining outfit classification and making the industry more efficient, intelligent, and user- centric.