Explainable Artificial Intelligence (XAI) is increasingly important in computer vision, aiming to connect complex model outputs with human understanding. This review provides a focused comparative analysis of representative XAI methods in four main categories, attribution-based, activation-based, perturbation-based, and transformer-based approaches, selected from a broader literature landscape. Attribution-based methods like Grad-CAM highlight key input regions using gradients and feature activation. Activation-based methods analyze the responses of internal neurons or feature maps to identify which parts of the input activate specific layers or units, helping to reveal hierarchical feature representations. Perturbation-based techniques, such as RISE, assess feature importance through input modifications without accessing internal model details. Transformer-based methods, which use self-attention, offer global interpretability by tracing information flow across layers. We evaluate these methods using metrics such as faithfulness, localization accuracy, efficiency, and overlap with medical annotations. We also propose a hierarchical taxonomy to classify these methods, reflecting the diversity of XAI techniques. Results show that RISE has the highest faithfulness but is computationally expensive, limiting its use in real-time scenarios. Transformer-based methods perform well in medical imaging, with high IoU scores, though interpreting attention maps requires care. These findings emphasize the need for context-aware evaluation and hybrid XAI methods balancing interpretability and efficiency. The review ends by discussing ethical and practical challenges, stressing the need for standard benchmarks and domain-specific tuning.

This research paper provides a pragmatic basis to use quaternions in application to machine learning and assesses cat and dog image classification with a twist of using OBLR (Orthogonal Basis and Logistic Regression) with PCA (Principal Component Analysis) and Entropy. The OBLR method uses the Gram-Schmidt technique of orthogonalization to derive an independent, orthogonal feature space for cats and dogs separately, followed by application with logistic regression for categorization. In simple terms, “The Entropy and PCA Method” reduces the data dimensionality in the image with PCA and classifies based on the variation of entropy among classes. It picks the limitations of these two methods and chooses the advantages. The result of the study indicated that both the methods considered were found effective in the classification of images containing cats and dogs, and therefore, useful applications in the management of stray animals and control of pet health. Our forthcoming scopes will include the implementation of OBLR and PCA with entropy, the implementation of more sophisticated machine learning models like CNNs, and statistical metrics of feature selection techniques that would be useful to further improve the classification accuracy.

This study explores the impact of big data analytics and corporate equity concentration on Total Factor Productivity (TFP) in Chinese enterprises. In today's globalized economy, where efficiency and innovation are crucial for economic growth, understanding the factors that influence TFP is essential. Big data analytics, encompassing models and algorithms, architectures, management, and data security, has become a transformative force in corporate governance and decision-making processes. The integration of big data techniques enables firms to enhance transparency, optimize resource allocation, and improve production efficiency. Concurrently, corporate equity concentration significantly affects decision-making and management oversight within firms. While higher equity concentration can mitigate agency problems and enhance oversight, potentially boosting TFP, it may also lead to issues such as insider control and reduced innovation if excessively high. Using empirical data from A-share listed companies in Shanghai and Shenzhen from 2007 to 2022, this study examines the relationship between equity concentration and TFP, considering the moderating effects of ownership structure, regional financial development, and big data analytics. The findings provide theoretical insights and policy recommendations for optimizing corporate governance and leveraging big data to enhance productivity. This research contributes to the ongoing debate on the role of equity concentration in corporate performance, highlighting its complex influence on TFP and the need for balanced governance structures and advanced data analytics to foster sustainable economic growth.

Over the past few years, the importance of data analytics in sports has increased dramatically, reshaping the way teams and athletes prepare for and participate in competitions. As a globally popular sport, soccer has particularly benefited from the application of machine learning techniques, which aim to enhance multiple aspects of the game, such as improving player performance and refining tactical strategies. One of the critical areas gaining attention in this context is the prediction and optimization of shot trajectories. Conventional methods for analyzing soccer shots often depend on observational data and basic statistical approaches, which might not adequately represent the complexities involved in a player’s decision-making or the multitude of factors affecting the success of a shot [1].

The world's premier source for conference proceedings, offering Print-on-Demand, DOI, and Content Hosting services.