Clustering analysis is a primary method for data mining. The ever increasing volumes of data in different applications forces clustering algorithms to cope with it. DBSCAN is a well-known algorithm for density-based clustering. It is both effective so it can detect arbitrary shaped clusters of dense regions and efficient especially in existence of spatial indexes to perform the neighborhood queries efficiently. In this paper we introduce a new algorithm GriDBSCAN to enhance the performance of DBSCAN using grid partitioning and merging, yielding a high performance with the advantage of high degree of parallelism. We verified the correctness of the algorithm theoretically and experimentally, studied the performance theoretically and using experiments on both real and synthetic data. It proved to run much faster than original DBSCAN. We compared the algorithm with a similar algorithm, EnhancedDBSCAN, which is also an enhancement to DBSCAN using partitioning. Experiments showed the new algorithm's superiority in performance and degree of parallelism.

Although there is an improvement in breast cancer detection and classification (CAD) tools, there are still some challenges and limitations that need more investigation. The significant development in machine learning and image processing techniques in the last ten years affected hugely the development of breast cancer CAD systems especially with the existence of deep learning models. This survey presents in a structured way, the current deep learning-based CAD system to detect and classify masses in mammography, in addition to the conventional machine learning-based techniques. The survey presents the current publicly mammographic datasets, also provides a dataset-based quantitative comparison of the most recent techniques and the most used evaluation metrics for the breast cancer CAD systems. The survey provides a discussion of the current literature and emphasizes its pros and limitations. Furthermore, the survey highlights the challenges and limitations in the current breast cancer detection and classification techniques.

No abstract

No abstract

No abstract