Microcalcifications in mammogram images are primary indicators for detecting the early stages of breast cancer. However, dense tissues and noise in the images make it challenging to classify the microcalcifications. Currently, preprocessing procedures such as noise removal techniques are applied directly on the images, which may produce a blurry effect and loss of image details. Further, most of the features used in classification models focus on local information of the images and are often burdened with details, resulting in data complexity. This research proposed a filtering and feature extraction technique using persistent homology (PH), a powerful mathematical tool used to study the structure of complex datasets and patterns. The filtering process is not performed directly on the image matrix but through the diagrams arising from PH. These diagrams will enable us to distinguish prominent characteristics of the image from noise. The filtered diagrams are then vectorised using PH features. Supervised machine learning models are trained on the MIAS and DDSM datasets to evaluate the extracted features’ efficacy in discriminating between benign and malignant classes and to obtain the optimal filtering level. This study reveals that appropriate PH filtering levels and features can improve classification accuracy in early cancer detection.
5 December 2025 in International Journal of Data Science and Analytics
Evaluating behavioral patterns through logic mining within a given dataset has become a primary focus in current research. Unfortunately, there are several weaknesses in the research regarding the logic mining models, including an uncertainty of the attribute selected in the model, random distribution of negative literals in a logical structure, non-optimal computation of the best logic, and the generation of overfitting solutions. Motivated by these limitations, a novel logic mining model incorporating the mechanism to control the negative literal in the systematic Satisfiability, namely Weighted Systematic 2 Satisfiability in Discrete Hopfield Neural Network, is proposed as a logical structure to represent the behavior of the dataset. For the proposed logic mining models, we used ratio of r to control the distribution of the negative literals in the logical structures to prevent overfitting solutions and optimize synaptic weight values. A new computational approach of the best logic by considering both true and false classification values of the learning system was applied in this work to preserve the significant behavior of the dataset. Additionally, unsupervised learning techniques such as Topological Data Analysis were proposed to ensure the reliability of the selected attributes in the model. The comparative experiments of the logic mining models by utilizing 20 repository real-life datasets were conducted from repositories to assess their efficiency. Following the results, the proposed logic mining model dominated in all the metrics for the average rank. The average ranks for each metric were Accuracy (7.95), Sensitivity (7.55), Specificity (7.93), Negative Predictive Value (7.50), and Mathews Correlation Coefficient (7.85). Numerical results and in-depth analysis demonstrated that the proposed logic mining model consistently produced optimal induced logic that best represented the real-life dataset for all the performance metrics used in this study.
6 January 2025 in Environmental Monitoring and Assessment
Efficient investigation tools are required to elucidate the changes in climatic change caused by various climate processes, variables, and socioeconomic development activities around the world. In this study, we track the changes of daily rainfall at three flood-prone sites in Terengganu between 2012 to 2017. In recent years, topological data analysis (TDA) has been applied in many fields of data analytics to rank, classify, and cluster time series datasets. In this work, we employ Persistent Homology to quantify and identify topological patterns from a rainfall data. A sliding window (SW) approach is used for each 1D rainfall dataset to embed in higher dimensions before computing its Persistence Diagrams (PD). The topological information obtained from PD, namely connected components (H0) is then retrieved and vectorized in the form of Persistence Curves (Persistence Landscape (PL), Persistence lifetime Curve (PLC), and Persistence Lifetime Entropy (PLE)) to identify unusual rainfall patterns. We employ various types of L1-norms from these Persistence vectors to identify anomalies in rainfall data which can be used as an early warning flood system. The irregular pattern of Persistence lifetime and Persistence entropy mismatch the actual flood events suggesting that the irregular points may not be as closely related to flood risk. However, PL analysis of the irregular points shows match of about 59% to the flood events.It is expected that other determining factors, for example, land use, cloud cover, and wind information, which can be obtained via satellite gridded data may increase the predictability of flood events thus promotes an effective flood risk management strategies.