Modelling Benign Ovarian Cyst Risk Factors and Symptoms via Log-Linear Model

Jamaludin, Siti Zulaikha Mohd; Ismail, Mohd Tahir; Kasihmuddin, Mohd Shareduwan Mohd; Mansor, Mohd. Asyraf; Antony, Siti Noor Farwina Mohamad Anwar; Makhul, Adnin Adawiyah

doi:10.47836/pjst.29.3.26

Cited by 4 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…E2SATRA uses similar objective functions to that of 2SATRA and only utilizes a single-unit DHNN. (c) L2SATRA was inspired by the work of [50], which employed the log-linear method to extract a model for an ovarian cyst dataset. This standard selection method utilized characteristics and incorporated conventional 2SATRA based on a log-linear analysis.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…The application of the log-linear analysis is assumed to be highly effective in pre-processing methods, as it identifies significant attributes with a p-value of p ≤ 0.05. This results in optimal synaptic weight values associated with the resulting attributes for L3SAT [50]. Furthermore, since the logical rules embedded in the G3SATRAµ model are well-structured, the outcomes have the potential to achieve higher values for the true positives (TPs) and true negatives (TNs).…”

Section: Accuracy For Current and G3satraµ Logic Mining Modelsmentioning

confidence: 99%

“…The multidimensional solution in the proposed systematic logical structure led to obtaining more TNs and less FPs. The existing logic mining methods L2SATRA [50] and A2SATRA [30] obtained sup-optimal performances in the testing phase, obtaining more FPs that reduce the precision value for their model.…”

Section: Precision For Current and G3satraµ Logic Mining Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Log-Linear-Based Logic Mining with Multi-Discrete Hopfield Neural Network

et al. 2023

View full text Add to dashboard Cite

Choosing the best attribute from a dataset is a crucial step in effective logic mining since it has the greatest impact on improving the performance of the induced logic. This can be achieved by removing any irrelevant attributes that could become a logical rule. Numerous strategies are available in the literature to address this issue. However, these approaches only consider low-order logical rules, which limit the logical connection in the clause. Even though some methods produce excellent performance metrics, incorporating optimal higher-order logical rules into logic mining is challenging due to the large number of attributes involved. Furthermore, suboptimal logical rules are trained on an ineffective discrete Hopfield neural network, which leads to suboptimal induced logic. In this paper, we propose higher-order logic mining incorporating a log-linear analysis during the pre-processing phase, the multi-unit 3-satisfiability-based reverse analysis with a log-linear approach. The proposed logic mining also integrates a multi-unit discrete Hopfield neural network to ensure that each 3-satisfiability logic is learned separately. In this context, our proposed logic mining employs three unique optimization layers to improve the final induced logic. Extensive experiments are conducted on 15 real-life datasets from various fields of study. The experimental results demonstrated that our proposed logic mining method outperforms state-of-the-art methods in terms of widely used performance metrics.

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Section: Accuracy For Current and G3satraµ Logic Mining Modelsmentioning

confidence: 99%