Conference Publications
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 19
-
PublicationExploring the efficacy of a supervised learning approach in 3 satisfiability reverse analysis method(AIP Publishing, 2024-08-27)The conventional Discrete Hopfield Neural Network encounters a notable challenge in generating an output representation that is interpretable by the user. In response to this challenge, a symbolic rule has been introduced to govern the information embedded in the network. This approach has proven successful, leading us to develop a logic mining model that utilizes the logical rule of 3 Satisfiability in Discrete Hopfield Neural Network to represent attributes for repository datasets. Nevertheless, the existing 3 Satisfiability Reverse Analysis model faces two primary issues: random attribute selection and predetermined attribute arrangement. These issues can significantly impact the ability of the model to retrieve the optimal induced logic. In response, a solution that involves a supervised attribute selection benchmark using correlation analysis is proposed. Additionally, a permutation operator to allow for various attribute arrangements was implemented, thereby expanding the search space and increasing the likelihood of finding an optimal solution. Furthermore, a novel objective function for determining the best logic, which considers both true positives and true negatives is also introduced. This differs from the conventional 3 Satisfiability Reverse Analysis method, which relies solely on true positives. Three performance metrics, including accuracy, precision, and Matthews Correlation Coefficient (MCC), and tested on 13 real-life datasets to validate the efficiency of our proposed model. The results clearly demonstrated that our proposed model consistently outperforms the conventional 3 Satisfiability Reverse Analysis method, achieving the highest values for all performance metrics.
-
PublicationLogic mining model in 3-satisfiability reverse analysis into discrete hopfield neural network(AIP Publishing, 2024-08-27)Logic mining is a powerful tool for organizations seeking to derive insights from large datasets. By analyzing data and identifying trends, logic mining can help solve problems, prevent losses, and uncover opportunities. In this study, we introduce an innovative approach that uses 3-Satisfiability logical rules and integrates them into the Hopfield neural network to better understand specific datasets. Our primary objective is to develop a robust statistical method called log-linear analysis, which can extract the most relevant attributes and insights. To accomplish this, we employ the 3-Satisfiability Reverse Analysis Method to extract attributes as logical rules from carefully selected 15 datasets. This method serves as a standalone logic mining paradigm, which we seamlessly integrate with the 3-Satisfiability logic within the Hopfield Neural network. Our proposed method assesses and trains datasets generated by standard algorithms. We then compare the performance of the 3-Satisfiability Reverse Analysis results with existing logic mining models, and our proposed method achieves superior accuracy, sensitivity, and Matthews Correlation Coefficient.
-
PublicationNumerical analysis of one-mass mechanical model of vocal cord using normal and pathological voices through cubic B-spline collocation method(AIP Publishing, 2024-09-13)Vocal cords play a crucial role in human speech production. The development of mechanical models of vocal cords has increased the understanding of their role and functionality. Numerous numerical studies have been explored to investigate the properties of vocal cord. In this work, one-mass mechanical model of vocal cord has been identified to be solved numerically using B-spline collocation method. Parameters of the model have been extracted from real voices data classified as normal and pathological voices. New results, displacement of vocal cord at time, t, have been generated for each voice. The findings indicated that each voice produced a different value of displacement due to the damping and subglottal pressure of each voice. The number of phases and highest peaks displacement have also been discovered in the finding.
-
PublicationUnsteady stagnation-point flow and heat transfer over an exponential stretching/shrinking sheet in hybrid nanofluid exhibiting slip effect(AIP Publishing, 2024-08-19)This study focuses on the investigation of unsteady stagnation-point flow and heat transfer over an exponential stretching/shrinking sheet immersed in a hybrid nanofluid. Hybrid nanofluid is an engineered fluid and can enhance thermal conductivity and heat transfer efficiency and stagnation-point flow is important in designing heat exchangers. Hence, the heat exchange process such as in power generation, and refrigeration becomes more effective. This mathematical model applied the Tiwari and Das model where Al2O3 - Cu hybrid nanofluid is considered. The base fluid is water, and the shape of the nanoparticle is considered in sphere shape. The ordinary differential equations are solved using the bvp4c function in the Matlab program to obtain the skin friction coefficient, heat transfer rate as well as velocity and temperature profiles. This study provides some tables of the skin-fiction coefficients and heat transfer rate values for the validation with the previous study and new values for the future study. This study reveals that dual solutions exist for suction s > sc. The increase of copper nanoparticles expands the solution and increases the skin friction coefficient at the surface. Meanwhile, by considering the higher effect of the slip parameter, the findings show an increment in both skin friction coefficient and heat transfer rate at the surface. The heat transfer rate is seen increasing by considering the same value of nanoparticle Volume fraction for copper and alumina compared to the different values.
-
PublicationOutlier detection method in multiple circular regression model via robust circular distance(AIP Publishing, 2024-08-19)The method of outlier detection with regards to circular regression have been widely developed nowadays. Several diagrammatical plots, numerical presentation as well as hypothesis testing have been recommended in detecting the outliers. As we know, the presence of outliers in dataset significantly impacts the parameter estimation and inference of the statistics. The outlier detection that exists in multiple circular regression model (MCRM) also attracting the interest of statisticians and researchers to do the research in depth. This paper presents the outlier detection method in MCRM using circular distance as well as circular error. The proposed method has been investigated through simulation study and the 5% upper percentiles is considered in obtaining the cut-off point as well as the performance power. Here, the procedure successfully identifies two outliers detected in the data set.