Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Computer Science

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Ensemble machine learning methods to predict the balancing of ayurvedic constituents in the human body

Rajasekar Vani, Krishnamoorthi Sathya, Saracevic Muzafer, Pepic Dzenis, Zajmovic Mahir, Zogic Haris

Computer Science

2022

T. 23 (1)

117--132

In this paper, we demonstrate the result of certain machine-learning methods like support vector machine (SVM), naive Bayes (NB), decision tree (DT), k-nearest neighbor (KNN), artificial neural network (ANN), and AdaBoost algorithms for various performance characteristics to predict human body constituencies. Ayurveda-dosha studies have been used for a long time, but the quantitative reliability measurement of these diagnostic methods still lags. The careful and appropriate analysis leads to an effective treatment to predict human body constituencies. From an observation of the results, it is shown that the AdaBoost algorithm with hyperparameter tuning provides enhanced accuracy and recall (0.97), precision and F-score (0.96), and lower RSME values (0.64). The experimental results reveal that the improved model (which is based on ensemble-learning methods) significantly outperforms traditional methods. According to the findings, advancements in the proposed algorithms could give machine learning a promising future.

Memoization method for storing of minimum-weight triangulation of a convex polygon

Selimi Aybeyan, Krrabaj Samedin, Saracevic Muzafer, Pepić Selver

Computer Science

2019

Vol. 20 (2)

195--211

This study presents a practical view of dynamic programming, specifically in the context of the application of finding the optimal solutions for the polygon triangulation problem. The problem of the optimal triangulation of polygon is considered to be as a recursive substructure. The basic idea of the constructed method lies in finding to an adequate way for a rapid generation of optimal triangulations and storing - them in as small as possible memory space. The upgraded method is based on a memoization technique, and its emphasis is in storing the results of the calculated values and returning the cached result when the same values again occur. The significance of the method is in the generation of the optimal triangulation for a large number of n. All the calculated weights in the triangulation process are stored and performed in the same table. Results processing and implementation of the method was carried out in the Java environment and the experimental results were compared with the square matrix and Hurtado-Noy method.