Comparative Analysis of Supervised Learning Algorithms for Predictive Modeling of Abalone Age
Abstract
Abalone is a marine snail found in the cold coastal regions. Age is a vital characteristic that is used to determine its worth. Currently, the only viable solution to determine the age of abalone is through very detailed steps in a laboratory. This paper exploits various machine learning models for determining its age. The model was built based on a dataset obtained from the UCI Machine Learning Repository. A comprehensive analysis of various machine learning algorithms for abalone age prediction is performed which include, K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree and Support Vector Machine (SVM). The three classifiers tested to evaluate their effect on its performance. Comprehensive experiments were performed using our data set.
Keywords
Download Options
Introduction
Abalone is a sort of single-shelled marine snails. It is otherwise called the snail of the ocean with a huge beefy body including expansive strong food, which has turned into a costly connoisseur delicacy because of its short fishing seasons [1]. The worth of abalone is monetarily connected with its age. Hence, the age of the abalone assumes an essential part for the two ranchers and shoppers to decide its cost. The age of the abalone is profoundly connected to its costs as it is the sole variable used to decide its worth [4]. In any case, deciding the time of abalone is a profoundly elaborate cycle that is normally done in a research center. Deciding its age is expected in logical examinations like sea life science on abalone. Ordinarily, the quantities of layers of shell rings are estimated to appraise the abalone age [7]. The rings framed relates to the development of the abalone. The most common way of deciding the abalone age begins with chopping down the shell of an abalone. The shell cone is then stained so the rings will be more noticeable to count [8]. Abalone age can be assessed in light of the quantity of dim groups on the right-hand side of the segment. Because of the vulnerability of totally staining all rings, specialists have chosen to add a worth of 1.5 during the ring build up to work on the estimation of the abalone ages. This customary strategy influences ranchers as far as expenses and time handling[4]. Subsequently, to ad lib this cycle, AI can be carried out to help specialists utilizing an enormous number of information containing actual estimations of abalone to foresee its age in a short measure of time.
Conclusion
The results indicate that Support Vector Machine offers the highest accuracy, precision, and recall, making it the recommended algorithm for predicting the age of abalone in this specific context. These findings emphasize the importance of selecting appropriate algorithms for specific tasks, as different algorithms can yield different levels of performance. Overall, this study highlights the potential of machine learning algorithms, particularly Support Vector Machine, in accurately predicting the age of abalone. Further research and experimentation can help refine and improve these results, leading to more accurate predictions in real-world applications.