Journal of Food, Agriculture and Environment

A GPU accelerated mushroom classifier system using machine learning algorithm

Author(s):

Vandana Shah, Dhruvi Kapadia

Recieved Date: 2021-10-22, Accepted Date: 2021-12-18

Abstract:

This paper studies the classification method for mushroom based on Machine Learning Algorithm and Graphic Processors. As mushrooms have large number of species (approximately 14,000 species are described) classification of mushrooms turns out to be difficult. These large number of species contain some edible and some poisonous or deadly poisonous mushrooms. Sometimes mushroom recognition is difficult through our naked eyes and also due to lack of knowledge of identification of edible mushrooms, recognition turns out to be complicated. Although there are experts in distinguishing poisonous mushrooms from list of edible mushrooms, where 70-80 species are reported as poisonous, yet occasional cases occur of misidentification of fatal mushrooms. Also, mushroom collectors have no formal discipline for testimony of mushrooms, due to which people consume such wild mushrooms misidentified as nutritious mushrooms resulting in life threatening disease or death causing illnesses. The main aim of this project was to apply a method to detect that the mushrooms which fit for human consumption or not. This paper proposes a method to determine the mushrooms quality using categorical dataset which has 23 distinct characteristics. To solve the complication of classification of mushrooms, a supervised learning model with associated learning model is used. This method achieves a good result through the comparison of total time and speed between gpu and cpu;

Keywords:

Categorical features, support vector machine, convolution neural network, graphics processor, machine learning

---

Journal: Journal of Food, Agriculture and Environment
Year: 2022
Volume: 20
Issue: 1
Category: Food and Health
Pages: 62-69

---

Full text for Subscribers

---

Information:

Note to users

The requested document is freely available only to subscribers / registered users with an online subscription to this Journal. If you have set up a personal subscription to this title please enter your user name and password (https://www.wflpublisher.com/Pages/subscription-procedure). All abstracts are available for free.

Article purchasing

If you like to purchase this specific document such as article, visit the site https://www.wflpublisher.com/Journal. Software and compilation, Science & Technology, all rights reserved. Your use of this website details or service is governed by terms of use. Authors are invited to check from time to time news or information.

---

Purchase this Article:   20 Purchase PDF Order Reprints for 15

---

Share this article :