Artificial Neural Network: Gas recognition
The objective of this paper is to describe development of gas recognition tool based on Artificial Neural Network (ANN). This recognition tool has capability to recognize five different gases: ammonia, acetaldehyde, acetone, ethylene, and ethanol. Develop
- PDF / 270,539 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 54 Downloads / 242 Views
ernational Burch University Sarajevo Bosnia and Herzegovina [email protected], [email protected], [email protected]
Abstract. The objective of this paper is to describe development of gas recognition tool based on Artificial Neural Network (ANN). This recognition tool has capability to recognize five different gases: ammonia, acetaldehyde, acetone, ethylene, and ethanol. Developed ANN is trained using data from the UC Irvine Machine Learning Repository database from October, 2013. The implemented system for gas recognition uses following input parameters: concentration of gas (ppmv), flammability, constant pressure (kJ/kgK), constant volume (Kj/kgK), specific heat capacities (cp/cv) and molecular weight (g/mol). Developed neural network consists of 30 neurons distributed in a single hidden layer. For purpose of training 174 samples were used. Testing dataset contained 64 samples, 38 of which were used as a testing set. With 36 samples correctly classified resulting in accuracy and specificity were 97.37%. These results were obtained after adjusting neural network using several different parameters which is explained in this paper. Keywords: Artificial Neural Network, human olfactory system, electronic nose, gas recognition, ammonia, acetyl aldehyde, acetone, ethylene, ethanol
1
Introduction
Humans can identify a large number of odors and use this information to interact successfully with their environment. Individual features of odor molecules descend on various parts of the olfactory system in the brain and combine to form a representation of odor [1, 2]. Since most odor molecules have several individual features, the number of possible combinations allows the olfactory system to detect an impressively broad range of smells [2]. Gas sensors are used widely in many different fields such as the prevention of natural disasters, environmental monitoring of automobile industry outputs, and other pollution-related industries [3]. Many types of gas sensors are used for gas detection. In particular, a semiconductor gas sensor is used to detect specific gases based on the variation
© Springer Nature Singapore Pte Ltd. 2017 A. Badnjevic (ed.), CMBEBIH 2017, IFMBE Proceedings 62, DOI: 10.1007/978-981-10-4166-2_42
in resistance or thermal conductivity due to absorption or desorption on the surface of an oxide semiconductor [4, 5]. A variety of gas recognition methods is contemporarily used to detect a wide range of gasses and vapors, especially those that are dangerous for human health, environment and property, dissolved Gas Analysis (DGA) being one of the most used ones. DGA uses majority techniques of interpreting results among which the most common ones are feed- forward neural-network classifiers [6].Support Vector Machine (SVM) approach is also used as a method for gas classification which strongly relies on statistical learning theory [7]. Neural networks are nowadays introduced to further enhancement to provide more accurate and precise results as: neural networks that are run in p
Data Loading...
