In Vivo Pattern Classification of Ingestive Behavior in Ruminants Using FBG Sensors and Machine Learning

• Published in: Sensors (Basel, Switzerland) Vol. 15; no. 11; pp. 28456 - 28471
• Main Authors: Pegorini, Vinicius, Karam, Leandro Zen, Pitta, Christiano Santos Rocha, Cardoso, Rafael, da Silva, Jean Carlos Cardozo, Kalinowski, Hypolito José, Ribeiro, Richardson, Bertotti, Fábio Luiz, Assmann, Tangriani Simioni
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 11.11.2015; MDPI
• Subjects: Algorithms; Animal behavior; Animals; Automation; biomechanical forces; Biomechanical Phenomena; Biomechanics; Biomedical materials; Chewing; Classification; Decision trees; Equipment Design; Feeding Behavior - classification; Feeding Behavior - physiology; fiber Bragg grating sensor (FBG); Fiber Optic Technology - instrumentation; Fiber Optic Technology - methods; Food; In vivo testing; In vivo tests; ingestive behavior; Machine Learning; Mastication - physiology; pattern classification; Ruminants; Sensors; Success; Surgical implants; Brazil; pattern classification; fiber Bragg grating sensor (FBG); ingestive behavior; machine learning; biomechanical forces
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s151128456

Pattern classification of ingestive behavior in grazing animals has extreme importance in studies related to animal nutrition, growth and health. In this paper, a system to classify chewing patterns of ruminants in in vivo experiments is developed. The proposal is based on data collected by optical fiber Bragg grating sensors (FBG) that are processed by machine learning techniques. The FBG sensors measure the biomechanical strain during jaw movements, and a decision tree is responsible for the classification of the associated chewing pattern. In this study, patterns associated with food intake of dietary supplement, hay and ryegrass were considered. Additionally, two other important events for ingestive behavior were monitored: rumination and idleness. Experimental results show that the proposed approach for pattern classification is capable of differentiating the five patterns involved in the chewing process with an overall accuracy of 94%.