Classification of puffed snacks freshness based on crispiness-related mechanical and acoustical properties. (June 2018)

• Record Type: Journal Article
• Authors: Sanahuja, Solange; Fédou, Manuel; Briesen, Heiko
• Is Part Of: Journal of food engineering. Volume 226(2018)
• Page Start: 53
• Page End: 64
• Publication Date: 2018-06
• Subjects: Food texture -- Mechanical properties -- Crushing sounds -- Sensory crispiness/crispness -- Multisensory integration -- Machine learning; Food industry and trade -- Periodicals; Food -- Analysis -- Periodicals; Aliments -- Industrie et commerce -- Périodiques; Aliments -- Analyse -- Périodiques; Aliments -- Recherche -- Périodiques; 664.005
• DOI: 10.1016/j.jfoodeng.2017.12.013
• Languages: English
• ISSNs: 0260-8774

Abstract

Abstract: The use of instrumental methods to support sensory panels in the routine quality control of crispiness remains challenging. Texture analysis is often insufficient to accurately classify this complex sensory attribute. Herein, 70 different food properties were combined via machine learning algorithms to mimic multisensory integration. Force and sound were measured during crushing of puffed snacks equilibrated at different humidity levels. Sensory panels then ranked crispiness-related freshness and preference based on the recorded sounds. Selected feature combinations were used to train machine learning models to recognize the freshness levels at different humidity levels. The classification accuracy was improved compared with traditional texture analysis techniques; an accuracy of up to 92% could be achieved with quadratic support vector machine or artificial neural network algorithms. Moreover, third-octave frequency bands, characterizing breakage frequencies and sound pitches, were determined to be main descriptors to be taken into account during the research and development of puffed snacks. Highlights: Acoustics strongly influence the sensory perception of puffed snacks' freshness. Multisensory integration of crispiness is modeled using instrumental data. The parameters impacting crispiness are evaluated to enable product optimization. The classification accuracy of crispiness is improved using spectral features. Machine learning is introduced for rapid quality control of food texture.