Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk

Multifunctional, Hybrid Materials Design via Spray-Drying: Much more than Just Drying

Spray-drying is a popular and well-known "drying tool" for engineers. This perspective highlights that, beyond this application, spray-drying is a very interesting and powerful tool for materials chemists to enable the design of multifunctional and hybrid materials. Upon spray-drying, the confined space of a liquid droplet is narrowed down, and its ingredients are forced together upon "falling dry." As  detailed in this article, this enables the following material formation strategies either individually or even in combination: nanoparticles and/or molecules can be assembled; precipitation reactions as well as chemical syntheses can be performed; and templated materials can be designed. Beyond this, fragile moieties can be processed, or "precursor materials" be prepared. Post-treatment of spray-dried objects eventually enables the next level in the design of complex materials. Using spray-drying to design (particulate) materials comes with many advantages-but also with many challenges-all of which are outlined here. It is believed that multifunctional, hybrid materials, made via spray-drying, enable very unique property combinations that are particularly highly promising in myriad applications-of which catalysis, diagnostics, purification, storage, and information are highlighted.

Online Machine Vision-Based Modeling during Cantaloupe Microwave Drying Utilizing Extreme Learning Machine and Artificial Neural Network

Online microwave drying process monitoring has been challenging due to the incompatibility of metal components with microwaves. This paper developed a microwave drying system based on online machine vision, which realized real-time extraction and measurement of images, weight, and temperature. An image-processing algorithm was developed to capture material shrinkage characteristics in real time. Constant-temperature microwave drying experiments were conducted, and the artificial neural network (ANN) and extreme learning machine (ELM) were utilized to model and predict the moisture content of materials during the drying process based on the degree of material shrinkage. The results demonstrated that the system and algorithm operated effectively, and ELM provided superior predictive performance and learning efficiency compared to ANN.

Design of experiments meets immersive environment: Optimising eating atmosphere using artificial neural network

Design of experiments (DOE) is a family of statistical tools commonly used in food science to optimise recipes and facilitate new food development. In a novel cross-disciplinary twist, we propose to adapt DOE approach to the optimisation of restaurant atmosphere. In this study, an artificial neural network (ANN) with particle swarm optimisation algorithm (PSO; hereafter ANN-PSO) was selected and compared with classical Response Surface Method (RSM) as ANN-PSO has been reported to yield better reliability and predictability compared to RSM. Recent research has increasingly demonstrated that perceived food quality, enjoyment, and willingness to pay are influenced by contextual factors such as lighting, decoration, and background noise/music. Moreover, virtual reality (VR) technology, which has become increasingly accessible, sophisticated, and widespread over the past years, presents a new way to study scenarios which may be otherwise too expensive/implausible to test in real life this includes delivering immersive environment. We hereby demonstrate a novel proof-of-concept study by varying the degree of illumination and of background sound level in an immersive restaurant setup. Participants (N = 283) watched immersive 360° videos while rating situational appropriateness and food wanting for two different dishes in various ambient conditions as determined by DOE's Central Composite Design (CCD). Participants did not actually consume the foods but rather only viewed them. Optimal restaurant lighting and sound levels were then estimated using ANN-PSO model which was found to be at 289 lux and -21.38 Loudness Unit Full Scale (LUFS) for burger and 186.9 lux and -30 LUFS for pizza. While the results of our study are of obvious interest to those in the hospitality industry, this work further highlights the transferability of methods across different disciplines and the applicability of time-tested methods to new emerging areas.