The work presented describes the development of a novel integrated optical sensor system for the
simultaneous and online measurement of the colour and temperature of food as it cooks in a
microwave and hybrid oven systems. The integrated probe contains two different sensor concepts, one to
monitor temperature and based on Fibre Bragg Grating (FBG) technology and a second for meat quality,
based on reflection spectroscopy in the visible wavelength range. The combination of the two sensors into a
single probe requires a careful configuration of the sensor approaches in the creation of an integrated probe
This paper reports on an optical fibre based sensor system to detect the occurrence of premature browning in ground
beef. Premature browning (PMB) occurs when, at a temperature below the pasteurisation temperature of 71°C, there are
no traces of pink meat left in the patty. PMB is more frequent in poorer quality beef or beef that has been stored under
imperfect conditions. The experimental work pertaining to this paper involved cooking fresh meat and meat that has been
stored in a freezer for, 1 week, 1 month and 3 months and recording the reflected spectra and temperature at the core of
the product, during the cooking process, in order to develop a classifier based on the spectral response and using a Self-Organising Map (SOM) to classify the patties into one of four categories, based on their colour. The combination of both
the classifier and temperature data can be used to determine the presence of PMB for a given patty and can thus be used
for Quality Control by food producers.
Research into the development of an Early Warning Harmful Algae Bloom (HAB) Sensing System for use in
Underwater Monitoring Applications is presented. The sensor proposed by the authors utilises the complex ties between
ocean colour, absorption and scattering, along with algae pigmentation. The objective is to develop a robust inexpensive
sensor for use in an early warning system for the detection and possible identification of Harmful Algae Blooms. The
sensing mechanism utilised in this system is based on a combination of absorption and reflection spectroscopy and
Principle Component Analysis (PCA) signal processing. Spectroscopy is concerned with the production, measurement,
and interpretation of electromagnetic spectra arising from either emission or absorption of radiant energy by various
substances (or HABs in this application). Preliminary results are presented from the interrogation of chlorophyll, yeast
and saline solutions, as well as levels of absorption obtained utilising two dyes Blue (brilliant Blue (E133) and
Carmoisine (E122) mix) and Red (Ponceau (E124) and Sunset yellow (E110) mix).
Sliced ham products undergo significant discolouration and fading when placed in retail display cabinets. This is due to factors such as illumination of the display cabinet, packaging, i.e. low OTR (Oxygen Transmission Rate) or very low OTR packaging, product to headspace ratio and percentage of residual oxygen. This paper presents initial investigations into the development of a sensor to measure rate of colour fading in cured ham, in order to predict an optimum colour sell-by-date. An investigation has been carried out that shows that spectral reflections offer more reproducibility than CIE L*a*b* readings, which are, at present, most often used to measure meat colour. Self-Organising Maps were then used to classify the data into five colour fading stages, from very pink to grey. The results presented here show that this classifier could prove an effective system for determining the rate of colour fading in ham.
This paper reports on three methods of classifying the spectral data from an optical fibre based sensor system as used in the food industry. The first method uses a feed-forward back-propagation Artificial Neural Network; the second method involves using Kohonen Self-Organising Maps while the third method is k-Nearest Neighbour analysis. The sensor monitors the food colour online as the food cooks by examining the reflected light from both the surface and the core of the product. The combination of using Principal Component Analysis and Backpropagation Neural Networks has been successfully investigated previously. In this paper, results obtained using all three classifiers are presented and compared. The Principal Components used to train each classifier are evaluated from data that generate a "colourscale" comprising six colour classifications. This scale has been developed to allow several products of similar colour to be tested using a single network that had been trained using the colourscale. The results presented show that both the neural network and the Self-Organising Map approach perform comparably, while the k-NN method tested under-performs the other two.