N. Jackman

Design of a system that uses optical-fiber sensors and neural networks to control a large-scale industrial oven by monitoring the food quality online

An optical-fiber sensor-based system has been designed to assist in the controlling of a large-scale industrial by monitoring the color of the food product being cooked. The system monitors the color of the food as it cooks by examining the reflected visible light, from the surface and/or core of the cooked product. A trained backpropagation neural network acts as a classifier and is used to interpret the extent to which each product is cooked with regard to the aesthetics of the food. Principal component analysis is also included before the neural network as a method of feature extraction. This is implemented using Karhunen-Loeve decomposition. A wide range of food products have been examined and accurately classified, demonstrating the versatility and repeatability of the system over time. These products include minced beef burgers and steamed chicken fillets.

Intelligent Processing of Spectroscopic Signals Obtained Using an Optical Fibre Based System for Food Quality Control

An Optical fibre based sensor system has been developed for the purpose of examining the colour of food products online as they cook in a large-scale industrial oven. Spectroscopic techniques are employed to interrogate the sensor signal and the resultant output spectral patterns are examined by an Artificial Neural Network. A Pattern recognition system has, therefore, been developed which is capable of classifying colours that are favourable and those that are not optimum, in order to control the cooking process and optimise food quality.

Online Optical Fiber Sensor for Detecting Premature Browning in Ground Beef Using Pattern Recognition Techniques and Reflection Spectroscopy

This paper examines the design of an optical fiber sensor that monitors ground beef online, as it cooks, in order to determine the quality of the meat; in particular, if premature browning has occurred. The experimental work involved cooking fresh meat and meat that has been stored in a freezer for, one week, one month and three months, and recording the reflected spectra and temperature during the cooking process in order to develop a classifier, based on pattern recognition techniques that can determine premature browning and the degree to which the meat has been cooked. A comparison of this sensor is made with traditional research methods of detecting premature browning, to demonstrate that it would be more commercially viable as an online solution.

An examination of ham colour fading using optical fibre methods

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.

Principal component analysis and pattern recognition combined with visible spectroscopy in the classification of food quality

The online measurement of the colour of food internally and externally has already been shown to be an invaluable parameter in the process control of large industrial ovens. The system, described in this article is based on optical fibre technology is intended for accurate measurement of food colour. It employs artificial intelligence through the use of neural networks to make decisions regarding the cooking stage of the product. This paper examines the application of principal component analysis, using Karhunen Loeve decomposition, to the spectral data before applying the pattern recognition technique. With Karhunen Loeve decomposition it is possible to reduce the dimensions of this solution to a smaller subspace by only including significant data and thus eliminating redundant or highly correlated information. This method was tested on the following food products: steamed skinless chicken fillets, roast whole chickens, sausages, pastry, bread crumb coating and char-grilled chicken fillets.

Employing spectroscopic and pattern recognition techniques to examine food quality both internally and externally as it cooks in an industrial oven

An Optical fiber based sensor system has been developed for the purpose of examining the color of food products online as they cook in a large-scale industrial oven. By classifying the color of each cooking stage it is possible to automatically determine if the food is cooked to an optimum perceived color. Developments have been made on previous work by the authors by further examining the internal color of the food and testing the repeatability of the system. Spectroscopic techniques are employed to determine the color and this signal is interrogated using an Artificial Neural Network.

Design of a slim-line integrated probe using optical fibre technology that is suitable for microwave environments and measures reflection spectroscopy and temperature

The work presented describes the development of a novel integrated optical sensor system for the simultaneous and online measurement of colour and temperature of food as it cooks in a large-scale microwave and hybrid oven systems. The integrated probe contains two different sensor concepts, one to monitor temperature, based on Fibre Bragg Grating (FBG) technology and a second for food quality, based on reflection spectroscopy in the visible wavelength range. The in-house designed probe was used to obtain measurements of product temperature in a conventional and microwave oven. The performance of the FBG temperature sensor within the combined optical probe was thus evaluated for use in conventional and microwave ovens.

Detection of premature browning in ground beef using an optical-fibre-based sensor

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.

An intelligent optical fibre based sensor system for monitoring food quality

It is evident that colour analysis of food is critical in the sale of pre-cooked foods. Through the use of spectroscopy, in the region of the visible and near infra-red spectrum, it is possible to examine different colours and then analyse them. Combining this with Artificial Neural Networks (ANNs), a pattern recognition system is generated to classify between colours that are favourable and those that are not optimum, in an effort to control the cooking process.

Blood detection in the spinal column of whole cooked chicken using an optical fibre based sensor system

An optical fibre based sensor has been developed to aid the quality assurance of food cooked in industrial ovens by monitoring the product in situ as it cooks. The sensor measures the product colour as it cooks by examining the reflected visible light from the surface as well as the core of the product. This paper examines the use of the sensor for the detection of blood in the spinal area of cooked whole chickens. The results presented here show that the sensor can be successfully used for this purpose.