Manabendra Bhuyan

Tea quality prediction using a tin oxide-based electronic nose: an artificial intelligence approach

In this paper, we have (analyzed using a metal oxide sensor (MOS)-based electronic nose (EN)) five tea samples with different qualities, namely, drier month, drier month again over-fired, well-fermented normal fired in oven, well-fermented over-fired in oven, and under-fermented normal fired in oven. The flavour of tea is determined mainly by its taste and smell, which are determined by hundreds of volatile organic compounds (VOC) and non-volatile organic compounds present in tea. Tea flavour is traditionally measured through the use of a combination of conventional analytical instrumentation and human organoleptic profiling panels. These methods are expensive in terms of for example time and labour. The methods are also inaccurate because of a lack of either sensitivity or quantitative information. In this paper an investigation has been made to determine the flavours of different tea samples using an EN and thus to explore the possibility of replacing existing analytical and profiling panel methods. The technique uses an array of four MOSs, each of, which has an electrical resistance that has partial sensitivity to the headspace of tea. The signals from the sensor array are then conditioned by suitable interface circuitry resulting in our tea data-set. The data were processed using principal component analysis (PCA), fuzzy C means (FCM) algorithm. The data were then analyzed following the neural network paradigms, following the self-organizing map (SOM) method along with radial basis function (RBF) network and probabilistic neural network (PNN) classifier. Using FCM and SOM feature extraction techniques along with RBF neural network, we achieved 100% correct classification for the five different tea samples, each of which have different qualities. These results prove that our EN is capable of discriminating between the flavours of teas manufactured under different processing conditions, viz. over-fermented, over-fired, under-fermented, etc.

Electronic Nose for Black Tea Classification and Correlation of Measurements With “Tea Taster” Marks

Tea is an extensively consumed beverage worldwide with an expanding market. The major quality attributes of tea are flavor, aroma, color, and strength. Out of these, flavor and aroma are the most important attributes. Human experts called ldquotea tastersrdquo conventionally evaluate tea quality, and they usually assign scores to samples of tea that are under evaluation on a scale of 1 to 10, depending on the flavor, the aroma, and the taste of the sample. This paper presents a study where, first, the selection of appropriate sensors was carried out based on sensitivity with the major aroma-producing chemicals of black tea. Then, this sensor array was exposed to black tea samples that were collected from the tea gardens in India, and the computational model has been developed based on artificial neural network methods to correlate the measurements with the tea tasters scores. With unknown tea samples, encouraging results have been obtained with a more than 90% classification rate.

Electronic nose based tea quality standardization

In this paper we have used a metal oxide sensor (MOS) based electronic nose (EN) to analyze five tea samples with different qualities, namely, drier month, drier month again over-fired, well fermented normal fired in oven, well fermented overfired in oven, and under fermented normal fired in oven. The flavour of tea is determined mainly by its taste and smell, which is generated by hundreds of Volatile Organic Compounds (VOCs) and Non-Volatile Organic Compounds present in tea. These VOCs are present in different ratios and determine the quality of the tea. For example Assamica (Sri Lanka and Assam Tea) and Assamica Sinesis (Darjeeling and Japanese Tea) are two different species of tea giving different flavour notes. Tea flavour is traditionally measured through the use of a combination of conventional analytical instrumentation and human or ganoleptic profiling panels. These methods are expensive in terms of time and labour and also inaccurate because of a lack of either sensitivity or quantitative information. In this paper an investigation has been made to determine the flavours of different tea samples using an EN and to explore the possibility of replacing existing analytical and profiling panel methods. The technique uses an array of 4 MOSs, each of, which has an electrical resistance that has partial sensitivity to the headspace of tea. The signals from the sensor array are then conditioned by suitable interface circuitry. The data were processed using Principal Components Analysis (PCA), Fuzzy C Means algorithm (FCM). We also explored the use of a Self-Organizing Map (SOM) method along with a Radial Basis Function network (RBF) and a Probabilistic Neural Network classifier. Using FCM and SOM feature extraction techniques along with RBF neural network we achieved 100% correct classification for the five different tea samples with different qualities. These results prove that our EN is capable of discriminating between the flavours of teas manufactured under different processing conditions, viz. over-fermented, over-fired, under fermented, etc.

Robust electronic-nose system with temperature and humidity drift compensation for tea and spice flavour discrimination

The aim of this paper is to determine aroma and flavour of the tea and spices by using Electronic-nose (E-nose) system with temperature and humidity drift compensation techniques. E-nose sensors are used with variable temperature and humidity conditions. Compensation for drift is an important factor and that generally is neglected. Therefore, we have put an effort to compensate the drifts in E-nose response data. Firstly, drift coefficients for E-noses sensors due to temperature and humidity variations in samples are determined and subsequently, these coefficients are used to eliminate drift in E-nose response data during online capturing and processing. We have described the results and experiments conducted by using four metal oxide semiconductor (MOS) based E-nose sensors. Artificial neural network (ANN) based pattern recognition techniques are used for discrimination and classification of electronic nose response data for different flavour terms of tea and spice.

Measurement and Control in Food Processing

Introduction to Instrumentation and Control in Food Processing. Measuring and Controlling Devices. Instruments in Food Processing Technology. Controllers and Indicators. Computer Based Monitoring and Control for Food Processing Technology.

Determination of tea quality by using a neural network based electronic nose

In these paper we have used a metal oxide sensor based electronic nose (EN) to analyse five tea samples with different qualities, namely, drier month, drier month again over fired, well fermented normal fired in oven, well fermented over fired in oven, and under fermented normal fired in oven. The flavour of team is determined mainly by its taste and smell, which generated by hundreds of volatile organic compounds (VOCs) and non-volatile organic compounds present in tea. These VOCs are present in different ratios and determine the quality of the tea. For example Assamica (Sri Lanka and Assam tea) and Assamica Sinesis (Dajeeling and Japanese tea) are two different species of tea giving different flavour notes. Tea flavour is traditionally measured through the use of a combination of conventional analytical instrumentation and human organoleptic profiling panels. These methods are expensive in terms of time and labour and also inaccurate because of lack of either sensitivity or quantitative information. In this paper an investigation has been made to determine the flavours of different tea samples using an EN and to explore the possibility of replacing existing analytical and profiling panel methods. The technique uses as array of 4 metal oxide sensors (MOS), each of, which has an electrical resistance that has partial sensitivity to the headspace of tea. The signals from the sensor array are then conditioned by suitable interface circuitry. The data were processed using principal component analysis (PCA), fuzzy C means algorithm (FCM). We also explored the use of self-organizing map (SOM) method along with a radial basis function network (RBF) and a probabilistic neural network (PNN) classifier. Using FCM and SOM feature extraction techniques along with RBF neural network we achieved 100% correct classification for the five different tea samples with different qualities. These results prove that our EN is capable of discriminating between the flavours of teas manufactured under different processing conditions, viz. over-fermented, over-fired, under fermented etc.

Aroma characterization of orthodox black tea with electronic nose

Black tea quality is a very complex phenomenon. There are almost two hundred varieties of bio-chemical compounds, both volatile and nonvolatile present in tea and each of these compounds contribute to tea quality (B. Banerjee, 1996), The major quality attributes of tea are flavour, aroma, colour and strength. Acceptance by consumers and price realized depend on these attributes (S.Y. Dheodhar et al.,). Out of these, aroma is the most important of the attributes and in common parlance, aroma means smell of the tea. Characterization of aroma of tea has been a challenge for tea scientists for long. Efforts have been made towards this through chemical analysis and instrumental studies through gas chromatography (GC) and high profile liquid chromatography (HPLC) techniques. Research and studies have been reported with success for quality characterization of food and beverages using electronic nose (T.C. Pearce et al., 2003). This paper reports a study and results on applicability of electronic nose for aroma characterization of orthodox black tea. Six varieties of orthodox tea samples were tested using Alpha MOS 2000 Electronic Nose and data obtained from the experimental setup have been successfully classified using principal component analysis (PCA) and back-propagation multilayer perceptron model.

Rule based fuzzy approach for peripheral motor neuropathy (PMN) diagnosis based on NCS data

The development of artificial intelligence methodology (AIM) led to development of computer assist diagnosis systems which are based on expert medical knowledge. Medical diagnosis is a complex system as well as subjective in nature and needs expert person for interpretation of medical information. Moreover, abundance of data in database is often beyond human cognition and comprehension. It is widely pointed that the conventional diagnosis cannot sufficiently handle imprecise and vague knowledge for some real world applications, but expert system such as fuzzy model can effectively resolve/interpretate data and knowledge problems with uncertainty. This paper presents a novel fuzzy expert system (FES) for neuropathy decision support application. In this study group, 120 neuropathy patients, 4 nerves and 5 variables of each nerve were considered for analysis. 26 rules were evaluated based on medical knowledge. After the system is completely constructed, new data were encoded to linguistic variables and tested to predict the model performance. The simulation results have shown that the proposed FES can be used for medical data analysis effectively. The comparison results show that the linguistic rules extracted are competitive with or even superior to some well-known medical methods. Results are presented showing the effectiveness of the method for supporting differential diagnosis.

Despeckling SAR images in the lapped transform domain

In this paper, a novel lapped transform (LT) based approach to SAR image despeckling is introduced. It is shown that LT coefficients of the log transformed, noise free SAR images, obey Generalized Gaussian distribution. The proposed method uses a Bayesian minimum mean square error (MMSE) estimator which is based on modeling the global distribution of the rearranged LT coefficients in a subband using Generalized Gaussian distribution. Finally the proposed algorithm is implemented in cycle spinning mode to compensate for the lack of translation invariance property of LT. Experiments are carried out using synthetically speckled natural and SAR images. The proposed Bayesian based technique in LT based framework, when compared with several existing despeckling techniques, yields very good despeckling results while preserving the important details and textural information of the scene.

Linearizing thermistor characteristics by piecewise linear interpolation in real time FPGA

This paper describes FPGA (Field Programmable Gate Array) implementation of piecewise linear interpolation method for linearization of a nonlinear thermistor characteristic. The known data points of the nonlinear thermistor characteristic are interpolated to determine the unknown points in the range. The value of an unknown intermediate point is determined by using a straight line equation between the nearest two known data points. The interpolation technique is implemented in FPGA Spartan-III for linearization of nonlinear thermistor characteristic for real time applications. In this method fixed point arithmetic is used for data representation and calculation in FPGA.