Near-infrared (NIR) spectral sensors can deliver the spectral response of light absorbed by materials. Data analysis technology based on NIR sensors has been a useful tool for quality identification. In this paper, an improved deep convolutional neural network (CNN) with batch normalization and MSRA (Microsoft Research Asia) initialization is proposed to discriminate the tobacco cultivation regions using data collected from NIR sensors. The network structure is created with six convolutional layers and three full connection layers, and the learning rate is controlled by exponential attenuation method. One-dimensional kernel is applied as the convolution kernel to extract features. Meanwhile, the methods of L2 regularization and dropout are used to avoid the overfitting problem, which improve the generalization ability of the network. Experimental results show that the proposed deep network structure can effectively extract the complex characteristics inside the spectrum, which proves that it has excellent recognition performance on tobacco cultivation region discrimination, and it also demonstrates that the deep CNN is more suitable for information mining and analysis of big data.

Near-infrared (NIR) spectroscopy has been widely used in agricultural operations to obtain various crop parameters, such as water content, sugar content, and different indicators of ripeness, as well as other potential information concerning crops that cannot be directly obtained by human observation. The chemical compositions of tobacco play an important role in the quality of cigarettes. The NIR spectroscopy-based chemical composition analysis has recently become one of the most effective methods in tobacco quality analysis. Existing NIR spectroscopy-related solutions either have relatively low analysis accuracy, or are only able to analyze one or two chemical components. Thus, a precise prediction model is needed to improve the analysis accuracy of NIR data. This paper proposes a tobacco chemical component analysis method based on a neural network (TCCANN) to quantitatively analyze the chemical components of tobacco leaves by using NIR spectroscopy, including nicotine, total sugar, reducing sugar, total nitrogen, potassium, chlorine, and pH value. The proposed TCCANN consists of both residual network (ResNet) and long short-term memory (LSTM) neural network. ResNet is applied to the feature extraction of high-dimension NIR spectroscopy, which can effectively avoid the gradient-disappearance issue caused by the increase of network depth. LSTM is used to quantitatively analyze the multiple chemical compositions of tobacco leaves in a simultaneous manner. LSTM selectively allows information to pass through by a gated unit, thereby comprehensively analyzing the correlation between multiple chemical components and corresponding spectroscopy. The experimental results confirm that the proposed TCCANN not only predicts the corresponding values of seven chemical components simultaneously, but also achieves better prediction performance than other existing machine learning methods.

Near-infrared (NIR) spectral sensors deliver the spectral response of the light absorbed by materials for quantification, qualification or identification. Spectral analysis technology based on the NIR sensor has been a useful tool for complex information processing and high precision identification in the tobacco industry. In this paper, a novel method based on the support vector machine (SVM) is proposed to discriminate the tobacco cultivation region using the near-infrared (NIR) sensors, where the genetic algorithm (GA) is employed for input subset selection to identify the effective principal components (PCs) for the SVM model. With the same number of PCs as the inputs to the SVM model, a number of comparative experiments were conducted between the effective PCs selected by GA and the PCs orderly starting from the first one. The model performance was evaluated in terms of prediction accuracy and four parameters of assessment criteria (true positive rate, true negative rate, positive predictive value and F1 score). From the results, it is interesting to find that some PCs with less information may contribute more to the cultivation regions and are considered as more effective PCs, and the SVM model with the effective PCs selected by GA has a superior discrimination capacity. The proposed GA-SVM model can effectively learn the relationship between tobacco cultivation regions and tobacco NIR sensor data.