Plant electrical signal is a kind of weak signal which is generated when the resting potential of plant cells or tissues changes under outside stimuli and can be transmitted among plant cells and tissues. Important physiological information of plant can be obtained through processing and analysis of the signal. Based on characteristics of plant electrical signal, this paper analyses electrical signals of plant in time domain, frequency domain and time-frequency domain and discusses advantages and existing problems of each processing method. Result shows that time-frequency analysis reflects substantive characteristics of plants signals more deeply and effectively than another two methods. This study provides certain theoretical references and analytic bases for future studies in this area.

Stacking is one of the major types of ensemble learning techniques in which a set of base classifiers contributes their outputs to the meta-level classifier, and the meta-level classifier combines them so as to produce more accurate classifications. In this paper, we propose a new stacking algorithm that defines the cross-entropy as the loss function for the classification problem. The training process is conducted by using a neural network with the stochastic gradient descent technique. One major characteristic of our method is its treatment of each meta instance as a whole with one optimization model, which is different from some other stacking methods such as stacking with multi-response linear regression and stacking with multi-response model trees. In these methods each meta instance is divided into a set of sub-instances. Multiple models apply to those sub-instances and each for a class label. There is no connection between different models. It is very likely that our treatment is a better choice for finding suitable weights. Experiments with 22 data sets from the UCI machine learning repository show that the proposed stacking approach performs well. It outperforms all three base classifiers, several state-of-the-art stacking algorithms, and some other representative ensemble learning methods on average.

To solve the difficulties of feature extraction of plant electrical signals and to realize effectively the classification of plant electrical signals, a method of plant electrical signal recognition which is combined with wavelet packet decomposition and the BP neural network was put forward in this paper. The method first decomposes wavelet packet of the plant signals, and puts the maximum of the eigenvalue of signal covariance matrix. The mean absolute value and zerocrossing rate as the eigenvalues, and then put the constructing feature set into the BP neural network, realizing different plant signal identification. The experimental results show that the optimal wavelet packet decomposition reduces the size of the BP neural network, and reduces the complexity algorithm, speeds up the network training time and classification speed. Therefore, this method has good recognition effect.

Multilabel classification is a supervised learning problem wherein each individual instance is associated with multiple labels. Ensemble methods are effective in managing multilabel classification problems by creating a set of accurate, diverse classifiers and then combining their outputs to produce classifications. This paper presents a novel stacking-based ensemble algorithm, ABC-based stacking, for multilabel classification. The artificial bee colony algorithm, along with a single-layer artificial neural network, is used to find suitable meta-level classifier configurations.The optimization goal of the meta-level classifier is to maximize the average accuracy of classification of all the instances involved. We run an experiment on 10 benchmark datasets of varying domains and compare the proposed approach to five other ensemble algorithms to demonstrate the feasibility and effectiveness of ABC-based stacking.