Feature selection plays a very significant role for the success of pattern recognition and data mining. Based on the maximal relevance and minimal redundancy (mRMR) method, combined with feature subset, this paper proposes an improved maximal relevance and minimal redundancy (ImRMR) feature selection method based on feature subset. In ImRMR, the Pearson correlation coefficient and mutual information are first used to measure the relevance of a single feature to the sample category, and a factor is introduced to adjust the weights of the two measurement criteria. And an equal grouping method is exploited to generate candidate feature subsets according to the ranking features. Then, the relevance and redundancy of candidate feature subsets are calculated and the ordered sequence of these feature subsets is gained by incremental search method. Finally, the final optimal feature subset is obtained from these feature subsets by combining the sequence forward search method and the classification learning algorithm. Experiments are conducted on seven datasets. The results show that ImRMR can effectively remove irrelevant and redundant features, which can not only reduce the dimension of sample features and time of model training and prediction, but also improve the classification performance.

With the intensification of ecosystem damage, birds have become the symbolic species of the ecosystem. Ornithology with interdisciplinary technical research plays a great significance for protecting birds and evaluating ecosystem quality. Deep learning shows great progress for birdsongs recognition. However, as the number of network layers increases in traditional CNN, semantic information gradually becomes richer and detailed information disappears. Secondly, the global information carried by the entire input may be lost in convolution, pooling, or other operations, and these problems will weaken the performance of classification. In order to solve such problems, based on the feature spectrogram from the wavelet transform for the birdsongs, this paper explored the multi-scale convolution neural network (MSCNN) and proposed an ensemble multi-scale convolution neural network (EMSCNN) classification framework. The experiments compared the MSCNN and EMSCNN models with other CNN models including LeNet, VGG16, ResNet101, MobileNetV2, EfficientNetB7, Darknet53 and SPP-net. The results showed that the MSCNN model achieved an accuracy of 89.61%, and EMSCNN achieved an accuracy of 91.49%. In the experiments on the recognition of 30 species of birds, our models effectively improved the classification effect with high stability and efficiency, indicating that the models have better generalization ability and are suitable for birdsongs species recognition. It provides methodological and technical scheme reference for bird classification research.

Pine nuts are not only the important agent of pine reproduction and afforestation, but also the commonly consumed nut with high nutritive values. However, it is difficult to distinguish among pine nuts due to the morphological similarity among species. Therefore, it is important to improve the quality of pine nuts and solve the adulteration problem quickly and non-destructively. In this study, seven pine nuts (Pinus bungeana,Pinus yunnanensis,Pinus thunbergii,Pinus armandii,Pinus massoniana,Pinus elliottiiandPinus taiwanensis) were used as study species. 210 near-infrared (NIR) spectra were collected from the seven species of pine nuts, five machine learning methods (Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Naive Bayes (NB)) were used to identify species of pine nuts. 303 images were used to collect morphological data to construct a classification model based on five convolutional neural network (CNN) models (VGG16, VGG19, Xception, InceptionV3 and ResNet50). The experimental results of NIR spectroscopy show the best classification model is MLP and the accuracy is closed to 0.99. Another experimental result of images shows the best classification model is InceptionV3 and the accuracy is closed to 0.964. Four important range of wavebands, 951–957 nm, 1,147–1,154 nm, 1,907–1,927 nm, 2,227–2,254 nm, were found to be highly related to the classification of pine nuts. This study shows that machine learning is effective for the classification of pine nuts, providing solutions and scientific methods for rapid, non-destructive and accurate classification of different species of pine nuts.

Environmental sound recognition has been a hot topic in the domain of audio recognition. How to select the optimal feature subsets and enhance the performance of classification precisely is an urgent problem to be solved. Ensemble learning, a new kind of method presented recently, has been an effective way to improve the accuracy of classification in feature selection. In this paper, experiments were performed on environmental sound dataset. An improved method based on constraint score and multimodels ensemble feature selection methods (MmEnFs) were exploited in the experiments. The experimental results show that when enough attributes are selected, the improved method can get a better performance compared to other feature selection methods. And the ensemble feature selection method, which combines other methods, can obtain the optimal performance in most cases.

With the advent of big data era and the rapid improvement of raw data scale, feature selection is the basic and critical technologies for data mining. However, in most of the studies on feature selection methods before, mainly directed to treat the single feature or overall feature subset, while the influence of the correlation and redundancy of features in the feature subset on the classification results is ignored. In this paper, combination of feature subset grouping and factor analysis (FA), a hybrid feature selection method based on feature subsets generation through factor analysis (FAFS_HFS) is proposed. Firstly, generate feature subsets based on the maximum load (maximum explanatory power) of each feature through factor analysis. Then, minimum redundancy maximum relevance (mRMR) and sequential forward selection (SFS) is used to remove the redundancy of each feature subset. Finally, fisher score (F-score) and feature subset SFS (FS_SFS) was utilized to evaluate and select feature subset, and obtain the optimal feature subset. Experiments are conducted on 14 datasets, the results show that FAFS_HFS has high classification accuracy and dimension reduction on almost all datasets, especially in high-dimensional datasets, and it has excellent efficiency and competitive classification performance compared with other contrastive methods.

Birds are significant bioindicators in the assessment of habitat biodiversity, ecological impacts and ecosystem health. Against the backdrop of easier bird vocalization data acquisition, and with deep learning and machine learning technologies as the technical support, exploring recognition and classification networks suitable for bird calls has become the focus of bioacoustics research. Due to the fact that the spectral differences among various bird calls are much greater than the differences between human languages, constructing birdsong classification networks based on human speech recognition networks does not yield satisfactory results. Effectively capturing the differences in birdsong across species is a crucial factor in improving recognition accuracy. To address the differences in features, this study proposes multi-scale deep features. At the same time, we separate the classification part from the deep network by using machine learning to adapt to classification with distinct feature differences in birdsong. We validate the effectiveness of multi-scale deep features on a publicly available dataset of 20 bird species. The experimental results show that the accuracy of the multi-scale deep features on a log-wavelet spectrum, log-Mel spectrum and log-power spectrum reaches 94.04%, 97.81% and 95.89%, respectively, achieving an improvement over single-scale deep features on these three spectrograms. Comparative experimental results show that the proposed multi-scale deep feature method is superior to five state-of-the-art birdsong identification methods, which provides new perspectives and tools for birdsong identification research, and is of great significance for ecological monitoring, biodiversity conservation and forest research.