Search

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The species and distribution of trees in a forest are critical to the understanding of forest ecosystem processes and the development of forest management strategies. Subtropical forest landscapes feature a complex canopy structure and high stand density. Studies on the effects of classification algorithms on the remote sensing-based identification of tree species are few. GF-2 is the first satellite in China with sub-meter accuracy which has the high resolution and short replay cycle. Here, we considered three representative tree types (Masson pine, Chinese fir, and broadleaved evergreen trees) in the southern subtropical evergreen broadleaved forest region of China as research objects. We quantitatively compared the effects of five machine learning algorithms, including the backpropagation neural network, k-nearest neighbour, polytomous logistic regression, random forest (RF) and support vector machine (SVM), and four features (vegetation index, band reflectance, textural features, and topographic factors) on tree species identification using Gaofen-2 panchromatic and multispectral remote sensing images and field survey data. All five classification algorithms could effectively identify major tree species in subtropical forest areas (overall accuracy [OA] > 87.40%, kappa coefficient > 81.08%). The SVM model exhibited the best identification ability (OA = 90.27%, kappa coefficient = 85.37%), followed by RF (OA = 88.90%, Kappa coefficient = 83.30%). The combination of band reflectance, vegetation index, and the topographic factor performed exhibited the best, followed by the combination of band reflectance, vegetation index, textural feature, and topographic factor. In addition, we find that the classifier constructed by a single feature is not as effective as the combination of multiple feature factors. The addition of topographic factors can significantly improve the ability of tree species identification. According to the results of the five classifiers, the separability of the three tree species was good. The producer's accuracy and user's accuracy of Masson pine were more than 90%, and the evergreen broad-leaved tree and Chinese fir were more than 80%. The commission errors and omission errors of the three tree species were evergreen broadleaved tree > Chinese fir > Masson pine. The variable importance assessment results showed that the normalized difference greenness index, altitude, and the modified soil-adjusted vegetation index were the key variables. The results of this study used GF-2 to accurately identify the main tree species of subtropical evergreen forests in China, which can help forest managers to regularly monitor tree species composition and provide theoretical support for forest managers to formulate policies, monitor sustainable plans for wood mining, and forest conservation and management measures. [ABSTRACT FROM AUTHOR]

Existing track-to-track association methods are mainly based on statistics and fuzzy mathematics.However, most methods based on statistics depend on thresholds, and parameters based on fuzzy mathematics are complex to set. In addition, most methods only consider the information of a single track point in comparison. To solve the existing problems, this paper presents a distance distribution histogram feature to extract the similarity features of a trajectory and measure them using the standardized Euclidean distances; this method effectively utilizes the characteristics of the whole trajectory and has a good anti-noise performance and accuracy. The motion features of ships and the location accuracy of different data sources were fully considered. After obtaining the histogram features of velocity difference and the source features of sensors, the authors combined them and trained association models using machine learning, which effectively avoids the problem of manually setting thresholds and complex parameter settings. Finally, a real ship data set was constructed. The experimental results show that compared with the traditional distance feature, the overall association accuracy was improved by 3.23%～11.65% using the distance distribution histogram feature, and by 0.068% using the combination feature, which verifies the effectiveness of the proposed method.

Accurate recognition of gestures based on surface EMG signals is of very importance in the study of human prosthetic interaction. In this paper, multi-feature combination and adaptive AdaBoost algorithm are used to identify nine kinds of fine gestures. First, in order to adaptively set the threshold for extracting the active segment, the algorithm for detecting the active segment of the surface myoelectric signal is improved, and the effective active segment value is obtained by rejecting the invalid active segment. Second, a fine gesture classification method based on multi-feature combination is proposed. In this paper, the recursive feature elimination algorithm based on cyclic feature selection is used to screen out the feature set with the top classification effect, and the feature set selected by eight experimental objects is counted, and the optimal feature combination is obtained according to the experimental analysis. Finally, nine fine gesture actions are identified through a weak classifier constructed by combining the AdaBoost algorithm and the single-layer decision tree. The experimental results show that the proposed algorithm can achieve an average recognition rate of 98.56 (±1.44)% for nine fine gestures.

The imbalance of power supply and demand is an important problem to solve in power industry and Non Intrusive Load Monitoring (NILM) is one of the representative technologies for power demand management. The most critical factor to the NILM is the performance of the classifier among the last steps of the overall NILM operation, and therefore improving the performance of the NILM classifier is an important issue. This paper proposes a new architecture based on the RNN to overcome the limitations of existing classification algorithms and to improve the performance of the NILM classifier. The proposed model, called Multi-Feature Combination Multi-Layer Long Short-Term Memory (MFC-ML-LSTM), adapts various feature extraction techniques that are commonly used for audio signal processing to power signals. It uses Multi-Feature Combination (MFC) for generating the modified input data for improving the classification performance and adopts Multi-Layer LSTM (ML-LSTM) network as the classification model for further improvements. Experimental results show that the proposed method achieves the accuracy and the F1-score for appliance classification with the ranges of 95−100% and 84−100% that are superior to the existing methods based on the Gated Recurrent Unit (GRU) or a single-layer LSTM.

Visual localization is widely used in autonomous navigation system and Advanced Driver Assistance Systems (ADAS). However, visual-based localization in seasonal changing situations is one of the most challenging topics in computer vision and the intelligent vehicle community. The difficulty of this task is related to the strong appearance changes that occur in scenes due to weather or season changes. In this paper, a place recognition based visual localization method is proposed, which realizes the localization by identifying previously visited places using the sequence matching method. It operates by matching query image sequences to an image database acquired previously (video acquired during traveling period). In this method, in order to improve matching accuracy, multi-feature is constructed by combining a global GIST descriptor and local binary feature CSLBP (Center-symmetric local binary patterns) to represent image sequence. Then, similarity measurement according to Chi-square distance is used for effective sequences matching. For experimental evaluation, the relationship between image sequence length and sequences matching performance is studied. To show its effectiveness, the proposed method is tested and evaluated in four seasons outdoor environments. The results have shown improved precision–recall performance against the state-of-the-art SeqSLAM algorithm. [ABSTRACT FROM AUTHOR]

As a common disease in the elderly, neural foramina stenosis (NFS) brings a significantly negative impact on the quality of life due to its symptoms including pain, disability, fall risk and depression. Accurate boundary delineation is essential to the clinical diagnosis and treatment of NFS. However, existing clinical routine is extremely tedious and inefficient due to the requirement of physicians’ intensively manual delineation. Automated delineation is highly needed but faces big challenges from the complexity and variability in neural foramina images. In this paper, we propose a pure image-driven unsupervised boundary delineation framework for the automated neural foramina boundary delineation. This framework is based on a novel multi-feature and adaptive spectral segmentation (MFASS) algorithm. MFASS firstly utilizes the combination of region and edge features to generate reliable spectral features with a good separation between neural foramina and its surroundings, then estimates an optimal separation threshold for each individual image to separate neural foramina from its surroundings. This self-adjusted optimal separation threshold, estimated from spectral features, successfully overcome the diverse appearance and shape variations. With the robustness from the multi-feature fusion and the flexibility from the adaptively optimal separation threshold estimation, the proposed framework, based on MFASS, provides an automated and accurate boundary delineation. Validation was performed in 280 neural foramina MR images from 56 clinical subjects. Our method was benchmarked with manual boundary obtained by experienced physicians. Results demonstrate that the proposed method enjoys a high and stable consistency with experienced physicians (Dice: 90.58% ± 2.79%; SMAD: 0.5657 ± 0.1544 mm). Therefore, the proposed framework enables an efficient and accurate clinical tool in the diagnosis of neural foramina stenosis. [ABSTRACT FROM AUTHOR]

Bowel sounds is an important indicator to monitor and reflect intestinal motor function, and traditional manual auscultation requires high professional knowledge and rich clinical experience of doctors. In addition, long-time auscultation is time-consuming and laborious， which may lead to misjudgment caused by subjective error. To solve the problem, firstly, the wavelet transform is used to preprocess the bowel sounds signal for noise reduction and enhancement. Secondly, three typical features of intestinal sound were extracted. According to the combination of these features, a three-stage decision was designed to carry out multi-parameter and multi-feature joint threshold detection. This algorithm realized the detection of bowel sound signal and the location of its start and end points, making it possible that the complete bowel sound signal was extracted effectively. In this study, a large number of clinical data and label of bowel sounds were collected, and a new effective evaluation method was proposed to verify the proposed method. The accuracy rate is 83.51%. Results of this study will provide systematic support and theoretical guarantee for the diagnosis of intestinal diseases and the monitoring of postoperative intestinal function recovery of patients.

The imbalance of power supply and demand is an important problem to solve in power industry and Non Intrusive Load Monitoring (NILM) is one of the representative technologies for power demand management. The most critical factor to the NILM is the performance of the classifier among the last steps of the overall NILM operation, and therefore improving the performance of the NILM classifier is an important issue. This paper proposes a new architecture based on the RNN to overcome the limitations of existing classification algorithms and to improve the performance of the NILM classifier. The proposed model, called Multi-Feature Combination Multi-Layer Long Short-Term Memory (MFC-ML-LSTM), adapts various feature extraction techniques that are commonly used for audio signal processing to power signals. It uses Multi-Feature Combination (MFC) for generating the modified input data for improving the classification performance and adopts Multi-Layer LSTM (ML-LSTM) network as the classification model for further improvements. Experimental results show that the proposed method achieves the accuracy and the F1-score for appliance classification with the ranges of 95–100% and 84–100% that are superior to the existing methods based on the Gated Recurrent Unit (GRU) or a single-layer LSTM. [ABSTRACT FROM AUTHOR]