Chengfan Li

Dr. Chengfan Li

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
CLChengfan Li
Chengfan Li
YQyueyu qi
yueyu qi
DXDing xuehai
Ding xuehai
JZJunjuan Zhao
Junjuan Zhao
TSTian Sang
Tian Sang
MLMatthew Lee
Matthew Lee
The classification of sleep stages is an important process. However, this process is time-consuming, subjective, and error-prone. Many automated classification methods use electroencephalogram (EEG) signals for classification. These methods do not classify well enough and perform poorly in the N1 due to unbalanced data. In this paper, we propose a sleep stage classification method using EEG spectrogram. We have designed a deep learning model called EEGSNet based on multi-layer convolutional neural networks (CNNs) to extract time and frequency features from the EEG spectrogram, and two-layer bi-directional long short-term memory networks (Bi-LSTMs) to learn the transition rules between features from adjacent epochs and to perform the classification of sleep stages. In addition, to improve the generalization ability of the model, we have used Gaussian error linear units (GELUs) as the activation function of CNN. The proposed method was evaluated by four public databases, the Sleep-EDFX-8, Sleep-EDFX-20, Sleep-EDFX-78, and SHHS. The accuracy of the method is 94.17%, 86.82%, 83.02% and 85.12%, respectively, for the four datasets, the MF1 is 87.78%, 81.57%, 77.26% and 78.54%, respectively, and the Kappa is 0.91, 0.82, 0.77 and 0.79, respectively. In addition, our proposed method achieved better classification results on N1, with an F1-score of 70.16%, 52.41%, 50.03% and 47.26% for the four datasets.

11 November 2019 in IEEE Access
Verified
Journal Article
Open access
XSXiankun Sun
Xiankun Sun
LLlan liu
lan liu
CLChengfan Li
Chengfan Li
JYJingyuan Yin
Jingyuan Yin
JZJunjuan Zhao
Junjuan Zhao
WSWen Si
Wen Si
The efficient classification of remote sensing images (RSIs) has become the key of remote sensing application. To tackle the high computational cost in the traditional classification method, in this paper we propose a new RSI classification method based on improved convolutional neural network (CNN) and support vector machine (SVM) (CNN-SVM). In this method, we first designed a seven-layer CNN structure and took the ReLU function as the activation function. We then inputted the RSI into the CNN model and extracted feature maps and replaced the output layer of the CNN network via training the feature maps in the SVM classifier. Next, taking the simulation experiments of MNIST handwritten digital dataset and UC Merced Land Use remote sensing dataset as examples, we tested and verified the proposed method in this experiment. Finally, the empirical study of volcanic ash cloud (VAC) classification from moderate resolution imaging spectroradiometer (MODIS) RSI was carried out and evaluated. The experimental results show that compared with the traditional methods, the proposed method has lower loss value and better generalization in modeling training; the total classification accuracy of VAC and Kappa coefficient reached 93.5 and 0.8502, respectively, and achieved preferable VAC identification and visual effects. It will enhance the classification accuracy to the massive remote sensing data.

17 July 2017 in Arabian Journal of Geosciences
Verified
Journal Article
Closed access
PDF file
LLLan Liu
Lan Liu
CLChengfan Li
Chengfan Li
YLYong-Mei Lei
Yong-Mei Lei
JYJing-Yuan Yin
Jing-Yuan Yin
JZJun-Juan Zhao
Jun-Juan Zhao

11 December 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
CLChengfan Li
Chengfan Li
ZZZixuan Zhang
Zixuan Zhang
LLlan liu
lan liu
JKJungYoon Kim
JungYoon Kim
Arun Kumar SangaiahArun Kumar Sangaiah
Arun Kumar Sangaiah
The fully-supervised deep convolutional neural network (CNN) cannot detect the discriminant local information which is responsible for spatial transformations in high-resolution remote sensing images. To address the various types and missing labels of natural disasters, a new deep multi-instance convolutional neural network (DMCNN) model for disaster classification in high-resolution remote sensing image is presented in this article. Specifically, based on sample enhancement and atrous spatial pyramid pooling (ASPP), we first extract and integrate the features via the CNN structure to obtain the instance feature of bags in the image. Besides, introducing a prototype learning layer with distance measure, the instance features extracted from pretrained CNN are mapped into a series of prototype instance features with bag-level. And then all instance features from prototype and bag take part in disaster detection and image classification. Finally, we conduct extensive experiments on xBD dataset and discussions from qualitative and quantitative aspects. Experimental results show that the proposed DMCNN model achieves better classification accuracy of natural disaster from high-resolution remote sensing image compared to traditional CNNs, and effectively improves the disaster classification performance with weakly-supervised from high-resolution remote sensing image.

1 May 2017 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
PDF file
CLChengfan Li
Chengfan Li
LLLan Liu
Lan Liu
YLYong-Mei Lei
Yong-Mei Lei
JYJing-Yuan Yin
Jing-Yuan Yin
JZJun-Juan Zhao
Jun-Juan Zhao
XSXian-Kun Sun
Xian-Kun Sun
Feature extraction from hyperspectral remote sensing data is an effective method for object classification, and how to classify the object information from hyperspectral remote sensing image has become one of the core technologies of the remote sensing application. Aiming at the characteristics of space modulated interference hyperspectral image (HSI) hyperspectral remote sensing image, in this article a new remote sensing clustering method is presented on the basis of analyzing the principal component analysis (PCA) and independent component analysis (ICA), which is able both to extract data’s independent features in terms on the second-order statistics and higher-order statistical information. The proposed method classifies the HSI hyperspectral remote sensing image better than the traditional methods. Firstly, the definition of the feature weighting between PCA and ICA is used in order to calculate the weighted value. Then, similarity measure contains distance similarity and cosine similarity is introduced. Finally, the recognition rule is constructed to classify the hyperspectral remote sensing image. The true HSI hyperspectral remote sensing is used to evaluate the performance of our method. Experimental results indicate that the proposed clustering method outperforms traditional classification methods, and the classification accuracy reaches to 85% under certain conditions with the suitable number of eigenvectors is 12 and weighted values is 0.8. Meanwhile, the image quality of our method is well preserved.

27 October 2016 in IEEE Access
Verified
Journal Article
Open access
LLLan Liu
Lan Liu
CLChengfan Li
Chengfan Li
YLYong-Mei Lei
Yong-Mei Lei
JZJun-Juan Zhao
Jun-Juan Zhao
JYJing-Yuan Yin
Jing-Yuan Yin
XSXian-Kun Sun
Xian-Kun Sun
Remote sensing classification for volcanic ash cloud is a difficult task in the remote sensing application, and how to accurately obtain the volcanic ash cloud information from remote sensing image has become a key step in remote sensing classification of volcanic ash cloud. Aiming at the characteristics of the remote sensing images, via introducing the neighborhood pixels based on the classical fuzzy C-means clustering algorithm, this paper proposed a new fuzzy clustering remote sensing classification method with neighborhood distance constraint for volcanic ash cloud. This paper is tested from simulation texture image and moderate resolution imaging spectroradiometer remote sensing image, and finally explored the Sangeang Api volcanic ash cloud case on May 30, 2014. Our experiments show that the proposed method can effectively classify the volcanic ash cloud from remote sensing images, and the overall classification accuracy and Kappa coefficient reach 88.4% and 0.8064. To some extent, it overcomes the deficiency of the approaches in traditional volcanic ash cloud remote sensing classification.