This paper proposes a motor imagery recognition algorithm based on feature fusion and transfer adaptive boosting (TrAdaboost) to address the issue of low accuracy in motor imagery (MI) recognition across subjects, thereby increasing the reliability of MI-based brain-computer interfaces (BCI) for cross-individual use. Using the autoregressive model, power spectral density and discrete wavelet transform, time-frequency domain features of MI can be obtained, while the filter bank common spatial pattern is used to extract spatial domain features, and multi-scale dispersion entropy is employed to extract nonlinear features. The IV-2a dataset from the 4 ^th International BCI Competition was used for the binary classification task, with the pattern recognition model constructed by combining the improved TrAdaboost integrated learning algorithm with support vector machine (SVM), k nearest neighbor (KNN), and mind evolutionary algorithm-based back propagation (MEA-BP) neural network. The results show that the SVM-based TrAdaboost integrated learning algorithm has the best performance when 30% of the target domain instance data is migrated, with an average classification accuracy of 86.17%, a Kappa value of 0.723 3, and an AUC value of 0.849 8. These results suggest that the algorithm can be used to recognize MI signals across individuals, providing a new way to improve the generalization capability of BCI recognition models.
Brain-Computer Interfaces ; Humans ; Support Vector Machine ; Algorithms ; Neural Networks, Computer ; Imagination/physiology* ; Pattern Recognition, Automated/methods* ; Electroencephalography ; Wavelet Analysis

To address the problem of large reconstruction errors in 3D pulse signals caused by excessively small out-of-plane displacement of the contact membrane in the existing traditional Chinese medicine fingertip tactile binocular vision detection technology, this study proposes a 3D pulse image detection method based on subtle motion magnification technology and explores its application in pulse pattern recognition. Firstly, a 3D pulse image detection system based on binocular vision to obtain pulse image signals is developed as experimental data. Then, the phase motion video magnification algorithm is used to amplify the original signals, and the amplified signals are reconstructed in three dimensions to obtain 3D pulse signals. On this basis, nine features are extracted from the 3D pulse signals and features selection is performed using a two-sample Kolmogorov-Smirnov test. Finally, machine learning algorithms such as decision trees and random forests are used to identify the five types of pulse conditions: deep pulse, intermittent pulse, flooding pulse, slippery pulse, and rapid pulse. The experimental results show that compared to the methods without subtle motion magnification technology, the proposed method significantly improves waveform clarity, amplitude stability, and periodic regularity. Meanwhile, the average accuracy in pulse pattern recognition reaches 96.29%±0.26%.
Algorithms ; Imaging, Three-Dimensional/methods* ; Pattern Recognition, Automated ; Medicine, Chinese Traditional ; Motion ; Humans ; Pulse ; Signal Processing, Computer-Assisted ; Machine Learning

This study aims to address the limitations in gesture recognition caused by the susceptibility of temporal and frequency domain feature extraction from surface electromyography signals, as well as the low recognition rates of conventional classifiers. A novel gesture recognition approach was proposed, which transformed surface electromyography signals into grayscale images and employed convolutional neural networks as classifiers. The method began by segmenting the active portions of the surface electromyography signals using an energy threshold approach. Temporal voltage values were then processed through linear scaling and power transformations to generate grayscale images for convolutional neural network input. Subsequently, a multi-view convolutional neural network model was constructed, utilizing asymmetric convolutional kernels of sizes 1 × n and 3 × n within the same layer to enhance the representation capability of surface electromyography signals. Experimental results showed that the proposed method achieved recognition accuracies of 98.11% for 13 gestures and 98.75% for 12 multi-finger movements, significantly outperforming existing machine learning approaches. The proposed gesture recognition method, based on surface electromyography grayscale images and multi-view convolutional neural networks, demonstrates simplicity and efficiency, substantially improving recognition accuracy and exhibiting strong potential for practical applications.
Electromyography/methods* ; Neural Networks, Computer ; Humans ; Gestures ; Signal Processing, Computer-Assisted ; Machine Learning ; Pattern Recognition, Automated/methods* ; Algorithms ; Convolutional Neural Networks

OBJECTIVES: Clinical discharge summaries provide valuable information about patients' clinical history, which is helpful for the realization of intelligent healthcare applications. The documents tend to take the form of separate segments based on temporal or topical information. If a patient's clinical history can be seen as a consecutive sequence of clinical events, then each temporal segment can be seen as a snapshot, providing a certain clinical context at a specific moment. This study aimed to demonstrate a temporal segmentation method of Korean clinical narratives for identifying textual snapshots of patient history as a proof-of-a-concept. METHODS: Our method uses pattern-based segmentation to approximate human recognition of the temporal or topical shifts in clinical documents. We utilized rheumatic patients' discharge summaries and transformed them into sequences of constituent chunks. We built 97 single pattern functions to denote whether a certain chunk has attributes that indicate that it can be a segment boundary. We manually defined the relationships between the pattern functions to resolve multiple pattern matchings and to make a final decision. RESULTS: The algorithm segmented 30 discharge summaries and processed 1,849 decision points. Three human judges were asked whether they agreed with the algorithm's prediction, and the agreement percentage on the judges' majority opinion was 89.61%. CONCLUSIONS: Although this method is based on manually constructed rules, our findings demonstrate that the proposed algorithm can achieve fairly good segmentation results, and it may be the basis for methodological improvement in the future.
Delivery of Health Care ; Electronic Health Records ; Humans ; Methods ; Natural Language Processing ; Pattern Recognition, Automated ; Rheumatic Diseases

Breast cancer is the second leading cancer for Korean women and its incidence rate has been increasing annually. If early diagnosis were implemented with epidemiologic data, the women could easily assess breast cancer risk using internet. National Cancer Institute in the United States has released a Web-based Breast Cancer Risk Assessment Tool based on Gail model. However, it is inapplicable directly to Korean women since breast cancer risk is dependent on race. Also, it shows low accuracy (58%-59%). In this study, breast cancer discrimination models for Korean women are developed using only epidemiological case-control data (n = 4,574). The models are configured by different classification techniques: support vector machine, artificial neural network, and Bayesian network. A 1,000-time repeated random sub-sampling validation is performed for diverse parameter conditions, respectively. The performance is evaluated and compared as an area under the receiver operating characteristic curve (AUC). According to age group and classification techniques, AUC, accuracy, sensitivity, specificity, and calculation time of all models were calculated and compared. Although the support vector machine took the longest calculation time, the highest classification performance has been achieved in the case of women older than 50 yr (AUC = 64%). The proposed model is dependent on demographic characteristics, reproductive factors, and lifestyle habits without using any clinical or genetic test. It is expected that the model could be implemented as a web-based discrimination tool for breast cancer. This tool can encourage potential breast cancer prone women to go the hospital for diagnostic tests.
Adult ; Aged ; Aged, 80 and over ; Breast Neoplasms/*diagnosis/*epidemiology ; Diagnosis, Computer-Assisted/*methods ; Early Detection of Cancer/*methods ; Female ; Humans ; *Machine Learning ; Middle Aged ; Pattern Recognition, Automated/methods ; Prevalence ; Reproducibility of Results ; Republic of Korea/epidemiology ; Risk Assessment/methods ; Risk Factors ; Sensitivity and Specificity ; Women's Health/*statistics & numerical data

To improve accuracy of estimation in planted safflower acreage,we selected agricultural area in Yumin County, Xinjiang as the study area. There safflower was concentrated planted. Supervised classification based on Principal Component Analysis (PCA) and texture feature were used to obtain the safflower acreage from image captured by ZY-3. The classification result was compared with only spectral feature and spectral feature with texture feature. The research result shows that this method can effectively solve the problem of low accuracy and fracture classification result in single data source classification. The overall accuracy is 87.519 1%, which increases by 7.117 2% compared with single data source classification. Therefore, the classification method based on PCA and texture features can be adapted to RS image classification and estimate the acreage of safflower. This study provides a feasible solution for estimation of planted safflower acreage by image captured by ZY-3 satellite.
Algorithms ; Carthamus tinctorius ; chemistry ; growth & development ; Image Processing, Computer-Assisted ; Pattern Recognition, Automated ; Principal Component Analysis ; methods ; Remote Sensing Technology ; methods

Medical image fusion and recognition has a wide range of applications, such as focal location, cancer staging and treatment effect assessment. Multi-model medical image fusion and recognition are analyzed and summarized in this paper. Firstly, the question of multi-model medical image fusion and recognition is discussed, and its advantage and key steps are discussed. Secondly, three fusion strategies are reviewed from the point of algorithm, and four fusion recognition structures are discussed. Thirdly, difficulties, challenges and possible future research direction are discussed.
Algorithms ; Artificial Intelligence ; Diagnostic Imaging ; methods ; Image Enhancement ; methods ; Image Interpretation, Computer-Assisted ; methods ; Image Processing, Computer-Assisted ; methods ; Magnetic Resonance Imaging ; methods ; Pattern Recognition, Automated ; methods ; Positron-Emission Tomography ; methods ; Tomography, X-Ray Computed ; methods

Facial paralysis is a frequently-occurring disease, which causes the loss of the voluntary muscles on one side of the face due to the damages the facial nerve and results in an inability to close the eye and leads to dropping of the angle of the mouth. There have been few objective methods to quantitatively diagnose it and assess this disease for clinically treating the patients so far. The skin temperature distribution of a healthy human body exhibits a contralateral symmetry. Facial paralysis usually causes an alteration of the temperature distribution of body with the disease. This paper presents the use of the histogram distance of bilateral local binary pattern (LBP) in the facial infrared thermography to measure the asymmetry degree of facial temperature distribution for objective assessing the severity of facial paralysis. Using this new method, we performed a controlled trial to assess the facial nerve function of the healthy subjects and the patients with Bell's palsy respectively. The results showed that the mean sensitivity and specificity of this method are 0.86 and 0.89 respectively. The correlation coefficient between the asymmetry degree of facial temperature distribution and the severity of facial paralysis is an average of 0.657. Therefore, the histogram distance of local binary pattern in the facial infrared thermography is an efficient clinical indicator with respect to the diagnosis and assessment of facial paralysis.
Facial Paralysis ; diagnosis ; physiopathology ; Humans ; Infrared Rays ; Pattern Recognition, Automated ; methods ; Skin Temperature ; Thermography ; instrumentation

Discriminative common vector (DCV) is an effective method that was proposed for the small sample size problems of face recognition. There is the same problem in brain-computer interface (BCI). Using directly the linear discriminative analysis (LDA) could result in errors because of the singularity of the within-class matrix of data. In our studies, we used the DCV method from the common vector theory in the within-class scatter matrix of data of all classes, and then applied eigenvalue decomposition to the common vectors to obtain the final projected vectors. Then we used kernel discriminative common vector (KDCV) with different kernel. Three data sets that include BCI Competition I data set, Competition II data set IV, and a data set collected by ourselves were used in the experiments. The experiment results of 93%, 77% and 97% showed that this feature extraction method could be used well in the classification of imagine data in BCI.
Algorithms ; Artificial Intelligence ; Brain-Computer Interfaces ; Discriminant Analysis ; Electroencephalography ; Face ; anatomy & histology ; Humans ; Pattern Recognition, Automated ; methods ; Principal Component Analysis ; Sample Size ; Signal Processing, Computer-Assisted ; User-Computer Interface

This paper is aimed to fulfill a prototype system used to classify and retrieve retinal image automatically. With the content-based image retrieval (CBIR) technology, a method to represent the retinal characteristics mixing the fundus image color (gray) histogram with bright, dark region features and other local comprehensive information was proposed. The method uses kernel principal component analysis (KPCA) to further extract nonlinear features and dimensionality reduced. It also puts forward a measurement method using support vector machine (SVM) on KPCA weighted distance in similarity measure aspect. Testing 300 samples with this prototype system randomly, we obtained the total image number of wrong retrieved 32, and the retrieval rate 89.33%. It showed that the identification rate of the system for retinal image was high.
Algorithms ; Fundus Oculi ; Humans ; Image Processing, Computer-Assisted ; methods ; Information Storage and Retrieval ; methods ; Numerical Analysis, Computer-Assisted ; Ophthalmoscopy ; standards ; Pattern Recognition, Automated ; methods ; Retina ; pathology ; Retinal Vessels ; pathology