The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.
Algorithms ; Artificial Intelligence ; Breast Neoplasms ; classification ; diagnosis ; Discriminant Analysis ; Female ; Humans

Objective To investigate the influence of age on the perioperative characteristics of posterior lumbar interbody fusion (PLIF). Methods 129 patients (25~91 years old) with spondylolisthesis, lumbar stenosis and/or disc degeneration/herniation with instability,or unsuccessful results after a failed previous PLIF. They were divided into control group (<65 years old, n=85) and experimental group (<65 years old, n=44). The American Society of Anesthesiologists (ASA) score, the number of fusion segments, estimated blood loss and hospital stay were observed. Results The ASA score was higher in the experimental group than in the control group (P<0.001). There was no significant difference in complications, estimated blood loss and operative time (P>0.05) between 2 groups. Conclusion Age can not increase the rate of perioperative complications of PLIF, and the advanced age should not be surgical contraindication.

To increase efficiency of automated leucocyte pattern recognition using lower feature dimensions, a novel inter-class distinctive feature selection method for chromatic leucocyte images was proposed based on attribute hierarchical relationship. According to the attribute constraints in formal concept analysis, we established a knowledge representation and discovery method based on the hierarchical optimal diagram by defining attribute value and visual representation of optimized hierarchical relationship. It was applied to human peripheral blood leucocytes classification and 12 distinctive attributes were simplified from 60 inter-class attributes, which contributes significantly to reduced feature dimensions and efficient inter-class feature classification. Compared with the classical experimental data, the inter-class distinctive feature selection method based on hierarchical optimal diagram was proved to be usable and effective for six leucocyte pattern recognition.
Humans ; Leukocytes ; classification ; Pattern Recognition, Automated

Objective To detect the spatial point pattern distribution rules of neural tube defects.Methods The kernel density estimation and Ripley's K-function were used to analyze the spatial point pattern of the neural tube birth defects in Heshun county in 1998-2001.Results The kernel density estimation result showed that there was two clusters' distribution in central area and southeastern area respectively.In addition,the result by the Ripley's K-function presented that the location of neural tube birth defects had a significant cluster tendency in the spatial distance from 3.17 to 10.41 kilometers in the investigated area.Conclusion These results can provide an important clue for identifying the relations between environment risk factors and birth defects in this area in the future.

Mixed reality technology can achieve a 3D reconstruction of the patient's imaging data and organically combine the real scene. This allows to simulate a real medical operation in clinical teaching. Combined with large data analysis, mixed reality technology allows to build situational awareness data models, thus providing data support for teaching interaction and disease simulations. In the present work, the application of mixed reality technology and situational awareness in clinical teaching of cardiac macrovascular surgery is explored innovatively. These technologies open a new avenue for teaching, solving the issue that stymies traditional teaching approaches and improving the teaching efficiency. It is thus important to explore and promote the applications of this innovative teaching methodology particularly in clinical teaching.

ObjectiveTo investigate the relationship between the level of plasma D-dimer(D-D) and hepatic functional reserve status in patients with hepatitis B (HB).Methods77 cases with HB were divided into two groups, hepatic function compensated group and hepatic function decompensated group.Plasma D-D, hepatic functional indexes and PT of all patients were detected.ResultsThe level of D-D in the hepatic function decompensated group was higher than that in the hepatic function compensated group(299.0 ± 498.5) μg/L vs (27.9 ± 34.0) μg/L(t =3.1, P ＜ 0.01).D-D negatively correlated with ALB and PA(r =-0.6,-0.6, all P ＜ 0.01), and positively correlated with TBIL and PT(r = 0.4,0.6, all P ＜ 0.01).ConclusionThe level of plasma D-D related with hepatic functional reserve status,and detecting the level of D-D could be helpful to estimate hepatic functional reserve and prognosis of patients with HB.

Electroencephalogram (EEG) classification for brain-computer interface (BCI) is a new way of realizing human-computer interreaction. In this paper the application of semi-supervised sparse representation classifier algorithms based on help training to EEG classification for BCI is reported. Firstly, the correlation information of the unlabeled data is obtained by sparse representation classifier and some data with high correlation selected. Secondly, the boundary information of the selected data is produced by discriminative classifier, which is the Fisher linear classifier. The final unlabeled data with high confidence are selected by a criterion containing the information of distance and direction. We applied this novel method to the three benchmark datasets, which were BCI I, BCI II_IV and USPS. The classification rate were 97%, 82% and 84.7%, respectively. Moreover the fastest arithmetic rate was just about 0. 2 s. The classification rate and efficiency results of the novel method are both better than those of S3VM and SVM, proving that the proposed method is effective.
Algorithms ; Brain-Computer Interfaces ; Electroencephalography ; classification ; Humans

Objective To summarize the value of early mechanical ventilation plus continuous vacuum suction in treatment of serious pulmonary contusion.Methods Forty-eight cases of severe pulmonary contusion were assigned to mechanical ventilation plus continuous vacuum suction (observation group,n =20) and mechanical ventilation plus discontinuous vacuum suction (control group,n =28)according to the random number table.Modes of mechanical ventilation were synchronized intermittent mandatory ventilation (SIMV),pressure support ventilation (PSV),and positive and expiratory pressure (PEEP).Changes in blood gas analysis,mechanical ventilation time,and associated complications were compared between groups.Results At ventilation time of 6 and 24 hours,PaO2 in observation group was (100.36 ± 5.90) mmHg and (105.34 ± 7.40) mmHg respectively,with significant differences from (75.36 ± 8.95) mmHg and (76.36 ± 8.35) mmHg in control group (P ＜ 0.01).At ventilation time of 24 hours,PaO2/FiO2 was (283.50 ± 15.20) mmHg in observation group and (201.50 ± 10.20) mmHg in control group (P ＜0.01).Mechanical ventilation time and PEEP at ventilation time of 48 hours in observation group was (3.2 ± 1.1) days and (4.5 ± 2.3) cmH2 O,with significant differences from (6.5 ± 2.8) days and (8.5 ± 2.5) cmH2O in control group (P ＜ 0.01).Associated complications of the two groups revealed no significant difference (P ＞ 0.05).Conclusion Early mechanical ventilation with sustained vacuum suction is effective to keep airway clear,improve oxygenation index,decrease PEEP level,and control the duration of mechanical ventilation,but may not lower the risks of ventilator-associated pneumonia and pulmonary atelectasis.

Humans ; Liver Neoplasms ; pathology ; Sarcoma ; pathology

Based on the histories of moxibustion and moxibustion apparatus, this paper studies two basic patterns and the problem of categorizing about moxibustion instrument, and summarizes and experimentalizes its mechanism. Its developing way is brought up.