ABSTRACT
When performing eye movement pattern classification for different tasks, support vector machines are greatly affected by parameters. To address this problem, we propose an algorithm based on the improved whale algorithm to optimize support vector machines to enhance the performance of eye movement data classification. According to the characteristics of eye movement data, this study first extracts 57 features related to fixation and saccade, then uses the ReliefF algorithm for feature selection. To address the problems of low convergence accuracy and easy falling into local minima of the whale algorithm, we introduce inertia weights to balance local search and global search to accelerate the convergence speed of the algorithm and also use the differential variation strategy to increase individual diversity to jump out of local optimum. In this paper, experiments are conducted on eight test functions, and the results show that the improved whale algorithm has the best convergence accuracy and convergence speed. Finally, this paper applies the optimized support vector machine model of the improved whale algorithm to the task of classifying eye movement data in autism, and the experimental results on the public dataset show that the accuracy of the eye movement data classification of this paper is greatly improved compared with that of the traditional support vector machine method. Compared with the standard whale algorithm and other optimization algorithms, the optimized model proposed in this paper has higher recognition accuracy and provides a new idea and method for eye movement pattern recognition. In the future, eye movement data can be obtained by combining it with eye trackers to assist in medical diagnosis.
Subject(s)
Animals , Support Vector Machine , Whales , Eye Movements , AlgorithmsABSTRACT
Objective:To investigate the efficacy of magnesium sulfate combined with labetalol on severe preeclampsia and the effects on serum levels of soluble intercellular adhesion molecule-1 (sICAM-1), vascular endothelial growth factor (VEGF) and pregnancy associated plasma protein-A (PAPP-A).Methods:Eighty-five patients with severe preeclampsia who received treatment in Jinhua Municipal Central Hospital between January 2019 and June 2020 were included in this study. They were randomly assigned to receive treatment either with magnesium sulfate (control group, n = 42) or magnesium sulfate combined with labetalol (observation group, n = 43). Before and after treatment, 24-hour dynamic blood pressure, 24-hour urinary protein excretion and umbilical artery hemodynamics were determined. In addition, serum levels of sICAM-1, VEGF and PAPP-A were detected. Results:After treatment, 24-hour mean arterial pressure, 24-hour urine protein excretion in the control and observation groups were significantly decreased compared with before treatment. After treatment, the 24-hour mean arterial pressure [(116.45 ± 9.63) mmHg vs. (120.74 ± 9.48) mmHg] and 24-hour urine protein excretion [(1.85 ± 0.52) g vs. (2.33 ± 0.75) g] were significantly lower than those in the control group ( t = 2.069, 3.436, both P < 0.05). The umbilical artery resistance index in the control group, and the peak systolic velocity/end-diastolic velocity ratio and the umbilical artery resistance index in the observation group were significantly decreased after treatment compared with before treatment (all P < 0.05). After treatment, the peak systolic velocity/end-diastolic velocity ratio in the observation group was significantly lower than that in the control group [(2.80 ± 0.50) vs. (3.01 ± 0.45), t = 2.034, P < 0.05]. After treatment, serum sICAM-1 and PAPP-A levels were significantly decreased, and serum VEGF level was significantly increased, in each group (all P < 0.05). After treatment, serum levels of sICAM-1 [(548.52 ± 102.74) mg/L vs. (647.52 ± 124.15) mg/L, t = 4.009, P < 0.05] and PAPP-A [(111.74 ± 28.52) U/L vs. (134.24 ± 35.96) U/L, t = 3.200, P < 0.05] in the observation group were significantly lower than those in the control group, and serum VEGF level in the observation group was significantly higher than that in the control group [(32.12 ± 7.45) ng/L vs. (28.17 ± 6.23) ng/L, t =2.659, P < 0.05]. There was no significant difference in the incidence of poor pregnancy outcome between the control and study groups ( P > 0.05). Conclusion:Magnesium sulfate combined with labetalol exhibits good therapeutic effects on severe preeclampsia. The treatment method can improve umbilical artery hemodynamics, and its mechanism may be related to its effect on vascular endothelial function.
ABSTRACT
Vision is an important way for human beings to interact with the outside world and obtain information. In order to research human visual behavior under different conditions, this paper uses a Gaussian mixture-hidden Markov model (GMM-HMM) to model the scanpath, and proposes a new model optimization method, time-shifting segmentation (TSS). The TSS method can highlight the characteristics of the time dimension in the scanpath, improve the pattern recognition results, and enhance the stability of the model. In this paper, a linear discriminant analysis (LDA) method is used for multi-dimensional feature pattern recognition to evaluates the rationality and the accuracy of the proposed model. Four sets of comparative trials were carried out for the model evaluation. The first group applied the GMM-HMM to model the scanpath, and the average accuracy of the classification could reach 0.507, which is greater than the opportunity probability of three classification (0.333). The second set of trial applied TSS method, and the mean accuracy of classification was raised to 0.610. The third group combined GMM-HMM with TSS method, and the mean accuracy of classification reached 0.602, which was more stable than the second model. Finally, comparing the model analysis results with the saccade amplitude (SA) characteristics analysis results, the modeling analysis method is much better than the basic information analysis method. Via analyzing the characteristics of three types of tasks, the results show that the free viewing task have higher specificity value and a higher sensitivity to the cued object search task. In summary, the application of GMM-HMM model has a good performance in scanpath pattern recognition, and the introduction of TSS method can enhance the difference of scanpath characteristics. Especially for the recognition of the scanpath of search-type tasks, the model has better advantages. And it also provides a new solution for a single state eye movement sequence.
Subject(s)
Humans , Algorithms , Discriminant Analysis , Eye Movements , Markov Chains , Normal Distribution , ProbabilityABSTRACT
Glaucoma is the leading cause of irreversible blindness, but its early symptoms are not obvious and are easily overlooked, so early screening for glaucoma is particularly important. The cup to disc ratio is an important indicator for clinical glaucoma screening, and accurate segmentation of the optic cup and disc is the key to calculating the cup to disc ratio. In this paper, a full convolutional neural network with residual multi-scale convolution module was proposed for the optic cup and disc segmentation. First, the fundus image was contrast enhanced and polar transformation was introduced. Subsequently, W-Net was used as the backbone network, which replaced the standard convolution unit with the residual multi-scale full convolution module, the input port was added to the image pyramid to construct the multi-scale input, and the side output layer was used as the early classifier to generate the local prediction output. Finally, a new multi-tag loss function was proposed to guide network segmentation. The mean intersection over union of the optic cup and disc segmentation in the REFUGE dataset was 0.904 0 and 0.955 3 respectively, and the overlapping error was 0.178 0 and 0.066 5 respectively. The results show that this method not only realizes the joint segmentation of cup and disc, but also improves the segmentation accuracy effectively, which could be helpful for the promotion of large-scale early glaucoma screening.
Subject(s)
Humans , Diagnostic Techniques, Ophthalmological , Fundus Oculi , Glaucoma/diagnostic imaging , Neural Networks, Computer , Optic Disk/diagnostic imagingABSTRACT
<p><b>OBJECTIVE</b>To assess the value of 15 short tandem repeat (STR) loci selected by an AmpFLSTR Identifilersystem for personal identification and paternity testing among ethnic Hans from Xiamen, Fujian.</p><p><b>METHODS</b>For 400 unrelated individuals, allelic frequencies for the 15 STR loci from the AmpFLSTR Identifilerkit were determined. Population genetics parameters for forensic usage were calculated.</p><p><b>RESULTS</b>No deviation of the observed allele frequency from Hardy-Weinberg equilibrium expectations was found by Chi-square test (P>0.05). All of the 15 loci were highly polymorphic. Observed heterozygosity has varied between 0.580 and 0.868. Matching probability was between 0.036 and 0.148. Power of discrimination was between 0.798 and 0.967. Polymorphic information content was between 0.560 and 0.850. And power of exclusion was between 0.268 and 0.730.</p><p><b>CONCLUSION</b>All of the 15 loci selected by the AmpFLSTR Identifilersystem are highly polymorphic among ethnic Hans from Xiamen. By determining the alleles and allelic frequencies, data for genetic polymorphisms usable for paternity testing and personal identification for local population were obtained.</p>
Subject(s)
Humans , Alleles , Asian People , Genetics , Chi-Square Distribution , China , Forensic Genetics , Methods , Gene Frequency , Genetics, Population , Methods , Genotype , Linkage Disequilibrium , Microsatellite Repeats , Genetics , Polymorphism, GeneticABSTRACT
Objective To study the incidence of age-related macular degeneration (AMD) in operated and nonoperated eyes of patients received cataract surgery.Methods 221 cataract patients in the people's hospital of Xianju county from 2004 to 2006 were selected and followed for at least for 60 months after surgery.The incidence of AMD in operated and nonoperated eyes were compared.Results 132 patients (59.70%) were followed for at least 60 months.3 months after cataract surgery,the take-off residual rate was 80.30% (106/132),the literacy rate was 99.20% (131/132).5 years after catarct surgery,the incidence of AMD in operated and nonoperated eyes were 16.67 % (22/132) and 15.15 % (20/132),the difference was not significant (x2 =0.11,P > 0.05),OR was 1.120,95% CI 0.579 ~ 2.167.In mild AMD,OR was 1.092,95% CI 0.479 ~ 2.492 ;moderate AMD OR was 1.187,95% CI 0.387 ~ 3.644 ; severe AMD OR was 1.188,95% CI 0.387 ~ 3.647.Conclusion Cataract surgery did not increase the the risk of AMD over 5 years.
ABSTRACT
<p><b>OBJECTIVE</b>In vivo Micro-PETICT imaging of mouse/rat brain has been widely used to non-invasively monitor brain and provides researchers a better understanding of therapeutic effects in models of human neurological disease. For the need of further processing, extraction of brain tissue from head is required and vital.</p><p><b>METHODS</b>An automatic multistep combination methods was proposed based on an improved level set framework, which includes (1) Use Fuzzy-C-Means method together with threshold and morphology methods to get the initial level-set surface automatically. (2) Combine gradient vector flow to enhance the gradient contrast and enforce the surface move toward to the object's surface much faster, especially obtain a significantly improvement in the regions of forehead and the joint between brain and neck. (3) introduce an automatic stop condition based on average bandwidth energy maximization to overcome the leakage problem.</p><p><b>RESULTS</b>3 Micro-CT images of rat and 3 of mouse have been tested using the proposed methods and the average accuracy has increased by 33% for rat and 6.7% for mouse. The average processing duration for rat and mouse are about 8 minutes and 4 minutes, respectively.</p><p><b>CONCLUSIONS</b>The proposed methods were proved that it can be effectively used for Micro-PET/CT imaging of mouse/rat brain segmentation and have a great improvement on accuracy and convenience.</p>
Subject(s)
Animals , Mice , Rats , Image Processing, Computer-Assisted , Methods , Imaging, Three-Dimensional , Methods , Neuroimaging , Methods , Pattern Recognition, Automated , Methods , X-Ray Microtomography , MethodsABSTRACT
Objective: To evaluate the efficacy of 3LL/GM-CSF tumor vaccine combined with pacilitaxel chemotherapy in treatment of mice bearing transplanted Lewis lung carcinoma. Methods: The tumor vaccine 3LL/GM-CSF was prepared by infecting Lewis lung carcinoma cell line 3LL with adenovirus encoding GM-GSF. Mice model of Lewis lung carcinoma was established by subcutaneous injection of 2?104 3LL cells into C57BL/6(H-2b)mice. The sensitivity of Lewis lung carcinoma cell line-3LL to the treatment of pacilitaxel was detected in vivo and in vitro. The mice tumor model was first treated with pacilitaxel chemotherapy and then with 3LL/GM-CSF, or first with 3LL/GM-CSF and then with pacilitaxel. Tumor growth and the long-term survival of mice were observed after treatment. The immune memory and cytotoxicity against target cells were studied in the mice. Results: Pacilitaxel at 100 nmol/L killed 32.10% 3LL cells after 24 hour in vitro; but pacilitaxel at 5-25 mg/kg only had a poor effect on growth of 3LL cells in vivo. The tumors rebated in 70% of mice treated with pacilitaxel chemotherapy and 3LL/GM-CSF vaccination successively, and the survival of these mice was obviously longer than that of pure pacilitaxel chemotherapy group (70.0 days vs 27.5 days). The killing rate of 3LL/GM-CSF after pacilitaxel chemotherapy was 41.35% on day 3. Meanwhile, the survival mice could resist the re-attack of 3LL cells (2?104). We also noticed that first treatment with 3LL/GM-CSF and then pacilitaxel chemotherapy had no effect on tumors. Conclusion: Application of tumor vaccine shortly after pacilitaxel chemotherapy can induce specific immune responses and prolong the survival of experimental mice, which provide a basis for future clinical practice.