Early Stroke Prediction Methods for Prevention of Strokes

Predictive modelling and identification of key risk factors for stroke using machine learning

Strokes are a leading global cause of mortality, underscoring the need for early detection and prevention strategies. However, addressing hidden risk factors and achieving accurate prediction become particularly challenging in the presence of imbalanced and missing data. This study encompasses three imputation techniques to deal with missing data. To tackle data imbalance, it employs the synthetic minority oversampling technique (SMOTE). The study initiates with a baseline model and subsequently employs an extensive range of advanced models. This study thoroughly evaluates the performance of these models by employing k-fold cross-validation on various imbalanced and balanced datasets. The findings reveal that age, body mass index (BMI), average glucose level, heart disease, hypertension, and marital status are the most influential features in predicting strokes. Furthermore, a Dense Stacking Ensemble (DSE) model is built upon previous advanced models after fine-tuning, with the best-performing model as a meta-classifier. The DSE model demonstrated over 96% accuracy across diverse datasets, with an AUC score of 83.94% on imbalanced imputed dataset and 98.92% on balanced one. This research underscores the remarkable performance of the DSE model, compared to the previous research on the same dataset. It highlights the model's potential for early stroke detection to improve patient outcomes.

Stroke risk prediction models: A systematic review and meta-analysis

BACKGROUND

Prediction algorithms/models are viable methods for identifying individuals at high risk of stroke across diverse populations for timely intervention. However, evidence summarizing the performance of these models is limited. This study examined the performance and weaknesses of existing stroke risk-score-prediction models (SRSMs) and whether performance varied by population and region.

METHODS

PubMed, EMBASE, and Web of Science were searched for articles on SRSMs from the earliest records until February 2022. The Prediction Model Risk of Bias Assessment Tool was used to assess the quality of eligible articles. The performance of the SRSMs was assessed by meta-analyzing C-statistics (0 and 1) estimates from identified studies to determine the overall pooled C-statistics by fitting a linear restricted maximum likelihood in a random effect model.

RESULTS

Overall, 17 articles (cohort study = 15, nested case-control study = 2) comprising 739,134 stroke cases from 6,396,594 participants from diverse populations/regions (Asia; n = 8, United States; n = 3, and Europe and the United Kingdom; n = 6) were eligible for inclusion. The overall pooled c-statistics of SRSMs was 0.78 (95%CI: 0.75, 0.80; I2 = 99.9%), with most SRSMs developed using cohort studies; 0.78 (95%CI: 0.75, 0.80; I2 = 99.9%). The subgroup analyses by geographical region: Asia [0.81 (95%CI: 0.79, 0.83; I2 = 99.8%)], Europe and the United Kingdom [0.76 (95%CI: 0.69, 0.83; I2 = 99.9%)] and the United States only [0.75 (95%CI: 0.72, 0.78; I2 = 73.5%)] revealed relatively indifferent performances of SRSMs.

CONCLUSION

SRSM performance varied widely, and the pooled c-statistics of SRSMs suggested a fair predictive performance, with very few SRSMs validated in independent population group(s) from diverse world regions.

Unlocking stroke prediction: Harnessing projection-based statistical feature extraction with ML algorithms

Non-communicable diseases, such as cardiovascular disease, cancer, chronic respiratory diseases, and diabetes, are responsible for approximately 71% of all deaths worldwide. Stroke, a cerebrovascular disorder, is one of the leading contributors to this burden among the top three causes of death. Early recognition of symptoms can encourage a balanced lifestyle and provide essential information for stroke prediction. To identify a stroke patient and risk factors, machine learning (ML) is a key tool for physicians. Due to different data measurement scales and their probability distributional assumptions, ML-based algorithms struggle to detect risk factors. Furthermore, when dealing with risk factors with high-dimensional features, learning algorithms struggle with complexity. In this study, rigorous statistical tests are used to identify risk factors, and PCA-FA (Integration of Principal Components and Factors) and FPCA (Factor Based PCA) approaches are proposed for projecting suitable feature representations for improving learning algorithm performances. The study dataset consists of different clinical, lifestyle, and genetic attributes, allowing for a comprehensive analysis of potential risk factors associated with stroke, which contains 5110 patient records. Using significant test (P-value <0.05), chi-square and independent sample t-test identified age, heart_disease, hypertension, work_type, ever_married, bmi, and smoking_status as risk factors for stroke. To develop the predicting model with proposed feature extraction techniques, random forests approach provides the best results when utilizing the PCA-FA method. The best accuracy rate for this approach is 92.55%, while the AUC score is 98.15%. The prediction accuracy has increased from 2.19% to 19.03% compared to the existing work. Additionally, the prediction results is robustified and reproducible with a stacking ensemble-based classification algorithm. We also developed a web-based application to help doctors diagnose stroke risk based on the findings of this study, which could be used as an additional tool to help doctors diagnose.

Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Elderly hypertensive patients diagnosed with transient ischemic attack (TIA) are at a heightened risk for developing acute ischemic stroke (AIS). This underscores the critical need for effective risk prediction and identification of predictive factors. In our study, we utilized patient data from peripheral blood tests and clinical profiles within hospital information systems. These patients were followed for a three-year period to document incident AIS. Our cohort of 11,056 individuals was randomly divided into training, validation, and testing sets in a 5:2:3 ratio. We developed an XGBoost model, developed using selected indicators, provides an effective and non-invasive method for predicting the risk of AIS in elderly hypertensive patients diagnosed with TIA. Impressively, this model achieved a balanced accuracy of 0.9022, a recall of 0.8688, and a PR-AUC of 0.9315. Notably, our model effectively encapsulates essential data variations involving mixed nonlinear interactions, providing competitive performance against more complex models that incorporate a wider range of variables. Further, we conducted an in-depth analysis of the importance and sensitivity of each selected indicator and their interactions. This research equips clinicians with the necessary tools for more precise identification of high-risk individuals, thereby paving the way for more effective stroke prevention and management strategies.

Retracted: Early Stroke Prediction Methods for Prevention of Strokes

[This retracts the article DOI: 10.1155/2022/7725597.].

Non-invasive and accurate risk evaluation of cerebrovascular disease using retinal fundus photo based on deep learning

Background

Cerebrovascular disease (CeVD) is a prominent contributor to global mortality and profound disability. Extensive research has unveiled a connection between CeVD and retinal microvascular abnormalities. Nonetheless, manual analysis of fundus images remains a laborious and time-consuming task. Consequently, our objective is to develop a risk prediction model that utilizes retinal fundus photo to noninvasively and accurately assess cerebrovascular risks.

Materials and methods

To leverage retinal fundus photo for CeVD risk evaluation, we proposed a novel model called Efficient Attention which combines the convolutional neural network with attention mechanism. This combination aims to reinforce the salient features present in fundus photos, consequently improving the accuracy and effectiveness of cerebrovascular risk assessment.

Result

Our proposed model demonstrates notable advancements compared to the conventional ResNet and Efficient-Net architectures. The accuracy (ACC) of our model is 0.834 ± 0.03, surpassing Efficient-Net by a margin of 3.6%. Additionally, our model exhibits an improved area under the receiver operating characteristic curve (AUC) of 0.904 ± 0.02, surpassing other methods by a margin of 2.2%.

Conclusion

This paper provides compelling evidence that Efficient-Attention methods can serve as effective and accurate tool for cerebrovascular risk. The results of the study strongly support the notion that retinal fundus photo holds great potential as a reliable predictor of CeVD, which offers a noninvasive, convenient and low-cost solution for large scale screening of CeVD.

Machine learning and data analysis-based study on the health issues post-pandemic

The COVID-19 pandemic has had significant impacts on the health of individuals and communities around the world. While the immediate health impacts of the virus itself are well-known, there are also a number of post-pandemic health issues that have emerged as a result of the pandemic. The pandemic has caused increased levels of anxiety, depression, and other mental health issues among people of all ages. The isolation, uncertainty, and grief caused by the pandemic have taken a toll on people's mental well-being, and there is a growing concern that the long-term effects of the pandemic on mental health could be severe. Many people have delayed or avoided medical care during the pandemic, which could lead to long-term health problems. Additionally, people who have contracted COVID-19 may experience ongoing symptoms, such as fatigue, shortness of breath, and muscle weakness, which could impact their long-term health. Machine learning (ML) can be a powerful tool to analyze the health impact of the post-pandemic period. With the vast amounts of data available from electronic health records, public health databases, and other sources, this article is making use of ML methods which can help identify patterns and insights to conclude the study. The proposed ML models can analyze health data to identify trends and patterns that may indicate future health problems. By monitoring patterns in medical records and public health data, the proposed ML model can help public health officials detect and respond to outbreaks more quickly. The survey outcome reveals that the level of physical activities has been decreased by 22% during COVID-19-outbreak. The variance is shown at 49% during COVID-19 outbreak. The absence of physical activity (PA) and perceived stress (PS) are observed to be suggestively correlated with the QoL (quality of life) of adults. Deteriorated mental health also disrupts the normal lives and impacts the sleeping quality of people. The analysis of the data is performed using statistical analytical tools to depict the consequences of pandemic on the health of individuals aged between 50 to 80 years.

A Study on THE Mechanism of Electroacupuncture to Alleviate Visceral Pain and NGF Expression

Visceral pain is unbearable, and natural methods are needed to relieve it. Electroacupuncture is a relatively new technique that helps relieve visceral pain by improving blood circulation and providing energy to clogged parts of the body. However, its analgesic effect and mechanism in colorectal pain are still unknown. In this study, the visceral pain models of electroacupuncture in rats were compared and discussed, using nanocomponents to stimulate the expression and mechanism of the nerve growth factor in colorectal pain and electroacupuncture and to observe the expression and mechanism of nerve growth factor in visceral pain relief rats induced by nanocomponents and electroacupuncture. The results show that nanocomponents can effectively relieve visceral pain under the action of electroacupuncture. NGF can activate endogenous proliferation, migration, differentiation, and integration. NSC can promote nerve regeneration and recovery after injury.

Analysis of Structured Data in Biomedicine Using Soft Computing Techniques and Computational Analysis

In the field of biomedicine, enormous data are generated in a structured and unstructured form every day. Soft computing techniques play a major role in the interpretation and classification of the data to make appropriate decisions for making policies. The field of medical science and biomedicine needs efficient soft computing-based methods which can process all kind of data such as structured data, categorical data, and unstructured data to generate meaningful outcome for decision-making. The soft-computing methods allow clustering of similar data, classification of data, predictions from big-data analysis, and decision-making on the basis of analysis of data. A novel method is proposed in the paper using soft-computing methods where clustering mechanisms and classification mechanisms are used to process the biomedicine data for productive outcomes. Fuzzy logic and C-means clustering are devised as a collaborative approach to analyze the biomedicine data by reducing the time and space complexity of the clustering solutions. This research work is considering categorical data, numeric data, and structured data for the interpretation of data to make further decisions. Timely decisions are very important especially in the field of biomedicine because human health and human lives are involved in this field and delays in decision-making may cause threats to human lives. The COVID-19 situation was a recent example where timely diagnosis and interpretations played significant roles in saving the lives of people. Therefore, this research work has attempted to use soft computing techniques for the successful clustering of similar medical data and for quicker interpretation of data to support the decision-making processes related to medical fields.

Computational Analysis of Influencing Factors and Multiple Scoring Systems of Stone Clearance Rate after Flexible Ureteroscopic Lithotripsy

Our research aims at the analysis of various stone scoring systems which are referred to as STONE scoring system (SSS) in this study. GUY's scoring system and RUSS scoring system (RSS) are utilized to predict stone-free status (SFS) after surgery and problems after percutaneous nephrolithotomy (PCNL) for harder stones. The data of 68 patients with renal calculi who received FURL in Ren Ji Hospital from Jan 2020 to Mar 2021 are collected as the study subjects. There were 44 male and 24 female patients, with an average age of 55.6 ± 11.4 years. Reliability analysis of related influencing factors (IF) of stone clearance rate (SCR) and multiple scoring systems after flexible ureteroscopic lithotripsy (FURL) was performed. Relevant factors with statistical significance for postoperative SCR were selected for logistic regression analysis (RA). According to the SSS score, GSS classification, and RUSS score, the SCR after FURL was statistically analyzed. The results showed that the P values corresponding to stone position (lower caliceal), cumulative stone diameter (CSD), urinary tract infection, and external physical vibration lithecbole (EPVL) were less than 0.05. The area under the ROC curve of RUSS score, SSS score, and GSS grading was 0.932, 0.841, and 0.533, respectively. The main IF of SCR after FURL were stone location (lower caliceal), CSD, urinary tract infection, and EPVL. The RUSS score system was the best in the evaluation of SCR after FURL. In the previous research, the score systems such as CROES (CRS), SSS, S-ReS, C, and GSS for the prediction of SFS were compared. In our analysis, we have compared the RUSS scoring system which has proven to be giving better results as compared to SSS and GSS. We also performed the regression analysis and found that the stone location shows the strongest correlation of all the other factors for stone clearing rate.

A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke

Background: The ability to accurately detect ischemic stroke and predict its neurological recovery is of great clinical value. This study intended to evaluate the performance of whole-brain dynamic radiomics features (DRF) for ischemic stroke detection, neurological impairment assessment, and outcome prediction. Methods: The supervised feature selection (Lasso) and unsupervised feature-selection methods (five-feature dimension-reduction algorithms) were used to generate four experimental groups with DRF in different combinations. Ten machine learning models were used to evaluate their performance by ten-fold cross-validation. Results: In experimental group_A, the best AUCs (0.873 for stroke detection, 0.795 for NIHSS assessment, and 0.818 for outcome prediction) were obtained by outstanding DRF selected by Lasso, and the performance of significant DRF was better than the five-feature dimension-reduction algorithms. The selected outstanding dimension-reduction DRF in experimental group_C obtained a better AUC than dimension-reduction DRF in experimental group_A but were inferior to the outstanding DRF in experimental group_A. When combining the outstanding DRF with each dimension-reduction DRF (experimental group_B), the performance can be improved in ischemic stroke detection (best AUC = 0.899) and NIHSS assessment (best AUC = 0.835) but failed in outcome prediction (best AUC = 0.806). The performance can be further improved when combining outstanding DRF with outstanding dimension-reduction DRF (experimental group_D), achieving the highest AUC scores in all three evaluation items (0.925 for stroke detection, 0.853 for NIHSS assessment, and 0.828 for outcome prediction). By the method in this study, comparing the best AUC of Ft-test in experimental group_A and the best_AUC in experimental group_D, the AUC in stroke detection increased by 19.4% (from 0.731 to 0.925), the AUC in NIHSS assessment increased by 20.1% (from 0.652 to 0.853), and the AUC in prognosis prediction increased by 14.9% (from 0.679 to 0.828). This study provided a potential clinical tool for detailed clinical diagnosis and outcome prediction before treatment.

A Comprehensive Study on Epidemiology Case Studies Using Computational Analysis

Health-related issues and occurrences with regard to a particular population are the subject of an epidemiology study. This paper presents the results of a retrospective epidemiological investigation on 15922 hospitalized hand trauma patients from Central China between 2011 and 2020. Gender, age, onset season, injury mechanism, injury environment, injury location, and clinical characteristics are among the characteristics of the data gathered. The study is using computational analysis to draw inferences from the case studies collected in the databases of the hospitals. The types and characteristics of occupational injuries at home and outdoor are compared and analyzed. The purpose of the study is to present the findings from recent case studies for future reference and to recommend useful roles for the industrial sector in the care of patients with hand trauma in order to lower occupational harm. The injuries of preschool children are also analyzed. The incidence rate of hand injuries in infants has been increasing year by year which is directly related to the inefficient growth of children in rural areas. The data are collected from hospitals, then the data analytical tools are applied to draw conclusions. The suggested model is intelligently learned through the application of computational techniques, which are also used to suggest treatments to trauma victims. According to this study, males are more likely than females to sustain hand trauma; occupational injuries are more common than living injuries; males between the ages of 20 and 50 are at an increased risk of suffering an occupational injury. This study showed that the proportion of hand trauma in preschool children was higher (12.27%), and the 2-3-year-old group was the main injury target of preschool children (45.70%). The accidental injuries of newborns and young children can be reduced by government assistance, social support, and tighter monitoring.

The Relationship between Physical Activity and Academic Achievement in Multimodal Environment Using Computational Analysis

Health has always been recognized as the imperative parameter to excel in any field whether professional or personal. People with sound health having regular habit of physical activities show more potential in their professional and personal lives than the people who do not participate in the physical activities. Many state-of-the-art studies exist in the literature where researchers have proved the significance of physical activities as supportive treatment for the existing ailments and in improving the overall health of human beings. Our research aims at accessing the correlation between physical activities carried out by the students and its impact on the success rate of academic achievements. The study is using computational techniques to investigate the relevance of physical activities on the academic achievements of middle school children. The study employs data mining techniques for processing the data. The computational methods are used in a multimodal environment where the surrounding parameters of the environment are considered before performing computational techniques on the subjects (participants in terms of sample for the study). In this cross-sectional study, we have considered the data on various physical activities such as aerobic fitness, running, playing, and participation in extracurricular activities. After collection of data in a real multimodal environment from middle school students, the data preprocessing is performed to handle the missing values. Then, the computational techniques are applied in a step-by-step approach using regression and the bootstrap methods to examine the data and predict the outcome. The correlation is assessed between academic achievements and physical activities. The outcome predicts that physical activities promote the success rate of academic achievements including extra-curricular activities.

Influence of Autologous Bone Marrow Stem Cell Therapy on the Levels of Inflammatory Factors and Conexin43 of Patients with Moyamoya Disease

Moyamoya disease is a medical condition that shows the typical characteristics like continuous and chronic thickening of the walls and the contraction of the internal carotid artery; as a result, the internal diameter of the artery gets narrowed. There are six phases of the disease ranging from I to VI (moyamoya vessels completely disappear, followed by the complete blockage of the arteries). Surgery is a commonly recommended treatment for the moyamoya disease. Our research study identifies the effect of autologous bone marrow stem cell therapy (ABMSCT) on the levels of inflammatory factors and Conexin43 (Cx43) protein in patients suffering from moyamoya. In our study, we have selected 52 moyamoya patients admitted to our hospital from 30 July 2019 to 10 February 2020. The control group (CG) was treated with superficial temporal artery to a middle cerebral artery (STA-MCA) bypass + encephalo-duro-myosinangiosis (EDMS). The experimental group (Exp. Grp) was treated with ABMSC. The cerebral vascular tissue of the patients was treated with hematoxylin-eosin (HE) staining. Immunohistochemical staining was used to identify the levels of Cx43 protein. The concentrations of vascular endothelial growth factor (VEGF), inflammatory factor interleukin-6 (IL6), interleukin-1β (IL1β), tumor necrosis factor (TNFα), and anti-inflammatory factor interleukin-1β (IL1β) were determined by enzyme-linked immunosorbent assay (ELISA). We have found that after treatment of the expression of Cx43 protein, the proportions of grade IV (7.7%), grade III (311.5%), and grade II (3.8%) patients in the Exp. Grp were lower than those in the CG. The proportion of grade I patients in the Exp. Grp (77%) was higher than that in the CG (38.5%). After treatment, the inflammatory factors IL6 (0.97 ± 0.82 pg/mL), IL1β (8.33 ± 1.21 pg/mL), and TNFα (1.73 ± 0.71 pg/mL) in the Exp. Grp were lower than those in the CG. The anti-inflammatory factor IL1β (15.09 ± 4.72 pg/mL) increased in the Exp. Grp compared with the CG (11.25 ± 3.48 pg/mL) post treatment. Intracranial infection, hydrocephalus, hemiplegia, and transient neurological dysfunction in the Exp. Grp were lower than those in the CG, with statistical differences (P < 0.05). Our study suggests that the treatment of autologous bone marrow stem cells (ABMSC) was beneficial to balance the inflammatory response of disorders, reduce the damage of vascular tissue in the brain, and regulate tissue repair by co-acting with various inflammatory factors as compared to traditional surgery. We conclude that the involvement of Cx43 in the occurrence and development of moyamoya. We also have found that the risk factors of intracranial infection after ABMSCT were less as compared to those after conventional surgery.

Diagnostic Significance of 3D Automated Breast Volume Scanner in a Combination with Contrast-Enhanced Ultrasound for Breast Cancer

The incidence of cancer is increasing today, particularly lung and chest cancer. Employing novel methods to detect cancer in its earliest stages and discover painless, noninvasive treatments are urgently needed. The goal of the proposed study is to investigate the value of automated breast volume scanning (ABUS) in conjunction with contrast-enhanced ultrasonography (CEUS) in properly diagnosing breast cancer in its early stages and the effectiveness of neoadjuvant chemotherapy (NAC) in treating the disease. For the research study, information on 98 patients who had NAC and surgery in the breast surgery department of the Shaanxi Provincial Cancer Hospital has been gathered. All patients have received four cycles of NAC and underwent conventional ultrasound (HUSS), CEUS, ABUS, and pathological examination. At the same time, receiver operating characteristic (ROC) curve analysis, single factor, multiple linear regression, and other methods have also been used to analyze the diagnostic efficacy of breast cancer and NAC efficacy evaluation results. The study of this paper is totally based on the data collected from Shaanxi Provincial Cancer Hospital. The statistical and computational analyses are performed on the data collected for drawing inferences. When the findings are compared to the results of the pathological examination, HUSS has demonstrated a significant distinction between benign and malignant diagnoses with a statistical value of P < 0.05.ABUS combined with CEUS has shown no considerable differences in correlation study. Except for negative likelihood ratio, the diagnostic performance indexes of CEUS+ ABUS are substantially higher than HHUS with P < 0.05. ROC curve analysis is also performed which shows that CEUS and ABUS combination has higher precision in the analysis of breast cancer. ABUS pooled with CEUS shows great application value in the judgment of breast cancer as per the results obtained from the statistical analysis on data of 98 patients.

Image Super-Resolution Reconstruction Method for Lung Cancer CT-Scanned Images Based on Neural Network

The super-resolution (SR) reconstruction of a single image is an important image synthesis task especially for medical applications. This paper is studying the application of image segmentation for lung cancer images. This research work is utilizing the power of deep learning for resolution reconstruction for lung cancer-based images. At present, the neural networks utilized for image segmentation and classification are suffering from the loss of information where information passes through one layer to another deep layer. The commonly used loss functions include content-based reconstruction loss and generative confrontation network. The sparse coding single-image super-resolution reconstruction algorithm can easily lead to the phenomenon of incorrect geometric structure in the reconstructed image. In order to solve the problem of excessive smoothness and blurring of the reconstructed image edges caused by the introduction of this self-similarity constraint, a two-layer reconstruction framework based on a smooth layer and a texture layer is proposed for a medical application of lung cancer. This method uses a global nonzero gradient number constrained reconstruction model to reconstruct the smooth layer. The proposed sparse coding method is used to reconstruct high-resolution texture images. Finally, a global and local optimization models are used to further improve the quality of the reconstructed image. An adaptive multiscale remote sensing image super-division reconstruction network is designed. The selective core network and adaptive gating unit are integrated to extract and fuse features to obtain a preliminary reconstruction. Through the proposed dual-drive module, the feature prior drive loss and task drive loss are transmitted to the super-resolution network. The proposed work not only improves the subjective visual effect but the robustness has also been enhanced with more accurate construction of edges. The statistical evaluators are used to test the viability of the proposed scheme.

Recognition Method of Corn and Rice Crop Growth State Based on Computer Image Processing Technology

The agriculture field is one of the most important fields where computational techniques play an imperative role for decision-making whether it is the automation of watering of plants, controlling of humidity levels, and detection of plant diseases and growth of plants. There are problems in the conventional methods where newer computational techniques and image processing methods are not used to keep track of growth of plants. The traditional image capturing and processing models have problems of large image segmentation error, excessive feature extraction time, and poor recognition output. In order to overcome the problems in the traditional plant growth methods based on image processing automations, computer image processing with computational method has been proposed to analyze the plant growth by utilizing state recognition method for corn and rice crops. An image acquisition platform is established on the basis of CMOS image sensor for crop image acquisition. The binary processing is performed, and then the images are segmented to reduce error of segmentation results in the traditional methods. To extract image features of corn and rice crops, convolution neural network (CNN) with newer architecture is used. According to contour information of images, the block wavelet transform method is used for feature adaptive matching. The binary tree structure is used to divide the growth period of corn and rice crops. The fuzzy mathematical model is also devised to identify the characteristics of crops in different growth periods and to complete the identification of growth state. Experimental results show that the proposed method effectively improves problems of traditional methods with better image recognition effect and reduces the time of feature recognition. The time to extract features by the proposed method is 1.4 seconds, whereas comparative methods such as random forest (RF) take 3.8 s and other traditional techniques take 4.9 s. Segmentation result error of the recognition method is also reduced significantly.