RESUMO
As a result of its important role in video surveillance, pedestrian attribute recognition has become an attractive facet of computer vision research. Because of the changes in viewpoints, illumination, resolution and occlusion, the task is very challenging. In order to resolve the issue of unsatisfactory performance of existing pedestrian attribute recognition methods resulting from ignoring the correlation between pedestrian attributes and spatial information, in this paper, the task is regarded as a spatiotemporal, sequential, multi-label image classification problem. An attention-based neural network consisting of convolutional neural networks (CNN), channel attention (CAtt) and convolutional long short-term memory (ConvLSTM) is proposed (CNN-CAtt-ConvLSTM). Firstly, the salient and correlated visual features of pedestrian attributes are extracted by pre-trained CNN and CAtt. Then, ConvLSTM is used to further extract spatial information and correlations from pedestrian attributes. Finally, pedestrian attributes are predicted with optimized sequences based on attribute image area size and importance. Extensive experiments are carried out on two common pedestrian attribute datasets, PEdesTrian Attribute (PETA) dataset and Richly Annotated Pedestrian (RAP) dataset, and higher performance than other state-of-the-art (SOTA) methods is achieved, which proves the superiority and validity of our method.
Assuntos
Atenção/fisiologia , Reconhecimento Automatizado de Padrão/métodos , Pedestres , Reconhecimento Psicológico/fisiologia , Algoritmos , Identificação Biométrica , Humanos , Processamento de Imagem Assistida por Computador , Memória de Longo Prazo/fisiologia , Redes Neurais de Computação , Gravação em VídeoRESUMO
This study aims to develop an automatic assessment of after-stroke dyskinesias degree by combining machine learning and near-infrared spectroscopy (NIRS). Thirty-five subjects were divided into five stages (healthy, patient: Brunnstrom stages 3, 4, 5, 6). NIRS was used to record the muscular hemodynamic responses from bilateral femoris (biceps brachii) muscles during passive and active upper (lower) limbs circular exercise. We used the D-S evidence theory to conduct feature information fusion and established a Gradient Boosting DD-MLP Net model, combining the dendrite network and multilayer perceptron, to realize automatic dyskinesias degree evaluation. Our model classified the upper limb dyskinesias with high accuracy: 98.91% under the passive mode and 98.69% under the active mode, and classified the lower limb dyskinesias with high accuracy: 99.45% and 99.63% under the passive and active modes, respectively. Our model combined with NIRS has great potential in monitoring the after-stroke dyskinesias degree and guiding rehabilitation training.
Assuntos
Discinesias , Acidente Vascular Cerebral , Humanos , Espectroscopia de Luz Próxima ao Infravermelho/métodos , Acidente Vascular Cerebral/complicações , Acidente Vascular Cerebral/diagnóstico por imagem , Músculo Esquelético , Aprendizado de Máquina , Discinesias/etiologiaRESUMO
Introduction: This study was conducted to evaluate whether a non-immersive virtual reality (VR)-based intervention can enhance lower extremity movement in patients with cerebral infarction and whether it has greater short-term and long-term effectiveness than conventional therapies (CTs). Materials and methods: This was a single-blinded, randomized clinical controlled trial. Forty-four patients with subacute cerebral infarction were randomly allocated to the VR or CT group. All intervention sessions were delivered in the inpatient unit for 3 weeks. Outcomes were measured before (baseline) and after the interventions and at 3-month, 6-month and 1-year follow-ups. The outcomes included clinical assessments of movement and balance function using the Fugl-Meyer Assessment of Lower Extremity (FMA-LE) and Berg Balance Scale (BBS), and gait parameters in the sagittal plane. Results: In the VR group, the walking speed after intervention, at 3-month, 6-month, and 1-year follow-ups were significantly greater than baseline (p = 0.01, <0.001, 0.007, and <0.001, respectively). Compared with baseline, BBS scores after intervention, at 3-month, 6-month, and 1-year follow-ups were significantly greater in both the VR group (p = 0.006, 0.002, <0.001, and <0.001, respectively) and CT group (p = <0.001, 0.002, 0.001, and <0.001, respectively), while FMA-LE scores after intervention, at 3-month, 6-month, and 1-year follow-ups were significant increased in the VR group (p = 0.03, <0.001, 0.003, and <0.001, respectively), and at 3-month, 6-month, and 1-year follow-ups in the CT group (p = 0.02, 0.004 and <0.001, respectively). In the VR group, the maximum knee joint angle in the sagittal plane enhanced significantly at 6-month follow-up from that at baseline (p = 0.04). Conclusion: The effectiveness of the non-immersive VR-based intervention in our study was observed after the intervention and at the follow-ups, but it was not significantly different from that of CTs. In sum, our results suggest that non-immersive VR-based interventions may thus be a valuable addition to conventional physical therapies to enhance treatment efficacy. Clinical trial registration: http://www.chictr.org.cn/showproj.aspx?proj=10541, ChiCTR-IOC-15006064.
RESUMO
Objectives: Poststroke shoulder pain (PSSP) is a common complication after stroke. This review aimed to provide updated information on the epidemiological characteristics of PSSP, reveal their trends over time and region. Study Design and Setting: We searched the PubMed, Embase, Cochrane Library and Web of Science databases from inception until Dec 31, 2020. Data were extracted from the eligible studies, and their quality was assessed. The pooled incidence and prevalence estimates of PSSP and their 95% confidence intervals (CIs) were calculated. We analyzed the incidence and prevalence of PSSP by different geographical regions and countries and separately calculated the annual incidence and prevalence (and 95% CIs) of PSSP. Results: A total of 21 studies were eligible for the meta-analysis. Eleven cohort studies were included to analyze the incidence of PSSP, and the estimated pooled incidence in 3,496 stroke patients was 0.29 (95% CI 0.21-0.36). Ten cross-sectional studies were included to analyze the prevalence of PSSP, and the pooled prevalence in 3,701 stroke patients was 0.33 (95% CI 0.22-0.43). In addition, we found that there were significant differences in the incidence and prevalence of PSSP between different geographical regions and different countries. Additionally, the incidence of PSSP fluctuated around 30%, and the prevalence had a downward trend over time. Conclusions: Current evidence suggests that the incidence and prevalence of PSSP are high and may be influenced by geographical region and time.
RESUMO
BACKGROUND AND PURPOSE: Mild Cognitive Impairment (MCI) is thought to be the signal of many progressive diseases but is easily ignored. Therefore, a simple and easy screening method for recognizing and predicting MCI is urgently needed. The study aimed to establish machine learning models of retinal vascular features to categorize and predict MCI. PATIENTS AND METHODS: Subjects enrolled underwent cognitive function assessment and were divided into a normal group, an MCI group, and a dementia group, and fundus photography was performed. MATLAB 2019b was used for fundus image preprocessing and vascular segmentation. Via the Green channel, adaptive histogram equalization (AHE), image binarization, and median filtering, we obtained the original and segmentation retinal vessel images. Afterwards, the histogram of oriented gradient (HOG) was used for image feature extraction. Support vector machine (SVM) and extreme learning machine (ELM) were selected for training models in the fundus original images and fundus vascular segmentation images, respectively. Among the three cognitive groups, sensitivity, specificity, the receiver operating characteristic (ROC) curves, and the area under the curve (AUC) were used to evaluate and compare the predictive performance of the two models in the fundus original and vascular segmentation images, respectively. RESULTS: A total of 86 eligible subjects were enrolled in the study. After a clinical cognitive assessment, the participants were divided into the normal group (N = 38), the MCI group (N = 26), and the dementia group (N = 22). A total of 332 qualified fundus images were adopted after screening. Comparing the models among the three groups showed that the SVM model had more advantages than the ELM model in the fundus original images and vascular segmentation images. Meanwhile, we found that the original images performed better than the segmentation images in the same prediction model. Among the three groups, the SVM model of the fundus original images had the best performance. CONCLUSION: The establishment of a predictive model based on vascular-related feature extraction from fundus images has high recognition and prediction abilities for cognitive function and can be used as a screening method for MCI. CLINICAL TRIAL REGISTRATION: ChiCTR.org.cn (ChiCTR1900027404), Registered on Nov 12, 2019.