Search

As a form of body language, the gesture plays an important role in smart homes, game interactions, and sign language communication, etc. The gesture recognition methods have been carried out extensively. The existing methods have inherent limitations regarding user experience, visual environment, and recognition granularity. Millimeter wave radar provides an effective method for the problems lie ahead gesture recognition because of the advantage of considerable bandwidth and high precision perception. Interfering factors and the complexity of the model raise an enormous challenge to the practical application of gesture recognition methods as the millimeter wave radar is applied to complex scenes. Based on multi-feature fusion, a gesture recognition method for complex scenes is proposed in this work. We collected data in variety places to improve sample reliability, filtered clutters to improve the signal's signal-to-noise ratio (SNR), and then obtained multi features involves range-time map (RTM), Doppler-time map (DTM) and angle-time map (ATM) and fused them to enhance the richness and expression ability of the features. A lightweight neural network model multi-CNN-LSTM is designed to gestures recognition. This model consists of three convolutional neural network (CNN) for three obtained features and one long short-term memory (LSTM) for temporal features. We analyzed the performance and complexity of the model and verified the effectiveness of feature extraction. Numerous experiments have shown that this method has generalization ability, adaptability, and high robustness in complex scenarios. The recognition accuracy of 14 experimental gestures reached 97.28%. [ABSTRACT FROM AUTHOR]

Background and objectives: Helicobacter pylori (H. pylori) infection is the most common etiology of chronic gastric. H. pylori gastritis would gradually evolve into gastric atrophy, intestinal metaplasia, dysplasia and malignant lesions. Herein, this study aimed to investigate the potential impact of H. pylori colonization density and depth on the severity of histological parameters of gastritis. Methods: A prospective monocentric study was conducted from December 2019 to July 2022, enrolling patients with confirmed chronic H. pylori infection via histopathological evaluation. H. pylori colonization status was detected by immunohistochemical staining, pathological changes of gastric specimens were detected by hematoxylin eosin staining. Epidemiological, endoscopic and histopathological data were collected. Results: A total of 1120 patients with a mean age of 45.8 years were included. Regardless of the previous history of H. pylori eradication treatment, significant correlations were observed between the density and depth of H. pylori colonization and the intensity of gastritis activity (all P < 0.05). Patients with the lowest level of H. pylori colonization density and depth exhibited the highest level of mild activity. In whole participants and anti-H. pylori treatment-naive participants, H. pylori colonization density and depth were markedly correlated with the severity of chronic gastritis and gastric atrophy (all P < 0.05). H. pylori colonization density (P = 0.001) and depth (P = 0.047) were significantly associated with ulcer formation in patients naive to any anti-H. pylori treatment. No significant associations were observed between the density and depth of H. pylori colonization and other histopathological findings including lymphadenia, lymphoid follicle formation and dysplasia. Conclusions: As the density and depth of H. pylori colonization increased, so did the activity and severity of gastritis, along with an elevated risk of ulcer formation. [ABSTRACT FROM AUTHOR]

To address the limitations of wireless sensing in static gesture recognition and the issues of Computer Vision's dependence on lighting conditions, we propose a method that utilizes millimeter-wave near-field SAR (Synthetic Aperture Radar) imaging for static gesture recognition. First, a millimeter-wave near-field SAR imaging system is used to scan the defined static gestures to obtain data. Then, based on the distance plane, the three-dimensional gesture is divided into multiple two-dimensional planes, constructing an imaging dataset. Finally, an HOG (Histogram of Oriented Gradients) is used to extract features from the imaging results, PCA (Principal Component Analysis) is applied for feature dimensionality reduction, and RF (Random Forest) performs classification. Experimental verification shows that the proposed method achieves an average recognition precision of 97% in unobstructed situations and 93% in obstructed situations, providing an effective means for wireless-sensing-based static gesture recognition. [ABSTRACT FROM AUTHOR]