External ventricular drainage (EVD) combined with intraventricular fibrinolysis (IVF) is rarely used in severe spontaneous cerebellar hemorrhage (SCH) with intraventricular hemorrhage (IVH). Recently, the treatment strategy was repeatedly performed in our hospital to elderly patients with severe SCH + IVH. To analyze its clinical value, we compared it to two treatment strategies which now commonly are used for these patients: conservative management (CM) and clot evacuation (CE). In this study, a total of 118 cases were observed, of which 28 cases received CM, 43 cases received EVD + IVF and 47 cases received CE. The Glasgow Coma Scale score, frequency of complication, mortality in one month, modified Rankin Scale (mRS) at six months, and causes of death were analyzed. The outcomes of patients in the CM group were extremely poor compared to patients undergoing surgery (P = 0.034) and the mortality was up to 61.3 % (18/28), which was much higher than those of the two surgical groups (P = 0.026). No significant difference was found in mortality and mRS between the two surgical groups (P > 0.05). Patients in the CE group mostly died of deterioration of comorbidities and postoperative complications, whereas more deaths occurred in the CM group and the EVD + IVF group due to rebleeding, brainstem compression, perilesional edema and tight posterior fossa (χ (2), P = 0.006). It is suggested that EVD + IVF is a treatment option for elderly patients with severe SCH + IVH.
Aiming at the problem that the existing Point of Interest (POI) recommendation model in social network big data is difficult to extract deep feature information, a POI recommendation model based on deep learning in social networks and big data is proposed in this article. The input data are all gathered through intelligent sensors to apply some raw data pre-processing tasks and thus reduce the computational burden on the model. First, a POI static feature extraction method based on symmetric matrix decomposition is designed to capture the geographical location and POI category features in Location-Based Social Networking (LBSN). Second, the improved Continuous Bags-of-Words (CBOW) model is used to extract the semantic features in the user comment information, and realize the implicit vector representation of POI in geographic, category, semantic and temporal feature space. Finally, by adaptively selecting relevant check-in activities from the check-in history to learn and change user preferences, the Geographical-Spatiotemporal Gated Recurrent Unit Network (GSGRUN) can distinguish the user preferences of different check-in. Experiments show that when the length of the recommendation list is 15, the precision of the proposed algorithm on the loc-Gowalla data set is 0.0686, the recall is 0.0769, and the precision on the loc-Brightkite data set is 0.0659, the recall is 0.0835, both of which are better than the comparative recommendation methods. Therefore, compared with the comparison methods, the proposed method can significantly improve the performance of the POI recommendation system.
In the process of multiperson pose estimation, there are problems such as slow detection speed, low detection accuracy of key point targets, and inaccurate positioning of the boundaries of people with serious occlusion. A multiperson pose estimation method using depthwise separable convolutions and feature pyramid network is proposed. Firstly, the YOLOv3 target detection algorithm model based on the depthwise separable convolution is used to improve the running speed of the human body detector. Then, based on the improved feature pyramid network, a multiscale supervision module and a multiscale regression module are added to assist training and to solve the difficult key point detection problem of the human body. Finally, the improved soft-argmax method is used to further eliminate redundant attitudes and improve the accuracy of attitude boundary positioning. Experimental results show that the proposed model has a score of 73.4% in AP on the 2017 COCO test-dev dataset, and it scored 86.24% on PCKh@0.5 on the MPII dataset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.