Prediction of patient's neurological recovery from cervical spinal cord injury through XGBoost learning approach.

Due to the diversity of patient characteristics, therapeutic approaches, and radiological findings, it can be challenging to predict outcomes based on neurological consequences accurately within cervical spinal cord injury (SCI) entities and based on machine learning (ML) technique. Accurate neurological outcomes prediction in the patients suffering with cervical spinal cord injury is challenging due to heterogeneity existing in patient characteristics and treatment strategies. Machine learning algorithms are proven technology for achieving greater prediction outcomes. Thus, the research employed machine learning model through extreme gradient boosting (XGBoost) for attaining superior accuracy and reliability followed with other MI algorithms for predicting the neurological outcomes. Besides, it generated a model of a data-driven approach with extreme gradient boosting to enhance fault detection techniques (XGBoost) efficiency rate. To forecast improvements within functionalities of neurological systems, the status has been monitored through motor position (ASIA [American Spinal Injury Association] Impairment Scale [AIS] D and E) followed by the method of prediction employing XGBoost, combined with decision tree for regression logistics. Thus, with the proposed XGBoost approach, the enhanced accuracy in reaching the outcome is 81.1%, and from other models such as decision tree (80%) and logistic regression (82%), in predicting outcomes of neurological improvements within cervical SCI patients. Considering the AUC, the XGBoost and decision tree valued with 0.867 and 0.787, whereas logistic regression showed 0.877. Therefore, the application of XGBoost for accurate prediction and decision-making in the categorization of pre-treatment in patients with cervical SCI has reached better development with this study.

An Optimized Deep Learning Approach for the Prediction of Social Distance Among Individuals in Public Places During Pandemic.

Social distancing is considered as the most effective prevention techniques for combatting pandemic like Covid-19. It is observed in several places where these norms and conditions have been violated by most of the public though the same has been notified by the local government. Hence, till date, there has been no proper structure for monitoring the loyalty of the social-distancing norms by individuals. This research has proposed an optimized deep learning-based model for predicting social distancing at public places. The proposed research has implemented a customized model using detectron2 and intersection over union (IOU) on the input video objects and predicted the proper social-distancing norms continued by individuals. The extensive trials were conducted with popular state-of-the-art object detection model: regions with convolutional neural networks (RCNN) with detectron2 and fast RCNN, RCNN with TWILIO communication platform, YOLOv3 with TL, fast RCNN with YOLO v4, and fast RCNN with YOLO v2. Among all, the proposed (RCNN with detectron2 and fast RCNN) delivers the efficient performance with precision, mean average precision (mAP), total loss (TL) and training time (TT). The outcomes of the proposed model focused on faster R-CNN for social-distancing norms and detectron2 for identifying the human 'person class' towards estimating and evaluating the violation-threat criteria where the threshold (i.e., 0.75) is calculated. The model attained precision at 98% approximately (97.9%) with 87% recall score where intersection over union (IOU) was at 0.5.