Vol. 2 No. 3 (2023)

In recent years, Artificial Intelligence has experienced significant growth thanks to technological advances such as high performance computing and massive data processing. This evolution has led to a new reflection as well as a serious interest on the part of managers of hospital structures, who are beginning to take an interest in the automation and optimization of surgical processes. Machine Learning finds its place as a preferred technique for developing intelligent decision support systems in the operating room. In this aisle, it has become crucial to automate and optimize preoperative procedures. Through this paper, we focus on the development of an intelligent decision support system for the surgical preoperative phase, using the Random Forest model, which is an extension of the decision tree algorithm, to analyze a variety of preoperative predictive data such as hypertension, body temperature, ECG, hemoglobin, etc. We use a dataset previously approved by an institutional review board, while validating our model in a development environment dedicated to the field of Artificial Intelligence.

Nanointendation technique for testing casting module made by NiTinol Sensors trace defects in the cast components and on the basis of PP (Paddle Paddle)YOLOv2 (You only Look once) algorithm and Convolution network results are validated which eliminates false negatives and positives of defective cast component before pouring in mold going into production run.Monitoring of  f1 score is done of 0.9939 for CNN, unlike to precision and accuracy for standardize Automate systems for non destructive testing is highly expensive and non effective in certain defect tracing.but ,using an advanced technological advent of applying this methodology of using smart material NiTinol as sensors in gripper mechanism  not only provides scope for an early stage detection of non destructive testing but also through comparative analysis gives parameter optimization results. Software of MATLAB for detection analysis is used and Roboflow is used to track cast part repair using PP YOLOv3.From inception by sensor detection defects captured is analyzed by train graph and optimized by comparative analysis of MATLAB and Roboflow results gives accurate data .The study of this of this paper is to reconnoiter  to find out the exact location of defects in cast part  using NiTinol wire used as stimulus material in tactile sensor.It tracks defects  during initial stage of cast defects of surface detection,porosity of geometrically complex parts and it can prevents further progression.This technique have decreased the expenses and enhanced productivity as  results are captured in fraction of minutes unlike test reports thus saving time and taking timely action.It tackles with the issues of addressing major  casting challenges which scales up the production rate.Defects like incongruities as gas contamination,porosity,hard spots are traced easily and graphical comparative analysis can be done using augmenting technology.The sensors using NiTinol wire in mechanical gripper captures substantial defects in casting for assessing melt pool with increased thermal deformation.Defect testing using Paddle Paddle framework of  YOLOv3 is used.Deep learning technology data gave accurate results in detecting surface  defects which was further compared  using available defect free data to preternatural defects.The research data using CNN network results  were compared with classical AlexNet which reached efficiency result of 93.12%,wherein  FLOPs quantity reduced by 98.73% and accuracy was 0.02 % higher than AlexNet.Applying improvised R-CNN using Spatial Pyramid Pooling reduced average running time unlike other models and result accuracy was 98.76%.Comparative analysis of conventional method of detecting cast defect & CNN network analysis was done to validate using LiDAR augmented technique

The approach from the teacher's side to improve the classroom is to establish a learning discipline and an improvement method. However, there are various ways to do this, and it is an important part of teachers' work. In this paper, we propose a system for estimating the level of interest from class videos as a means of knowing the learning status of individual students. Using OpenPose, the system detects a person in a class video and extracts feature data of his/her joints. And we measure the concentration level based on the information of posture, facial orientation, and other movements. In addition, assuming that a person's face is facing the direction of the target when he/she is concentrating, we measure the concentration level based on the information of posture, facial direction, and other movements.