Biomedical images contain a huge number of sensor measurements that can provide disease characteristics. Computer-assisted analysis of such parameters aids in the early detection of disease, and as a result aids medical professionals in quickly selecting appropriate medications. Human Activity Recognition, abbreviated as ‘HAR’, is the prediction of common human measurements, which consist of movements such as walking, running, drinking, cooking, etc. It is extremely advantageous for services in the sphere of medical care, such as fitness trackers, senior care, and archiving patient information for future use. The two types of data that can be fed to the HAR system as input are, first, video sequences or images of human activities, and second, time-series data of physical movements during different activities recorded through sensors such as accelerometers, gyroscopes, etc., that are present in smart gadgets. In this paper, we have decided to work with time-series kind of data as the input. Here, we propose an ensemble of four deep learning-based classification models, namely, ‘CNN-net’, ‘CNNLSTM-net’, ‘ConvLSTM-net’, and ‘StackedLSTM-net’, which is termed as ‘Ensem-HAR’. Each of the classification models used in the ensemble is based on a typical 1D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network; however, they differ in terms of their architectural variations. Prediction through the proposed Ensem-HAR is carried out by stacking predictions from each of the four mentioned classification models, then training a Blender or Meta-learner on the stacked prediction, which provides the final prediction on test data. Our proposed model was evaluated over three benchmark datasets, WISDM, PAMAP2, and UCI-HAR; the proposed Ensem-HAR model for biomedical measurement achieved 98.70%, 97.45%, and 95.05% accuracy, respectively, on the mentioned datasets. The results from the experiments reveal that the suggested model performs better than the other multiple generated measurements to which it was compared.

United Arab Emirates is seeking to become self-sufficient in gas supply by 2030. This has led the country to initiate several exploratory and appraisal projects to achieve this goal. This study covers one such pilot project targeting production from tight gas reservoirs in three wells through coiled tubing (CT) underbalanced drilling (UBD). CT pressure control equipment was rigged up on top of production trees with wells already completed and cemented. A CT tower was used to accommodate the drilling bottomhole assembly (BHA) and eliminate risks related to its deployment. CT strings were designed to reach target intervals with sufficient weight on bit (WOB), suitable for sour environment, and able to withstand high pumping rates with mild circulating pressures. To address the hazards of H2S handling at surface, a custom-fit closed-loop system was deployed. The recovered water was treated on surface and reused for drilling to decrease the water consumption throughout the operations. The plan was to drill three 3/4-in. horizontal laterals in all candidate wells. Each well was completed with a combination of a 4 1/2-in. and a 5 1/2-in. tubing and a 7-in. liner. Five laterals were drilled across the three candidate wells targeting carbonate reservoirs with each lateral having an average length of ~4,000 ft. The achieved rates of penetration varied significantly from 15 ft/min to 30 ft/min while drilling through the various formations. Over the course of the pilot project, several challenges had to be addressed, such as material accretion on the CT string during wiper trips, treatment of return fluids having high H2S content and rock cuttings and ensuring integrity of the CT pipe while operating in severe downhole environments. Solutions and lessons learnt from each well were implemented subsequently in the campaign, such as the use of increased concentrations of H2S inhibitor to coat the CT string, use of nitrified fluids based on changing well parameters to maintain underbalance, thorough pipe management through real-time CT inspection, and adding a fixed quantity of fresh water to the drilling system every day to avoid chemical reactions between the drilling fluid additives and hydrocarbons. The wells completed with this method exceeded production expectations by 35 to 50% across the project, while reconfirming the value of the technology. The use of CT for UBD is still considered a challenging intervention worldwide. Such cases in high H2S environments are rare. This study outlines best practices for a CT UBD and a setup that can be replicated in other locations to implement this methodology with high H2S and when rig sourcing is a concern.