3 research outputs found
Self burial of offshore pipelines in fine grained cohesive sediment
No full textVita.Pipelines laid in soft cohesive sediments may attain burial because of their own weight. Shear strength of the sediment, pipe diameter, specific gravity of the pipe and the submerged unit weight of the sediment are the main parameters influencing the process of self burial of pipelines. Based on experimental studies, a theoretical procedure has been developed to predict initial sinkage of pipes. The contribution of consolidation settlement on total sinkage attained by a pipe has been studied through conventional procedure. The stress distribution in a soil mass underneath a pipe was ascertained by finite element analysis. Buoyancy tests were performed to determine the net weight of a pipe causing consolidation. Possible sinkage due to secondary consolidation of the sediment has been disregarded in this study. Experimental evidence of pipe sinkage in a test tank suggests the validity of the theoretical procedure developed- Parameter studies were conducted to show the influence of various parameters on the sinking process. Non-dimensional data analysis was performed to develop a family of curves which can be used to determine the minimum specific gravity of a pipe needed for self burial if the undrained shear strength of sediment and the diameter of the pipe are known. A discussion of the experimental results along with comparative studies of the procedures suggested by different investigators to determine initial pipe sinkage have been presented to bolster the applicability of the developed procedure. Recommendations have also been made for further relevant work
Social Media User’s Safety Level Detection through Classification via Clustering Approach
No full textEvaluation of machine learning techniques for hypertension risk prediction based on medical data in Bangladesh
No full textHypertension in Bangladesh is a leading cause of cardiovascular diseases, stroke, and kidney failure, resulting in significant morbidity and mortality. Preventive measures and simple health practices can effectively reduce hypertension and its complications. This study utilizes machine learning algorithms (Naive Bayes, support vector machine, logistic regression, random forest) to predict hypertension in high-risk individuals. The proposed hybrid model achieves a prediction accuracy of 78.17%, surpassing other machine learning methods. Random forest has the highest accuracy among the individual algorithms at 73.86%. Classification performance is evaluated using sensitivity, specificity, precision, and F-score, along with receiver operating characteristic analyses and confusion matrices through 10-fold cross-validation. These findings emphasize the importance of managing risk factors for better population health and highlight the efficacy of the hybrid model in hypertension prediction. The study underscores the significance of preventive measures in reducing the burden of hypertension-related diseases and improving overall well-being
