People who keep lifelogs about themselves are known as lifeloggers (or sometimes lifebloggers or lifegloggers). In recent years, some lifelog data has been automatically captured by wearable technology or mobile devices. The data could be used to increase knowledge about how people live their lives. The record contains a comprehensive dataset of a human's activities. From left to right: Mann (1998) Microsoft (2004) Mann, Fung, Lo (2006) Memoto (2013)Ī lifelog is a personal record of one's daily life in a varying amount of detail, for a variety of purposes. TheĮxperimental analysis proves the suitability of the proposed approach asĬompared to the conventional classifiers and our newly constructed modelĪchieved highest accuracy and reduced training complexity among all among all.Evolution of the lifelogging lanyard camera. The experiment to compute the accuracy, recall, precision, and f1-score. For this purpose, two-time series datasets are used in Models to get best results, and (v) performance evaluation using Spark Some domain knowledge or selection algorithm, (iv) hyper parameter tuning for (ii) making the data labelled using clustering and partitioning the data intoĬlasses, (iii) identifying the suitable subset of features by applying either Using a series of steps such as (i) removing redundant or invalid instances, The proposed approach improves the performance of existing methods Then training a learning algorithm with suitable hyper parameters for better The vital part of building a good modelĭepends on pre-processing of the dataset, identifying important features, and Therefore,ĭesigning new classifiers for the classification of chronic diseases using Since lifelog data analysis is crucial due to its sensitive nature thus theĬonventional classification models show limited performance. Unsupervised logistic regression model (OFS-ULR) to classify chronic diseases. This paper is to construct an optimal feature selection-based Now harnessing the potential of lifelog data to explore better healthcare Chronic disease classification models are According to WHO, this accounts for 73% of all deaths andĦ0% of the global burden of diseases. Chronicĭiseases are one of the most serious health challenges in developing andĭeveloped countries. Download a PDF of the paper titled Empirical Analysis of Lifelog Data using Optimal Feature Selection based Unsupervised Logistic Regression (OFS-ULR) Model with Spark Streaming, by Sadhana Tiwari and 1 other authors Download PDF Abstract: Recent advancement in the field of pervasive healthcare monitoring systemsĬauses the generation of a huge amount of lifelog data in real-time.
0 kommentar(er)
