Towards a Clustering Guided Hierarchical Framework for Sensor-Based Activity Recognition.

Human activity recognition plays a prominent role in numerous applications like smart homes, elderly healthcare and ambient intelligence. The complexity of human behavior leads to the difficulty of developing an accurate activity recognizer, especially in situations where different activities have similar sensor readings. Accordingly, how to measure the relationships among activities and construct an activity recognizer for better distinguishing the confusing activities remains critical. To this end, we in this study propose a clustering guided hierarchical framework to discriminate on-going human activities. Specifically, we first introduce a clustering-based activity confusion index and exploit it to automatically and quantitatively measure the confusion between activities in a data-driven way instead of relying on the prior domain knowledge. Afterwards, we design a hierarchical activity recognition framework under the guidance of the confusion relationships to reduce the recognition errors between similar activities. Finally, the simulations on the benchmark datasets are evaluated and results show the superiority of the proposed model over its competitors. In addition, we experimentally evaluate the key components of the framework comprehensively, which indicates its flexibility and stability.

Intelligent postoperative morbidity prediction of heart disease using artificial intelligence techniques.

Endovascular aneurysm repair (EVAR) is an advanced minimally invasive surgical technology that is helpful for reducing patients' recovery time, postoperative morbidity and mortality. This study proposes an ensemble model to predict postoperative morbidity after EVAR. The ensemble model was developed using a training set of consecutive patients who underwent EVAR between 2000 and 2009. All data required for prediction modeling, including patient demographics, preoperative, co-morbidities, and complication as outcome variables, was collected prospectively and entered into a clinical database. A discretization approach was used to categorize numerical values into informative feature space. Then, the Bayesian network (BN), artificial neural network (ANN), and support vector machine (SVM) were adopted as base models, and stacking combined multiple models. The research outcomes consisted of an ensemble model to predict postoperative morbidity after EVAR, the occurrence of postoperative complications prospectively recorded, and the causal effect knowledge by BNs with Markov blanket concept.