Energy-efficient context classification with dynamic sensor control

A General Framework for Making Context-Recognition Systems More Energy Efficient

Context recognition using wearable devices is a mature research area, but one of the biggest issues it faces is the high energy consumption of the device that is sensing and processing the data. In this work we propose three different methods for optimizing its energy use. We also show how to combine all three methods to further increase the energy savings. The methods work by adapting system settings (sensors used, sampling frequency, duty cycling, etc.) to both the detected context and directly to the sensor data. This is done by mathematically modeling the influence of different system settings and using multiobjective optimization to find the best ones. The proposed methodology is tested on four different context-recognition tasks where we show that it can generate accurate energy-efficient solutions—in one case reducing energy consumption by 95% in exchange for only four percentage points of accuracy. We also show that the method is general, requires next to no expert knowledge about the domain being optimized, and that it outperforms two approaches from the related work.

Analysis of Interventionalists' Natural Behaviors for Recognizing Motion Patterns of Endovascular Tools During Percutaneous Coronary Interventions

Many robotic platforms can indeed reduce radiation exposure to clinicians during percutaneous coronary intervention (PCI), however, interventionalists' natural manipulations are rarely involved in robot-assisted PCI. This requires more attention to analyze interventionalists' natural behaviors during conventional PCI. In this study, four types of natural behavior (i.e., muscle activity, hand motion, proximal force, and finger motion) were synchronously acquired from ten subjects while performing six typical types of guidewire manipulation. These behaviors are evaluated by a hidden Markov model (HMM) based analysis framework for relevant behavior selection. Relevant behaviors are further used as the input of two HMM-based classification frameworks to recognize guidewire motion patterns. Experimental results show that under the basic classification framework (BCF), 91.01% and 93.32% recognition accuracies can be achieved by using all behaviors and relevant behaviors, respectively. Furthermore, the hierarchical classification framework can significantly enhance the recognition ability of relevant behaviors with an accuracy of 96.39%. These promising results demonstrate great potential of proposed methods for promoting the future design of human-robot interfaces in robot-assisted PCI.