Search for: All records

Recent studies have shown that, experiencing the appropriate lighting environment in our day-to-day life is paramount, as different types of light sources impact our mental and physical health in many ways. Researchers have intercon-nected daylong exposure of natural and artificial lights with circadian health, sleep and productivity. That is why having a generalized system to monitor human light exposure and recommending lighting adjustments can be instrumental for maintaining a healthy lifestyle. At present methods for collecting daylong light exposure information and source identification contain certain limitations. Sensing devices are expensive and power consuming and methods of classifications are either inac-curate or possesses certain limitations. In addition, identifying the source of exposure is challenging for a couple of reasons. For example, spectral based classification can be inaccurate, as different sources share common spectral bands or same source can exhibit variation in spectrum. Also irregularities of sensed information in real world makes scenario complex for source identification. In this work, we are presenting a Low Power BLE enabled Color Sensing Board (LPCSB) for sensing background light parameters. Later, utilizing Machine learning and Neural Network based architectures, we try to pinpoint the prime source in the surrounding among four dissimilar types: Incandescent, LED, CFL and Sunlight. Our experimentation includes 27 distinct bulbs and sunlight data in various weather/time of the day/spaces. After tuning classifiers, we have investigated best parameter settings for indoor deployment and also analyzed robustness of each classifier in several imperfect situations. As observed performance degraded significantly after real world deployment, we include synthetic time series examples and filtered data in the training set for boosting accuracy. Result shows that our best model can detect the primary light source type in the surroundings with accuracy up to 99.30% in familiar and up to 90.25% in unfamiliar real world settings with enlarged training set, which is much elevated than earlier endeavors. 

The key to optimal occupant comfort as well as resource utilization in a smart building is to provide personalized control over smart appliances. Additionally, with an exponentially growing Internet-of-Things (IoT), reducing the need of frequent user attention and effort involving building management to control and manage an enormous number of smart devices becomes inevitable. One crucial step to enable occupant-specific personalized spaces in smart buildings is accurate identification of different occupants. In this paper, we introduce SolarWalk to show that small and unobtrusive indoor photovoltaic harvesters can identify occupants in smart home scenarios. The key observations are that i) photovoltaics are commonly used as a power source for many indoor energy-harvesting devices, ii) a PV cell's output voltage is perturbed differently when different persons pass in close range, creating an unique signature voltage trace, and iii) the voltage pattern can also determine the person' walking direction. SolarWalk identifies occupants in a smart home by training a classifier with their shadow voltage traces. SolarWalk achieves an average accuracy of 88% to identify five occupants in a home and on average 77% accurate to determine whether someone entered or exited the room. SolarWalk enables an accurate occupant identification system that is non-invasive, ubiquitous, and does not require dedicated hardware and rigorous installation.