- Data Depot
Pervasive building occupancy sensors for energy efficient lighting control are already a given as mandated in ASHRAE 90.1 and IECC codes. With physical sensors like IR and audio being integrated in lighting controllers used to support energy management, innovative manufacturers are exploring additional smart building services that can be offered leveraging the same infrastructure and sensor arrays. Building servicing, security, and conference room scheduling are but a few such examples of value-added smart building services that can be offered by such systems.
Privacy considerations and objections to centralized data collection and monitoring of cameras / audio
Limited network throughput for rich sensor streaming over building automation networks
Emergent building service applications lack ROI / mandate to drive additional sensor / processing BOM
Intelligent building services while an attractive proposition, face considerable cost and privacy concerns where dependent upon image and audio sensing with centralized AI recognition technologies. An alternative approach utilizes existing simple sensors and distributed intelligence to derive insights from sensors already well accepted for use in smart lighting control systems. Low-cost passive infrared (PIR) occupancy sensors when combined with low-cost MCUs and ML-based pattern recognition algorithms, can infer much more than simple presence detection. SensiML has demonstrated the ability to enable the next generation of smart building occupancy sensors.
More reliable IR sensing for determining actual space occupancy
Ability to delineate types of movement for better contextual information
Enable real-time room occupancy counts (ex. meeting rooms, auditoriums, restrooms)
Can provide traffic profiles for over-the-top applications like footfall traffic heatmaps in retail settings
Can adapt and learn building usage profiles over time and adapt automatically without continuous intervention
Building sensor and system OEMs seeking to provide smart services can rapidly integrate such capability into their existing PIR sensor endpoints to deliver truly intelligent lighting and occupant sensing.
Smart city initiatives are sprouting up across the globe with great promise of harnessing the power of cloud computing and analytics to solve some of the biggest urban growth challenges. A variety of applications and approaches have been envisioned and are beginning to be piloted and tested. The promise of such systems are more efficient use of available roads, water, energy, waste management infrastructure, improved citizen safety, and emergency response.
Volume of data generated by many sensors in remote locations served by wide-area wireless networks
Real-time responsiveness of systems with centralized analytics
With tools enabling smart city sensor OEMs to quickly integrate learning algorithms directly into their devices, SensiML can support distributed processing of raw sensor data into key insight events. This distributed approach can offer distinct advantages for broad sensor deployments in smart city use cases otherwise greatly challenging to deliver through centralized analytics. SensiML endpoint optimized machine learning algorithms are designed to execute autonomously on devices ranging from low-cost/low-power microcontrollers integrated in battery powered sensor devices up to more powerful processors found in edge hubs, servers, and gateways. SensiML can provide smart city sensor OEMs and system integrators the ability to offer meaningful insights such as:
Audio profile-based alerts - Sensors programmed to recognize and report gunshots, spoken keywords, breaking glass, vehicle accidents, and other sonic events
Visual cues - Using PIR or optical sensors to provide motion triggers and activity type/volume data
Vibration/motion-based pattern recognition – Low-cost, real-time traffic monitoring and classification, emergency / earthquake response, and structural health monitoring
Using endpoint intelligence, SensiML can enable the autonomous pre-processing of raw sensor data needed to make smart city deployments practical.