A5075257692- Building Energy and Comfort Optimization
- Refrigeration and Air Conditioning Technologies
- Video Surveillance and Tracking Methods
- Electric and Hybrid Vehicle Technologies
- Electric Vehicles and Infrastructure
- Noise Effects and Management
- Infrared Target Detection Methodologies
- Smart Agriculture and AI
- Advanced Optical Sensing Technologies
- Semiconductor Lasers and Optical Devices
- Advanced Battery Technologies Research
- Optical Wireless Communication Technologies
- Robotics and Sensor-Based Localization
- Smart Grid Energy Management
- Vehicle License Plate Recognition
Columbia University
2023-2024
We present the design and implementation of RECA, a novel human-centric recommender system for co-optimizing energy consumption, comfort air quality in commercial buildings. Existing works generally optimize these objectives separately, or by only controlling consuming resources within building without directly engaging occupants. develop deep reinforcement learning architecture based on multitask learning, demonstrate how it can be used to jointly learn savings, improvements different...
Abstract We introduce a novel human-centric deep reinforcement learning recommender system designed to co-optimize energy consumption, thermal comfort, and air quality in commercial buildings. Existing approaches typically optimize these objectives separately or focus solely on controlling energy-consuming building resources without directly engaging occupants. develop architecture based multitask with humans-in-the-loop demonstrate how it can jointly learn savings, improvements for...
In complex environments where visibility is severely compromised, such as smoke-filled areas or dense forests, traditional single-sensor systems often fail to provide accurate and reliable data for robots autonomously navigate avoid obstacles effectively, posing significant operational challenges safety risks. Ground-based sensing platforms are further limited by their restricted mobility, hindering access remote hazardous areas. Multimodal sensing, which combines various sensor...
We present a demo showcasing the capabilities of an infrared (IR)-based light communication system with movable receiver. The employs IR laser (VCSEL) together scattering lens as transmitter and avalanche photo-diode (APD) collimator receiver, using reflection cross section existing in environment (ceilings, walls, etc.) to spread coverage system. demonstration involves transmitting messages encoded binary data through modulated signals receiver captures APD, which are then decoded retrieve...
Electric vehicles (EVs) have gained widespread popularity in recent years, and the scheduling routing of EV charging impacted welfare both drivers grid. In this paper, we present a practical, data-driven, human-centric recommendation system at city-scale based on deep reinforcement learning (DRL). The co-optimizes We augmented aggregated data from various sources, including public data, location-based companies, government authorities, with different formats time granularities. includes...