CSH researcher Franz Papst will give his talk at the Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (AIChallengeIoT) which takes place within the framework of the 19th ACM Conference on Embedded Networked Sensor Systems (SenSys 2021) in Coimbra (Portugal) from Nov 15–17, 2021.
Abstract:
Low-cost sensors are extensively used in numerous Internet of Things (IoT) applications to measure relevant physical processes. Today, processing context data is increasingly done by proprietary algorithms tuned to a specific use-case, e.g., a sensor measuring activity intensity of a cow. Readings from these sensors may be subject to data distribution shifts, which challenge robustness of models using these sensor readings.
In this paper, we propose a new sensor data processing framework, which leverages a co-dependency between data quality and model robustness to detect performance issues of data-driven predictive models in the field.
We show how distribution shifts in the input data impact the quality of the model, which relies on application-specific sensors, and present indicators capable of detecting such shifts in the wild. The proposed framework used in the context of precision cattle farming allows improving the quality of cow lameness predictive models on the field data by up to 62%.
About the conference:
The 19th ACM Conference on Embedded Networked Sensor Systems (SenSys 2021) introduces a highly selective, single-track forum for research on systems issues of sensors and sensor-enabled smart systems, broadly defined. Systems of smart sensors will revolutionize a wide array of application areas by providing an unprecedented density and fidelity of instrumentation. They also present various systems challenges because of resource constraints, uncertainty, irregularity, mobility, and scale.
This conference provides an ideal venue to address research challenges facing the design, development, deployment, use, and fundamental limits of these systems. Sensing systems require contributions from many fields, from wireless communication and networking, embedded systems and hardware, energy harvesting and management, distributed systems and algorithms, data management, and applications, so we welcome cross-disciplinary work.