Adaptation for Automated Drift Detection in Electromechanical Machine Monitoring.

Practical machine learning applications for streaming data can involve concept drift (the change in statistical properties of data over time), one-shot or few-shot learning (starting with only one or a few examples for each class), a scarcity of representative training data, and extreme verification latency (only the initial dataset has ground-truth labels). This work presents a framework for organizing signal processing and machine learning techniques to provide adaptive classification and drift detection. Nonintrusive load monitoring (NILM) serves as an ideal case study, as modern sensing solutions provide a wellspring of electromechanical data sources. There is a lack of training datasets that generalize across different load and fault scenarios. Accordingly, training must be accomplished with a limited set of data when deploying a NILM to a new power system. Also, loads can exhibit concept drift over time either due to faults or normal variation. NILM field data is used as an illustrative case study to demonstrate the proposed framework for adaptation and drift tracking.

Using talking lights illumination-based communication networks to enhance word comprehension by people who are deaf or hard of hearing.

This article details a new method that has been developed to transmit auditory and visual information to people who are deaf or hard of hearing. In this method, ordinary fluorescent lighting is modulated to carry an assistive data signal throughout a room while causing no flicker or other distracting visual problems. In limited trials with participants who are deaf or hard of hearing, this assistive system, combined with commercial voice recognition software, showed statistically significant improvement in sentence recognition compared to recognition of audio-only or audio-plus-speech-reading stimuli.