<p>The proliferation of efficient edge computing has enabled a paradigm shift of how we monitor and interpret urban air quality. Coupled with the dense spatiotemporal resolution realized from large-scale wireless sensor networks, we can achieve highly accurate realtime local inference of airborne pollutants. In this paper, we introduce a novel Deep Neural Network architecture targeted at latent time-series regression tasks from continuous, exogenous sensor measurements, based on the Transformer encoder scheme and designed for deployment on low-cost power-efficient edge processors.


This dataset was prepared to estimate the winding temperature of a BLDC motor for a variable load and speed profile. It contains two files. The first one is the measurement results for the motor without cooling, while the second one is the measurement results after installing an additional cooling fan on the shaft. The data included in the files are time stamp, winding temperature, casing temperature, speed, current, power loss, mean and standard deviation of the measured quantities for 14400 data records.


This dataset is in support of my research paper 'Comparative Non-Linear Flux Matrices & Thermal Losses in BLDC with Different Pole Pairs' .

Preprint : https://doi.org/10.36227/techrxiv.19687287.v1


The large variability of system and types of heating load is a feature of the commercial metering of thermal energy. Heating consumption depends on many factors, for example, wall and roof material, floors number, system (opened and closed) etc. The daily data from heating meters in the residential buildings are presented in this dataset for comparing the thermal characteristics. These data are supplemented by floors number, wall material and year of construction, as well as data on average daily outdoor temperatures.


The videos demonstrate 2D thermal gradient mappings based on two pairs of 50 µm x- an y- thin film thermocouple (TFTC) sensors. We investigate thin film thermocouples (TFTC) asthermal gradient sensors at the micro-scale and demonstrate two-dimensional dynamic thermal gradient mapping for features as small as 20 μm. Pairs of x-direction and y-direction thermocouples sense the thermal gradient while another calibrates the Seebeck coefficient as S = 20.33±0.01μV/K. The smallest detectable temperature difference is 10 mK, and the sensitivity is 0.5 mK/μm.


Early data was collected by technicians using mercury thermometers, where any variation in the visit time impacted measurements. In the 1940s, the construction of airports caused many weather stations to be moved. In the 1980s, there was a move to electronic thermometers that are said to have a cooling bias.

Given this complexity, there are a range of organizations that collate climate trends data. The three most cited land and ocean temperature data sets are NOAA’s MLOST, NASA’s GISTEMP and the UK’s HadCrut.