A Novel Experimental Apparatus for Characterizing Flow Regime in Mechanically Stirred Tanks through Force Sensors.

Pressure fluctuations in a mixing tank can provide valuable information about the existing flow regime within the tank, which in turn influences the degree of mixing that can be achieved. In the present work, we propose a prototype for identifying the flow regime in mechanically stirred tanks equipped with four vertical baffles through the characterization of pressure fluctuations. Our innovative proposal is based on force sensors strategically placed in the baffles of the mixing tank. The signals coming from the sensors are transmitted to an electronic module based on an Arduino UNO development board. In the electronic module, the pressure signals are conditioned, amplified and sent via Bluetooth to a computer. In the computer, the signals can be plotted or stored in an Excel file. In addition, the proposed system includes a moving average filtering and a hierarchical bottom-up clustering analysis that can determine the real-time flow regime (i.e., the Reynolds number, Re) in which the tank was operated during the mixing process. Finally, to demonstrate the versatility of the proposed prototype, experiments were conducted to identify the Reynolds number for different flow regimes (static, laminar, transition and turbulent), i.e., 0≤Re≤ 42,955. Obtained results were in agreement with the prevailing consensus on the onset and developed from different flow regimes in mechanically stirred tanks.

Coarse-Fine Convolutional Deep-Learning Strategy for Human Activity Recognition.

In the last decade, deep learning techniques have further improved human activity recognition (HAR) performance on several benchmark datasets. This paper presents a novel framework to classify and analyze human activities. A new convolutional neural network (CNN) strategy is applied to a single user movement recognition using a smartphone. Three parallel CNNs are used for local feature extraction, and latter they are fused in the classification task stage. The whole CNN scheme is based on a feature fusion of a fine-CNN, a medium-CNN, and a coarse-CNN. A tri-axial accelerometer and a tri-axial gyroscope sensor embedded in a smartphone are used to record the acceleration and angle signals. Six human activities successfully classified are walking, walking-upstairs, walking-downstairs, sitting, standing and laying. Performance evaluation is presented for the proposed CNN.