High detection accuracy in piezoelectric-based force sensing in interactive displays has gained global attention. To achieve this, artificial neural networks (ANN)—successful and widely used machine learning algorithms—have been demonstrated to be potentially powerful tools, providing acceptable location detection accuracy of 95.2% and force level recognition of 93.3% in a previous study. While these values might be acceptable for conventional operations, e.g., opening a folder, they must be boosted for applications where intensive operations are performed. Furthermore, the relatively high computational cost reported prevents the popularity of ANN-based techniques in conventional artificial intelligence (AI) chip-free end-terminals. In this article, an ANN is designed and optimized for piezoelectric-based touch panels in interactive displays for the first time. The presented technique experimentally allows a conventional smart device to work smoothly with a high detection accuracy of above 97% for both location and force level detection with a low computational cost, thereby advancing the user experience, and serviced by piezoelectric-based touch interfaces in displays.

No abstract

Piezoelectric force touch panels receive increased attentions in recent years. However, userinduced nonstable force-voltage responsivity limits their successful use in interactive displays. In this work, touch-induced capacitive information is used for estimating contact area and touch angle, which are further employed to interpret user performed force amplitude. A promising result of improving the stability of force-voltage responsivity by 85% is achieved, enhancing user experience and advancing the development of piezoelectric force sensing in interactive displays. INDEX TERMS Interactive display, piezoelectric material, force sensing and capacitive touch sensing.

A smart thermal flow sensor system is presented. It makes use of a novel heater control circuit which can automatically set the operating mode to either constant power or constant temperature difference. It overcomes the limitations of single-mode thermal flow sensors, such as temperature overshoots at low flow rates at constant power mode, or excessive power consumption at high flow rates at constant temperature difference mode. The system is especially useful for temperature sensitive and portable applications, such as respiratory monitoring for medical diagnostics. In this paper, detailed description of the sensor's design, implementation, and experimental validation are presented. The proposed dual-mode flow sensor achieves an overtemperature reduction up to 9.5% compared with thermal flow sensors operating in constant power mode alone, and a power reduction up to 13.6% compared with thermal flow sensors operating in constant temperature difference mode alone for the flow range of 0 to 50 slm while offering an improved overall sensitivity.

This paper evaluates the impact of the operating modes, power consumption, and placement of temperature sensors against the heater to the design of a calorimetric flow sensor, for the range of 4.7 to 56.5 liters per minute (slm). In contrast to previous works most of which simply indicated the choice of various design parameters rather than providing a justification, this work provides useful guidelines for optimizing low-power small-area flow sensors for respiratory monitoring applications. A figure of merit (FoM) which is defined as the product of power consumption and sensor size, the two most challenging design parameters in developing small medical devices and systems, is proposed for quantifying flow sensor performance. Although the analysis and simulation was drawn upon designs in the mm scale, a similar optimization process can be applied to flow sensors of any size.