Energy Harvesting Smart Mat for Automation Control and Activity Monitoring


Electronics - Sensors & Instrumentation
Energy - Sensor, Network, Power Conversion, Power Quality & Energy Management
Show more >


This technology offer presents a deep learning-enabled smart mat, which is based on the triboelectric mechanism. This deep learning-enabled smart mat is achieved through the integration of a minimal-electrode-output triboelectric floor mat array with advanced deep learning (DL)-based data analytics. By walking/stepping over the smart mat, the unique fingerprint-like output signal can be captured by the electrode array. With the integrated deep learning-based data analytics, identity information associated with walking gait patterns can be extracted from the output signals using the convolutional neural network (CNN) model.

The smart mat can be applied in automation control, such as lighting and air conditioning and fall detection. The smart mat can also be adopted for activity monitoring (e.g., walking, running, exercising) and potential energy harvesting from our daily activities.

The technology owner is keen to out-license this patented technology and looking for partners and collaborators to further develop this technology. 


The deep learning-enabled smart mats are fabricated by screen printing, exhibiting the merits of cost-effectiveness, high scalability, and self-sustainability in large-area applications. A distinct electrode pattern with varying coverage rates is designed for each deep learning-enabled smart mat, mimicking the unique identification of the QR (quick response) code system. Hence, after the parallel connection in an interval scheme, minimal two-electrode outputs with distinguishable and stable characteristics for the whole deep learning-enabled smart mat array can be achieved.


  • Automation control, such as lighting and air-conditioning control. This can be achieved by positioning different patterned electrodes at different positions. By stepping on the specific patterned electrode, the designated control can be actuated.
  • Fall detection. This can be achieved by detecting the abnormal signal patterns of multiple peaks in a short period due to the falling-induced rapid contacts and no outputs in the following.
  • Activity monitoring. Different types of activities can be easily distinguished based on the overall magnitude and time period (frequency) of the output signals, indicating the activity monitoring capability.
  • Energy harvesting. In practical applications, the rectified output voltages can be applied to charge up capacitors as sustainable power sources for other Internet of Things (IoT) devices in smart buildings.
  • Individual recognition. The walking gait pattern of a person is different from others, it can generate a unique output signal for the person.

Unique Value Proposition

  • Smart home application. The realized individual recognition can be adopted in the automatic access by opening the door for recognized valid users. The smart floor monitoring system with the superior capability of position sensing, activity monitoring, and individual recognition exhibits great potential toward realizing the automation control and security.
  • Elderly care system. The detected sensory information is of great importance in the aspect of elderly people nursing. For example, fall detection by monitoring the irregular output signals in the time domain—abnormal outputs in a short period followed by no outputs.
  • Healthcare application. The smart mat can be adopted to track the time period of the exercise (based on activity monitoring), and the burned calories based on the type and period of the exercise.
  • Battery-free sensors. The energy harvested (generated when people walk over the mat) from the smart mat can be used to operate various sensors.
Face Anti-Spoofing Technology
Elimination of Wasted Energy from Buildings via Machine Learning
Asset Tracking Device with Customisable Sensors
High Speed and Sensitive Artificial Olfactory Sensor
AI-Aided Analysis of Capsule Endoscopy Images
Contactless Palm Biometrics for Person Authentication and Identification
AI-Assisted Image Labelling Tool for Large Scale Data Labelling Efficiency
AI-enabled Virtual Modelling for Reduction of Energy, Carbon Dioxide Emission
Deep Neural Network (DNN) Approach for Non-Intrusive Load Monitoring (NILM)
High-performant Vector Database for Artificial Intelligence (AI) Applications