AI Sensors

The rapid development of the Artificial Intelligence of Things (AIoT) has created unprecedented demands for distributed, long-term, and maintenance-free sensing systems. Conventional battery-powered sensors suffer from inherent drawbacks such as limited lifetime, high maintenance costs, and environmental concerns, which hinder large-scale deployment. Self-powered sensing technologies provide a transformative pathway by integrating energy harvesting and sensing into a single platform, thereby eliminating the reliance on external power supplies. This review systematically summarizes the key components of self-powered wireless sensing systems, with a particular focus on different energy harvesting technologies, self-powered sensing technologies, and the latest advances in low-power intelligent computation for diverse application scenarios. The integration of energy harvesting, self-sensing, and intelligent computation will make self-powered wireless sensing systems an inevitable direction for the evolution of AIoT, enabling sustainable, scalable, and intelligent monitoring networks.

To better serve human life with smart and harmonic communication between the real and digital worlds, wearable human–machine interfaces (HMIs) with edge computing capabilities indicate the path to the next revolution of information technology. In this review, we focus on wearable HMIs and highlight several key aspects which are worth investigating. Firstly, we review wearable HMIs powered by commercial-ready technologies, highlighting some limitations. Next, to establish a dual-way interaction for exchanging comprehensive information, sensing and feedback functions on the human body need to be customized based on specific scenarios. Power consumption is another primary issue that is critical to wearable applications due to limited space, one that is possible to be solved by energy harvesting techniques and self-powered data transmission approaches. To further improve the data interpretation with higher intelligence, machine learning (ML)-assisted analysis is preferred for multi-dimensional data. Eventually, with the presence of edge computing systems, those data can be pre-processed locally for downstream applications. Generally, this review offers an overview of the development of intelligent wearable HMIs with edge computing capabilities and self-sustainability, which can greatly enhance the user experience in healthcare, industrial productivity, education, etc.

Accurate and continuous, non-invasive blood pressure (BP) monitoring plays a vital role in the long-term management of cardiovascular diseases. Advances in wearable and flexible sensing technologies have facilitated the transition of non-invasive BP monitoring from clinical settings to ambulatory home environments. However, the measurement consistency and algorithm adaptability of existing devices have not yet reached the level required for routine clinical practice. To address these limitations, comprehensive innovations have been made in material development, sensor design, and algorithm optimization. This review examines the evolution of non-invasive continuous BP measurement, highlighting cutting-edge advances in flexible electronic devices and BP estimation algorithms. First, we introduce measurement principles, sensing devices and limitations of traditional non-invasive BP measurement, including arterial tonometry, arterial volume clamp, and ultrasound-based methods. Subsequently, we review the pulse wave analysis-based BP estimation methods from two perspectives: flexible sensors based on optical, mechanical, and electrical principles, and estimation models that use physiological features or raw waveforms as input. Finally, we conclude the existing challenges and future development directions of flexible electronic technology and intelligent estimation algorithms for non-invasive continuous BP measurement.