Droplet microfluidics has gained widespread attention in recent years due to its advantages of high throughput, high integration, high sensitivity and low power consumption in droplet-based micro-reaction. Meanwhile, with the rapid development of computer technology over the past decade, deep learning architectures have been able to process vast amounts of data from various research fields. Nowadays, interdisciplinarity plays an increasingly important role in modern research, and deep learning has contributed greatly to the advancement of many professions. Consequently, intelligent microfluidics has emerged as the times require, and possesses broad prospects in the development of automated and intelligent devices for integrating the merits of microfluidic technology and artificial intelligence. In this article, we provide a general review of the evolution of intelligent microfluidics and some applications related to deep learning, mainly in droplet generation, control, and analysis. We also present the challenges and emerging opportunities in this field.

Researchers are investigating how to make machines read our body language to make human-machine interaction (HMI) more intelligent and efficient. The lower limbs contain a variety of gestures, and it is also one of the most effective ways to express body information. Therefore, foot gesture recognition (FGR) has become a popular technology for human-machine interface with simple, fast and accurate features. To give the reader a quick overview of the current state of FGR research, this review takes the sensing methods used in FGR technology as an entry point, introduces different sensing methods, machine learning algorithms and applications, and discusses the limitations and future work on FGR systems. The results show that the mainstream sensing methods for FGR are plantar pressure, inertial, visual, surface electromyography and ultrasound. Current applications of FGR are simplified control, medical rehabilitation, virtual reality, and smart prosthetics. Research on hybrid sensing methods and deep learning algorithms has gradually increased in recent years. Future research will focus on designing sensor hardware that can respond to environmental changes, using multimodal sensing for interaction, and designing more comfortable and portable FGR systems.

Exoskeletons can track the wearer’s movements in real time, thereby enhancing physical performance or restoring mobility for individuals with gait impairments. These wearable assistive devices have demonstrated significant potential in both rehabilitation and industrial applications. This review focuses on the major advancements in exoskeleton technology published since 2020, with particular emphasis on the development of structural designs for lower-limb exoskeletons employed in locomotion assistance. We employed a systematic literature review methodology, categorizing the included studies into three main types: rigid exoskeleton, soft exoskeleton, and tethered platform. The current development status of robotic exoskeletons is analyzed based on publication year, system weight, target assistive joints, and main effects. Furthermore, we examine the factors driving these advancements and their implications for the field. The key challenges and opportunities that may influence the future development of exoskeleton technologies are also highlighted in this review.

Rapid on-site analysis of airborne trace metals has been heavily favored over traditional methodologies because air pollutants can be altered by environmental, behavioral, and social patterns at any given time and location. However, existing portable approaches are either not capable of performing integrated on-site analysis or not yet practically applicable. Exploiting graphene oxide (GO) in enhancing the analytical performance of paper-based colorimetric detection, for the first time, this paper reports the development of a practically useful portable system for accurate, sensitive on-site characterization of trace metals in ambient particulate matter (PM). The system consists of GO-nanosheet-coated paper devices, unmanned aerial vehicle multiaxial sampling, and cellphone-based colorimetric detection. The increased specific surface area and the homogeneity of color distribution from the coating of GO improves the accuracy and sensitivity of the assays. Additionally, by leveraging a Wi-Fi camera, a self-developed app and a sample pretreatment cartridge, metal in PM samples can be readily processed and characterized on-site within 30 min. The effects of chip geometric design, pH, reaction volume, and metal interference on detection results have been studied. The detection limits of the system were calibrated to be 16.6, 5.1, and 9.9 ng for metals Fe, Cu, and Ni, respectively, which are comparable to the detection limits of commercial inductively coupled plasma (ICP) instruments, thus making our portable system practically useful. Finally, the system was used for airborne trace-metal study at 6 locations in Fuzhou City (China), and the results obtained using our system demonstrated good agreement with those obtained by the ICP. The significance of our system in supplementing air pollution study and furthering research on rapid, accurate, on-site air toxicity assessment was demonstrated.