In this study, an integrated flexible gas sensor was developed based on a polymer/multi-walled carbon nanotube composite film by using Bluetooth wireless communication/interface technology. Polymer/multi-walled carbon nanotube composite films were deposited over a polyimide flexible substrate for building a gas sensor array by using a drop-casting method. Sensor response was acquired through interdigitated electrodes and multi-channel sensor boards, which were linked to a Bluetooth wireless transceiver. Additionally, a double-spiral-shaped heater was built into the backside of the gas sensor array as a thermostat to protect it from the influence of ambient temperature. Multi-channel sensing responses were read on a display screen via a smartphone application (app). The advantages of this system include light weight, low cost, highly integrated sensors, wireless telecommunication, and real-time functioning. Thus, it is a promising candidate for deployment in a wearable gas-sensing system used to study air pollution.

There is a need to develop a chemiresistive gas sensor equipped with a thermostat over a wide area for the sensor, which can protect the sensor from the influence of ambient temperature due to the uniform temperature of the thermostat. In this paper, we demonstrated an acetone gas sensor based on a polyethylene glycol (PEG)/Multi-walled Carbon Nanotubes (MWCNTs) composite film, which was equipped with a thermostat. The sensor was operated at modest working temperatures for sensor sensitivity enhancement. The optimum design of the polyimide-based thermostat with widely uniform thermal distribution was investigated in detail. It was found that the temperature uniformity of the thermostat was achieved using double spiral geometry. The experimental results of the sensor response showed that the PEG/MWCNTs composite film with a moderate working temperature revealed a higher sensitivity than that without thermal treatment. Moreover, the sensing mechanisms of the PEG/MWCNTs composite gas sensor to acetone vapor were studied as well.

Infections of orchids by the Odontoglossum ringspot virus or Cymbidium mosaic virus cause orchid disfiguration and are a substantial source of economic loss for orchid farms. Although immunoassays can identify these infections, immunoassays are expensive, time consuming, and labor consuming and limited to sampling-based testing methods. This study proposes a noncontact inspection platform that uses a spectrometer and Android smartphone. When orchid leaves are illuminated with a handheld optical probe, the Android app based on the Internet of Things and artificial intelligence can display the measured florescence spectrum and determine the infection status within 3 s by using an algorithm hosted on a remote server. The algorithm was trained on optical data and the results of polymerase chain reaction assays. The testing accuracy of the algorithm was 89%. The area under the receiver operating characteristic curve was 91%; thus, the platform with the algorithm was accurate and convenient for infection screening in orchids.

Convolutional neural networks (CNNs) have been widely and successfully demonstrated for closed set recognition in gait identification, but they still lack robustness in open set recognition for unknown classes. To improve the disadvantage, we proposed a convolutional neural network autoencoder (CNN-AE) architecture for user classification based on plantar pressure gait recognition. The model extracted gait features using pressure-sensitive mats, focusing on foot pressure distribution and foot size during walking. Preprocessing techniques, including region of interest (ROI) selection, feature image extraction, and data horizontal flipping, were utilized to establish a CNN model that assessed gait recognition accuracy under two conditions: without carried items and carrying a 500 g object. To extend the application of the CNN to open set recognition for unauthorized personnel, the proposed convolutional neural network-autoencoder (CNN-AE) architecture compressed the average foot pressure map into a 64-dimensional feature vector and facilitated identity determination based on the distances between these vectors. Among 60 participants, 48 were classified as authorized individuals and 12 as unauthorized. Under the condition of not carrying an object, an accuracy of 91.218%, precision of 93.676%, recall of 90.369%, and an F1-Score of 91.993% were achieved, indicating that the model successfully identified most actual positives. However, when carrying a 500 g object, the accuracy was 85.648%, precision was 94.459%, recall was 84.423%, and the F1-Score was 89.603%.

This study proposed a SU-8 based gas sensor, integrated with heater and sensing electrodes, to develop a multi-channel gas sensor with PEG/SWCNTs composite films. The impedance of single-walled carbon nanotubes (SWCNTs) on each sensing electrode was well controlled via dielectrophoresis technology. To investigate dielectrophoretic mobility characteristics, the concentric circular sensing electrode has three different spacing between the inner and outer electrodes, including 10 μm, 15 μm, and 20 μm. The electrodes were applied with a 5 MHz AC source with a voltage ranging from 1 Vpp to 5 Vpp. Polyethylene glycol (PEG) was deposited on the gas sensor via drop casting. The fabricated gas sensor was operated at different working temperatures, including 25 °C, 40 °C, 50 °C and 60 °C, to examine the sensing response. The response results revealed that the PEG/SWCNTs composites gas sensor with 60 °C working temperature exhibited the ability to detect 80 ppm ethanol vapor.

Falls in health and social care require privacy-preserving and cost-effective monitoring solutions to ensure safety. Low-resolution infrared (IR) array sensors provide a promising balance between invasiveness and information content; however, their performance can be strongly affected by ambient temperature variations and thermal interference. In this work, an environment-adaptive fall-detection system was developed to achieve cross-domain robustness and embedded real-time feasibility. A 24×32 MLX90640 IR array integrated with an ESP32 microcontroller captures thermal sequences at 8 fps. The processing pipeline includes temperature-based filtering, background removal based on a U-Net architecture for isolating human motion, Farneback optical flow extraction, and a lightweight CNN–BiLSTM–Attention network for spatiotemporal modeling. Experiments conducted across three thermally distinct indoor environments (11,148 samples, six activity classes) demonstrate that the U-Net-based background subtraction significantly enhances model robustness, achieving a six-class classification accuracy of 86.31% and reaching 98.27% in a simplified three-class (normal/falling/empty) configuration. Ablation and profiling analyses confirm the contribution of each processing stage while maintaining a compact model (≈0.83 M parameters, ≈3.17 MB) operating in real time at 8 fps on the ESP32–MLX90640 platform.