Study on the Interaction Behaviors Identification of Construction Workers Based on ST-GCN and YOLO.

The construction industry is accident-prone, and unsafe behaviors of construction workers have been identified as a leading cause of accidents. One important countermeasure to prevent accidents is monitoring and managing those unsafe behaviors. The most popular way of detecting and identifying workers' unsafe behaviors is the computer vision-based intelligent monitoring system. However, most of the existing research or products focused only on the workers' behaviors (i.e., motions) recognition, limited studies considered the interaction between man-machine, man-material or man-environments. Those interactions are very important for judging whether the workers' behaviors are safe or not, from the standpoint of safety management. This study aims to develop a new method of identifying construction workers' unsafe behaviors, i.e., unsafe interaction between man-machine/material, based on ST-GCN (Spatial Temporal Graph Convolutional Networks) and YOLO (You Only Look Once), which could provide more direct and valuable information for safety management. In this study, two trained YOLO-based models were, respectively, used to detect safety signs in the workplace, and objects that interacted with workers. Then, an ST-GCN model was trained to detect and identify workers' behaviors. Lastly, a decision algorithm was developed considering interactions between man-machine/material, based on YOLO and ST-GCN results. Results show good performance of the developed method, compared to only using ST-GCN, the accuracy was significantly improved from 51.79% to 85.71%, 61.61% to 99.11%, and 58.04% to 100.00%, respectively, in the identification of the following three kinds of behaviors, throwing (throwing hammer, throwing bottle), operating (turning on switch, putting bottle), and crossing (crossing railing and crossing obstacle). The findings of the study have some practical implications for safety management, especially workers' behavior monitoring and management.

A compact immunoassay platform based on a multicapillary glass plate.

A highly sensitive, rapid immunoassay performed in the multi-channels of a micro-well array consisting of a multicapillary glass plate (MCP) and a polydimethylsiloxane (PDMS) slide is described. The micro-dimensions and large surface area of the MCP permitted the diffusion distance to be decreased and the reaction efficiency to be increased. To confirm the concept of the method, human immunoglobulin A (h-IgA) was measured using both the proposed immunoassay system and the traditional 96-well plate method. The proposed method resulted in a 1/5-fold decrease of immunoassay time, and a 1/56-fold cut in reagent consumption with a 0.05 ng/mL of limit of detection (LOD) for IgA. The method was also applied to saliva samples obtained from healthy volunteers. The results correlated well to those obtained by the 96-well plate method. The method has the potential for use in disease diagnostic or on-site immunoassays.

Inkjet nanoinjection for high-thoughput chemiluminescence immunoassay on multicapillary glass plate.

We report a novel chemiluminescence diagnosis system for high-throughput human IgA detection by inkjet nanoinjection on a multicapillary glass plate. As proof-of-concept, microhole-based polydimethylsiloxane (PDMS) sheets were aligned on a multicapillary glass plate to form a microwell array as microreactors for enzyme-linked immunosorbent assay (ELISA). The multicapillary glass plate was utilized as a switch that controlled the holding/passing of the solution. Further, anti-IgA-labeled polystyrene (PS) microbeads was assembled into the microwell array, and an inkjet nanoinjection was specially used to distribute the sample and reagent solution for chemiluminescence ELISA, enabling high-throughput detection of human IgA. As a result, the performance of human IgA tests revealed a wider range for the calibration curve and a lower limit of detection (LOD) of 0.1 ng mL(-1) than the ELISA by a standard 96-well plate. The analysis time and reagent consumption were significantly decreased. The IgA concentrations in saliva samples were determined after 10000-fold dilution by the developed ELISA system showing comparable results by conventional immune assay with 96-wells. Thus, we believe that the inkjet nanoinjection for high-throughput chemiluminescence immunoassay on a multicapillary glass plate will be promising in disease diagnosis.

Advances in electrically driven light-emitting diodes based on lead-free metal halides.

The emerging lead halide perovskites show great potential for their use as emitters in electrically driven light-emitting diodes (LEDs) with external quantum efficiency (EQE) over 25%. While the toxicity of lead and inferior device stability are the main obstacles for their commercialization, replacing Pb2+ with low- or non-toxic metal ions to form low- or zero-dimensional structures provides an alternative approach to effectively tackle these issues. Recently, luminescent lead-free metal halides have been increasingly developed toward eco-friendly and highly efficient electroluminescence. In this feature article, we give a brief overview of recent advances in luminescent lead-free metal halides and their applications in electrically driven LEDs. The challenges and prospects in this field are outlined at the end.

Determination of ammonium on an integrated microchip with LED-induced fluorescence detection.

A simply fabricated microfluidic device integrated with a fluorescence detection system has been developed for on-line determination of ammonium in aqueous samples. A 365-nm light-emitting diode (LED) as an excitation source and a minor band pass filter were mounted into a polydimethylsiloxane (PDMS)-based microchip for the purpose of miniaturization of the entire analytical system. The ammonium sample reacted with o-phthaldialdehyde (OPA) on-chip with sodium sulfite as reducing reagent to produce a fluorescent isoindole derivative, which can emit fluorescence signal at about 425 nm when excited at 365 nm. Effects of pH, flow rate of solutions, concentrations of OPA-reagent, phosphate and sulfite salt were investigated. The calibration curve of ammonium in the range of 0.018-1.8 microg/mL showed a good linear relationship with R2 = 0.9985, and the detection limit was (S/N = 3) 3.6 x 10(-4) microg/mL. The relative standard deviation was 2.8% (n = 11) by calculating at 0.18 microg/mL ammonium for repeated detection. The system was applied to determine the ammonium concentration in rain and river waters, even extent to other analytes fluorescence detection by the presented device.

An integrated enzyme-linked immunosorbent assay system with an organic light-emitting diode and a charge-coupled device for fluorescence detection.

A fluorescence detection system for a microfluidic device using an organic light-emitting diode (OLED) as the excitation light source and a charge-coupled device (CCD) as the photo detector was developed. The OLED was fabricated on a glass plate by photolithography and a vacuum deposition technique. The OLED produced a green luminescence with a peak emission at 512 nm and a half bandwidth of 55 nm. The maximum external quantum efficiency of the OLED was 7.2%. The emission intensity of the OLED at 10 mA/cm(2) was 13 µW (1.7 mW/cm(2)). The fluorescence detection system consisted of the OLED device, two band-pass filters, a five microchannel poly(dimethylsiloxane) (PDMS) microfluidic device and a linear CCD. The fluorescence detection system was successfully used in a flow-based enzyme-linked immunosorbent assay on a PDMS microfluidic device for the rapid determination of immunoglobulin A (IgA), a marker for human stress. The detection limit (S/N=3) for IgA was 16.5 ng/mL, and the sensitivity was sufficient for evaluating stress. Compared with the conventional 96-well microtiter plate assay, the analysis time and the amounts of reagent and sample solutions could all be reduced.

A microscale solid-phase extraction poly(dimethylsiloxane) chip for enrichment and fluorescent detection of metal ions.

A rapid and simple enrichment system was developed on microfluidic chip which was integrated with on-line complexing and fluorescence detection. Microparticles of ion-exchange resin were trapped into the microchannel by a fabricated weir-structure in the end of the microchannel to construct a micro-solid-phase extraction (µ-SPE) device. Some commonly existing metal ions in environment were served as models to evaluate the performance of the proposed microdevice, in combination with on-line derivatization with 8-hydroxyquinolin-5-sulfonic acid (HQS) and fluorescence detection. The concentration and pH value of HQS solution were optimized for metal-HQS fluorescent derivatization. The parameters, which affected the efficiency of the developed method, including composition and concentration of eluent, pH value and the flow rate of HQS solution and elution, were also investigated. Under the optimal conditions, Ca(2+), Mg(2+), Zn(2+) and Pb(2+) were successfully determined by the µ-SPE device on-chip. The experimental enrichment factors for Ca(2+), Mg(2+), Zn(2+) and Pb(2+) were up to 520, 565, 578 and 487 folds, respectively.