Occlusion Robust Cognitive Engagement Detection in Real-World Classroom.

Cognitive engagement involves mental and physical involvement, with observable behaviors as indicators. Automatically measuring cognitive engagement can offer valuable insights for instructors. However, object occlusion, inter-class similarity, and intra-class variance make designing an effective detection method challenging. To deal with these problems, we propose the Object-Enhanced-You Only Look Once version 8 nano (OE-YOLOv8n) model. This model employs the YOLOv8n framework with an improved Inner Minimum Point Distance Intersection over Union (IMPDIoU) Loss to detect cognitive engagement. To evaluate the proposed methodology, we construct a real-world Students' Cognitive Engagement (SCE) dataset. Extensive experiments on the self-built dataset show the superior performance of the proposed model, which improves the detection performance of the five distinct classes with a precision of 92.5%.

Bimodal Learning Engagement Recognition from Videos in the Classroom.

Engagement plays an essential role in the learning process. Recognition of learning engagement in the classroom helps us understand the student's learning state and optimize the teaching and study processes. Traditional recognition methods such as self-report and teacher observation are time-consuming and obtrusive to satisfy the needs of large-scale classrooms. With the development of big data analysis and artificial intelligence, applying intelligent methods such as deep learning to recognize learning engagement has become the research hotspot in education. In this paper, based on non-invasive classroom videos, first, a multi-cues classroom learning engagement database was constructed. Then, we introduced the power IoU loss function to You Only Look Once version 5 (YOLOv5) to detect the students and obtained a precision of 95.4%. Finally, we designed a bimodal learning engagement recognition method based on ResNet50 and CoAtNet. Our proposed bimodal learning engagement method obtained an accuracy of 93.94% using the KNN classifier. The experimental results confirmed that the proposed method outperforms most state-of-the-art techniques.

Rapid and sensitive detection of ß-agonists using a portable fluorescence biosensor based on fluorescent nanosilica and a lateral flow test strip.

A portable fluorescence biosensor with rapid and ultrasensitive response for Clenbuterol (CL) has been built up with fluorescent nanosilica and a lateral flow test strip. Quantitative detection of CL was realized by recording the fluorescence intensity of fluorescent nanosilica captured on the test line. The sensing results indicated that the sensitivity of the fluorescent nanosilica-based strip was better than that of conventional colloidal gold-based strips. The visual limit of detection of the strip for qualitative detection was 0.1 ng/mL while the LOD for quantitative detection could down to 0.037 ng/mL by using fluorescence biosensor. The recoveries of test samples were from 89.3% to 97.7%. The assay time for CL detection was less than 8 min, suitable for rapid testing on-site.

Development of a lateral flow colloidal gold immunoassay strip for the rapid detection of olaquindox residues.

A rapid immunochromatographic lateral flow test strip of competitive format has been developed for the specific determination of olaquindox (OLA) residues in pig urine and muscle tissues. The sensitivity of the test strip was found to be 1.58 ± 0.27 µg/kg and 1.70 ± 0.26 µg/kg of OLA in pig urine and muscle tissues, and the lower detection limit was 0.27 ± 0.08 µg/kg and 0.31 ± 0.07 µg/kg respectively. For negative pig urine and muscle samples spiked with 4, 12, and 36 µg/kg, the recovery range was 83.0-94.0% and 78.8-87.4% and the coefficient of variation scope [CV (%)] was 3.17-7.41% and 4.66-7.64% respectively. Parallel analysis of OLA samples from pig urine and muscle tissue showed comparable results from the test strip and HPLC. Each test requires 5-8 min, and the test strip can provide a useful screening method for quantitative, semiquantitative, or qualitative detection of OLA residues.

Development of immunoassays for the detection of sulfamethazine in swine urine.

The use of sulfonamides, such as sulfamethazine (SM2), in pig production is recognized as a public health risk as it inevitably results in sulfamethazine residues in pork. This study is aimed at establishing rapid, simple, reliable methods, with both sensitivity and specificity, for detecting sulfamethazine residues. For this purpose, monoclonal antibodies against sulfamethazine were prepared and characterized. No cross-reaction of the monoclonal antibodies was identified with other sulfonamides or analytes. Based on the competitive immunoassay principle, an indirect competitive ELISA kit (SM2 kit) and a rapid detection strip for detecting sulfamethazine residues were developed using monoclonal antibodies and the colloidal gold technique. The indirect competitive ELISA kit and the strip assay could be performed within 2 h and 5-10 min, respectively. The results showed that the detection limits were 1 ng ml(-1) for the indirect competitive ELISA kit and 8 ng ml(-1) with the unaided eye and 1 ng ml(-1) with the strip reader for the rapid strip assay. Comparing the HPLC method with the SM2-kit or the strip in pig urine spiked with standards of SM2, the difference was <4.6% for SM2-kit and 4.3% for the strip. The two methods are suitable for the rapid screening of sulfamethazine residues in swine urine. Experimental data revealed that the two methods, especially the strip, proved to be sensitive, specific, rapid and easy to use for the quantitative, semi-quantitative or qualitative detection of SM2 residues in swine urine.

Development of a lateral flow colloidal gold immunoassay strip for the rapid detection of enrofloxacin residues.

A rapid immunochromatographic lateral flow test strip of competitive format has been developed using a gold-conjugated monoclonal antibody for the specific determination of enrofloxacin (ENR) residues in chicken muscles. For this purpose, a specific monoclonal antibody (mAb) for ENR was generated and characterized. The mAb showed negligible cross-reactivity with other related compounds. Using ENR standards prepared in chicken muscle extracts from 0 to 24.3 ng/mL (microg/kg), the method indicated that the detection limit of the test strip, as measured in a strip scanner, was as low as 0.138 microg/kg of ENR and the half-maximal inhibition concentration (IC(50)) was 0.935 microg/kg. For samples spiked at 10, 20, and 30 microg/kg, the recovery was between 85.3 and 96.1% and the coefficient of variation [CV (%)] was between 4.5 and 7.91%. Parallel analysis of muscle samples from chickens fed ENR showed good comparable results obtained from the test strip and LC-MS. Each test requires 5-10 min. The data indicate that the method has high sensitivity, specificity, and the advantages of simplicity and speed of performance. Therefore, the test strip provides a useful screening method for quantitative, semiquantitative, or qualitative detection of ENR residues in chicken muscles.