Search

This article describes STEM education with artificial intelligence (AI) learning, particularly for non-engineering undergraduate students. In the designed three-week learning activities, students were encouraged to put their ideas about AI into practice through two hands-on activities, utilizing a provided deep learning-based web service. This study designed pre-test and post-test surveys to investigate the performance of students in different aspects of AI. With 328 students involved in these learning activities, we discovered from the surveys that the proposed learning method can effectively improve AI literacy among non-engineering students. This study also found that students' AI literacy correlated significantly with their awareness of AI ethical issues and that the STEM-based AI curriculum increased the awareness of AI ethical issues among low-AI-literate learners. This article discusses the association between learning activities and different aspects of AI learning. The proposed method can be used by teachers who want to introduce AI knowledge into general education courses.

For the advancement of smart grids, solar power generation predictions have become an important research topic. In the case of using traditional modeling methods, excessive computational costs may be incurred and it is difficult for these methods to learn the multi-variable dependencies of the data. Therefore, in this paper, a deep learning model was used to combine convolutional neural networks and long short-term memory recurrent network predictions. This method enables hourly power generation one day into the future. Convolutional neural networks are used to extract the features of multiple time series, while long short-term memory neural networks predict multivariate outcomes simultaneously. In order to obtain more accurate prediction results, we performed feature selection on meteorological features and combined the selected weather features to train the prediction model. We further distinguished sunny- and rainy-day models according to the predicted daily rainfall conditions. In the experiment, it was shown that the method of combining meteorological features further reduced the error. Finally, taking into account the differences in climate conditions between the northern and southern regions of Taiwan, the experimental results of case studies involving multiple regions were evaluated to verify the proposed method. The results showed that training combined with selected meteorological features can be widely used in regions with different climates in Taiwan. [ABSTRACT FROM AUTHOR]

Extracting the flight trajectory of the shuttlecock in a single turn in badminton games is important for automated sports analytics. This study proposes a novel method to extract shots in badminton games from a monocular camera. First, TrackNet, a deep neural network designed for tracking small objects, is used to extract the flight trajectory of the shuttlecock. Second, the YOLOv7 model is used to identify whether the player is swinging. As both TrackNet and YOLOv7 may have detection misses and false detections, this study proposes a shot refinement algorithm to obtain the correct hitting moment. By doing so, we can extract shots in rallies and classify the type of shots. Our proposed method achieves an accuracy of 89.7%, a recall rate of 91.3%, and an F1 rate of 90.5% in 69 matches, with 1582 rallies of the Badminton World Federation (BWF) match videos. This is a significant improvement compared to the use of TrackNet alone, which yields 58.8% accuracy, 93.6% recall, and 72.3% F1 score. Furthermore, the accuracy of shot type classification at three different thresholds is 72.1%, 65.4%, and 54.1%. These results are superior to those of TrackNet, demonstrating that our method effectively recognizes different shot types. The experimental results demonstrate the feasibility and validity of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract Background White sweet potato (WSP; Ipomoea batatas L. Simon No. 1) has many potential beneficial effects on metabolic control and diabetes-related insulin resistance. The improvement of insulin resistance by WSP tuber extracts on glucose uptake were not investigated in C2C12 myoblast cells. Results WSP tuberous ethanol extract (WSP-E) was partitioned with ethyl-acetate and water to obtain ethyl-acetate layer (WSP-EA) and water layer (WSP-EW). The WSP-EA shows the highest total phenolic contents and highest antioxidant activity by Folin-Ciocalteu and (2,2-diphenyl-1-picryl-hydrazyl-hydrate, DPPH) assay, respectively. After low concentration horse serum on differentiation inducement of C2C12 myoblasts into mature myotubes, the cells were treated with TNF-α to induce insulin resistance. WSP-EA and WSP-EW extracts increased the uptake of fluorescence glucose analogue (2-[N-(7-nitrobenz-2-oxa-1, 3-diazol-4-yl) amino]-2-deoxy-d-glucose, 2-NBDG) in a dose-dependent manner as examined by flow cytometry. The WSP-EA enhanced glucose uptake by activation of phosphorylation of IR (pIR), IRS-1 (pIRS-1) and Akt (pAkt) involved in PI3K (phosphatidylinositol 3-kinase)/protein kinase B (Akt) pathway, also upregulated glucose transporter 4 (GLUT4) expression in myotubes. Conclusions WSP-EA enhanced the glucose uptake in C2C12 myotubes through upregulating the PI3K/Akt pathway. The in vitro data reveal that WSP tuber extracts has potential applications to improve insulin resistance in diabetes.

Video action recognition is vital in the research area of computer vision. In this paper, we develop a novel model, named Separable ConvNet Spatiotemporal Mixer (SCSM). Our goal is to develop an efficient and lightweight action recognition backbone that can be applied to multi-task models to increase the accuracy and processing speed. The SCSM model uses a new hierarchical spatial compression, employing the spatiotemporal fusion method, consisting of a spatial domain and a temporal domain. The SCSM model maintains the independence of each frame in the spatial domain for feature extraction and fuses the spatiotemporal features in the temporal domain. The architecture can be adapted to different frame rate requirements due to its high scalability. It is suitable to serve as a backbone for multi-task video feature extraction or industrial applications with its low prediction and training costs. According to the experimental results, SCSM has a low number of parameters and low computational complexity, making it highly scalable with strong transfer learning capabilities. The model achieves video action recognition accuracy comparable to state-of-the-art models with a smaller parameter size and fewer computational requirements. [ABSTRACT FROM AUTHOR]

Avian influenza virus (AIV) can cause severe diseases in poultry worldwide. H6N1 AIV was the dominant enzootic subtype in 1985 in the chicken farms of Taiwan until the initial outbreak of a low pathogenic avian influenza (LPAI) H5N2 virus in 2003; thereafter, this and other LPAIs have been sporadically detected. In 2015, the outbreak of three novel H5Nx viruses of highly pathogenic avian influenza (HPAI) emerged and devastated Taiwanese chicken and waterfowl industries. The mechanism of variation in pathogenicity among these viruses is unclear; but, in light of the many biological functions of viral non-structural protein 1 (NS1), including interferon (IFN) antagonist and host range determinant, we hypothesized that NS genetic diversity contributes to AIV pathogenesis. To determine the impact of NS1 variants on viral infection dynamics, we established a reverse genetics system with the genetic backbone of the enzootic Taiwanese H6N1 for generation of reassortant AIVs carrying exogenous NS segments of three different Taiwanese H5N2 strains. We observed distinct cellular distributions of NS1 among the reassortant viruses. Moreover, exchange of the NS segment significantly influenced growth kinetics and induction of cytokines [IFN-α, IFN-β, and tumor necrosis factor alpha (TNF-α)] in an NS1- and host-specific manner. The impact of NS1 variants on viral replication appears related to their synergic effects on viral RNA-dependent RNA polymerase activity and IFN response. With these approaches, we revealed that NS1 is a key factor responsible for the diverse characteristics of AIVs in Taiwan.

Average Motion Energy (AME) image is a good way to describe human motions. However, it has to face the computation efficiency problem with the increasing number of database templates. In this paper, we propose a histogram-based approach to improve the computation efficiency. We convert the human action/gait recognition problem to a histogram matching problem. In order to speed up the recognition process, we adopt a multiresolution structure on the Motion Energy Histogram (MEH). To utilize the multiresolution structure more efficiently, we propose an automated uneven partitioning method which is achieved by utilizing the quadtree decomposition results of MEH. In that case, the computation time is only relevant to the number of partitioned histogram bins, which is much less than the AME method. Two applications, action recognition and gait classification, are conducted in the experiments to demonstrate the feasibility and validity of the proposed approach.

A GaN-based light-emitting diode (LED) grown on a nanocomb-shaped patterned sapphire substrate (PSS) is fabricated and studied. Nanocomb-shaped patterns are transferred on a sapphire substrate using a well-ordered anodized aluminum oxide (AAO) thin film as a mask for the inductively coupled plasma etching process. This well-ordered AAO thin film with a high aspect ratio is grown on a sapphire substrate by an oxalic acid-based electrochemical system and a three-step anodization. The strain state generated during epitaxial growth could be effectively alleviated by the use of nanocomb-shaped PSS. The treading dislocation density could be reduced. Thus, the enhanced crystalline quality is obtained. In addition, due to the presence of photonic crystal-like air buffer layer, part of reflected photons upward the top side could be scattered by this layer. Therefore, more photons could be extracted outside. Experimentally, at 20 mA, as compared with a conventional LED grown on a planar sapphire substrate, the studied LED grown on a nanocomb-shaped PSS shows 53.8% and 43.7% enhancements in light output power and external quantum efficiency as well as a reduced leakage current. [ABSTRACT FROM AUTHOR]