Explore the vast range of titles available.

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.

Electrochemical research has been developing with the advancement of laboratory equipment and sophisticated technologies. One of which is the portable potentiostat, which has been utilized to analyze various samples and help characterize their electrochemical properties. In this paper, we propose a comprehensive design and modular analysis of our proposed potentiostat called GaneStat. The proposed potentiostat has a low cost, portable, and high accuracy with battery-powered and electrical overstress circuit protection. The proposed analog front end of the potentiostat consists of several modules such as unipolar-to-bipolar converter (UBC), buffer, current-to-voltage converter (CVC), bipolar-to-unipolar converter (BUC), two-stage sallen key low-pass filter, and ADC input protection unit (AIPC). A maximum wide dynamic range of 98.95 dB provides flexibility in terms of current measurement. The potentiostat is also equipped with a dedicated power management circuit and an overstress protection circuit. Multi mode measurements are provided in our system for Cyclic voltammetry (CV), differential pulse voltammetry (DPV), Linear Sweep Voltammetry (LSV), and Chronoamperometry (CA) experiments with preliminary test on redox probe solution to validate the performance of the device. The final design occupies relatively small space of 6.95cm × 6.85 cm × 3.26 cm with 83.1 gr of weight, including the battery and the case. The potentiostat operates with sweep voltage within ±2.5 V with a 1.2 mV resolution, and it can measure current from 10 nA to 10 mA with 0.53 nA and 0.3 μ A resolutions, respectively. The potentiostat costs only $98.55 for the prototyping. This work is useful for laboratory applications in chemical, pharmacy and medical industries.

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.

This study presents a new blended learning model that combines a computer-assisted learning system called Cognitive Apprenticeship Programming Learning System (CAPLS) with instructor co-teaching in an introductory programming course. CAPLS, as its unique aspect, functions as a master in cognitive apprenticeship, guiding learners throughout their learning while also assessing their progress. In contrast, the instructor in physical class settings serves a supportive role, monitoring progress and articulating as needed to fill knowledge gaps. To investigate the impact of this learning model on students' motivation, we used the Motivated Strategies for Learning Questionnaire (MSLQ) at the beginning and end of the semester. College Entrance Math score, midterm and final exams were also used to assess student learning outcomes. The study was conducted with first-year students in the Department of Information and Computer Engineering, and two key findings emerged. First, students' programming proficiency was strongly correlated with their College Entrance Math scores. While math ability impacted programming learning, all students improved their final scores compared to their midterms, with high-scoring math students outperforming their peers. Second, the proposed blended cognitive teaching strategy significantly reduced students' extrinsic goal and self-efficacy levels, but their learning outcomes still significantly improved. This suggests that the proposed teaching model promotes more conscious learning. These results can be used as a reference for improving student learning outcomes and experiences with computer-assisted learning systems.

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.

Advancements in satellite and aerial imagery technology have made it easier to obtain high-resolution remote sensing images, leading to widespread research and applications in various fields. Remote sensing image semantic segmentation is a crucial task that provides semantic and localization information for target objects. In addition to the large-scale variation issues common in most semantic segmentation datasets, aerial images present unique challenges, including high background complexity and imbalanced foreground–background ratios. However, general semantic segmentation methods primarily address scale variations in natural scenes and often neglect the specific challenges in remote sensing images, such as inadequate foreground modeling. In this paper, we present a foreground-aware remote sensing semantic segmentation model. The model introduces a multi-scale convolutional attention mechanism and utilizes a feature pyramid network architecture to extract multi-scale features, addressing the multi-scale problem. Additionally, we introduce a Foreground–Scene Relation Module to mitigate false alarms. The model enhances the foreground features by modeling the relationship between the foreground and the scene. In the loss function, a Soft Focal Loss is employed to focus on foreground samples during training, alleviating the foreground–background imbalance issue. Experimental results indicate that our proposed method outperforms current state-of-the-art general semantic segmentation methods and transformer-based methods on the LS dataset benchmark.

Learning about artificial intelligence (AI) has become one of the most discussed topics in the field of education. However, it has become an equally important learning approach in contemporary education to propose a “general education” agenda that conveys instructional messages about AI basics and ethics, especially for those students without an engineering background. The current study proposes a situated learning design for education on this topic. Through a three-week lesson session and accompanying learning activities, the participants undertook hands-on tasks relating to AI. They were also afforded the opportunity to learn about the current attributes of AI and how these may apply to understanding AI-related ethical issues or problems in daily life. A pre- and post-test design was used to compare the learning effects with respect to different aspects of AI (e.g., AI understanding, cross-domain teamwork, AI attitudes, and AI ethics) among the participants. The study found a positive correlation among all the factors, as well as a strong link between AI understanding and attitudes on the one hand and AI ethics on the other. The implications of these findings are discussed, and suggestions are made for possible future revisions to current instructional design and for future research.

In this study, we realize acoustic aggregation and separation of microparticles in fluid channels driven by standing Lamb waves of a 300-μm-thick double-side polished lithium-niobate (LiNbO3) plate. We demonstrate that the counter-propagating lowest-order antisymmetric and symmetric Lamb modes can be excited by double interdigitated transducers on the LiNbO3 plate to produce interfacial coupling with the fluid in channels. Consequently, the solid–fluid coupling generates radiative acoustic pressure and streaming fields to actuate controlled acoustophoretic motion of particles by means of acoustic radiation and Stokes drag forces. We conducted finite-element simulations based on the acoustic perturbation theory with full-wave modeling to tailor the acoustic and streaming fields in the channels driven by the standing Lamb waves. As a result, the acoustic process and the mechanism of particle aggregation and separation were elucidated. Experiments on acoustic manipulation of particles in channels validate the capability of aggregation and separation by the designed devices. It is observed that strong streaming dominates the particle aggregation while the acoustic radiation force differentially expels particles with different sizes from pressure antinodes to achieve continuous particle separation. This study paves the way for Lamb-wave acoustofluidics and may trigger more innovative acoustofluidic systems driven by Lamb waves and other manipulating approaches incorporated on a thin-plate platform.

This paper presents a system applied to unmanned aerial vehicles based on Robot Operating Systems (ROSs). The study addresses the challenges of efficient object detection and real-time target tracking for unmanned aerial vehicles. The system utilizes a pruned YOLOv4 architecture for fast object detection and the SiamMask model for continuous target tracking. A Proportional Integral Derivative (PID) module adjusts the flight attitude, enabling stable target tracking automatically in indoor and outdoor environments. The contributions of this work include exploring the feasibility of pruning existing models systematically to construct a real-time detection and tracking system for drone control with very limited computational resources. Experiments validate the system’s feasibility, demonstrating efficient object detection, accurate target tracking, and effective attitude control. This ROS-based system contributes to advancing UAV technology in real-world environments.

While the use of deep neural networks is popular for predicting students’ learning outcomes, convolutional neural network (CNN)-based methods are used more often. Such methods require numerous features, training data, or multiple models to achieve week-by-week predictions. However, many current learning management systems (LMSs) operated by colleges cannot provide adequate information. To make the system more feasible, this article proposes a recurrent neural network (RNN)-based framework to identify at-risk students who might fail the course using only a few common learning features. RNN-based methods can be more effective than CNN-based methods in identifying at-risk students due to their ability to memorize time-series features. The data used in this study were collected from an online course that teaches artificial intelligence (AI) at a university in northern Taiwan. Common features, such as the number of logins, number of posts and number of homework assignments submitted, are considered to train the model. This study compares the prediction results of the RNN model with the following conventional machine learning models: logistic regression, support vector machines, decision trees and random forests. This work also compares the performance of the RNN model with two neural network-based models: the multi-layer perceptron (MLP) and a CNN-based model. The experimental results demonstrate that the RNN model used in this study is better than conventional machine learning models and the MLP in terms of F-score, while achieving similar performance to the CNN-based model with fewer parameters. Our study shows that the designed RNN model can identify at-risk students once one-third of the semester has passed. Some future directions are also discussed.