98047 research outputs found
Sort by
Analysis of Public Intentions and Perceptions of Physical-Mental Health Regarding Taipei Mass Rapid Transit Usage in the Post-Pandemic Era
No full text新冠疫情導致臺北捷運系統旅運量跌破日均200萬人次，本研究採用計畫行為理論，透過問卷調查蒐集資料，以統計檢定、結構方程式等方法探討民眾在後疫情時期的自我態度、主觀規範、感知行為控制、身心健康感知、防疫資訊接收態度等五大構面，是否影響搭乘捷運的意圖與行為。模式分析結果顯示，自我態度、感知行為控制、身心健康感知等構面具有顯著影響，若干疫情高風險族群或是身心健康、家庭經濟與親友受疫情衝擊較大之民眾，搭乘捷運的正向態度與感知偏低，經濟弱勢族群搭乘捷運更可能伴隨著焦慮感。連同都會區各種競合運具發展變化、人口下滑暨其他外部綜合因素，約可回應臺北捷運迄今未能恢復疫情之前的旅運量水準。文末建議交通部門除了透過多元方式推廣大眾運輸外，各界也須從疫情經驗中學習應變與適應力，短期仍應重視疫情的心理衝擊、中長期則有待捷運路網持續擴充，捷運旅運量方能逐步回升。補正完畢TW
Reversible data hiding with multi-round prediction and subsampling concepts
No full textReversible data hiding has attracted attention in recent years due to the capability of reversibility and the ease of implementation. With the consideration of manipulating difference values corresponding to original image, more amount of secret data can be embedded to compare to conventional schemes. By taking inherent characteristics of original image into account, subsampling techniques can be applied for reversible data hiding with a variety of combinations to enhance security. With the execution by taking the reverse order, both original and secret information can be extracted to guarantee the reversibility. Simulation results present the effectiveness of proposed method.補正完畢國際Bangkok, ThailandTH
Strategic Integration of Attention Modules in Object Detection: A Study on Regurgitation Echocardiography Dataset
No full textSeveral attention modules—such as SENet, CBAM, and SimAM—have been successfully applied in image classification tasks and could be integrated into object detection frameworks like YOLOv5, YOLOv7, and YOLOv9. However, the optimal insertion point within these detection architectures—whether in the backbone, neck, or head—remains an open question. In this study, we systematically investigate the effects of incorporating attention modules at various network locations. Experiments conducted on a regurgitation dataset of echocardiography images demonstrate that strategically inserting attention modules significantly improves performance, as measured by the mAP50 metric. Notably, the CBAM module proves particularly effective for the task at hand.補正完畢國際Tokyo, JapanJP
Exploring genetic programming in image processing: Challenges and enhanced techniques
No full textIn recent years, the advancement of AI has been primarily driven by neural networks, which, despite their success, pose challenges in terms of explainability and high-power consumption. Genetic Programming (GP) offers an interpretable alternative, although its complexity has limited its practical application. This paper explores the potential of GP through experiments on a simple image filtering task, aiming to understand its properties and limitations. We also investigate the integration of transformer concepts into the GP process. Preliminary results suggest that while GP faces convergence challenges, the introduction of symbolic transformers may enhance its effectiveness in image processing tasks. These findings open up new possibilities for optimizing GP in future applications.補正完畢國際Bangkok, ThailandTH
Promoting English as a Lingua Franca with“ Russian Doll”MOOCs Design for Senior High School Students: Analytics of the Bilingual Online Coaching Model
No full text補正完畢國內台中市，台灣TW
