-
Chapter and Conference Paper
Multi-physical Field Collaborative Simulation Optimization Technology and Reliability Analysis of Power Amplifiers
As the core RF front-end device of wireless communication systems, the performance of millimeter wave power amplifier chips determines the communication distance/quality of the system. In order to improve the ...
-
Chapter and Conference Paper
Real-Time Automated Body Condition Scoring of Dairy Cows
Traditional management and farming of dairy cows have relied primarily on human labor and experience. However, this approach has limitations such as the lack of real-time monitoring and predictive capabilities...
-
Chapter and Conference Paper
Distributed Deep Learning for Big Remote Sensing Data Processing on Apache Spark: Geological Remote Sensing Interpretation as a Case Study
The advent of sensor technologies has led to the sheer amount volume of remote sensing data containing fruitful spatial and spectral information. Insights into Earth’s surface’s objects are gained with the hel...
-
Chapter and Conference Paper
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been pro...
-
Chapter and Conference Paper
Application of New Light and High Strength Materials in Prefabricated Buildings
The application of new lightweight high-strength materials in prefabricated buildings refers to the application of new lightweight high-strength materials such as aluminum, steel or other metal structures in b...
-
Chapter and Conference Paper
Wetland Challenge—Using Service Design Research as an Approach to Establish an AR APP for Environmental Education
Given the looming threat of catastrophic environmental disasters, there has never been a more urgent need for establishing awareness of the importance of sustainable environments through environmental educatio...
-
Chapter and Conference Paper
Exploring Opportunities for Visualization-Based Information Translation in Environmental Education: Using Taiwan’s Chenglong Wetland as an Example
Global climate change has caused environmental and ecological anomalies and alterations, including catastrophes caused by climatic variations in the greater environment, the severity of disasters being affecte...
-
Chapter and Conference Paper
Tree-Based Unified Temporal Erasable-Itemset Mining
Erasable itemset mining is an important research area for manufacturers, as it aids in identifying less profitable materials in product datasets to facilitate better decision-making for managers. It allows for...
-
Chapter and Conference Paper
Develo** an Emotional Interaction Design for Social Anxiety Disorders (SAD)
This study focuses on using books in libraries as an interactive medium, aiming to help individuals with social anxiety disorder alleviate their anxiety and establish positive social experiences. The research ...
-
Chapter and Conference Paper
The Similarities and Differences of Thanks Responses between Native Speakers and Mandarin Teaching Materials in Taiwan
There is growing research on thanks responses in linguistics. However, there are still research gaps on thanks responses in varieties of Mandarin Chinese. To explore the similarities and differences between th...
-
Chapter and Conference Paper
Fingerprint Indexing with Minutiae-Aided Fingerprint Multiscale Representation
The huge fingerprint database limits the speed of large-scale fingerprint identification, which can be alleviated by fingerprint indexing. The previous fixed-length representation used for fingerprint indexing...
-
Chapter and Conference Paper
An UNet-Based Brain Tumor Segmentation Framework via Optimal Mass Transportation Pre-processing
This article aims to build a framework for MRI images of brain tumor segmentation using the deep learning method. For this purpose, we develop a novel 2-Phase UNet-based OMT framework to increase the ratio of ...
-
Chapter and Conference Paper
Lightweight Image Dehazing Neural Network Model Based on Estimating Medium Transmission Map by Intensity
Single image dehazing is a challenging ill-posed problem. The key to achieve haze removal is to estimate an accurate medium transmission map. By redefining the atmospheric scattering model, we obtain a new tra...
-
Chapter and Conference Paper
OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark Under Heterogeneous AI Computing Platforms
In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platform...
-
Chapter and Conference Paper
Offline Handwritten Mathematical Expression Recognition via Graph Reasoning Network
Handwritten mathematical expression recognition (HMER) remains a challenge due to the complex 2-D structure layout and variable writing styles. Recently, large progress has been made by using deep encoder-deco...
-
Chapter and Conference Paper
Learning Instance-Specific Adaptation for Cross-Domain Segmentation
We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conducting instance-specific BatchN...
-
Chapter and Conference Paper
Temporally Consistent Semantic Video Editing
Generative adversarial networks (GANs) have demonstrated impressive image generation quality and semantic editing capability of real images, e.g., changing object classes, modifying attributes, or transferring...
-
Chapter and Conference Paper
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Videos are created to express emotion, exchange information, and share experiences. Video synthesis has intrigued researchers for a long time. Despite the rapid progress driven by advances in visual synthesis,...
-
Chapter and Conference Paper
A Two-Phase Optimal Mass Transportation Technique for 3D Brain Tumor Detection and Segmentation
The goal of optimal mass transportation (OMT) is to transform any irregular 3D object (i.e., a brain image) into a cube without creating significant distortion, which is utilized to preprocess irregular brain ...
-
Chapter and Conference Paper
On Efficiency of Fully Probing Mechanisms in Nonogram Solving Algorithm
Fully probing plays an important role in the nonogram solving algorithm developed by Wu et al., whose implementation, named LalaFrogKK, has won several nonogram tournaments since 2011. Different fully probing met...