Hao-Yun Chang

ORCID: 0000-0003-0683-3401
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Brain Tumor Detection and Classification
  • Energy Efficient Wireless Sensor Networks
  • Context-Aware Activity Recognition Systems
  • Radiomics and Machine Learning in Medical Imaging
  • Interactive and Immersive Displays
  • Computer Graphics and Visualization Techniques
  • Advanced Photonic Communication Systems
  • Advanced Neural Network Applications
  • Augmented Reality Applications
  • Advanced Fiber Laser Technologies
  • Dental Radiography and Imaging
  • Advanced X-ray and CT Imaging
  • Vascular Malformations Diagnosis and Treatment
  • Radiation Effects in Electronics
  • Optical Network Technologies
  • Glioma Diagnosis and Treatment
  • Modular Robots and Swarm Intelligence
  • Medical Imaging and Analysis

National Yang Ming Chiao Tung University
2024

National Ilan University
2021

National Taiwan University
1999-2021

National United University
2016

Chung Hua University
2013

Dentists and medical personnel strive to provide patients with prompt services. In the past, Dental Panoramic Radiograph (DPR) was often used diagnose understand dental condition of patients. recent years, many machine learning deep methods have been applied image recognition problems. Moreover, when combined methods, data augmentation pre-processing can also give positive feedback. This study aims combine advanced build an innovative practical two-phase DPR classification method assist...

10.1109/access.2021.3136026 article EN cc-by IEEE Access 2021-01-01

Semantic segmentation of medical images with deep learning models is rapidly being developed. In this study, we benchmarked state-of-the-art algorithms on our clinical stereotactic radiosurgery dataset. The dataset consists 1688 patients various brain lesions (pituitary tumors, meningioma, schwannoma, metastases, arteriovenous malformation, and trigeminal neuralgia), divided the into a training set (1557 patients) test (131 patients). This study demonstrates strengths weaknesses...

10.3390/app11199180 article EN cc-by Applied Sciences 2021-10-02

10.1109/icip51287.2024.10647290 article EN 2022 IEEE International Conference on Image Processing (ICIP) 2024-09-27

A chirped-fibre-grating-based erbium-doped optical limiting amplifier (CFG-OLA) is experimentally demonstrated. Both high constant output power of >15 dBm with large dynamic range dB and dispersion compensation capability can be achieved simultaneously in a 10 Gbit/s standard (G.652) singlemode fibre link 80 km. satisfactory penalty obtained when the CFG-OLAs are used as in-line amplifiers.

10.1049/el:19990435 article EN Electronics Letters 1999-04-15

As the development of Internet Things (IoT) is increasingly emphasized, how to adopt interconnected sensors and devices in conjunction with situation-awareness based system smarten living applications has paid great attentions. On a multiple-units connected environment, scheme event-condition-action (ECA) frequently used serve automatic operation functions light defined rules. According previous works, ECA approach was often adopted IC designs but less applied advancing human-centered IoT...

10.1109/ics.2016.0114 article EN 2016-12-01

A Patrol is important for the safety of a building or factory. While sensors are becoming more popular, there trend integration and patrol. How to effectively efficiently facilitate patrol in advantage context-aware environment formed by interconnecting these wireless networks becomes an issue. In this paper we present mechanism which route deduced according context information acquired from so that possible hazardous condition can be either avoided damage diminished. The analyzed...

10.1109/compsacw.2013.42 article EN 2013-07-01

Semantic segmentation of medical images with deep learning models is rapidly developed. In this study, we benchmarked state-of-the-art algorithms on our clinical stereotactic radiosurgery dataset, demonstrating the strengths and weaknesses these in a fairly practical scenario. particular, compared model performances respect to their sampling method, architecture, choice loss functions, identifying suitable settings for applications shedding light possible improvements.

10.48550/arxiv.2007.11784 preprint EN other-oa arXiv (Cornell University) 2020-01-01
Coming Soon ...