A5005708914- Medical Image Segmentation Techniques
- Robot Manipulation and Learning
- Advanced Neural Network Applications
- Machine Fault Diagnosis Techniques
- Mineral Processing and Grinding
- Fault Detection and Control Systems
- Pediatric Urology and Nephrology Studies
- Optical Systems and Laser Technology
- Engineering Diagnostics and Reliability
- Robotics and Sensor-Based Localization
- Advanced MRI Techniques and Applications
- Brain Tumor Detection and Classification
- Hand Gesture Recognition Systems
- Urological Disorders and Treatments
- Advanced Surface Polishing Techniques
- Kidney Stones and Urolithiasis Treatments
- Fetal and Pediatric Neurological Disorders
- Oil and Gas Production Techniques
- Soft Robotics and Applications
- Metallurgical Processes and Thermodynamics
- Image and Video Stabilization
Dongguk University
2021
Hanyang University
2019-2020
Hyundai Research Institute
2012
Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has highest accuracy, it a time-consuming task. Therefore, various automatic algorithms MRI have been devised and proposed previously. However, there still no method that solves entire extraction problem satisfactorily for diverse datasets generic robust way. To address these shortcomings existing methods, we propose use 3D-UNet skull MRI. The was...
Skull stripping in brain magnetic resonance volume has recently been attracting attention due to an increased demand develop efficient, accurate, and general algorithm for diverse datasets of the brain. Accurate skull is a critical step neuroimaging diagnostic systems because neither inclusion non-brain tissues nor removal parts can be corrected subsequent steps, which results unfixed error through analysis. The objective this review article give comprehensive overview approaches, including...
As failures in rotating machines can have serious implications, the timely detection and diagnosis of faults these is imperative for their smooth safe operation. Although deep learning offers advantage autonomously fault characteristics from data, data scarcity different health states often limits its applicability to only binary classification (healthy or faulty). This work proposes synthetic augmentation through virtual sensors learning-based a machine with 42 classes. The original...
Due to growing electricity demand, developing an efficient fault-detection system in thermal power plants (TPPs) has become a demanding issue. The most probable reason for failure TPPs is equipment (boiler and turbine) fault. Advance detection of fault can help secure maintenance shutdowns enhance the capacity utilization rates equipment. Recently, intelligent diagnosis based on multivariate algorithms been introduced TPPs. In TPPs, huge number sensors are used process maintenance. However,...
To evaluate the impact of temporary internal ureteral stents on surgical outcomes dismembered pyeloplasty in children.The medical records 70 children (76 renal units) who underwent for ureteropelvic junction (UPJ) obstruction at Asan Medical Center between January 2005 and December 2010 were retrospectively reviewed. We classified units into stented group (22 nonstented (54 units). Fifty-four patients male their mean age was 2.2±3.8 years old. The follow-up period 29.6±16.8 months.Sixty-four...
Many industrial robots have been applied relatively simple operation that requires repeatable tasks. However, through the rapid development of deep learning with 4 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> revolution, it prospects a role will be extended, and are expected to do task human can do. For example, in service robotics, is being studied about shelf-stocking replenishment many types products such as food or cleaning rooms...
This paper proposes a hybrid singulation approach combining dynamic scattering and pushing techniques. Using the impulse-based model, guideline is provided to decide whether or conducted for object singulation. The Soma cube consisting of seven blocks used as test example. target singulate all blocks. technique was initially applied separate in formation. However, alone does not provide cases. So we combine quasi-static complete In pushing, image segmentation based on principal component...