A5042359557- Soft Robotics and Applications
- Micro and Nano Robotics
- Fault Detection and Control Systems
- Robot Manipulation and Learning
- Advanced Sensor and Energy Harvesting Materials
- Underwater Vehicles and Communication Systems
- Anomaly Detection Techniques and Applications
- Global Cancer Incidence and Screening
- Geotechnical Engineering and Analysis
- ECG Monitoring and Analysis
- Control Systems and Identification
- Structural Engineering and Vibration Analysis
- Analytical Chemistry and Sensors
- Rough Sets and Fuzzy Logic
- Target Tracking and Data Fusion in Sensor Networks
- Manufacturing Process and Optimization
- AI in cancer detection
- Adversarial Robustness in Machine Learning
- BIM and Construction Integration
- Digital Radiography and Breast Imaging
- Geotechnical Engineering and Underground Structures
- Advanced Computing and Algorithms
- Structural Engineering and Materials Analysis
Monash University Malaysia
2019-2025
Air Force Engineering University
2011
Sensory data are critical for soft robot perception. However, integrating sensors to robots remains challenging due their inherent softness. An alternative approach is indirect sensing through an estimation scheme, which uses dynamics and available measurements estimate variables that would have been measured by sensors. Nevertheless, developing adequately effective scheme not straightforward. First, it requires a mathematical model; modeling of analytically demanding complex dynamics....
The mechanical compliance of soft robots comes at a cost higher uncertainty in their sensing and perception, which deteriorates the accuracy predictive models. Predictive uncertainty, expresses confidence behind model predictions, is necessary to compensate for loss robot perceptive Nevertheless, developing general framework capture uncertainties further challenged by complex dynamics difficulties sensorizing them. In this work, we present estimation based on deep learning multimodal...
Soft sensors are widely used in many industrial systems to monitor key variables that difficult measure, using measurements from other available physical sensors. Because susceptible faults, it is crucial for soft sensor models be robust against them. Recently, deep learning has shown promising results developing data-driven various applications. However, existing learning-based still vulnerable which could deteriorate the performance of models. In this article, we propose a modeling...
Data-driven methods with deep neural networks demonstrate promising results for accurate modeling in soft robots. However, network models rely on voluminous data discovering the complex and nonlinear representations inherent Consequently, while it is not always possible, a substantial amount of effort required acquisition, labeling, annotation. This article introduces data-driven learning framework based synthetic to circumvent exhaustive collection process. More specifically, we propose...
Introduction For women of the same age and body mass index, increased mammographic density is one strongest predictors breast cancer risk. There are multiple methods measuring other features in a mammogram that could potentially be used screening setting to identify target at high risk developing cancer. However, it unclear which measurement method provides predictor Methods analysis The challenge has been established as an international resource offer common set anonymised images for...
Sensory data such as bending curvature and contact force are essential for controlling soft robots. However, it is inconvenient to measure these variables because sensorizing robots difficult due their inherent softness. An attractive alternative use an observer/filter estimate the that would have been measured by those sensors. Nevertheless, requires a model which can be analytically demanding high nonlinearity. In this paper, we propose Unknown Input Extended Kalman Filter (UI-EKF)...
The Coronary Heart Disease (CHD) is the most common cardiovascular disease due to risk of heart-related complications. Currently, pulse diagnosis in Chinese medicine an important method recognition tool CHD. Here we designed signal acquisition and system based on pressure sensors. sensing units utilized ionic gel-based Combined with circuit board convolution neural networks, was established identify This developed provides idea for CHD homes middle-aged elderly people, accelerated...
A note from Melanie Ooi: Soft robotics is a very new and interesting research area with many applications, sensing in soft robots remains big challenge. Our guest columnists Monash University Malaysia, Dr. Chee Pin Tan Surya Nurzaman, have expertise state estimation robotics, respectively. Together their graduate students, they share us how can be used for indirect robots, thus contributing solution to this long-standing challenge of enabling robots.
To solve the problem of lacking inferential evidence which exists in state transition battlefield situation Bayesian net, methodology based on rough sets and net is proposed. Furthermore, method getting causal intensity decision table to calculate confidence degree corresponding node researched, modified by non-redundant attribute value. Finally, inference discussed detail. And a case study anti-air operation given verify correctness validity proposed method.