A5008459412- Medical Image Segmentation Techniques
- Advanced Memory and Neural Computing
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Retinal Imaging and Analysis
- Advanced Image Fusion Techniques
- Neural dynamics and brain function
- Image Enhancement Techniques
- Artificial Intelligence in Healthcare
- Video Surveillance and Tracking Methods
- Ferroelectric and Negative Capacitance Devices
- AI in cancer detection
- COVID-19 diagnosis using AI
- Adversarial Robustness in Machine Learning
- Cardiovascular Health and Disease Prevention
- CCD and CMOS Imaging Sensors
- Physical Unclonable Functions (PUFs) and Hardware Security
- Advanced Chemical Sensor Technologies
- Interconnection Networks and Systems
- Parallel Computing and Optimization Techniques
- Hepatocellular Carcinoma Treatment and Prognosis
- Medical Imaging Techniques and Applications
- Medical Imaging and Analysis
- Digital Imaging for Blood Diseases
Technology Innovation Institute
2022-2024
Aarhus University
2021-2022
University of Córdoba
2019-2020
Indian Institute of Science Bangalore
2015
Birla Institute of Technology and Science, Pilani
2012
Pruning for Spiking Neural Networks (SNNs) has emerged as a fundamental methodology deploying deep SNNs on resource-constrained edge devices. Though the existing pruning methods can provide extremely high weight sparsity SNNs, brings workload imbalance problem. Specifically, happens when different number of non-zero weights are assigned to hardware units running in parallel. This results low utilization and thus imposes longer latency higher energy costs. In preliminary experiments, we show...
Tumor segmentation in Computed Tomography (CT) images is a crucial step image-guided surgery. However, low-contrast CT impede the performance of subsequent tasks. Contrast enhancement then used as preprocessing to highlight relevant structures, thus facilitating not only medical diagnosis but also image with higher accuracy. In this paper, we propose goal-oriented contrast method improve tumor performance. The proposed based on two concepts, namely guided and quality control through an...
Radial Basis Function Neural Networks (RBFNN) are used in variety of applications such as pattern recognition, control and time series prediction nonlinear identification. RBFNN with Gaussian the basis function is considered for classification purpose. Training done offline using K-means clustering method center learning Pseudo inverse weight adjustments. Offline training since objective any fixed set weights can be computed we see whether make progress training. Moreover, minimum to desired...
Object tracking has many applications like security and surveillance, traffic control others. In this Paper new methodology been proposed which uses tabu search algorithm along with joint color texture histogram to track object. Texture featurelike edges corners are extracted using uniform linear binary pattern, will help in increasing the robustness of object be tracked. After features battacharyya coefficient is calculated measure similarity between target's raw feature previous frame...
Fog computing is a key solution for internet of things (IoT) applications, which demands operational security, real-time and power efficient intelligent responses, low bandwidth usage. This paper introduces novel idea related to an hardware implementation High-performance classifiers sensor data analytic on the edge gateway running smart automobile. The high-performance uses artificial neural network (ANN) extract conclusive inferences from raw automotive sensors information. multiple are...
Obtaining rapid and accurate segmentation of organs remains an important challenging task. Liver algorithms are slow inaccurate due to noise low-quality images from abdominal computed tomography (CT) scans. Chan- Vese is image method with great robustness against noise, however it quite the computation complex partial differential equations, especially for large medical data sets. The very low contrast liver obtained by CT reduces overall quality segmentation. In this work we propose two...
Good blood vessel segmentation in medical imaging is critical during surgery. We propose a parallelized region growth algorithm (pSRG) computing the gradient using Persistence and grid-stride loops. This approach avoids unnecessary memory transfers. As result, addition to faster computation, we obtain more accurate segmentation.