A5071123496- Advanced Memory and Neural Computing
- Neuroscience and Neural Engineering
- CCD and CMOS Imaging Sensors
- Neural dynamics and brain function
- Neural Networks and Applications
- Ferroelectric and Negative Capacitance Devices
- Smart Agriculture and AI
- Spam and Phishing Detection
- Interconnection Networks and Systems
- Sentiment Analysis and Opinion Mining
- Image Retrieval and Classification Techniques
- Artificial Intelligence in Healthcare
- Emotion and Mood Recognition
- Advanced Numerical Analysis Techniques
- Photoreceptor and optogenetics research
- Neural Networks and Reservoir Computing
- Remote-Sensing Image Classification
- AI in cancer detection
- Image and Object Detection Techniques
- ECG Monitoring and Analysis
- Machine Learning and ELM
- Advanced Image and Video Retrieval Techniques
- Misinformation and Its Impacts
- Robotics and Automated Systems
- Transport Systems and Technology
MIT Academy of Engineering
2022-2025
MIT Art, Design and Technology University
2022-2025
Koneru Lakshmaiah Education Foundation
2019-2024
Université de Bretagne Sud
2024
Indian Institute of Technology Madras
2023-2024
University of California, Santa Barbara
2023
Dr. D. Y. Patil Medical College, Hospital and Research Centre
2021
Imec the Netherlands
2018-2020
Ollscoil na Gaillimhe – University of Galway
2009-2016
Spiking neural networks (SNNs) attempt to emulate information processing in the mammalian brain based on massively parallel arrays of neurons that communicate via spike events. SNNs offer possibility implement embedded neuromorphic circuits, with high parallelism and low power consumption compared traditional von Neumann computer paradigms. Nevertheless, lack modularity poor connectivity shown by neuron interconnect implementations shared bus topologies is prohibiting scalable hardware SNNs....
Liver disease diagnosis is a major medical challenge in developing nations. Every year around 30 billion people face liver failure issues resulting their death. The past abnormality detection models have faced less accuracy and high theory of constraint metrics. lesion on the hasn't been identified clearly with earlier models, so an advanced, efficient, effective essential. To overcome limitations existing this approach proposes deep DenseNet convolutional neural network (CNN) based learning...
Heart activity can be monitored by means of ElectroCardioGram (ECG) measure which is widely used to detect heart diseases due its non-invasive nature. Trained cardiologists anomalies visual inspecting recordings the ECG signals. However, arrhythmias occur intermittently especially in early stages and therefore they missed routine check recordings. We propose a hardware setup that enables always-on monitoring signals into wearables. The system exploits fully event-driven approach for carrying...
Heartbeat classification using electrocardiogram (ECG) data is an essential feature of modern day wearable devices.State-of-the-art machine learning-based heartbeat classifiers are designed convolutional neural networks (CNN).Despite their high accuracy, CNNs require significant computational resources and power.This makes the mapping on resource-and power-constrained devices challenging.In this paper, we propose spiking (SNN), alternative approach based a biologically inspired, event-driven...
Today's computing architectures and device technologies are unable to meet the increasingly stringent demands on energy performance posed by emerging applications. Therefore, alternative being explored that leverage novel post-CMOS technologies. One of these is a Computation-in-Memory architecture based memristive devices. This paper describes concept such an shows different applications could significantly benefit from it. For each application, algorithm, architecture, primitive operations,...
In this paper Cubic Bezier curve-based leaf classification system using CapsNet is proposed.This extracts image features in terms of shape characteristics query then the trained to classify input a particular class within desired range similarity.The proposed determines nonlinear relationship between image's for more accurate similarity comparison and existing images.Among approaches feature analysis, statistical approach extract adopted here.It works form control points curves from both...
Bio-inspired paradigms such as spiking neural networks (SNNs) offer the potential to emulate repairing and adaptive ability of brain. This paper presents EMBRACE-FPGA, a scalable, configurable network on chip (NoC)-based SNN architecture, implemented Xilinx Virtex II-Pro FPGA hardware. In association with genetic algorithm-based hardware evolution platform, EMBRACE-FPGA provides computing platform for intrinsic evolution, which can be used explore capabilities SNNs. Results demonstrate...
In this paper Cubic Bezier curve-based image retrieval system is proposed.This evaluates similarity of each in its database to a query terms shape characteristics.Then, returns those images within desired range similarity.The proposed determines nonlinear relationship between image's features for more accurate comparison and existing images.Among approaches feature analysis, statistical approach extract adopted here.It works form control points spline curves from both given available...
Awareness about the features of internet, easy access to data using mobile, and affordable facilities have caused a lot traffic on internet. Digitization came with opportunities challenges as well. One important advantages digitization is paperless transactions, transparency in payment, while privacy, fake news, cyber-attacks are evolving challenges. The extensive use social media networks e-commerce websites has user-generated information, misinformation, disinformation Internet. quality...
In accordance with the inability of various hair artefacts subjected to dermoscopic medical images, undergoing illumination challenges that include chest-Xray featuring conditions imaging acquisi-tion situations built clinical segmentation. The study proposed a novel deep-convolutional neural network (CNN)-integrated methodology for applying image segmentation upon and images. develops technique segmenting images merged CNNs an architectural comparison incorporates networks U-net fully...
To raise human living standards, technical advancements are driven mostly by this source of inspiration. Directly and indirectly, technological growth increases provides for safety comfort. The creation technology use immediately influences life standards through the design intelligent automation systems. Unlike general-purpose computers, PLC is designed multiple inputs output arrangements. Now a days with increase industrial PLC's find replacement to hard drawn relay wires. An example real...
The complexity of inter-neuron connectivity is prohibiting scalable hardware implementations spiking neural networks (SNNs). Traditional neuron interconnect using a shared bus topology not due to non-linear growth connections with the network size. This paper presents novel hierarchical NoC (H-NoC) architecture for SNN which addresses scalability issue by creating 3-dimensional array clusters neurons structure low and high-level routers. H-NoC also incorporates spike traffic compression...
Background: Image retrieval has a significant role in present and upcoming usage for different image processing applications where images within desired range of similarity are retrieved query image. Representation feature, accuracy feature selection, optimal storage size vector efficient methods obtaining features plays vital retrieval, represented based on the content an such as color, texture or shape. In this work control points Bezier curve is proposed which computation efficient. Aim:...