Study of end to end image processing system including image de-noising, image compression & image security
Over the last few years, the computer vision has a huge impact in the field of information
technology. The foundation for computer vision is laid by image processing. Digital Image …
technology. The foundation for computer vision is laid by image processing. Digital Image …
Low-power detection and classification for in-sensor predictive maintenance based on vibration monitoring
In this work, a new custom design of an anomaly detection and classification system is
proposed. It is composed of a convolutional Auto-Encoder (AE) hardware design to perform …
proposed. It is composed of a convolutional Auto-Encoder (AE) hardware design to perform …
Digital watermarking of ecg data for secure wireless commuication
S Kaur, R Singhal, O Farooq… - … conference on recent …, 2010 - ieeexplore.ieee.org
Use of wireless technology has made the bio-medical data vulnerable to attacks like
tampering, hacking etc. This paper proposes the use of digital watermarking to increase the …
tampering, hacking etc. This paper proposes the use of digital watermarking to increase the …
Optimal complexity architectures for pipelined distributed arithmetic-based LMS adaptive filter
This paper presents three optimal-complexity structures (I, II, III) for pipelined distributed
arithmetic (DA) based least-mean-square (LMS) adaptive filter. The complexity of proposed …
arithmetic (DA) based least-mean-square (LMS) adaptive filter. The complexity of proposed …
Low power tiny binary neural network with improved accuracy in human recognition systems
Human Activity Recognition requires very high accuracy to be effectively employed into
practical applications, ranging from elderly care to microsurgical devices. The highest …
practical applications, ranging from elderly care to microsurgical devices. The highest …
Low-power HWAccelerator for AI edge-computing in human activity recognition systems
In this paper, an energy efficient HW accelerator for AI edge-computing in Human Activity
Recognition is proposed. The system processes samples from a tri-axial accelerometer and …
Recognition is proposed. The system processes samples from a tri-axial accelerometer and …
A partially binarized hybrid neural network system for low-power and resource constrained human activity recognition
A custom Human Activity Recognition system is presented based on the resource-
constrained Hardware (HW) implementation of a new partially binarized Hybrid Neural …
constrained Hardware (HW) implementation of a new partially binarized Hybrid Neural …
Quantized ID-CNN for a low-power PDM-to-PCM conversion in TinyML KWS applications
P Vitolo, GD Licciardo, AC Amendola… - 2022 IEEE 4th …, 2022 - ieeexplore.ieee.org
This paper proposes a novel low-power HW accelerator for audio PDM-to-PCM conversion
based on artificial neural network. The system processes samples from a digital MEMS …
based on artificial neural network. The system processes samples from a digital MEMS …
A combined arithmetic-high-level synthesis solution to deploy partial carry-save radix-8 booth multipliers in datapaths
AA Del Barrio, R Hermida… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
While partial carry-save adders are easily designed by splitting them into several fragments
working in parallel, the design of partial carry-save multipliers is more challenging. Prior …
working in parallel, the design of partial carry-save multipliers is more challenging. Prior …
Multiplier-less stream processor for 2D filtering in visual search applications
GD Licciardo, C Cappetta… - … on Circuits and …, 2016 - ieeexplore.ieee.org
A new 2D convolution-based filter is presented, which is specifically designed to improve
visual search applications. It exploits a new radix-3 partitioning method of integer numbers …
visual search applications. It exploits a new radix-3 partitioning method of integer numbers …