Edge-AI-driven framework with efficient mobile network design for facial expression recognition
Facial Expression Recognition (FER) in the wild poses significant challenges due to realistic
occlusions, illumination, scale, and head pose variations of the facial images. In this article …
occlusions, illumination, scale, and head pose variations of the facial images. In this article …
Dyno: Dynamic onloading of deep neural networks from cloud to device
Recently, there has been an explosive growth of mobile and embedded applications using
convolutional neural networks (CNNs). To alleviate their excessive computational demands …
convolutional neural networks (CNNs). To alleviate their excessive computational demands …
Implementation of generative adversarial networks in mobile applications for image data enhancement
This article aims to explore and research GANs as a tool for mobile devices that can
generate high-resolution images from low-resolution samples and reduce blurring. In …
generate high-resolution images from low-resolution samples and reduce blurring. In …
A general hardware and software Co-design framework for energy-efficient edge AI
A huge number of edge applications including self-driving cars, mobile health, robotics, and
augmented reality/virtual reality are enabled by deep neural networks (DNNs). Currently …
augmented reality/virtual reality are enabled by deep neural networks (DNNs). Currently …
Real-time Blood Pressure Prediction on Wearables with Edge-Based DNNs: A Co-Design Approach
T Joseph, B TS - ACM Transactions on Design Automation of Electronic …, 2024 - dl.acm.org
This paper presents the hardware realization of a real-time blood pressure (BP) prediction
model for wearable devices, utilizing long short-term memory (LSTM) deep neural networks …
model for wearable devices, utilizing long short-term memory (LSTM) deep neural networks …
ZeroD-fender: A Resource-aware IoT Malware Detection Engine via Fine-grained Side-channel Analysis
Z Li, D Zhao - ACM Transactions on Design Automation of Electronic …, 2024 - dl.acm.org
In early 2023, cyberattacks experienced a significant rise due to unknown (zero-day)
malware targeting Internet of Things (IoT) devices. To tackle the challenge of zero-day …
malware targeting Internet of Things (IoT) devices. To tackle the challenge of zero-day …
Intelligence Inference on IoT Devices
With the rapid advancement of artificial intelligence (AI), the proliferation of deep neural
networks (DNNs) has ushered in a transformative era, revolutionizing modern lifestyles and …
networks (DNNs) has ushered in a transformative era, revolutionizing modern lifestyles and …
Adaptive Experimental Design for Optimizing Combinatorial Structures
A Deshwal - 2024 - search.proquest.com
Many real-world scientific and engineering problems can be formulated as instances of goal-
driven adaptive experimental design, wherein candidate experiments are chosen …
driven adaptive experimental design, wherein candidate experiments are chosen …
[BOOK][B] An Adaptive Framework for Energy-Efficient Edge AI: From Classification to Synthesis of Images and 3D Shapes
KJ Nitthilan - 2022 - search.proquest.com
A large number of real-time artificial intelligence (AI) applications including robotics, self-
driving cars, smart health and augmented (AR)/virtual reality (VR) are enhanced/boosted by …
driving cars, smart health and augmented (AR)/virtual reality (VR) are enhanced/boosted by …
An Adaptive Framework for Energy-Efficient Edge AI: from Classification to Synthesis of Images and 3D Shapes
NK Jayakodi - rex.libraries.wsu.edu
A large number of real-time artificial intelligence (AI) applications including robotics, self-
driving cars, smart health and augmented (AR)/virtual reality (VR) are enhanced/boosted by …
driving cars, smart health and augmented (AR)/virtual reality (VR) are enhanced/boosted by …