Search Results for author: Mohammad Abdullah Al Faruque

Found 33 papers, 7 papers with code

SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification

no code implementations20 Feb 2024 Junyao Wang, Mohammad Abdullah Al Faruque

Many real-world applications of the Internet of Things (IoT) employ machine learning (ML) algorithms to analyze time series information collected by interconnected sensors.

Domain Adaptation Time Series +1

Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets

no code implementations14 Dec 2023 Mohanad Odema, Hyoukjun Kwon, Mohammad Abdullah Al Faruque

To address increasing compute demand from recent multi-model workloads with heavy models like large language models, we propose to deploy heterogeneous chiplet-based multi-chip module (MCM)-based accelerators.

Scheduling

Robust and Scalable Hyperdimensional Computing With Brain-Like Neural Adaptations

no code implementations13 Nov 2023 Junyao Wang, Mohammad Abdullah Al Faruque

In this work, we present dynamic HDC learning frameworks that identify and regenerate undesired dimensions to provide adequate accuracy with significantly lowered dimensionalities, thereby accelerating both the training and inference.

DOMINO: Domain-invariant Hyperdimensional Classification for Multi-Sensor Time Series Data

no code implementations7 Aug 2023 Junyao Wang, Luke Chen, Mohammad Abdullah Al Faruque

With the rapid evolution of the Internet of Things, many real-world applications utilize heterogeneously connected sensors to capture time-series information.

Domain Generalization Time Series +1

MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment

no code implementations16 Jul 2023 Mohanad Odema, Halima Bouzidi, Hamza Ouarnoughi, Smail Niar, Mohammad Abdullah Al Faruque

To achieve this, MaGNAS employs a two-tier evolutionary search to identify optimal GNNs and mapping pairings that yield the best performance trade-offs.

Graph Learning Neural Architecture Search

CARMA: Context-Aware Runtime Reconfiguration for Energy-Efficient Sensor Fusion

no code implementations27 Jun 2023 Yifan Zhang, Arnav Vaibhav Malawade, Xiaofang Zhang, Yuhui Li, DongHwan Seong, Mohammad Abdullah Al Faruque, Sitao Huang

Autonomous systems (AS) are systems that can adapt and change their behavior in response to unanticipated events and include systems such as aerial drones, autonomous vehicles, and ground/aquatic robots.

Autonomous Vehicles Sensor Fusion

Stress Detection using Context-Aware Sensor Fusion from Wearable Devices

no code implementations14 Mar 2023 Nafiul Rashid, Trier Mortlock, Mohammad Abdullah Al Faruque

SELF-CARE uses a learning-based classifier to process sensor features and model the environmental variations in sensing conditions known as the noise context.

Sensor Fusion

ERUDITE: Human-in-the-Loop IoT for an Adaptive Personalized Learning System

no code implementations7 Mar 2023 Mojtaba Taherisadr, Mohammad Abdullah Al Faruque, Salma Elmalaki

Thanks to the rapid growth in wearable technologies and recent advancement in machine learning and signal processing, monitoring complex human contexts becomes feasible, paving the way to develop human-in-the-loop IoT systems that naturally evolve to adapt to the human and environment state autonomously.

Learning Theory

SEO: Safety-Aware Energy Optimization Framework for Multi-Sensor Neural Controllers at the Edge

no code implementations24 Feb 2023 Mohanad Odema, James Ferlez, Yasser Shoukry, Mohammad Abdullah Al Faruque

Runtime energy management has become quintessential for multi-sensor autonomous systems at the edge for achieving high performance given the platform constraints.

Autonomous Driving energy management +1

EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency

no code implementations13 Feb 2023 Mohanad Odema, James Ferlez, Goli Vaisi, Yasser Shoukry, Mohammad Abdullah Al Faruque

To mitigate the high energy demand of Neural Network (NN) based Autonomous Driving Systems (ADSs), we consider the problem of offloading NN controllers from the ADS to nearby edge-computing infrastructure, but in such a way that formal vehicle safety properties are guaranteed.

Autonomous Driving Edge-computing

HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling

1 code implementation6 Dec 2022 Halima Bouzidi, Mohanad Odema, Hamza Ouarnoughi, Mohammad Abdullah Al Faruque, Smail Niar

Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency.

Computational Efficiency Edge-computing +1

Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving Systems

no code implementations18 Jul 2022 Luke Chen, Mohanad Odema, Mohammad Abdullah Al Faruque

Due to the high performance and safety requirements of self-driving applications, the complexity of modern autonomous driving systems (ADS) has been growing, instigating the need for more sophisticated hardware which could add to the energy footprint of the ADS platform.

Autonomous Driving Edge-computing +2

Golden Reference-Free Hardware Trojan Localization using Graph Convolutional Network

no code implementations14 Jul 2022 Rozhin Yasaei, Sina Faezi, Mohammad Abdullah Al Faruque

Moreover, a few existing HT localization methods have several weaknesses: reliance on a golden reference, inability to generalize for all types of HT, lack of scalability, low localization resolution, and manual feature engineering/property definition.

Feature Engineering

Neural Contextual Bandits Based Dynamic Sensor Selection for Low-Power Body-Area Networks

no code implementations24 May 2022 Berken Utku Demirel, Luke Chen, Mohammad Abdullah Al Faruque

Providing health monitoring devices with machine intelligence is important for enabling automatic mobile healthcare applications.

Anomaly Detection Multi-Armed Bandits

SELF-CARE: Selective Fusion with Context-Aware Low-Power Edge Computing for Stress Detection

no code implementations8 May 2022 Nafiul Rashid, Trier Mortlock, Mohammad Abdullah Al Faruque

Detecting human stress levels and emotional states with physiological body-worn sensors is a complex task, but one with many health-related benefits.

Edge-computing Sensor Fusion

EcoFusion: Energy-Aware Adaptive Sensor Fusion for Efficient Autonomous Vehicle Perception

no code implementations23 Feb 2022 Arnav Vaibhav Malawade, Trier Mortlock, Mohammad Abdullah Al Faruque

Autonomous vehicles use multiple sensors, large deep-learning models, and powerful hardware platforms to perceive the environment and navigate safely.

Autonomous Vehicles Navigate +3

HydraFusion: Context-Aware Selective Sensor Fusion for Robust and Efficient Autonomous Vehicle Perception

1 code implementation17 Jan 2022 Arnav Vaibhav Malawade, Trier Mortlock, Mohammad Abdullah Al Faruque

To address these limitations, we propose HydraFusion: a selective sensor fusion framework that learns to identify the current driving context and fuses the best combination of sensors to maximize robustness without compromising efficiency.

Autonomous Vehicles Sensor Fusion

Energy-Efficient Real-Time Heart Monitoring on Edge-Fog-Cloud Internet-of-Medical-Things

no code implementations15 Dec 2021 Berken Utku Demirel, Islam Abdelsalam Bayoumy, Mohammad Abdullah Al Faruque

However, continuous monitoring of ECG signals is challenging in low-power wearable devices due to energy and memory constraints.

Artifact Detection

roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs

1 code implementation2 Sep 2021 Arnav Vaibhav Malawade, Shih-Yuan Yu, Brandon Hsu, Harsimrat Kaeley, Anurag Karra, Mohammad Abdullah Al Faruque

The goal of roadscene2vec is to enable research into the applications and capabilities of road scene-graphs by providing tools for generating scene-graphs, graph learning models to generate spatio-temporal scene-graph embeddings, and tools for visualizing and analyzing scene-graph-based methodologies.

Action Classification Graph Embedding +4

Energy-efficient Blood Pressure Monitoring based on Single-site Photoplethysmogram on Wearable Devices

no code implementations2 Aug 2021 Wenrui Lin, Berken Utku Demirel, Mohammad Abdullah Al Faruque, G. P. Li

The paper proposes accurate Blood Pressure Monitoring (BPM) based on a single-site Photoplethysmographic (PPG) sensor and provides an energy-efficient solution on edge cuffless wearable devices.

Edge-computing

HW2VEC: A Graph Learning Tool for Automating Hardware Security

1 code implementation26 Jul 2021 Shih-Yuan Yu, Rozhin Yasaei, Qingrong Zhou, Tommy Nguyen, Mohammad Abdullah Al Faruque

To attract more attention, we propose HW2VEC, an open-source graph learning tool that lowers the threshold for newcomers to research hardware security applications with graphs.

Graph Learning

SAGE: A Split-Architecture Methodology for Efficient End-to-End Autonomous Vehicle Control

no code implementations22 Jul 2021 Arnav Malawade, Mohanad Odema, Sebastien Lajeunesse-DeGroot, Mohammad Abdullah Al Faruque

We evaluate SAGE using an Nvidia Jetson TX2 and an industry-standard Nvidia Drive PX2 as the AV edge devices and demonstrate that our offloading strategy is practical for a wide range of DL models and internet connection bandwidths on 3G, 4G LTE, and WiFi technologies.

Autonomous Vehicles

LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies

no code implementations20 Jul 2021 Mohanad Odema, Nafiul Rashid, Berken Utku Demirel, Mohammad Abdullah Al Faruque

Edge-Cloud hierarchical systems employing intelligence through Deep Neural Networks (DNNs) endure the dilemma of workload distribution within them.

Neural Architecture Search

GNN4IP: Graph Neural Network for Hardware Intellectual Property Piracy Detection

no code implementations19 Jul 2021 Rozhin Yasaei, Shih-Yuan Yu, Emad Kasaeyan Naeini, Mohammad Abdullah Al Faruque

In this work, we propose a novel methodology, GNN4IP, to assess similarities between circuits and detect IP piracy.

AHAR: Adaptive CNN for Energy-efficient Human Activity Recognition in Low-power Edge Devices

no code implementations3 Feb 2021 Nafiul Rashid, Berken Utku Demirel, Mohammad Abdullah Al Faruque

Unlike traditional early exit architecture that makes the exit decision based on classification confidence, AHAR proposes a novel adaptive architecture that uses an output block predictor to select a portion of the baseline architecture to use during the inference phase.

Cloud Computing Edge-computing +1

Cannot find the paper you are looking for? You can Submit a new open access paper.