Exploiting On-Device Image Classification for Energy Efficiency in Ambient-Aware Systems

Shoaib, Mohammed; Venkataramani, Swagath; Hua, Xian-Sheng; Liu, Jie; Li, Jin

doi:10.1007/978-3-319-24702-1_7

Cited by 8 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 presents a gap analysis comparing existing works with the contributions of our study. [22] Introduced a lightweight ML model for image classification and an optimized hardware engine for IoT devices.…”

Section: Literature Reviewmentioning

confidence: 99%

A Comparative Analysis for Optimizing Machine Learning Model Deployment in IoT Devices

Islam,

Sayeedi,

Deepti

et al. 2024

Preprint

View full text Add to dashboard Cite

In the intersection of the Internet of Things (IoT) and Machine Learning (ML), the choice between high-level and low-level programming libraries presents a significant dilemma for developers, impacting not only the efficiency and effectiveness of ML models but also their environmental footprint. We have proposed a comprehensive framework to aid in this decision-making process, underpinned by a detailed comparative analysis of both types of libraries on one of the key IoT ML task; image classification. We have introduced a novel algorithm designed to calculate the green footprint of ML model training, factoring in execution time, memory utilization, power consumption, and CPU temperature, addressing the urgent need for sustainable ML practices. Through an empirical evaluation of popular libraries such as PyTorch for high-level and Libtorch for low-level development, we have assessed their performance, development efficiency, and hardware compatibility. The culmination of our research is a decision support system that synthesizes the experimental findings to guide developers toward choices that harmonize model performance with environmental sustainability.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Comparative Analysis for Optimizing Machine Learning Model Deployment in IoT Devices

Islam,

Sayeedi,

Deepti

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Shoaib et al [24] Introduced a lightweight ML model for image classification and an optimized hardware engine for IoT devices. The image classifier was used to remove irrelavant frame from video and reduce the communication time by training the model ondevice instead of relying on the cloud server.…”

Section: Reference Key Findings or Features Identified Gaps And Our C...mentioning

confidence: 99%

A Comparative Analysis for Optimizing Machine Learning Model Deployment in IoT Devices

Sayeedi,

Deepti,

Osmani

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In the intersection of the Internet of Things (IoT) and Machine Learning (ML), the choice between high-level and low-level programming libraries presents a significant dilemma for developers, impacting not only the efficiency and effectiveness of ML models but also their environmental footprint. We have proposed a comprehensive framework to aid in this decision-making process, underpinned by a detailed comparative analysis of both types of libraries on one of the key IoT ML tasks: image classification. We have introduced a novel algorithm designed to calculate the green footprint of ML model training, factoring in execution time, memory utilization, power consumption, and CPU temperature, addressing the urgent need for sustainable ML practices. Through an empirical evaluation of popular libraries such as PyTorch for high-level and Libtorch for low-level development, we have assessed their performance, development efficiency, and hardware compatibility. The culmination of our research is a decision support system that synthesizes the experimental findings to guide developers toward choices that harmonize model performance with environmental sustainability.

show abstract

“…We display example of such alignment problems on Figure 1. It takes on average more than 2 seconds to perform object recognition on a mobile CPU (Snapdragon 800) [54]. Besides alignment problems, such a high computation latency will result in an extremely low framerate that will further degrade the quality of experience (QoE).…”

Section: Introductionmentioning

confidence: 99%

EdgeXAR: A 6-DoF Camera Multi-target Interaction Framework for MAR with User-friendly Latency Compensation

Zhang¹,

Lin²,

Bijarbooneh³

et al. 2021

Preprint

View full text Add to dashboard Cite

The computational capabilities of recent mobile devices enable the processing of natural features for Augmented Reality (AR), but the scalability is still limited by the devices' computation power and available resources. In this paper, we propose EdgeXAR, a mobile AR framework that utilizes the advantages of edge computing through task offloading to support flexible camera-based AR interaction. We propose a hybrid tracking system for mobile devices that provides lightweight tracking with 6 Degrees of Freedom and hides the offloading latency from users' perception. A practical, reliable and unreliable communication mechanism is used to achieve fast response and consistency of crucial information. We also propose a multi-object image retrieval pipeline that executes fast and accurate image recognition tasks on the cloud and edge servers. Extensive experiments are carried out to evaluate the performance of EdgeXAR by building mobile AR Apps upon it. Regarding the Quality of Experience (QoE), the mobile AR Apps powered by EdgeXAR framework run on average at the speed of 30 frames per second with precise tracking of only 1∼2 pixel errors and accurate image recognition of at least 97% accuracy. As compared to Vuforia, one of the leading commercial AR frameworks, EdgeXAR transmits 87% less data while providing a stable 30 FPS performance and reducing the offloading latency by 50 to 70% depending on the transmission medium. Our work facilitates the large-scale deployment of AR as the next generation of ubiquitous interfaces.CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing systems and tools; • Information systems → Image search; • Networks → Cloud computing.

show abstract

Exploiting On-Device Image Classification for Energy Efficiency in Ambient-Aware Systems

Cited by 8 publications

References 32 publications

A Comparative Analysis for Optimizing Machine Learning Model Deployment in IoT Devices

A Comparative Analysis for Optimizing Machine Learning Model Deployment in IoT Devices

A Comparative Analysis for Optimizing Machine Learning Model Deployment in IoT Devices

EdgeXAR: A 6-DoF Camera Multi-target Interaction Framework for MAR with User-friendly Latency Compensation

Contact Info

Product

Resources

About