A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applications

Nayak, Sabuzima; Patgiri, Ripon; Waikhom, Lilapati; Ahmed, Arif

doi:10.1016/j.dcan.2022.10.016

Cited by 19 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the data in edge devices are highly heterogeneous, and integration of data is a big challenge. In the future, edge devices will be the key enabler for sixth-generation communication networks [ 107 ] where the latency is less than 1 ms. Edge and edge AI have to meet the global coverage needs of 6G.…”

Section: Discussionmentioning

confidence: 99%

A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)

Surianarayanan

Lawrence

Raj

et al. 2023

Sensors

View full text Add to dashboard Cite

Artificial Intelligence (Al) models are being produced and used to solve a variety of current and future business and technical problems. Therefore, AI model engineering processes, platforms, and products are acquiring special significance across industry verticals. For achieving deeper automation, the number of data features being used while generating highly promising and productive AI models is numerous, and hence the resulting AI models are bulky. Such heavyweight models consume a lot of computation, storage, networking, and energy resources. On the other side, increasingly, AI models are being deployed in IoT devices to ensure real-time knowledge discovery and dissemination. Real-time insights are of paramount importance in producing and releasing real-time and intelligent services and applications. Thus, edge intelligence through ondevice data processing has laid down a stimulating foundation for real-time intelligent enterprises and environments. With these emerging requirements, the focus turned towards unearthing competent and cognitive techniques for maximally compressing huge AI models without sacrificing AI model performance. Therefore, AI researchers have come up with a number of powerful optimization techniques and tools to optimize AI models. This paper is to dig deep and describe all kinds of model optimization at different levels and layers. Having learned the optimization methods, this work has highlighted the importance of having an enabling AI model optimization framework.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)

Surianarayanan

Lawrence

Raj

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The use of on-device processing provides several advantages over a traditional cloud-based deployment for this application. Performing inference at the edge eliminates privacy concerns associated with transmitting raw sensor data to the cloud [32]. It also reduces reliance on continuous connectivity and mitigates against network failures.…”

Section: Deploymentmentioning

confidence: 99%

Emotion on the Edge: Air Quality Sensors Decoded as a Real-World Emotion Indicator

Johnson,

Woodward,

Kanjo

2024

2024 IEEE International Conference on Pervasive Computing and Communications Workshops and Other Affiliated Events (PerCom Work

View full text Add to dashboard Cite

As the research community increasingly focuses on quantifying emotional states in real-world scenarios, there is a growing need for edge computing. In this work, we present a novel approach to on-device emotion classification through the development of a low-cost hand-held device. This device incorporates a range of environmental air quality factors, including Particulate Matter, Nitrogen Dioxide, Carbon Monoxide, Ammonia, and Noise. Our research addresses the current limitations in the field of emotional state measurement by leveraging environmental air quality data, which has been previously linked to affective states. This on-device approach not only offers an alternative to resource-intensive emotion recognition methods but also contributes to the development of more practical and affordable solutions for emotion assessment. The preliminary results of our device's performance in real-world scenarios suggest its effectiveness in quantifying emotional states through air quality factors, with the model achieving 95% accuracy demonstrating accurate on-device classification without the need for external high-processing power.

show abstract

“…In the realm of UTI diagnostics, ML algorithms hold the promise of leveraging complex clinical and laboratory data to predict infection presence and guide therapeutic decisions more accurately [19], [20], [21]. This potential comes against the backdrop of an ever-growing digitalization of healthcare data and advancements in computational power and algorithmic sophistication [22], [23], [24].…”

Section: Introductionmentioning

confidence: 99%

Efficacy of Machine Learning Techniques in Diagnosing Urinary Tract Infections: A Study Utilizing a Philippine Clinical Dataset

Airlangga

2024

INFEB

View full text Add to dashboard Cite

This research delves into the potential of machine learning models, namely Support Vector Machine (SVM), XGBoost, and LightGBM, to enhance the diagnosis of Urinary Tract Infections (UTIs) based on a comprehensive dataset collected from a local clinic in Northern Mindanao, Philippines, spanning from April 2020 to January 2023. The study integrates clinical variables such as age, gender, and various urine test results including color, transparency, and the presence of substances like glucose, protein, and cells, to determine the most accurate diagnostic model. The dataset presented unique preprocessing challenges, such as converting infant ages into decimal numbers. The SVM with a linear kernel showed remarkable test accuracy of 98.25%, indicating its robustness in handling linear separability in the data. Meanwhile, XGBoost and LightGBM, both with optimal hyperparameter configurations, achieved comparable accuracies of 97.95%. These results underscore the significance of machine learning in medical diagnostics, particularly in settings where swift and reliable decision-making is crucial. Our findings suggest that while ensemble methods like XGBoost and LightGBM are powerful tools for complex datasets, a well-tuned SVM can provide superior accuracy, thus advocating for a data-centric approach in model selection.

show abstract

A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applications

Cited by 19 publications

References 47 publications

A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)

A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)

Emotion on the Edge: Air Quality Sensors Decoded as a Real-World Emotion Indicator

Efficacy of Machine Learning Techniques in Diagnosing Urinary Tract Infections: A Study Utilizing a Philippine Clinical Dataset

Contact Info

Product

Resources

About