An Ingestion and Analytics Architecture for IoT Applied to Smart City Use Cases

Ta-Shma, Paula; Akbar, Adnan; Gerson-Golan, Guy; Hadash, Guy; Carrez, François; Moessner, Klaus

doi:10.1109/jiot.2017.2722378

Cited by 78 publications

(46 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ta-Shma et al [33] presented an architecture for extracting valuable historical insights and actionable knowledge from IoT data streams. Their architecture supports both real-time and historical data analytics using a hybrid data processing model.…”

Section: B Big Data and Machine Learning Tools Applied To Iotmentioning

confidence: 99%

“…In contrast to previous studies [31], [33], [34], this work focusses on providing methods to enable efficient development of ML applications with IoT data. Unlike the studies mentioned previously, this research examines the orchestration and automation of end-to-end ML workflows to support parallel training and deployment of multiple ML models with IoT data.…”

Section: B Big Data and Machine Learning Tools Applied To Iotmentioning

confidence: 99%

See 1 more Smart Citation

ML4IoT: A Framework to Orchestrate Machine Learning Workflows on Internet of Things Data

2019

View full text Add to dashboard Cite

Internet of Things (IoT) applications generate vast amounts of real-time data. Temporal analysis of these data series to discover behavioural patterns may lead to qualified knowledge affecting a broad range of industries. Hence, the use of machine learning (ML) algorithms over IoT data has the potential to improve safety, economy, and performance in critical processes. However, creating ML workflows at scale is a challenging task that depends upon both production and specialized skills. Such tasks require investigation, understanding, selection, and implementation of specific ML workflows, which often lead to bottlenecks, production issues, and code management complexity and even then may not have a final desirable outcome. This paper proposes the Machine Learning Framework for IoT data (ML4IoT), which is designed to orchestrate ML workflows, particularly on large volumes of data series. The ML4IoT framework enables the implementation of several types of ML models, each one with a different workflow. These models can be easily configured and used through a simple pipeline. ML4IoT has been designed to use container-based components to enable training and deployment of various ML models in parallel. The results obtained suggest that the proposed framework can manage real-world IoT heterogeneous data by providing elasticity, robustness, and performance. INDEX TERMS Big data, container-based virtualization, IoT, machine learning, machine learning workflow, microservices. JOSÉ M. ALVES received the B.Sc. degree in information systems from USP, Brazil, in 2010. He is currently pursuing the M.E.Sc. degree in software engineering with Western University, Canada. From 2010 to 2017, he was involved in numerous software development and data analytics projects for telecommunications companies in Brazil. His current research interests include big data, machine learning, the IoT, and cloud computing.

show abstract

Section: B Big Data and Machine Learning Tools Applied To Iotmentioning

confidence: 99%

Section: B Big Data and Machine Learning Tools Applied To Iotmentioning

confidence: 99%

ML4IoT: A Framework to Orchestrate Machine Learning Workflows on Internet of Things Data

2019

View full text Add to dashboard Cite

show abstract

“…The architecture can access the context information and provide services through a semantic match-making engine based on ontology models. Paula et al proposed a simplified architecture that provided services through a hybrid data processing model, including historical data analysis and real-time analysis [ 20 ]. This architecture supports data ingestion, data retrieval and machine learning to determine the services to be provided.…”

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence-Based Semantic Internet of Things in a User-Centric Smart City

Guo

Gao

et al. 2018

Sensors

View full text Add to dashboard Cite

Smart city (SC) technologies can provide appropriate services according to citizens’ demands. One of the key enablers in a SC is the Internet of Things (IoT) technology, which enables a massive number of devices to connect with each other. However, these devices usually come from different manufacturers with different product standards, which confront interactive control problems. Moreover, these devices will produce large amounts of data, and efficiently analyzing these data for intelligent services. In this paper, we propose a novel artificial intelligence-based semantic IoT (AI-SIoT) hybrid service architecture to integrate heterogeneous IoT devices to support intelligent services. In particular, the proposed architecture is empowered by semantic and AI technologies, which enable flexible connections among heterogeneous devices. The AI technology can support very implement efficient data analysis and make accurate decisions on service provisions in various kinds. Furthermore, we also present several practical use cases of the proposed AI-SIoT architecture and the opportunities and challenges to implement the proposed AI-SIoT for future SCs are also discussed.

show abstract

“…The IoT will comprise tens to hundreds of billions of heterogeneous and pervasive objects, and will enable an ecosystem with existing networks and software applications [10]. These new applications enable continuous connections with intelligent devices, and IoT solutions are increasingly becoming a staple of modern cities [11]. The IoT changes the requirements for wireless connectivity significantly, mainly with regard to its long range and need for high reliability.…”

Section: Wi-fi Enabled Iots In Narrowbandmentioning

confidence: 99%

Digital Pre-Distortion of Carrier Frequency Offset for Reliable Wi-Fi Enabled IoTs

Lee

2017

Future Internet

View full text Add to dashboard Cite

Abstract:The Internet of Things (IoTs) will change the requirements for wireless connectivity significantly, mainly with regard to service coverage, data rate, and energy efficiency. Therefore, to improve robustness and reliability, WiFi-enabled IoT devices have been developed to use narrowband communication. However, narrowband transmission in WiFi such as IEEE 802.11ah causes relatively higher frequency error due to the reduced subcarrier space, which is larger than legacy wireless local area networks (WLANs) in 2.4/5 GHz frequencies. In a direct conversion receiver, this error degrades the signal quality due to the presence of direct current (DC) offset cancellation circuits. In this paper, a digital carrier frequency offset (CFO) predistortion scheme is proposed for a reliable communication link in dense networks. Evaluation results demonstrate that the proposed scheme can improve received signal quality in terms of packet error rate and error vector magnitude.

show abstract

An Ingestion and Analytics Architecture for IoT Applied to Smart City Use Cases

Cited by 78 publications

References 9 publications

ML4IoT: A Framework to Orchestrate Machine Learning Workflows on Internet of Things Data

ML4IoT: A Framework to Orchestrate Machine Learning Workflows on Internet of Things Data

Artificial Intelligence-Based Semantic Internet of Things in a User-Centric Smart City

Digital Pre-Distortion of Carrier Frequency Offset for Reliable Wi-Fi Enabled IoTs

Contact Info

Product

Resources

About