Arkady Zaslavsky

ConQeng: A Middleware for Quality of Context Aware Selection, Measurement and Validation

Publisher: Springer International Publishing

Date: 2022

DOI: 10.1007/978-3-031-20936-9_17

IoT-based decision support system for monitoring and mitigating atmospheric pollution in smart cities

Publisher: Informa UK Limited

Date: 09-05-2018

DOI: 10.1080/12460125.2018.1468696

Crystal-Ball and Magic Wand Combined: Predicting Situations and Making Them Happen

Publisher: Springer International Publishing

Date: 2020

DOI: 10.1007/978-3-030-66471-8_52

A Multiagent Mission Coordination System for Continuous Situational Awareness of Bushfires

Publisher: Institute of Electrical and Electronics Engineers (IEEE)

Date: 04-2023

DOI: 10.1109/TASE.2022.3183233

Efficient Execution of Complex Context Queries to Enable Near Real-Time Smart IoT Applications

Publisher: MDPI AG

Date: 11-12-2019

DOI: 10.3390/S19245457

Abstract: As the Internet of Things (IoT) is evolving at a fast pace, the need for contextual intelligence has become more crucial for delivering IoT intelligence, efficiency, effectiveness, performance, and sustainability. Contextual intelligence enables interactions between IoT devices such as sensors/actuators, smartphones and connected vehicles, to name but a few. Context management platforms (CMP) are emerging as a promising solution to deliver contextual intelligence for IoT. However, the development of a generic solution that allows IoT devices and services to publish, consume, monitor, and share context is still in its infancy. In this paper, we propose, validate and explain the details of a novel mechanism called Context Query Engine (CQE), which is an integral part of a pioneering CMP called Context-as-a-Service (CoaaS). CQE is responsible for efficient execution of context queries in near real-time. We present the architecture of CQE and illuminate its workflows. We also conduct extensive experimental performance and scalability evaluation of the proposed CQE. Results of experimental evaluation convincingly demonstrate that CoaaS outperforms its competitors in executing complex context queries. Moreover, the advanced functionality of the embedded query language makes CoaaS a decent candidate for real-life deployments.

Decision support for optimizing waste management

Publisher: Informa UK Limited

Date: 25-04-2018

DOI: 10.1080/12460125.2018.1464312

Context-Aware Machine Learning for Intelligent Transportation Systems: A Survey

Publisher: Institute of Electrical and Electronics Engineers (IEEE)

Date: 2023

DOI: 10.1109/TITS.2022.3216462

Refresh Rate-Based Caching and Prefetching Strategies for Internet of Things Middleware

Publisher: MDPI AG

Date: 27-10-2023

DOI: 10.3390/S23218779

Deakin RF-Sensing: Experiments on Correlated Knowledge Distillation for Monitoring Human Postures with Radios

Publisher: Institute of Electrical and Electronics Engineers (IEEE)

Date: 2023

DOI: 10.1109/JSEN.2023.3320131

Adaptive Context Caching for Efficient Distributed Context Management Systems

Publisher: ACM

Date: 27-03-2023

DOI: 10.1145/3555776.3577602

Adaptive Context Caching for IoT-Based Applications: A Reinforcement Learning Approach

Publisher: MDPI AG

Date: 15-05-2023

DOI: 10.3390/S23104767

Abstract: Making internet-of-things (IoT)-based applications context-aware demands large amounts of raw data to be collected, interpreted, stored, and reused or repurposed if needed from many domains and applications. Context is transient but interpreted data can be distinguished from IoT data in many aspects. Managing context in cache is a novel area of research that has been given very little attention. Performance metric-driven adaptive context caching (ACOCA) can have a profound impact on the performance and cost efficiency of context-management platforms (CMPs) when responding to context queries in realtime. Our paper proposes an ACOCA mechanism to maximize both the cost and performance efficiency of a CMP in near realtime. Our novel mechanism encompasses the entire context-management life cycle. This, in turn, distinctively addresses the problems of efficiently selecting context for caching and managing the additional costs of context management in the cache. We demonstrate that our mechanism results in long-term efficiencies for the CMP that have not been observed in any previous study. The mechanism employs a novel, scalable, and selective context-caching agent implemented using the twin delayed deep deterministic policy gradient method. It further incorporates an adaptive context-refresh switching policy, a time-aware eviction policy, and a latent caching decision management policy. We point out in our findings that the additional complexity of adaptation introduced to the CMP through ACOCA is significantly justified, considering the cost and performance gains achieved. Our algorithm is evaluated using a real-world inspired heterogeneous context-query load and a data set based on parking-related traffic in Melbourne, Australia. This paper presents and benchmarks the proposed scheme against traditional and context-aware caching policies. We demonstrate that ACOCA outperforms the benchmarks in both cost and performance efficiency, i.e., up to 68.6%, 84.7%, and 67% more cost efficient compared to traditional data caching policies to cache context, redirector mode, and context-aware adaptive data caching under real-world-like circumstances.

Requirements, Limitations and Recommendations for Enabling End-to-End Quality of Context-Awareness in IoT Middleware

Publisher: MDPI AG

Date: 19-02-2022

DOI: 10.3390/S22041632

Abstract: Satisfying a context consumer’s quality of context (QoC) requirements is important to context management platforms (CMPs) in order to have credibility. QoC indicates the contextual information’s quality metrics (e.g., accuracy, timeliness, completeness). The outcomes of these metrics depend on the functional and quality characteristics associated with all actors (context consumers (or) context-aware applications, CMPs, and context providers (or) IoT-data providers) in context-aware IoT environments. This survey identifies and studies such characteristics and highlights the limitations in actors’ current functionalities and QoC modelling approaches to obtain adequate QoC and improve context consumers’ quality of experience (QoE). We propose a novel concept system based on our critical analysis this system addresses the functional limitations in existing QoC modelling approaches. Moreover, we highlight those QoC metrics affected by quality of service (QoS) metrics in CMPs. These recommendations provide CMP developers with a reference system they could incorporate, functionalities and QoS metrics to maintain in order to deliver an adequate QoC.

Monash University - Caulfield Campus

Location: Australia

View Organisation

Deakin University

Location: Australia

View Organisation

Ivane Javakhishvili Tbilisi State University

Location: Georgia

View Organisation

CSIRO

Location: Australia

View Organisation

Moscow Institute For Control Sciences (IPU-IAT)

Location: Russian Federation

View Organisation

Lulea Tekniska Universitet

Location: Sweden

View Organisation

Linkage Projects - Grant ID: LP0211384

Start Date: 04-2002

End Date: 06-2007

Amount: $135,270.00

Funder: Australian Research Council

Linkage Projects - Grant ID: LP0455234

Start Date: 09-2004

End Date: 12-2007

Amount: $240,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP200102299

Start Date: 06-2020

End Date: 12-2024

Amount: $390,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP0345713

Start Date: 02-2003

End Date: 12-2005

Amount: $193,035.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP0880874

Start Date: 01-2008

End Date: 06-2012

Amount: $315,000.00

Funder: Australian Research Council

Special Research Initiatives - Grant ID: SR0354696

Start Date: 2004

End Date: 12-2004

Amount: $30,000.00

Funder: Australian Research Council

Research Networks - Grant ID: RN0459895

Start Date: 09-2004

End Date: 12-2011

Amount: $1,600,000.00

Funder: Australian Research Council

Linkage Projects - Grant ID: LP0774834

Start Date: 07-2009

End Date: 10-2013

Amount: $156,000.00

Funder: Australian Research Council