Dimitrios Georgakopoulos

Jinze Wang, Jiong Jin, Tiehua Zhang et al.

The accurate diagnosis of machine breakdowns is crucial for maintaining operational safety in smart manufacturing. Despite the promise shown by deep learning in automating fault identification, the scarcity of labeled training data, particularly for equipment failure instances, poses a significant challenge. This limitation hampers the development of robust classification models. Existing methods like model-agnostic meta-learning (MAML) do not adequately address variable working conditions, affecting knowledge transfer. To address these challenges, a Related Task Aware Curriculum Meta-learning (RT-ACM) enhanced fault diagnosis framework is proposed in this paper, inspired by human cognitive learning processes. RT-ACM improves training by considering the relevance of auxiliary sensor working conditions, adhering to the principle of ``paying more attention to more relevant knowledge", and focusing on ``easier first, harder later" curriculum sampling. This approach aids the meta-learner in achieving a superior convergence state. Extensive experiments on two real-world datasets demonstrate the superiority of RT-ACM framework.

Muhammad Sakib Khan Inan, Kewen Liao, Haifeng Shen et al.

Internet of Things (IoT) sensor data or readings evince variations in timestamp range, sampling frequency, geographical location, unit of measurement, etc. Such presented sequence data heterogeneity makes it difficult for traditional time series classification algorithms to perform well. Therefore, addressing the heterogeneity challenge demands learning not only the sub-patterns (local features) but also the overall pattern (global feature). To address the challenge of classifying heterogeneous IoT sensor data (e.g., categorizing sensor data types like temperature and humidity), we propose a novel deep learning model that incorporates both Convolutional Neural Network and Bi-directional Gated Recurrent Unit to learn local and global features respectively, in an end-to-end manner. Through rigorous experimentation on heterogeneous IoT sensor datasets, we validate the effectiveness of our proposed model, which outperforms recent state-of-the-art classification methods as well as several machine learning and deep learning baselines. In particular, the model achieves an average absolute improvement of 3.37% in Accuracy and 2.85% in F1-Score across datasets

Abhik Banerjee, Abdur Rahim Mohammad Forkan, Dimitrios Georgakopoulos et al.

Consistency in product quality is of critical importance in manufacturing. However, achieving a target product quality typically involves balancing a large number of manufacturing attributes. Existing manufacturing practices for dealing with such complexity are driven largely based on human knowledge and experience. The prevalence of manual intervention makes it difficult to perfect manufacturing practices, underscoring the need for a data-driven solution. In this paper, we present an Industrial Internet of Things (IIoT) machine model which enables effective monitoring and control of plant machinery so as to achieve consistency in product quality. We present algorithms that can provide product quality prediction during production, and provide recommendations for machine control. Subsequently, we perform an experimental evaluation of the proposed solution using real data captured from a food processing plant. We show that the proposed algorithms can be used to predict product quality with a high degree of accuracy, thereby enabling effective production monitoring and control.

Charith Perera, Arkady Zaslavsky, Michael Compton et al.

We propose a Context Aware Sensor Configuration Model (CASCoM) to address the challenge of automated context-aware configuration of filtering, fusion, and reasoning mechanisms in IoT middleware according to the problems at hand. We incorporate semantic technologies in solving the above challenges.

Charith Perera, Arkady Zaslavsky, Michael Compton et al.

We are currently observing emerging solutions to enable the Internet of Things (IoT). Efficient and feature rich IoT middeware platforms are key enablers for IoT. However, due to complexity, most of these middleware platforms are designed to be used by IT experts. In this paper, we propose a semantics-driven model that allows non-IT experts (e.g. plant scientist, city planner) to configure IoT middleware components easier and faster. Such tools allow them to retrieve the data they want without knowing the underlying technical details of the sensors and the data processing components. We propose a Context Aware Sensor Configuration Model (CASCoM) to address the challenge of automated context-aware configuration of filtering, fusion, and reasoning mechanisms in IoT middleware according to the problems at hand. We incorporate semantic technologies in solving the above challenges. We demonstrate the feasibility and the scalability of our approach through a prototype implementation based on an IoT middleware called Global Sensor Networks (GSN), though our model can be generalized into any other middleware platform. We evaluate CASCoM in agriculture domain and measure both performance in terms of usability and computational complexity.

Charith Perera, Arkady Zaslavsky, Peter Christen et al.

As we are moving towards the Internet of Things (IoT), the number of sensors deployed around the world is growing at a rapid pace. Market research has shown a significant growth of sensor deployments over the past decade and has predicted a significant increment of the growth rate in the future. These sensors continuously generate enormous amounts of data. However, in order to add value to raw sensor data we need to understand it. Collection, modelling, reasoning, and distribution of context in relation to sensor data plays critical role in this challenge. Context-aware computing has proven to be successful in understanding sensor data. In this paper, we survey context awareness from an IoT perspective. We present the necessary background by introducing the IoT paradigm and context-aware fundamentals at the beginning. Then we provide an in-depth analysis of context life cycle. We evaluate a subset of projects (50) which represent the majority of research and commercial solutions proposed in the field of context-aware computing conducted over the last decade (2001-2011) based on our own taxonomy. Finally, based on our evaluation, we highlight the lessons to be learnt from the past and some possible directions for future research. The survey addresses a broad range of techniques, methods, models, functionalities, systems, applications, and middleware solutions related to context awareness and IoT. Our goal is not only to analyse, compare and consolidate past research work but also to appreciate their findings and discuss their applicability towards the IoT.

Charith Perera, Arkady Zaslavsky, Peter Christen et al.

Internet of Things (IoT) will create a cyberphysical world where all the things around us are connected to the Inter net, sense and produce "big data" that has to be stored, processed and communicated with minimum human intervention. With the ever increasing emergence of new sensors, interfaces and mobile devices, the grand challenge is to keep up with this race in developing software drivers and wrappers for IoT things. In this paper, we examine the approaches that automate the process of developing middleware drivers/wrappers for the IoT things. We propose ASCM4GSN architecture to address this challenge efficiently and effectively. We demonstrate the proposed approach using Global Sensor Network (GSN) middleware which exemplifies a cluster of data streaming engines. The ASCM4GSN architecture significantly speeds up the wrapper development and sensor configuration process as demonstrated for Android mobile phone based sensors as well as for Sun SPOT sensors.

Charith Perera, Arkady Zaslavsky, Peter Christen et al.

Internet of Things (IoT) will connect billions of sensors deployed around the world together. This will create an ideal opportunity to build a sensing-as-a-service platform. Due to large number of sensor deployments, there would be number of sensors that can be used to sense and collect similar information. Further, due to advances in sensor hardware technology, new methods and measurements will be introduced continuously. In the IoT paradigm, selecting the most appropriate sensors which can provide relevant sensor data to address the problems at hand among billions of possibilities would be a challenge for both technical and non-technical users. In this paper, we propose the Context Awareness for Internet of Things (CA4IOT) architecture to help users by automating the task of selecting the sensors according to the problems/tasks at hand. We focus on automated configuration of filtering, fusion and reasoning mechanisms that can be applied to the collected sensor data streams using selected sensors. Our objective is to allow the users to submit their problems, so our proposed architecture understands them and produces more comprehensive and meaningful information than the raw sensor data streams generated by individual sensors.

Dimitrios Georgakopoulos, Rajiv Ranjan, Karan Mitra et al.

The MediaWise project aims to expand the scope of existing media delivery systems with novel cloud, personalization and collaboration capabilities that can serve the needs of more users, communities, and businesses. The project develops a MediaWise Cloud platform that supports do-it-yourself creation, search, management, and consumption of multimedia content. The MediaWise Cloud supports pay-as-you-go models and elasticity that are similar to those offered by commercially available cloud services. However, unlike existing commercial CDN services providers such as Limelight Networks and Akamai the MediaWise Cloud require no ownerships of computing infrastructure and instead rely on the public Internet and public cloud services (e.g., commercial cloud storage to store its content). In addition to integrating such public cloud services into a public cloud-based Content Delivery Network, the MediaWise Cloud also provides advanced Quality of Service (QoS) management as required for the delivery of streamed and interactive high resolution multimedia content. In this paper, we give a brief overview of MediaWise Cloud architecture and present a comprehensive discussion on research objectives related to its service components. Finally, we also compare the features supported by the existing CDN services against the envisioned objectives of MediaWise Cloud.