Predictive intelligence to the edge through approximate collaborative context reasoning

Abstract

We focus on Internet of Things (IoT) environments where a network of sensing and computing devices are responsible to locally process contextual data, reason and collaboratively infer the appearance of a specific phenomenon (event). Pushing processing and knowledge inference to the edge of the IoT network allows the complexity of the event reasoning process to be distributed into many manageable pieces and to be physically located at the source of the contextual information. This enables a huge amount of rich data streams to be processed in real time that would be prohibitively complex and costly to deliver on a traditional centralized Cloud system. We propose a lightweight, energy-efficient, distributed, adaptive, multiple-context perspective event reasoning model under uncertainty on each IoT device (sensor/actuator). Each device senses and processes context data and infers events based on different local context perspectives: (i) expert knowledge on event representation, (ii) outliers inference, and (iii) deviation from locally predicted context. Such novel approximate reasoning paradigm is achieved through a contextualized, collaborative belief-driven clustering process, where clusters of devices are formed according to their belief on the presence of events. Our distributed and federated intelligence model efficiently identifies any localized abnormality on the contextual data in light of event reasoning through aggregating local degrees of belief, updates, and adjusts its knowledge to contextual data outliers and novelty detection. We provide comprehensive experimental and comparison assessment of our model over real contextual data with other localized and centralized event detection models and show the benefits stemmed from its adoption by achieving up to three orders of magnitude less energy consumption and high quality of inference.Keywords Collaborative event inference · Federated reasoning · Edge predictive intelligence · Optimal stopping theory · Adaptive vector quantization · Type-2 fuzzy logic inference

Large-scale predictive modeling and analytics through regression queries in data management systems

“…Then, we use the approximatef to address Problem 2 to approximate the data function g by a data-PLR functionĝ. Concerning Problem 1 and Theorem 2, we approximate f (x, θ) = E[y|x, θ] that minimizes (5). However, the answer y in (4) involves the average of the outputs g(…”

“…Out-with DMS environments, statistical packages like MAT-LAB and R 5 support fitting regression functions. However, 5 https://www.r-project.org/. their algorithms for doing so are inefficient and hardly scalable.…”

“…To obtain quality approximation, the CoD metric should be strictly greater than zero. This is achieved by setting the mean radius value μ θ < (0.4, 0.5) for d ∈ (5,2). Then, we can compensate the RMSE and training time (number of training pairs |T |) as shown in Figs.…”

“…Predictive Modeling and Analytics (PMA) concerns data exploration, model fitting, and regression model learning tasks used in many real-life applications [5,16,22,40,43]. The major goal of PMA is to explore and analyze multidimensional feature vector data spaces [1].…”

On the Optimality of Task Offloading in Mobile Edge Computing Environments

“…The vehicles can generate different types of data to be processed by the server. For example, these data can be for real time services such as image recognition, image processing or analytical task for data generated by embedded sensors within the car [16] or any other tasks as inferential and predictive analytics [17], statistical learning models building and/or models selection, [18]. Furthermore, the task can be generated by the passengers in vehicles using smart phones.…”