A Data Analytics Schema for Activity Recognition in Smart Home Environments

Fortino, Giancarlo; Giordano, Andrea; Guerrieri, Antonio; Spezzano, Giandomenico; Vinci, Andrea

doi:10.1007/978-3-319-26401-1_9

Cited by 10 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Smart home has a linear growth, with 230 documents, and 111 in the last year, with China as the leading country. The most important related topics for Smart home are security [91][92][93], ZigBee [94][95][96], and activity recognition [97][98][99].…”

Section: Applicationsmentioning

confidence: 99%

Internet of Things: A Scientometric Review

et al. 2017

View full text Add to dashboard Cite

Abstract:Internet of Things (IoT) is connecting billions of devices to the Internet. These IoT devices chain sensing, computation, and communication techniques, which facilitates remote data collection and analysis. wireless sensor networks (WSN) connect sensing devices together on a local network, thereby eliminating wires, which generate a large number of samples, creating a big data challenge. This IoT paradigm has gained traction in recent years, yielding extensive research from an increasing variety of perspectives, including scientific reviews. These reviews cover surveys related to IoT vision, enabling technologies, applications, key features, co-word and cluster analysis, and future directions. Nevertheless, we lack an IoT scientometrics review that uses scientific databases to perform a quantitative analysis. This paper develops a scientometric review about IoT over a data set of 19,035 documents published over a period of 15 years (2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013)(2014)(2015)(2016) in two main scientific databases (Clarivate Web of Science and Scopus). A Python script called ScientoPy was developed to perform quantitative analysis of this data set. This provides insight into research trends by investigating a lead author's country affiliation, most published authors, top research applications, communication protocols, software processing, hardware, operating systems, and trending topics. Furthermore, we evaluate the top trending IoT topics and the popular hardware and software platforms that are used to research these trends.

show abstract

Section: Applicationsmentioning

confidence: 99%

Internet of Things: A Scientometric Review

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Moreover, especially the requirement for flexible data processing extension as well as personalization of data analytics were only partially tackled by two solutions. In this regard, Fortino et al propose an architecture for activity recognition in smart home environments [21]. While they describe their solution as a platform-and software-as-a-service solution, the amount of configuration needed and individualization remains nebulous.…”

Section: Related Researchmentioning

confidence: 99%

A Cloud-based Analytics-Platform for User-centric Internet of Things Domains – Prototype and Performance Evaluation

Zschörnig¹,

Windolph²,

Wehlitz³

et al. 2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Data analytics have the potential to increase the value of data emitted from smart devices in usercentric Internet of Things environments, such as smart home, drastically. In order to allow businesses and end-consumers alike to tap into this potential, appropriate analytics architectures must be present. Current solutions in this field do not tackle all of the diverse challenges and requirements, which were identified in previous research. Specifically, personalized, extensible analytics solutions, which still offer the means to address big data problems are scarce. In this paper, we therefore present an architectural solution, which was specifically designed to address the named challenges. Furthermore, we offer insights into the prototypical implementation of the proposed concept as well as an evaluation of its performance against traditional big data architectures.

show abstract

“…For instance, the smart home is being discussed as a solution that can socially and medically assist the infirm by monitoring them through numerous smart devices [9]. Furthermore, various research is being conducted on how smart home data can be processed and analyzed efficiently [10].…”

Section: Introductionmentioning

confidence: 99%

Low-Power On-Chip Implementation of Enhanced SVM Algorithm for Sensors Fusion-Based Activity Classification in Lightweighted Edge Devices

2022

View full text Add to dashboard Cite

Smart homes assist users by providing convenient services from activity classification with the help of machine learning (ML) technology. However, most of the conventional high-performance ML algorithms require relatively high power consumption and memory usage due to their complex structure. Moreover, previous studies on lightweight ML/DL models for human activity classification still require relatively high resources for extremely resource-limited embedded systems; thus, they are inapplicable for smart homes’ embedded system environments. Therefore, in this study, we propose a low-power, memory-efficient, high-speed ML algorithm for smart home activity data classification suitable for an extremely resource-constrained environment. We propose a method for comprehending smart home activity data as image data, hence using the MNIST dataset as a substitute for real-world activity data. The proposed ML algorithm consists of three parts: data preprocessing, training, and classification. In data preprocessing, training data of the same label are grouped into further detailed clusters. The training process generates hyperplanes by accumulating and thresholding from each cluster of preprocessed data. Finally, the classification process classifies input data by calculating the similarity between the input data and each hyperplane using the bitwise-operation-based error function. We verified our algorithm on `Raspberry Pi 3’ and `STM32 Discovery board’ embedded systems by loading trained hyperplanes and performing classification on 1000 training data. Compared to a linear support vector machine implemented from Tensorflow Lite, the proposed algorithm improved memory usage to 15.41%, power consumption to 41.7%, performance up to 50.4%, and power per accuracy to 39.2%. Moreover, compared to a convolutional neural network model, the proposed model improved memory usage to 15.41%, power consumption to 61.17%, performance to 57.6%, and power per accuracy to 55.4%.

show abstract

A Data Analytics Schema for Activity Recognition in Smart Home Environments

Cited by 10 publications

References 16 publications

Internet of Things: A Scientometric Review

Internet of Things: A Scientometric Review

A Cloud-based Analytics-Platform for User-centric Internet of Things Domains – Prototype and Performance Evaluation

Low-Power On-Chip Implementation of Enhanced SVM Algorithm for Sensors Fusion-Based Activity Classification in Lightweighted Edge Devices

Contact Info

Product

Resources

About