Figure 2 - uploaded by Jean Hennebert
Content may be subject to copyright.
(a) End-to-end mode and (b) sync-based mode.  

(a) End-to-end mode and (b) sync-based mode.  

Source publication
Article
Full-text available
Internet-of-Things (IoT) devices, especially sensors are producing large quantities of data that can be used for gathering knowledge. In this field, machine learning technologies are increasingly used to build versatile data-driven models. In this paper, we present a novel architecture able to execute machine learning algorithms within the sensor n...

Similar publications

Conference Paper
Full-text available
Resource constrained devices are the building blocks of the internet of things (IoT) era. Since the idea behind IoT is to develop an interconnected environment where the devices are tiny enough to operate with limited resources, several control systems have been built to maintain low energy and area consumption while operating as IoT edge devices....
Conference Paper
Full-text available
User testing is often used to inform the development of user interfaces (UIs). But what if an interface needs to be developed for a system that does not yet exist? In that case, existing datasets can provide valuable input for UI development. We apply a data-driven approach to the development of a privacy-setting interface for Internet-of-Things (I...

Citations

... Previous work already adopted similar algorithms to address such matters, as in Bovet et.al and Shahriar et. al [11] [12]. However, most of them use machine learning algorithms on static data series. ...
Conference Paper
Full-text available
IoT environments are typically composed of hundreds of geographically distributed sensors. Usually, these sensors are not physically protected from unauthorized access, which makes them vulnerable to exploitation where they can be manipulated to send incorrect data. The identification of such compromised sensors can be helpful in the process of exclusion or verification by administrators. To perform the detection of anomalous sensors, several algorithms can be used. However, based on the algorithm used, this evaluation may be delayed or can be inaccurate. Therefore, to detect sensors with different behavior compared to others, we evaluated the trade-off between performance and accuracy of different anomalies detection algorithms. The results showed that Mahalanobis Distance could improve the trade-off between detecting multiple anomalous sensors at execution time and accuracy to avoid false-positives.
... Diferentemente dos trabalhos anteriores, nossa proposta visa utilizar aprendizagem de máquina [Manadhata 2015] com o objetivo de analisar questões de segurança nos dados enviados por sensores em um ambiente de IoT. Alguns trabalhos já se utilizam desse tipo de técnica para endereçar tais questões, como em [Bovet et al. 2014] [Shahriar and Rahman 2015]. Porém, a maioria deles utiliza aprendizagem de máquina sobre séries estáticas de dados. ...
Conference Paper
Full-text available
Ambientes IoT podem manter centenas de sensores geograficamente distribuídos. Geralmente, esses sensores não são fisicamente protegidos con-tra acesso não autorizado. Isso significa que tais sensores podem ser comprometidos, e manipulados a enviar dados incorretos. Neste artigo, propomos a utilização de um algoritmo de descoberta de anomalias, que descobre sensores com comportamento distinto em comparação com os demais. Os resultados mostraram que Isolation Forest consegue detectar sensores anômalos em tempo de execução, o que permite a exclusão ou verificação desse sensor pelo administrador do ambiente.
... The system is able to detect in real time the appliance class and the state of the appliances. Another version of our system is able to perform appliance and state recognition directly on distributed devices by using the Internet-of-Things (IoT) paradigm [16]. The ACS-F2 database contains 450 electrical signatures coming from 225 appliances. ...