Antonio Ridi

A Survey on Intrusive Load Monitoring for Appliance Recognition

Electricity load monitoring of appliances has become an important task considering the recent economic and ecological trends. In this game, machine learning has an important part to play, allowing for energy consumption understanding, critical equipment monitoring and even human activity recognition. This paper provides a survey of current researches on Intrusive Load Monitoring (ILM) techniques. ILM relies on low-end electricity meter devices spread inside the habitations, as opposed to Non-Intrusive Load Monitoring (NILM) that relies on an unique point of measurement, the smart meter. Potential applications and principles of ILMs are presented and compared to NILM. A focus is also given on feature extraction and machine learning algorithms typically used for ILM applications.

Unseen Appliances Identification

We assess the feasibility of unseen appliance recognition through the analysis of their electrical signatures recorded using low-cost smart plugs. By unseen, we stress that our approach focuses on the identification of appliances that are of different brands or models than the one in training phase. We follow a strictly defined protocol in order to provide comparable results to the scientific community. We first evaluate the drop of performance when going from seen to unseen appliances. We then analyze the results of different machine learning algorithms, as the k-Nearest Neighbor (k-NN) and Gaussian Mixture Models (GMMs). Several tunings allow us to achieve 74% correct accuracy using GMMs which is our current best system.

Toward Web Enhanced Building Automation Systems

The emerging concept of Smart Building relies on an intensive use of sensors and actuators and therefore appears, at first glance, to be a domain of predilection for the IoT. However, technology providers of building automation systems have been functioning, for a long time, with dedicated networks, communication protocols and APIs. Eventually, a mix of different technologies can even be present in a given building. IoT principles are now appearing in buildings as a way to simplify and standardise application development. Nevertheless, many issues remain due to this heterogeneity between existing installations and native IP devices that induces complexity and maintenance efforts of building management systems. A key success factor for the IoT adoption in Smart Buildings is to provide a loosely-coupled Web protocol stack allowing interoperation between all devices present in a building. We review in this chapter different strategies that are going in this direction. More specifically, we emphasise on several aspects issued from pervasive and ubiquitous computing like service discovery. Finally, making the assumption of seamless access to sensor data through IoT paradigms, we provide an overview of some of the most exciting enabling applications that rely on intelligent data analysis and machine learning for energy saving in buildings.

Hidden Markov Models for ILM Appliance Identification.

Abstract The automatic recognition of appliances through the monitoring of their electricity consumption finds many applications in smart buildings. In this paper we discuss the use of Hidden Markov Models (HMMs) for appliance recognition using so-called intrusive load monitoring (ILM) devices. Our motivation is found in the observation of electric signatures of appliances that usually show time varying profiles depending to the use made of the appliance or to the intrinsic internal operating of the appliance. To determine the benefit of such modelling, we propose a comparison of stateless modelling based on Gaussian mixture models and state-based models using Hidden Markov Models. The comparison is run on the publicly available database ACS-F1. We also compare differ- ent approaches to determine the best model topologies. More specifically we compare the use of a priori information on the device, a procedure based on a criteria of log-likelihood maximization and a heuristic approach.

A Multi-sensor Office-building Database for Experimental Validation and Advanced Control Algorithm Development☆

Data from multiple sensors and actuators has been recorded from December 2001 to March 2008 at the LESO-PB building of the EPFL campus, using the EIB/KNX bus standard. Sensors and actuators provided data on room temperature, presence, lighting level, windows opening, blinds position, electric lights and heating power. Weather data has also been collected and includes ambient temperature, solar radiation on a horizontal surface (direct and diffuse components), wind speed and direction and rain alarm. The data was written continuously to a MySQL database, each EIB/KNX telegram being recorded into the database. The primary goal of that setup was the experimental validation and checking of advanced control algorithms for the actuation of solar shadings (outside fabric blinds), electric lighting and heating equipment. With the aid of the database it was shown that such control algorithms were able to reduce significantly the energy consumption while keeping the same comfort or even improving it. Since 2002, the database has been used in various research projects carried out in LESO-PB. As of 2014 the database has been made freely accessible to the scientific community as a tool to work on.

Machine learning with the internet of virtual things

Peripheral devices working in the context of the Internet of Things, specifically sensors, produce large amounts of data that can be used to infer knowledge. In this area, machine learning technologies are increasingly used to establish versatile models. In this article, we present a new architecture capable of running machine learning algorithms in a sensor network. This approach has advantages in terms of confidentiality and energy efficiency-related data transfer. First, we argue that some types of machine learning algorithms are consistent with this approach, particularly those based on the use of generative algorithms. Subsequently we detail our proposed architecture based on Internet of Things and Web of Things paradigms facilitating the integration in sensor networks. The convergence of generative models and Web Objects leads to the concept of virtual sensors exposing high-level knowledge using data from various sensors. Finally, we demonstrate the feasibility and performance of our proposal using a real scenario.

Virtual Things for Machine Learning Applications

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 network, presenting advantages in terms of privacy and data transfer efficiency. We first argument that some classes of machine learning algorithms are compatible with this approach, namely based on the use of generative models that allow a distribution of the computation on a set of nodes. We then detail our architecture proposal, leveraging on the use of Web-of-Things technologies to ease integration into networks. The convergence of machine learning generative models and Web-of-Things paradigms leads us to the concept of virtual things exposing higher level knowledge by exploiting sensor data in the network. Finally, we demonstrate with a real scenario the feasibility and performances of our proposal.

Optimization of an electromyography-based activity recognition system

We present the optimization of a wearable surface electromyography-based system for activity recognition in relation with the number of sensed muscles. The muscles of interest were four: Gastrocnemius, Tibialis Anterior, Vastus Lateralis and Erector Spinae. In particular, the system has been tested for the recognition of five everyday activities: “walking”, “running”, “cycling”, “sitting” and “standing”. We conducted two types of analysis: impersonal and subjective. The impersonal analysis aimed to evaluate the recognition rate when the system was trained over different users. On the opposite, during the subjective analysis the system has been trained using the data coming from a single user. Moreover, we computed the relative computational costs. Among the results, we can highlight that using the signals sensed from three opportunely selected muscles (Gastrocnemius, Tibialis Anterior and Vastus Lateralis) instead of four did not entail a sensible loss of accuracy, whereas it reduced the computational cost of the 24.1 %. In particular, sensing four and three muscles we achieved an activity recognition accuracy higher than 96% for the impersonal analysis; for the subjective analysis, the attained accuracy was higher than 99%.

Towards glaucoma detection using intraocular pressure monitoring

Diagnosing the glaucoma is a very difficult task for healthcare professionals. High intraocular pressure (IOP) remains the main treatable symptom of this degenerative disease which leads to blindness. Nowadays, new types of wearable sensors, such as the contact lens sensor Triggerfish®, provide an automated recording of 24-hour profile of ocular dimensional changes related to IOP. Through several clinical studies, more and more IOP-related profiles have been recorded by those sensors and made available for elaborating data-driven experiments. The objective of such experiments is to analyse and detect IOP pattern differences between ill and healthy subjects. The potential is to provide medical doctors with analysis and detection tools allowing them to better diagnose and treat glaucoma. In this paper we present the methodologies, signal processing and machine learning algorithms elaborated in the task of automated detection of glaucomatous IOP-related profiles within a set of 100 24-hour recordings. As first convincing results, we obtained a classification ROC AUC of 81.5%.