Temporal data are typically generated by natural processes that themselves may evolve or not with time going through a sequence of generative states. In this thesis, we investigate the use of generative approaches for machine learning systems applied on time series, such as Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs). More specifically, we investigate the opportunities under which such systems are comparing advantageously against discriminative approaches such as ANNs or SVMs. For example, we show the advantages of GMMs and HMMs in situations where scalability, adaptability and distributability of the models are important criteria. This thesis has been elaborated along two real-life applications for which such criteria revealed important.

Green-Mod. This project covered an interesting task aiming at identifying appliances through their electricity consumption signatures. An important contribution is in the collection of a database of 15 models/brands of 15 different categories that allowed us to compare systematically the machine learning algorithms. For this project, the scalability and distributability of GMMs revealed important.

Sensimed Data Intelligence. This project aims at the understanding and early detection of glaucoma from Internal Ocular Pressure related time series. Here the GMMs and HMMs, thanks to their solid probability framework, offered interesting opportunities to interpret the obtained results, which is a critical criterion for medical applications.

Publications

• A. Ridi, C. Gisler, and J. Hennebert, “Aggregation procedure of Gaussian Mixture Models for additive features,” in 23rd International Conference on Pattern Recognition (ICPR), 2016, pp. 2545-2550.
  [Bibtex]

  @conference{ridi:icpr2016,
  author = "Antonio Ridi and Christophe Gisler and Jean Hennebert",
  abstract = "In this work we provide details on a new and effective approach able to generate Gaussian Mixture Models (GMMs) for the classification of aggregated time series. More specifically, our procedure can be applied to time series that are aggregated together by adding their features. The procedure takes advantage of the additive property of the Gaussians that complies with the additive property of the features. Our goal is to classify aggregated time series, i.e. we aim to identify the classes of the single time series contributing to the total. The standard approach consists in training the models using the combination of several time series coming from different classes. However, this has the drawback of being a very slow operation given the amount of data. The proposed approach, called GMMs aggregation procedure, addresses this problem. It consists of three steps: (i) modeling the independent classes, (ii) generation of the models for the class combinations and (iii) simplification of the generated models. We show the effectiveness of our approach by using time series in the context of electrical appliance consumption, where the time series are aggregated by adding the active and reactive power. Finally, we compare the proposed approach with the standard procedure.",
  booktitle = "23rd International Conference on Pattern Recognition (ICPR)",
  editor = "IEEE",
  keywords = "machine learning, electric signal, appliance signatures, GMMs",
  month = "December",
  note = "Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.",
  pages = "2545-2550",
  title = "{A}ggregation procedure of {G}aussian {M}ixture {M}odels for additive features",
  url = "http://www.hennebert.org/download/publications/icpr-2016-aggregation-procedure-of-Gaussian-mixture-models-for-additive-features.pdf",
  year = "2016",
  }

• C. Gisler, A. Ridi, J. Hennebert, R. N. Weinreb, and K. Mansouri, “Automated Detection and Quantification of Circadian Eye Blinks Using a Contact Lens Sensor,” Translational Vision Science and Technology (TVST), vol. 4, iss. 1, pp. 1-10, 2015.
  [Bibtex]

  @article{gisler2015automated,
  Abstract = {Purpose: To detect and quantify eye blinks during 24-hour intraocular pressure (IOP) monitoring with a contact lens sensor (CLS). Methods: A total of 249 recordings of 24-hour IOP patterns from 202 participants using a CLS were included. Software was developed to automatically detect eye blinks, and wake and sleep periods. The blink detection method was based on detection of CLS signal peaks greater than a threshold proportional to the signal amplitude. Three methods for automated detection of the sleep and wake periods were evaluated. These relied on blink detection and subsequent comparison of the local signal amplitude with a threshold proportional to the mean signal amplitude. These methods were compared to manual sleep/wake verification. In a pilot, simultaneous video recording of 10 subjects was performed to compare the software to observer-measured blink rates. Results: Mean (SD) age of participants was 57.4 $\pm$ 16.5 years (males, 49.5%). There was excellent agreement between software-detected number of blinks and visually measured blinks for both observers (intraclass correlation coefficient [ICC], 0.97 for observer 1; ICC, 0.98 for observer 2). The CLS measured a mean blink frequency of 29.8 $\pm$ 15.4 blinks/min, a blink duration of 0.26 $\pm$ 0.21 seconds and an interblink interval of 1.91 $\pm$ 2.03 seconds. The best method for identifying sleep periods had an accuracy of 95.2 $\pm$ 0.5%. Conclusions: Automated analysis of CLS 24-hour IOP recordings can accurately quantify eye blinks, and identify sleep and wake periods. Translational Relevance: This study sheds new light on the potential importance of eye blinks in glaucoma and may contribute to improved understanding of circadian IOP characteristics.},
  Author = {Christophe Gisler and Antonio Ridi and Jean Hennebert and Robert N Weinreb and Kaweh Mansouri},
  Doi = {10.1167/tvst.4.1.4},
  Journal = {Translational Vision Science and Technology (TVST)},
  Keywords = {machine learning, bio-medical signals, glaucoma prediction},
  Month = {January},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Number = {1},
  Pages = {1-10},
  Publisher = {The Association for Research in Vision and Ophthalmology},
  Title = {{A}utomated {D}etection and {Q}uantification of {C}ircadian {E}ye {B}links {U}sing a {C}ontact {L}ens {S}ensor},
  Pdf = {http://www.hennebert.org/download/publications/TVST-2015-Automated-Detection-and-Quantification-of-Circadian-Eye-Blinks-Using-a-Contact-Lens-Sensor.pdf},
  Volume = {4},
  Year = {2015},
  Pdf = {http://www.hennebert.org/download/publications/TVST-2015-Automated-Detection-and-Quantification-of-Circadian-Eye-Blinks-Using-a-Contact-Lens-Sensor.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1167/tvst.4.1.4}}

• A. Ridi, N. Zarkadis, C. Gisler, and J. Hennebert, “Duration Models for Activity Recognition and Prediction in Buildings using Hidden Markov Models,” in Proceedings of the 2015 International Conference on Data Science and Advanced Analytics (DSAA 2015), Paris, France, 2015, p. 10.
  [Bibtex]

  @inproceedings{RidiDSAA2015,
  abstract = {Activity recognition and prediction in buildings can have multiple positive effects in buildings: improve elderly monitoring, detect intrusions, maximize energy savings and optimize occupant comfort. In this paper we apply human activity recognition by using data coming from a network of motion and door sensors distributed in a Smart Home environment. We use Hidden Markov Models (HMM) as the basis of a machine learning algorithm on data collected over an 8-month period from a single-occupant home available as part of the WSU CASAS Smart Home project. In the first implementation the HMM models 24 hours of activities and classifies them in 8 distinct activity categories with an accuracy rate of 84.6{\%}. To improve the identification rate and to help detect potential abnormalities related with the duration of an activity (i.e. when certain activities last too much), we implement minimum duration modeling where the algorithm is forced to remain in a certain state for a specific amount of time. Two subsequent implementations of the minimum duration HMM (mean-based length modeling and quantile length modeling) yield a further 2{\%} improvement of the identification rate. To predict the sequence of activities in the future, Artificial Neural Networks (ANN) are employed and identified activities clustered in 3 principal activity groups with an average accuracy rate of 71-77.5{\%}, depending on the forecasting window. To explore the energy savings potential, we apply thermal dynamic simulations on buildings in central European climate for a period of 65 days during the winter and we obtain energy savings for space heating of up to 17{\%} with 3-hour forecasting for two different types of buildings.},
  address = {Paris, France},
  author = {Ridi, Antonio and Zarkadis, Nikos and Gisler, Christophe and Hennebert, Jean},
  booktitle = {Proceedings of the 2015 International Conference on Data Science and Advanced Analytics (DSAA 2015)},
  editor = {Gaussier, Eric and Cao, Longbing},
  file = {:Users/gislerc/Documents/Mendeley/Articles/Ridi et al/Proceedings of the 2015 International Conference on Data Science and Advanced Analytics (DSAA 2015)/Ridi et al. - 2015 - Duration Models for Activity Recognition and Prediction in Buildings using Hidden Markov Models.pdf:pdf},
  isbn = {9781467382731},
  keywords = {Activity recognition,Energy savings in buildings,Expanded Hidden,Markov Models,Minimum Duration modeling,activity recognition,energy savings in buildings,expanded hidden,markov models,minimum duration modeling},
  mendeley-tags = {Activity recognition,Energy savings in buildings,Expanded Hidden,Markov Models,Minimum Duration modeling},
  pages = {10},
  publisher = {IEEE Computer Society},
  title = {{Duration Models for Activity Recognition and Prediction in Buildings using Hidden Markov Models}},
  url = {http://dsaa2015.lip6.fr},
  year = {2015}
  }

• A. Ridi, C. Gisler, and J. Hennebert, “Processing smart plug signals using machine learning,” in Wireless Communications and Networking Conference Workshops (WCNCW), 2015 IEEE, 2015, pp. 75-80.
  [Bibtex]

  @conference{ridi2015wcnc,
  Abstract = {The automatic identification of appliances through the analysis of their electricity consumption has several purposes in Smart Buildings including better understanding of the energy consumption, appliance maintenance and indirect observation of human activities. Electric signatures are typically acquired with IoT smart plugs integrated or added to wall sockets. We observe an increasing number of research teams working on this topic under the umbrella Intrusive Load Monitoring. This term is used as opposition to Non-Intrusive Load Monitoring that refers to the use of global smart meters. We first present the latest evolutions of the ACS-F database, a collections of signatures that we made available for the scientific community. The database contains different brands and/or models of appliances with up to 450 signatures. Two evaluation protocols are provided with the database to benchmark systems able to recognise appliances from their electric signature. We present in this paper two additional evaluation protocols intended to measure the impact of the analysis window length. Finally, we present our current best results using machine learning approaches on the 4 evaluation protocols.},
  Author = {A. Ridi and C. Gisler and J. Hennebert},
  Booktitle = {Wireless Communications and Networking Conference Workshops (WCNCW), 2015 IEEE},
  Doi = {10.1109/WCNCW.2015.7122532},
  Keywords = {learning,artificial intelligence, power engineering computing,power supplies to apparatus,ACS-F database,IoT smart plugs,machine learning approaches,smart buildings,smart plug signals,umbrella intrusive load monitoring,Accuracy,Databases,Hidden Markov mod},
  Month = {March},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Pages = {75-80},
  Title = {{P}rocessing smart plug signals using machine learning},
  Pdf = {http://www.hennebert.org/download/publications/wcncw-2015-Processing-smart-plug-signals-using-machine-learning.pdf},
  Year = {2015},
  Pdf = {http://www.hennebert.org/download/publications/wcncw-2015-Processing-smart-plug-signals-using-machine-learning.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1109/WCNCW.2015.7122532}}

• A. Ridi, C. Gisler, and J. Hennebert, “User Interaction Event Detection in the Context of Appliance Monitoring,” in The 13th International Conference on Pervasive Computing and Communications (PerCom 2015), Workshop on Pervasive Energy Services (PerEnergy), 2015, pp. 323-328.
  [Bibtex]

  @conference{ridi2015percom,
  Abstract = {In this paper we assess about the recognition of User Interaction events when handling electrical devices. This work is placed in the context of Intrusive Load Monitoring used for appliance recognition. ILM implies several Smart Metering Sensors to be placed inside the environment under analysis (in our case we have one Smart Metering Sensor per device). Our existing system is able to recognise the appliance class (as coffee machine, printer, etc.) and the sequence of states (typically Active / Non-Active) by using Hidden Markov Models as machine learning algorithm. In this paper we add a new layer to our system architecture called User Interaction Layer, aimed to infer the moments (called User Interaction events) during which the user interacts with the appliance. This layer uses as input the information coming from HMM (i.e. the recognised appliance class and the sequence of states). The User Interaction events are derived from the analysis of the transitions in the sequences of states and a ruled-based system adds or removes these events depending on the recognised class. Finally we compare the list of events with the ground truth and we obtain three different accuracy rates: (i) 96.3% when the correct model and the real sequence of states are known a priori, (ii) 82.5% when only the correct model is known and (iii) 80.5% with no a priori information.},
  Author = {Antonio Ridi and Christophe Gisler and Jean Hennebert},
  Booktitle = {The 13th International Conference on Pervasive Computing and Communications (PerCom 2015), Workshop on Pervasive Energy Services (PerEnergy)},
  Doi = {10.1109/PERCOMW.2015.7134056},
  Keywords = {domestic appliances;hidden Markov models;home automation;human computer interaction;learning (artificial intelligence);smart meters;HMM;ILM;appliance monitoring;appliance recognition;electrical devices;hidden Markov models;intrusive load monitoring;machine learning algorithm;ruled-based system;smart metering sensors;user interaction event detection;user interaction layer;Accuracy;Databases;Hidden Markov models;Home appliances;Mobile handsets;Monitoring;Senior citizens;Appliance Identification;Intrusive Load Monitoring (ILM);User-Appliance Interaction},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Pages = {323-328},
  Title = {{U}ser {I}nteraction {E}vent {D}etection in the {C}ontext of {A}ppliance {M}onitoring},
  Pdf = {http://www.hennebert.org/download/publications/percom-2015-User-Interaction-Event-Detection-in-the-Context-of-Appliance-Monitoring.pdf},
  Year = {2015},
  Pdf = {http://www.hennebert.org/download/publications/percom-2015-User-Interaction-Event-Detection-in-the-Context-of-Appliance-Monitoring.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1109/PERCOMW.2015.7134056}}

• G. Bovet, A. Ridi, and J. Hennebert, “Toward Web Enhanced Building Automation Systems – Big Data and Internet of Things: A Roadmap for Smart Environments,” , C. D. Nik Bessis, Ed., Springer, 2014, vol. 546, pp. 259-284.
  [Bibtex]

  @inbook{bovet:2014:bookchap,
  Abstract = {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.},
  Author = {G{\'e}r{\^o}me Bovet and Antonio Ridi and Jean Hennebert},
  Chapter = {11},
  Doi = {10.1007/978-3-319-05029-4_11},
  Editor = {Nik Bessis, Ciprian Dobre},
  Isbn = {9783319050287},
  Keywords = {iot, wot, smart building},
  Note = {http://www.springer.com/engineering/computational+intelligence+and+complexity/book/978-3-319-05028-7},
  Pages = {259-284},
  Publisher = {Springer},
  Series = {Studies in Computational Intelligence},
  Title = {{T}oward {W}eb {E}nhanced {B}uilding {A}utomation {S}ystems - {B}ig {D}ata and {I}nternet of {T}hings: {A} {R}oadmap for {S}mart {E}nvironments},
  Pdf = {http://hennebert.org/download/publications/springer-2014_towards-web-enhanced-building-automation-systems.pdf},
  Volume = {546},
  Year = {2014},
  Pdf = {http://hennebert.org/download/publications/springer-2014_towards-web-enhanced-building-automation-systems.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1007/978-3-319-05029-4_11}}

• G. Bovet, A. Ridi, and J. Hennebert, “Virtual Things for Machine Learning Applications:,” in Fifth International Workshop on the Web of Things – WoT 2014, 2014.
  [Bibtex]

  @conference{bovet2014:wot,
  Abstract = {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 setof 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.},
  Author = {G{\'e}r{\^o}me Bovet and Antonio Ridi and Jean Hennebert},
  Booktitle = {Fifth International Workshop on the Web of Things - WoT 2014},
  Doi = {10.1145/2684432.2684434},
  Isbn = {978-1-4503-3066-4},
  Journal = {Fifth International Workshop on the Web of Things (WoT 2014)},
  Keywords = {Machine learning, Sensor network, Web-of-Things, Internet-of-Things},
  Month = {oct},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Series = {International Conference on the Internet of Things - IoT 2014},
  Title = {{V}irtual {T}hings for {M}achine {L}earning {A}pplications:},
  Pdf = {http://www.hennebert.org/download/publications/wot-2014-virtual-things-for-machine-learning-applications.pdf},
  Year = {2014},
  Pdf = {http://www.hennebert.org/download/publications/wot-2014-virtual-things-for-machine-learning-applications.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1145/2684432.2684434}}

• G. Bovet, A. Ridi, and J. Hennebert, “Appliance Recognition on Internet-of-Things Devices,” in 4th Int. Conf. on Internet of Things. IoT 2014 MIT, MA, USA., 2014.
  [Bibtex]

  @conference{bovet2014:iotdemo,
  author = "G{\'e}r{\^o}me Bovet and Antonio Ridi and Jean Hennebert",
  abstract = "Machine Learning (ML) approaches are increasingly used to model data coming from sensor networks. Typical ML implementations are cpu intensive and are often running server-side. However, IoT devices provide increasing cpu capabilities and some classes of ML algorithms are compatible with distribution and downward scalability. In this demonstration we explore the possibility of distributing ML tasks to IoT devices in the sensor network. We demonstrate a concrete scenario of appliance recognition where a smart plug provides electrical measures that are distributed to WiFi nodes running the ML algorithms. Each node estimates class-conditional probabilities that are then merged for recognizing the appliance category. Finally, our architectures relies on Web technologies for complying with Web-of-Things paradigms.
  ",
  booktitle = "4th Int. Conf. on Internet of Things. IoT 2014 MIT, MA, USA.",
  keywords = "Internet-of-Things, Machine Learning, Appliance Recognition, NILM, Non Intrusive Load Monitoring, HMM, Hidden Markov Models",
  note = "Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.",
  title = "{A}ppliance {R}ecognition on {I}nternet-of-{T}hings {D}evices",
  Pdf = "http://www.hennebert.org/download/publications/iot-2014-appliance-recognition-on-internet-of-things-devices-demo-session.pdf",
  year = "2014",
  }

• C. Gisler, A. Ridi, M. Fauquey, D. Genoud, and J. Hennebert, “Towards Glaucoma Detection Using Intraocular Pressure Monitoring,” in The 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR 2014), 2014, pp. 255-260.
  [Bibtex]

  @conference{gisler2014:socpar,
  Abstract = {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{\textregistered}, 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%.},
  Author = {Christophe Gisler and Antonio Ridi and Mil{\`e}ne Fauquey and Dominique Genoud and Jean Hennebert},
  Booktitle = {The 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR 2014)},
  Doi = {10.1109/SOCPAR.2014.7008015},
  Isbn = {9781479959358},
  Keywords = {Biomedical signal processing, Glaucoma diagnosis, Machine learning},
  Pages = {255-260},
  Publisher = {Institute of Electrical and Electronics Engineers ( IEEE )},
  Title = {{T}owards {G}laucoma {D}etection {U}sing {I}ntraocular {P}ressure {M}onitoring},
  Pdf = {http://www.hennebert.org/download/publications/socpar-2014-towards-glaucoma-detection-using-intraocular-pressure-monitoring.pdf},
  Year = {2014},
  Pdf = {http://www.hennebert.org/download/publications/socpar-2014-towards-glaucoma-detection-using-intraocular-pressure-monitoring.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1109/SOCPAR.2014.7008015}}

• A. Ridi, C. Gisler, and J. Hennebert, “ACS-F2 – A new database of appliance consumption signatures,” in Soft Computing and Pattern Recognition (SoCPaR), 2014 6th International Conference of, 2014, pp. 145-150.
  [Bibtex]

  @conference{ridi2014socpar,
  Abstract = {We present ACS-F2, a new electric consumption signature database acquired from domestic appliances. The scenario of use is appliance identification with emerging applications such as domestic electricity consumption understanding, load shedding management and indirect human activity monitoring. The novelty of our work is to use low-end electricity consumption sensors typically located at the plug. Our approach consists in acquiring signatures at a low frequency, which contrast with high frequency transient analysis approaches that are costlier and have been well studied in former research works. Electrical consumption signatures comprise real power, reactive power, RMS current, RMS voltage, frequency and phase of voltage relative to current. A total of 225 appliances were recorded over two sessions of one hour. The database is balanced with 15 different brands/models spread into 15 categories. Two realistic appliance recognition protocols are proposed and the database is made freely available to the scientific community for the experiment reproducibility. We also report on recognition results following these protocols and using baseline recognition algorithms like k-NN and GMM.},
  Author = {A. Ridi and C. Gisler and J. Hennebert},
  Booktitle = {Soft Computing and Pattern Recognition (SoCPaR), 2014 6th International Conference of},
  Doi = {10.1109/SOCPAR.2014.7007996},
  Isbn = {9781479959358},
  Keywords = {machine learning, electric signal, appliance signatures},
  Month = {Aug},
  Pages = {145-150},
  Publisher = {IEEE},
  Title = {{ACS}-{F}2 - {A} new database of appliance consumption signatures},
  Pdf = {http://www.hennebert.org/download/publications/socpar-2014-ACS-F2-a-new-databas-of-appliance-consumption-signatures.pdf},
  Year = {2014},
  Pdf = {http://www.hennebert.org/download/publications/socpar-2014-ACS-F2-a-new-databas-of-appliance-consumption-signatures.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1109/SOCPAR.2014.7007996}}

• A. Ridi, C. Gisler, and J. Hennebert, “Appliance and State Recognition using Hidden Markov Models,” in The 2014 International Conference on Data Science and Advanced Analytics (DSAA 2014), Shangai, China, 2014, pp. 270-276.
  [Bibtex]

  @conference{ridi2014dsaa,
  Abstract = {We asset about the analysis of electrical appliance consumption signatures for the identification task. We apply Hidden Markov Models to appliance signatures for the identification of their category and of the most probable sequence of states. The electrical signatures are measured at low frequency (101 Hz) and are sourced from a specific database. We follow two predefined protocols for providing comparable results. Recovering information on the actual appliance state permits to potentially adopt energy saving measures, as switching off stand-by appliances or, generally speaking, changing their state. Moreover, in most of the cases appliance states are related to user activities: the user interaction usually involves a transition of the appliance state. Information about the state transition could be useful in Smart Home / Building Systems to reduce energy consumption and increase human comfort. We report the results of the classification tasks in terms of confusion matrices and accuracy rates. Finally, we present our application for a real-time data visualization and the recognition of the appliance category with its actual state.},
  Address = {Shangai, China},
  Author = {Antonio Ridi and Christophe Gisler and Jean Hennebert},
  Booktitle = {The 2014 International Conference on Data Science and Advanced Analytics (DSAA 2014)},
  Doi = {10.1109/DSAA.2014.7058084},
  Isbn = {9781479969821},
  Keywords = {Appliance Identification, Appliance State Recognition, Intrusive Load Monitoring, ILM},
  Month = {10/2014},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Pages = {270-276},
  Publisher = {Institute of Electrical and Electronics Engineers ( IEEE )},
  Title = {{A}ppliance and {S}tate {R}ecognition using {H}idden {M}arkov {M}odels},
  Pdf = {http://www.hennebert.org/download/publications/DSAA-2014-appliance-and-state-recognition-using-hidden-markov-models.pdf},
  Year = {2014},
  Pdf = {http://www.hennebert.org/download/publications/DSAA-2014-appliance-and-state-recognition-using-hidden-markov-models.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1109/DSAA.2014.7058084}}

• A. Ridi and J. Hennebert, “Hidden Markov Models for ILM Appliance Identification,” in The 5th International Conference on Ambient Systems, Networks and Technologies (ANT-2014), the 4th International Conference on Sustainable Energy Information Technology (SEIT-2014), 2014, p. 1010–1015.
  [Bibtex]

  @conference{ridi2014:ant,
  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.},
  Author = {Antonio Ridi and Jean Hennebert},
  Booktitle = {The 5th International Conference on Ambient Systems, Networks and Technologies (ANT-2014), the 4th International Conference on Sustainable Energy Information Technology (SEIT-2014)},
  Doi = {10.1016/j.procs.2014.05.526},
  Issn = {1877-0509},
  Keywords = {Hidden Markov Models, appliance recognition, Intrusive Load Monitoring},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Pages = {1010--1015},
  Series = {Procedia Computer Science},
  Title = {{H}idden {M}arkov {M}odels for {ILM} {A}ppliance {I}dentification},
  Pdf = {http://www.hennebert.org/download/publications/ant-ictsb-2014-hidden-markov-models-for-ILM-appliance-identification.pdf},
  Volume = {32},
  Year = {2014},
  Pdf = {http://www.hennebert.org/download/publications/ant-ictsb-2014-hidden-markov-models-for-ILM-appliance-identification.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.procs.2014.05.526}}

• A. Ridi, C. Gisler, and J. Hennebert, “A Survey on Intrusive Load Monitoring for Appliance Recognition,” in 22nd International Conference on Pattern Recognition – ICPR, 2014, pp. 3702-3707.
  [Bibtex]

  @conference{ridi2014:icpr,
  Abstract = {Electricity load monitoring of appliances has be- come 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.},
  Author = {Antonio Ridi and Christophe Gisler and Jean Hennebert},
  Booktitle = {22nd International Conference on Pattern Recognition - ICPR},
  Doi = {10.1109/ICPR.2014.636},
  Isbn = {9781479952106},
  Keywords = {Machine Learning, Intrusive Load Monitoring, ILM, IT for efficiency, Green Computing},
  Month = {August},
  Note = {Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.},
  Organization = {IEEE},
  Pages = {3702-3707},
  Title = {{A} {S}urvey on {I}ntrusive {L}oad {M}onitoring for {A}ppliance {R}ecognition},
  Pdf = {http://www.hennebert.org/download/publications/icpr-2014-a-survey-on-intrusive-load-monitoring-for-appliance-recognition.pdf},
  Year = {2014},
  Pdf = {http://www.hennebert.org/download/publications/icpr-2014-a-survey-on-intrusive-load-monitoring-for-appliance-recognition.pdf},
  Bdsk-Url-2 = {http://dx.doi.org/10.1109/ICPR.2014.636}}

• A. Ridi, C. Gisler, and J. Hennebert, “A Survey on Intrusive Load Monitoring for Appliance Recognition,” in 22nd International Conference on Pattern Recognition – ICPR, 2014, pp. 3702-3707.
  [Bibtex]

  @conference{ridi2014:icpr,
  author = "Antonio Ridi and Christophe Gisler and Jean Hennebert",
  abstract = "Electricity load monitoring of appliances has be- come 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.",
  booktitle = "22nd International Conference on Pattern Recognition - ICPR",
  doi = "10.1109/ICPR.2014.636",
  isbn = "9781479952106",
  keywords = "Machine Learning, Intrusive Load Monitoring, ILM, IT for efficiency, Green Computing",
  month = "August",
  note = "Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.",
  organization = "IEEE",
  pages = "3702-3707",
  title = "{A} {S}urvey on {I}ntrusive {L}oad {M}onitoring for {A}ppliance {R}ecognition",
  Pdf = "http://www.hennebert.org/download/publications/icpr-2014-a-survey-on-intrusive-load-monitoring-for-appliance-recognition.pdf",
  year = "2014",
  }

• C. Gisler, A. Ridi, and J. Hennebert, “Appliance Consumption Signature Database and Recognition Test Protocols,” in WOSSPA2013 The 9th International Workshop on Systems, Signal Processing and their Applications 2013, 2013, pp. 336-341.
  [Bibtex]

  @conference{gisler:2013:wosspa,
  author = "Christophe Gisler and Antonio Ridi and Jean Hennebert",
  abstract = "We report on the creation of a database of appliance consumption signatures and two test protocols to be used for appliance recognition tasks. By means of plug-based low-end sensors measuring the electrical consumption at low frequency, typically every 10 seconds, we made two acquisition sessions of one hour on about 100 home appliances divided into 10 categories: mobile phones (via chargers), coffee machines, computer stations (including monitor), fridges and freezers, Hi-Fi systems (CD players), lamp (CFL), laptops (via chargers), microwave oven, printers, and televisions (LCD or LED). We measured their consumption in terms of real power (W), reactive power (var), RMS current (A) and phase of voltage relative to current (varphi). We plan to give free access to the database for the whole scientific community. The proposed test protocols will help to objectively compare new algorithms. ",
  booktitle = "WOSSPA2013 The 9th International Workshop on Systems, Signal Processing and their Applications 2013",
  doi = "10.1109/WoSSPA.2013.6602387",
  isbn = "9781467355407",
  keywords = "electric consumption modelling, benchmark protocols",
  note = "Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.",
  pages = "336-341",
  title = "{A}ppliance {C}onsumption {S}ignature {D}atabase and {R}ecognition {T}est {P}rotocols",
  Pdf = "http://hennebert.org/download/publications/wosspa-2013-appliance-consumption-signature-database-and-recognition-test-protocols.pdf",
  year = "2013",
  }

• A. Ridi, N. Zarkadis, G. Bovet, N. Morel, and J. Hennebert, “Towards Reliable Stochastic Data-Driven Models Applied to the Energy Saving in Buildings,” in International Conference on Cleantech for Smart Cities & Buildings from Nano to Urban Scale (CISBAT 2013), 2013, pp. 501-506.
  [Bibtex]

  @conference{ridi2013:cisbat,
  author = "Antonio Ridi and Nikos Zarkadis and G{\'e}r{\^o}me Bovet and Nicolas Morel and Jean Hennebert",
  abstract = "We aim at the elaboration of Information Systems able to optimize energy consumption in buildings while preserving human comfort. Our focus is in the use of state-based stochas- tic modeling applied to temporal signals acquired from heterogeneous sources such as distributed sensors, weather web services, calendar information and user triggered events. Our general scientific objectives are: (1) global instead of local optimization of building automation sub-systems (heating, ventilation, cooling, solar shadings, electric lightings), (2) generalization to unseen building configuration or usage through self-learning data- driven algorithms and (3) inclusion of stochastic state-based modeling to better cope with seasonal and building activity patterns. We leverage on state-based models such as Hidden Markov Models (HMMs) to be able to capture the spatial (states) and temporal (sequence of states) characteristics of the signals. We envision several application layers as per the intrinsic nature of the signals to be modeled. We also envision room-level systems able to leverage on a set of distributed sensors (temperature, presence, electricity consumption, etc.). A typical example of room-level system is to infer room occupancy information or activities done in the rooms as a function of time. Finally, building-level systems can be composed to infer global usage and to propose optimization strategies for the building as a whole. In our approach, each layer may be fed by the output of the previous layers.
  More specifically in this paper, we report on the design, conception and validation of several machine learning applications. We present three different applications of state-based modeling. In the first case we report on the identification of consumer appliances through an analysis of their electric loads. In the second case we perform the activity recognition task, representing human activities through state-based models. The third case concerns the season prediction using building data, building characteristic parameters and meteorological data.",
  booktitle = "International Conference on Cleantech for Smart Cities {{\&}} Buildings from Nano to Urban Scale (CISBAT 2013)",
  keywords = "IT for Sustainability, Smart Buildings, Machine Learning",
  note = "Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.",
  pages = "501-506",
  title = "{T}owards {R}eliable {S}tochastic {D}ata-{D}riven {M}odels {A}pplied to the {E}nergy {S}aving in {B}uildings",
  Pdf = "http://www.hennebert.org/download/publications/cisbat-2013-towards-reliable-stochastic-data-driven-models-applied-to-the-energy-saving-in-building.pdf",
  year = "2013",
  }

• A. Ridi, C. Gisler, and J. Hennebert, “Unseen Appliances Identification,” in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 2013, p. 75–82.
  [Bibtex]

  @conference{ridi2013:ciarp,
  author = "Antonio Ridi and Christophe Gisler and Jean Hennebert",
  abstract = "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.",
  booktitle = "Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications",
  doi = "10.1007/978-3-642-41827-3_10",
  editor = "Jos{\'e} Ruiz-Shulcloper and Gabriella Sanniti di Baja",
  isbn = "9783642418266",
  keywords = "machine learning, nilm, appliance identification, load monitoring",
  pages = "75--82",
  publisher = "Springer",
  series = "Lecture Notes in Computer Science",
  title = "{U}nseen {A}ppliances {I}dentification",
  Pdf = "http://www.hennebert.org/download/publications/ciarp-2013-unseen-appliance-identification.pdf",
  volume = "8259",
  year = "2013",
  }

• A. Ridi, C. Gisler, and J. Hennebert, “Le machine learning: un atout pour une meilleure efficacité – applications à la gestion énergétique des bâtiments,” Bulletin Electrosuisse, iss. 10s, pp. 21-24, 2013.
  [Bibtex]

  @article{ridi2013:electrosuisse,
  author = "Antonio Ridi and Christophe Gisler and Jean Hennebert",
  abstract = "Comment g{\'e}rer de mani{\`e}re intelligente les consommations et productions d’{\'e}nergie dans les b{\^a}timents ? Les solutions {\`a} ce probl{\`e}me complexe pourraient venir du monde de l’apprentissage automatique ou «machine learning». Celui-ci permet la mise au point d’algorithmes de contr{\^o}le avanc{\'e}s visant simultan{\'e}ment la r{\'e}duction de la consommation d’{\'e}nergie, l’am{\'e}lioration du confort de l’utilisateur et l’adaptation {\`a} ses besoins.",
  issn = "1660-6728",
  journal = "Bulletin Electrosuisse",
  keywords = "Machine Learning, Energy Efficiency, Smart Buildings",
  number = "10s",
  pages = "21-24",
  title = "{L}e machine learning: un atout pour une meilleure efficacit{\'e} - applications {\`a} la gestion {\'e}nerg{\'e}tique des b{\^a}timents",
  Pdf = "http://hennebert.org/download/publications/electrosuisse-2013-machine-learning-meilleure-efficacite.pdf",
  year = "2013",
  }

• A. Ridi, C. Gisler, and J. Hennebert, “Automatic Identification of Electrical Appliances Using Smart Plugs,” in WOSSPA2013 The 9th International Workshop on Systems, Signal Processing and their Applications 2013, Algeria, 2013, pp. 301-305.
  [Bibtex]

  @conference{ridi:2013:wosspa,
  author = "Antonio Ridi and Christophe Gisler and Jean Hennebert",
  abstract = "We report on the evaluation of signal processing and classification algorithms to automatically recognize electric appliances. The system is based on low-cost smart-plugs measuring periodically the electricity values and producing time series of measurements that are specific to the appliance consumptions. In a similar way as for biometric applications, such electric signatures can be used to identify the type of appliance in use. In this paper, we propose to use dynamic features based on time derivative and time second derivative features and we compare different classification algorithms including K-Nearest Neighbor and Gaussian Mixture Models. We use the recently recorded electric signature database ACS-F1 and its intersession protocol to evaluate our algorithm propositions. The best combination of features and classifiers shows 93.6% accuracy.",
  address = "Algeria",
  booktitle = "WOSSPA2013 The 9th International Workshop on Systems, Signal Processing and their Applications 2013",
  doi = "10.1109/WoSSPA.2013.6602380",
  isbn = "9781467355407",
  keywords = "machine learning, electric consumption analysis, GMM, HMM",
  month = "May",
  note = "Some of the files below are copyrighted. They are provided for your convenience, yet you may download them only if you are entitled to do so by your arrangements with the various publishers.",
  pages = "301-305",
  publisher = "IEEE",
  title = "{A}utomatic {I}dentification of {E}lectrical {A}ppliances {U}sing {S}mart {P}lugs",
  Pdf = "http://hennebert.org/download/publications/wosspa-2013-automatic-identification-of-electrical-appliances-using-smart-plugs.pdf",
  year = "2013",
  }