« Back

Gisler Christophe

Adjoint scientifique HES

Main skills

Adjoint scientifique HES

Phone: +41 26 429 69 37

Desktop: HEIA_D20.19

Haute école d'ingénierie et d'architecture de Fribourg
Boulevard de Pérolles 80, 1700 Fribourg, CH

Institute
iCoSys - Institut des systèmes complexes

BSc HES-SO en Informatique - Haute école d'ingénierie et d'architecture de Fribourg

Human Computer Interfaces

Ongoing

Datalambic – Semi-Automated Linguistic Data Acquisition

Role: Collaborator

Financement: Innosuisse

Description du projet :

The purpose of the Datalambic Project is to create a tool ecosystem for semi-automated collection, preparation and correction of high-quality data in order to (re)train neural translation engines in the desired specialization(s), including looped feedback from linguists, lawyers and users.

Research team within HES-SO: Gisler Christophe , Hennebert Jean

Partenaires professionnels: Paula Reichenberg, Hieronymus AG

Durée du projet: 01.12.2020

Url of the project site: https://icosys.ch/datalambic

Statut: Ongoing

IREM – Intelligent Real Estate Marketing

Role: Co-applicant

Financement: Innosuisse

Description du projet :

Le projet IREM vise un système intelligent capable de conseiller automatiquement les agents immobiliers sur leur stratégie publicitaire numérique.

Research team within HES-SO: Gisler Christophe , Hennebert Jean

Partenaires professionnels: Maillard Patrick, Immomig SA

Statut: Ongoing

Completed

AINews

Role: Collaborator

Requérant(e)s: Faessler Jean-Daniel, DjeBots, Fribourg

Financement: Innosuisse

Description du projet :

IT technologies are revolutionizing ways readers access and consume the information. The local press must innovate to meet its readers’ expectations and face the competition of free news sites and social networks.

AINews aims to introduce artificial intelligence (AI) into chatbot technologies dedicated to the press profession. AI will allow to personalize the news content for the reader, to interact with the readers through dialogue interfaces of the trendiest messaging applications, and to bring information back to the newspaper’s editorial board in order to dynamize their editorial departments.

Co-financed by Innosuisse, the AINews project will allow Djebots to implement a cutting-edge digital solution that may be used by La Liberté in order to cope with digital transformations and new trends of information consumption. La Liberté will be able to adapt its offer thanks to these technologies and explore new options to retain its readers.

Research team within HES-SO: Biselx Timothée , Gisler Christophe , Hennebert Jean

Partenaires académiques: Ayer Jean-Marie, HEG-FR; Casagrande-Caille Laurence, HEG-FR

Partenaires professionnels: Faessler Jean-Daniel, DjeBots, Fribourg

Durée du projet: - 20.09.2020

Url of the project site: https://icosys.ch/ainews

Statut: Completed

TAKE – Tactical Ad-hoc networK Emulation

Role: Collaborator

Description du projet :

Development and emulation of new mobile tactical networks based on wireless communications

Research team within HES-SO: Wagen Jean-Frédéric , Buntschu François , Hennebert Jean , Gisler Christophe , Ruffieux Simon

Partenaires professionnels: Bovet Gérôme, Armasuisse, Thun

Durée du projet: - 31.12.2019

Statut: Completed

SPAMOR

AGP

Role: Collaborator

Requérant(e)s: Imagerie, Tièche François, Imagerie

Financement: HES-SO Rectorat

Description du projet : De nos jours, nous utilisons facilement, à travers le web, un service de calcul d'itinéraires pour trouver notre chemin pour aller d'un endroit à l'autre. Ces itinéraires sont dédiés à des voitures et des piétons mais ne sont pas adaptés à des personnes à mobilité réduite, comme des usagers de fauteuils roulants. En effet, il existe toute une série d'obstacles compliquant les déplacements en chaises roulantes qui ne sont pas cartographiés, comme la rugosité du sol, la largeur minimale des passages ou l'angle d'inclinaison des rampes, Ce projet a pour but de développer une application aidant les personnes en chaise roulante. D'une part, il propose de réaliser une application pour Smartphone qui permet de calculer des itinéraires adaptés aux caractéristiques des chaises roulantes. D'autre part, il consiste à réaliser un système de mesure, une sorte de GoogleCar dédié à la mobilité réduite, pour faciliter la cartographie des obstacles décrits ci-dessus. Le dispositif de mesure développé doit pouvoir être facilement installé sur une chaise roulante afin d`être mis à disposition de toute personne désirant participer à l'alimentation de la base de donnée collaborative. Une fois ce dispositif embarqué il enregistre les chemins parcourus et mesure les obstacles. De retour chez lui, un contributeur peut connecter son appareil à un ordinateur afin de transférer les données recueillies sur les bases de données de notre système. Ces données sont alors traitées par des algorithmes dédiés afin d'en extraire des métadonnées utilisables pour obtenir des itinéraire et visualiser les obstacles. Cette extraction nécessite de mettre ensemble toutes les informations provenant de différents capteurs et de mesures faites à différents instants, on utilise pour cela des techniques dites de fusion de données. A partir de ces données, il faut établir des métadonnées qui seront utilisées pour la visualisation des obstacles sur une carte, mais aussi pour le calcul d'itinéraires adaptés aux déplacements en chaises roulantes. L'innovation de ce projet est d'offrir un service d'itinéraire qui n'existe pas pour des personnes à mobilité réduite, mais surtout de faciliter la complétion des cartes adaptées à la mobilité réduite. Une autre innovation est d'ouvrir la construction de la carte, non pas à uniquement à des spécialistes mais à toute personne voulant contribuer sans avoir besoin de compétences particulières en cartographie

Research team within HES-SO: Gisler Christophe , Sommer Nicolas , Chabbi Houda , Tièche François , Wolf Beat

Partenaires académiques: FR - EIA - Institut iCoSys; Imagerie; Tièche François, Imagerie

Durée du projet: 01.01.2016 - 31.07.2017

Montant global du projet: 64'300 CHF

Statut: Completed

Sensimed - Glaucoma Prognostication Platform - CTI 17325.1 PFLS-LS

AGP

Role: Collaborator

Requérant(e)s: VS - Institut Informatique

Financement: CTI; SENSIMED AG

Description du projet : The purpose is to provide a machine learning platform for 24h profiles of ocular dimensional changes to predict the progression of glaucoma. The value in prognosing glaucoma is to escalate therapy of under-treated patients to the appropriate level of medication while keeping patients under current treatment stable during time. For both kind of patients the goal is to preserve their vision and reduce both direct and indirect cost to society

Research team within HES-SO: Martin Simon , Gisler Christophe , Genoud Dominique , Hennebert Jean , Beffa Yann-Ivain , Zayene Oussama , Donzallaz Jonathan , Chassot Laurent , Hunacek Daniel , Treboux Jérôme

Partenaires académiques: VS - Institut Informatique; FR - EIA - Institut iCoSys

Durée du projet: 01.12.2014 - 31.10.2016

Montant global du projet: 414'111 CHF

Url of the project site: https://icosys.ch/sensimed-diagnosis

Statut: Completed

2024

ZigZag: A Robust Adaptive Approach to Non-Uniformly Illuminated Document Image Binarization

Scientific paper

Jean-Luc Bloechle, Hennebert Jean, Gisler Christophe

Proceedings of the ACM Symposium on Document Engineering 2024, 2024

Link to the publication

Summary:

In the era of mobile imaging, the quality of document photos captured by smartphones often suffers due to adverse lighting conditions. Traditional document analysis and optical character recognition systems encounter difficulties with images that have not been effectively binarized, particularly under challenging lighting scenarios. This paper introduces a novel adaptive binarization algorithm optimized for such difficult lighting environments. Unlike many existing methods that rely on complex machine learning models, our approach is streamlined and machine-learning free, designed around integral images to significantly reduce computational and coding complexities. This approach enhances processing speed and improves accuracy without the need for computationally expensive training procedures. Comprehensive testing across various datasets, from smartphone-captured documents to historical manuscripts, validates its effectiveness. Moreover, the introduction of versatile output modes, including color foreground extraction, substantially enhances document quality and readability by effectively eliminating unwanted background artifacts. These enhancements are valuable in mobile document image processing across industries that prioritize efficient and accurate document management, spanning sectors such as banking, insurance, education, and archival management.

2023

YinYang, a Fast and Robust Adaptive Document Image Binarization for Optical Character Recognition

Scientific paper

Jean-Luc Bloechle, Hennebert Jean, Gisler Christophe

Proceedings of the ACM Symposium on Document Engineering 2023, 2023

Link to the publication

Summary:

Optical Character Recognition (OCR) from document photos taken by cell phones is a challenging task. Most OCR methods require prior binarization of the image, which can be difficult to achieve when documents are captured with various mobile devices in unknown lighting conditions. For example, shadows cast by the camera or the camera holder on a hard copy can jeopardize the bina- rization process and hinder the next OCR step. In the case of highly uneven illumination, binarization methods using global thresh- olding simply fail, and state-of-the-art adaptive algorithms often deliver unsatisfactory results. In this paper, we present a new bina- rization algorithm using two complementary local adaptive passes and taking advantage of the color components to improve results over current image binarization methods. The proposed approach gave remarkable results at the DocEng’22 competition on the bina- rization of photographed documents.

2018

Reproducing measured MANET radio performances using the EMANE framework

Scientific paper ArODES

Alexandre Nidokemski, Jean-Frédéric Wagen, François Buntschu, Christophe Gisler, Jérôme Bovet

IEEE Communications Magazine, 2018, vol. 56, no. 10, pp. 151-155

Link to the publication

Summary:

Simulation or emulation of mobile ad hoc networks (MANET) is used to predict or analyze the performance of MANETs under various scenarios. One challenge is to emulate realistically the MANET's radio performance. Running the Extendable Mobile Ad Hoc Network Emulator (EMANE) framework, we show how to reproduce measured characteristics, namely throughput and round-trip time, of real tactical radios using wideband or narrowband TDMA-based waveforms. Additionally, a solution to simulate rate adaptation is proposed. An introduction to EMANE and the EMANE radio model plugins is also provided.

Use of machine learning on contact lens sensor :

Scientific paper ArODES

derived parameters for the diagnosis of primary open-angle glaucoma

Keith R. Martin, Kaweh Mansouri, Robert N. Weinreb, Robert Wasilewicz, Christophe Gisler, Jean Hennebert, Dominique Genoud

American Journal of Ophthalmology, 2018, vol. 194, pp. 46-53

Link to the publication

Summary:

Purpose : To test the hypothesis that contact lens sensor (CLS)-based 24-hour profiles of ocular volume changes contain information complementary to intraocular pressure (IOP) to discriminate between primary open-angle glaucoma (POAG) and healthy (H) eyes. Design : Development and evaluation of a diagnostic test with machine learning. Methods : Subjects: From 435 subjects (193 healthy and 242 POAG), 136 POAG and 136 age-matched healthy subjects were selected. Subjects with contraindications for CLS wear were excluded. Procedure: This is a pooled analysis of data from 24 prospective clinical studies and a registry. All subjects underwent 24-hour CLS recording on 1 eye. Statistical and physiological CLS parameters were derived from the signal recorded. CLS parameters frequently associated with the presence of POAG were identified using a random forest modeling approach. Main Outcome Measures: Area under the receiver operating characteristic curve (ROC AUC) for feature sets including CLS parameters and Start IOP, as well as a feature set with CLS parameters and Start IOP combined. Results : The CLS parameters feature set discriminated POAG from H eyes with mean ROC AUCs of 0.611, confidence interval (CI) 0.493–0.722. Larger values of a given CLS parameter were in general associated with a diagnosis of POAG. The Start IOP feature set discriminated between POAG and H eyes with a mean ROC AUC of 0.681, CI 0.603–0.765. The combined feature set was the best indicator of POAG with an ROC AUC of 0.759, CI 0.654–0.855. This ROC AUC was statistically higher than for CLS parameters or Start IOP feature sets alone (both P < .0001). Conclusions : CLS recordings contain information complementary to IOP that enable discrimination between H and POAG. The feature set combining CLS parameters and Start IOP provide a better indication of the presence of POAG than each of the feature sets separately. As such, the CLS may be a new biomarker for POAG.

TAKE—tactical ad-hoc network emulation

Scientific paper

Ruffieux Simon, Gisler Christophe, Wagen Jean-Frédéric, Buntschu François, Gérôme Bovet

2018 International Conference on Military Communications and Information Systems (ICMCIS), 2018 , pp. 1-8

Link to the publication

Reproducing measured manet radio performances using the emane framework

Scientific paper

Alexandre Nikodemski, Gisler Christophe, Wagen Jean-Frédéric, Buntschu François, Gérôme Bovet

IEEE Communications Magazine, 2018 , vol. 56, no 10, pp. 151-155

Link to the publication

Use of machine learning on contact lens sensor–derived parameters for the diagnosis of primary open-angle glaucoma

Scientific paper

Keith R. Martin, Kaweh Mansouri, Robert N. Weinreb, Robert Wasilevicz, Gisler Christophe, Hennebert Jean, Genoud Dominique

American journal of ophthalmology, 2018 , vol. 194, pp. 46-53

Link to the publication

2016

Aggregation procedure of Gaussian Mixture Models for additive features

Scientific paper

Antonio Ridi, Gisler Christophe, Hennebert Jean

2016 23rd International Conference on Pattern Recognition (ICPR), 2016

Link to the publication

2015

Automated detection and quantification of circadian eye blinks using a contact lens sensor

Scientific paper ArODES

Christophe Gisler, Antonio Ridi, Jean Hennebert, Robert N. Winreb, Kaweh Mansouri

Translational Vision Science Technology (TVST), 2015, vol. 4, no. 1, article no. 4

Link to the publication

Summary:

To detect and quantify eye blinks during 24-hour intraocular pressure (IOP) monitoring with a contact lens sensor (CLS). 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. Mean (SD) age of participants was 57.4 ± 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 ± 15.4 blinks/min, a blink duration of 0.26 ± 0.21 seconds and an interblink interval of 1.91 ± 2.03 seconds. The best method for identifying sleep periods had an accuracy of 95.2 ± 0.5%. Automated analysis of CLS 24-hour IOP recordings can accurately quantify eye blinks, and identify sleep and wake periods. This study sheds new light on the potential importance of eye blinks in glaucoma and may contribute to improved understanding of circadian IOP characteristics.

Duration models for activity recognition and prediction in buildings using hidden markov models

Scientific paper

Antonio Ridi, Zarkadis Nikos, Gisler Christophe, Hennebert Jean

2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2015 , pp. 1-10

Link to the publication

User interaction event detection in the context of appliance monitoring

Scientific paper

Gisler Christophe

2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 2015 , pp. 323-328

Link to the publication

Processing smart plug signals using machine learning

Scientific paper

Antonio Ridi, Gisler Christophe, Hennebert Jean

2015 IEEE wireless communications and networking conference workshops (WCNCW), 2015 , pp. 75-80

Link to the publication

Automated detection and quantification of circadian eye blinks using a contact lens sensor

Scientific paper

Gisler Christophe, Antonio Ridi, Hennebert Jean, Robert N. Weinreb, Kaweh Mansouri

Translational vision science & technology, 2015 , vol. 4, no 1

Link to the publication

2014

Towards Glaucoma Detection Using Intraocular Pressure Monitoring

Scientific paper

Gisler Christophe, Antonio Ridi, Milène Fauquex, Genoud Dominique, Hennebert Jean

The 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR 2014), 2014

Link to the publication

Appliance and state recognition using Hidden Markov Models

Scientific paper

Antonio Ridi, Gisler Christophe, Hennebert Jean

2014 international conference on data science and advanced analytics (DSAA), 2014

Link to the publication

ACS-F2 – A New Database of Appliance Consumption Signatures

Scientific paper

Antonio Ridi, Gisler Christophe, Hennebert Jean

The 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR 2014), 2014

Link to the publication

A survey on intrusive load monitoring for appliance recognition

Scientific paper

Antonio Ridi, Gisler Christophe, Hennebert Jean

22nd international conference on pattern recognition, 2014

Link to the publication

2013

Le machine learning :

Professional paper ArODES

un atout pour une meilleure efficacité : applications à la gestion énergétique des bâtiments

Antonio Ridi, Christophe Gisler, Jean Hennebert

bulletin.ch = Fachzeitschrift und Verbandsinformationen von Electrosuisse und VSE = Bulletin SEV/AES : revue spécialisée et informations des associations Electrosuisse et AES, 2013, 104, 10s, 21-24

Link to the publication

Summary:

Comment gérer de manière intelligente les consommations et productions d'énergie dans les bâtiments? Les solutions à ce problème complexe pourraient venir du monde de l'apprentissage automatique ou « machine learning ». Celui-ci permet la mise au point d'algorithmes de contrôle avancés visant simultanément la réduction de la consommation d'énergie, l'amélioration du confort de l'utilisateur et l'adaptation à ses besoins.

Unseen Appliances Identification

Scientific paper

Antonio Ridi, Gisler Christophe, Hennebert Jean

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 2013 , vol. 8259, pp. 75-82

Link to the publication

Automatic Identification of Electrical Appliances Using Smart Plugs

Scientific paper

Gisler Christophe, Antonio Ridi, Hennebert Jean

The 8th International Workshop on Systems, Signal Processing and their Applications 2013 (WoSSPA 2013), 2013

Link to the publication

Appliance Consumption Signature Database and Recognition Test Protocols

Scientific paper

Gisler Christophe, Antonio Ridi, Hennebert Jean

The 8th International Workshop on Systems, Signal Processing and their Applications 2013 (WoSSPA 2013), 2013

Link to the publication

2012

Demonstration of a Monitoring Lamp to Visualize the Energy Consumption in Houses

Scientific paper

Gisler Christophe, Grazia Barchi, Gérôme Bovet, Mugellini Elena, Monnet Stephen

The 10th International Conference on Pervasive Computing (Pervasive 2012), 2012

Link to the publication

Machine Learning Approaches for Electric Appliance Classification

Scientific paper

Damien Zufferey, Gisler Christophe, Abou Khaled Omar, Hennebert Jean

The 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2012), 2012 , pp. 740-745

Link to the publication

2024

ZigZag :

Conference ArODES

a robust adaptive approach to non-uniformly illuminated document image binarization

Jean-Luc Bloechle, Jean Hennebert, Christophe Gisler

Proceedings of the DocEng'24: ACM Symposium on Document Engineering 2024, 20-23 August 2024, San Jose, CA, United States

Link to the conference

Summary:

2023

YinYang, a fast and robust adaptive document image binarization for optical character recognition

Conference ArODES

Jean Luc Bloechle, Jean Hennebert, Christophe Gisler

Proceedings of the ACM Symposium on Document Engineering (DocEng'23), 22-25 August 2023, Limerick, Ireland

Link to the conference

Summary:

Optical Character Recognition (OCR) from document photos taken by cell phones is a challenging task. Most OCR methods require prior binarization of the image, which can be difficult to achieve when documents are captured with various mobile devices in unknown lighting conditions. For example, shadows cast by the camera or the camera holder on a hard copy can jeopardize the binarization process and hinder the next OCR step. In the case of highly uneven illumination, binarization methods using global thresholding simply fail, and state-of-the-art adaptive algorithms often deliver unsatisfactory results. In this paper, we present a new binarization algorithm using two complementary local adaptive passes and taking advantage of the color components to improve results over current image binarization methods. The proposed approach gave remarkable results at the DocEng'22 competition on the binarization of photographed documents.

2017

Aggregation procedure of Gaussian Mixture Models for additive features

Conference ArODES

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of 2016 23rd International Conference on Pattern Recognition (ICPR), 4-8 December 2016, Cancun, Mexico

Link to the conference

Summary:

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.

2015

Duration models for activity recognition and prediction in buildings using hidden Markov models

Conference ArODES

Antonio Ridi, Nikos Zarkadis, Christophe Gisler, Jean Hennebert

Proceedings of 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 19-21 October 2015, Paris, France

Link to the conference

Summary:

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.

User interaction event detection in the context of appliance monitoring

Conference ArODES

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 23-27 March 2015, St. Louis, MO, USA

Link to the conference

Summary:

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.

Processing smart plug signals using machine learning

Conference ArODES

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of 2015 IEEE Wireless Communications and Networking Conference Workshops (WCNCW), 9-12 March 2015, New Orleans, LA, USA

Link to the conference

Summary:

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.

Towards glaucoma detection using intraocular pressure monitoring

Conference ArODES

Christophe Gisler, Antonio Ridi, Milène Fauquex, Dominique Genoud, Jean Hennebert

Proceedings of the 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR), 11-14 August 2014, Tunis, Tunisia

Link to the conference

Summary:

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%.

2014

Appliance and state recognition using hidden Markov models

Conference ArODES

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of the 2014 International Conference on Data Science and Advanced Analytics (DSAA), 30 October - 1 November 2014, Shanghai, China

Link to the conference

Summary:

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 (10 -1 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.

ACS-F2 :

Conference ArODES

a new database of appliance consumption signatures

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of the 2014 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR), 11-14 August 2014, Tunis, Tunisia

Link to the conference

Summary:

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.

A survey on intrusive load monitoring for appliance recognition

Conference ArODES

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of the 22nd International Conference on Pattern Recognition, 24-28 August 2014, Stockholm, Sweden

Link to the conference

Summary:

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.

2013

Unseen appliances identification

Conference ArODES

Antonio Ridi, Christophe Gisler

Proceedings of the CIARP 2013: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 13-20 November 2013, Havana, Cuba

Link to the conference

Summary:

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.

Automatic identification of electrical appliances using smart plugs

Conference ArODES

Antonio Ridi, Christophe Gisler, Jean Hennebert

Proceedings of the 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), 12-15 May 2013, Algiers, Algeria

Link to the conference

Summary:

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-Fl and its intersession protocol to evaluate our algorithm propositions. The best combination of features and classifiers shows 93.6% accuracy.

Appliance consumption signature database and recognition test protocols

Conference ArODES

Christophe Gisler, Antonio Ridi, Damien Zufferey, Omar Abou Khaled, Jean Hennebert

Proceedings of the 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), 12-15 May 2013, Algiers, Algeria

Link to the conference

Summary:

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 (φ). We now give free access to this ACS-Fl database. The proposed test protocols will help the scientific community to objectively compare new algorithms.

Achievements

PEOPLE@HES-SO
Directory and Skills inventory

Gisler Christophe

Adjoint scientifique HES

Main skills

Machine Learning

Deep Learning

Artificial Intelligence (AI)

Data Science

Data Engineering

Adjoint scientifique HES

PEOPLE@HES-SO Directory and Skills inventory

Gisler Christophe

Adjoint scientifique HES

Main skills

Machine Learning

Deep Learning

Artificial Intelligence (AI)

Data Science

Data Engineering

Adjoint scientifique HES

PEOPLE@HES-SO
Directory and Skills inventory