Skip to main content

Marco Derboni

Scuola universitaria professionale della Svizzera italiana, IDSIA, Researcher

Scuola universitaria professionale della Svizzera italiana, Dipartimento Tecnologie Innovative, Researcher

Universita' della Svizzera Italiana, IDSIA, Researcher

Followers

7

Following

4

Co-authors

3

Public Views

Karolinska Institutet

Kings College London

Universidade de Lisboa

Matti Kuittinen

University of Eastern Finland

Michael Nicholas

Interests

Uploads

Papers by Marco Derboni

Digital pain extent is associated with pain intensity but not with pain-related cognitions and disability in people with chronic musculoskeletal pain: a cross-sectional study

BMC Musculoskeletal Disorders

Background To evaluate whether digital pain extent is associated with an array of psychological f... more Background To evaluate whether digital pain extent is associated with an array of psychological factors such as optimism, pessimism, expectations of recovery, pain acceptance, and pain self-efficacy beliefs as well as to analyse the association between digital pain extent and pain intensity and pain-related disability in people with chronic musculoskeletal pain. Methods A descriptive cross-sectional study conducted in a primary health care setting was carried out including 186 individuals with chronic musculoskeletal pain. Patient-reported outcomes were used to assess psychological factors, pain intensity, and pain-related disability. Digital pain extent was obtained from pain drawings shaded using a tablet and analysed using novel customized software. Multiple linear regression models were conducted to evaluate the association between digital pain extent and the aforementioned variables. Results Digital pain extent was statistically significantly associated with pain intensity. How...

Pain Extent Is Not Associated with Sensory-Associated Symptoms, Cognitive or Psychological Variables in COVID-19 Survivors Suffering from Post-COVID Pain

Journal of Clinical Medicine

We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sen... more We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sensory-related, cognitive and psychological variables in hospitalized COVID-19 survivors with post-COVID pain. One hundred and forty-six (67 males, 79 females) previously hospitalized COVID-19 survivors with post-COVID pain completed demographic (age, sex, height, weight), sensory-related (Central Sensitization Inventory, Self-Report Leeds Assessment of Neuropathic Symptoms), cognitive (Pain Catastrophizing Scale, Tampa Scale for Kinesiophobia) and psychological (Hospital Anxiety and Depression Scale, Pittsburgh Sleep Quality Index) variables. Pain extent and frequency maps were calculated from pain drawings using customized software. After conducting a correlation analysis to determine the relationships between variables, a stepwise linear regression model was performed to identify pain extent predictors, if available. Pain extent was significantly and weakly associated with pain intensit...

Pain Extent Is Not Associated with Sensory-Associated Symptoms, Cognitive or Psychological Variables in COVID-19 Survivors Suffering from Post-COVID Pain

by Marco Derboni and César Fernández-de-Las-Peñas

Journal of Clinical Medicine, 2022

We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sen... more We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sensory-related, cognitive and psychological variables in hospitalized COVID-19 survivors with post-COVID pain. One hundred and forty-six (67 males, 79 females) previously hospitalized COVID-19 survivors with post-COVID pain completed demographic (age, sex, height, weight), sensory-related (Central Sensitization Inventory, Self-Report Leeds Assessment of Neuropathic Symptoms), cognitive (Pain Catastrophizing Scale, Tampa Scale for Kinesiophobia) and psychological (Hospital Anxiety and Depression Scale, Pittsburgh Sleep Quality Index) variables. Pain extent and frequency maps were calculated from pain drawings using customized software. After conducting a correlation analysis to determine the relationships between variables, a stepwise linear regression model was performed to identify pain extent predictors, if available. Pain extent was significantly and weakly associated with pain intensity (r = −0.201, p = 0.014): the larger the pain extent, the lower the pain intensity. No other significant association was observed between pain extent and sensory-related, cognitive, or psychological variables in individuals with post-COVID pain. Females had higher pain intensity, more sensitization-associated symptoms, higher anxiety, lower sleep quality, and higher kinesiophobia levels than males. Sex differences correlation analyses revealed that pain extent was associated with pain intensity in males, but not in females. Pain extent was not associated with any of the measured variables and was also not related to the presence of sensitization-associated symptoms in our sample of COVID-19 survivors with long-term post-COVID pain.

Digital pain extent is associated with pain intensity but not with pain-related cognitions and disability in people with chronic musculoskeletal pain: a cross-sectional study

by Marco Derboni and Vincenzo Giuffrida

BMC Musculoskeletal Disorders, 2022

Background To evaluate whether digital pain extent is associated with an array of psychological f... more Background
To evaluate whether digital pain extent is associated with an array of psychological factors such as optimism, pessimism, expectations of recovery, pain acceptance, and pain self-efficacy beliefs as well as to analyse the association between digital pain extent and pain intensity and pain-related disability in people with chronic musculoskeletal pain.

Methods
A descriptive cross-sectional study conducted in a primary health care setting was carried out including 186 individuals with chronic musculoskeletal pain. Patient-reported outcomes were used to assess psychological factors, pain intensity, and pain-related disability. Digital pain extent was obtained from pain drawings shaded using a tablet and analysed using novel customized software. Multiple linear regression models were conducted to evaluate the association between digital pain extent and the aforementioned variables.

Results
Digital pain extent was statistically significantly associated with pain intensity. However, digital pain extent was not associated with any psychological measure nor with pain-related disability.

Discussion
The results did not support an association between digital pain extent and psychological measures.

Integrating Public Transport and Car Pooling Services Evidence from a Field Test in Switzerland

This paper introduces a mobility platform aimed at reducing individual car use by combining the c... more This paper introduces a mobility platform aimed at reducing individual car use by combining the car flexibility and comfort with the advantages by public transport, such as punctuality, safety and lower environmental impact. The platform, named SocialCar, delivers its services by means of a smartphone app, which performs multi-modal vehicle routing by accounting for walking, public transport and car-pooling rides. SocialCar was developed within a Horizon2020 project and was field tested in four European sites, engaging common citizens and their everyday mobility needs. In this paper we first present the app and the field test of the SocialCar platform we run in Southern Switzerland. We then discuss the outcomes of the field test, by presenting the challenges to be addressed when using real-life data (shortcomings in mapping, public transport and car-pooling data) and summarizing the strengths and weaknesses with respect to the potential large-scale diffusion of the SocialCar platform.

Flexible Scheduling of Residential Energy Loads, the Optiflex concept

Proceedings of FTAL 2021, Lugano, Switzerland, 2021

In the context of the Optiflex project, we consider the problem of dispatching grid loads in pres... more In the context of the Optiflex project, we consider the problem of dispatching grid loads in presence of energy production coming from renewable sources. As renewables are mostly weather-dependent and therefore massively and quickly fluctuating, the imbalance between production and consumption, the over voltage and overload of grid components are just a few of implications. One of the technical measures for mastering these challenges is the intelligent management of available flexibilities in the grid. In order to let the distribution system operators face this challenge, a concept aimed to actively control heat pumps and electric heaters is proposed. This concept is concretised in four main steps: power profile disaggregation of the controllable flexibilities, photovoltaic power prediction, power demand estimation of the controllable loads, and loads actuation scheduling.

Integrating public transport and car-pooling services: Evidence from a field test in Switzerland

Proceedings of 8th Transport Research Arena TRA 2020, April 27-30, 2020, Helsinki, Finland , 2020

This paper introduces a mobility platform aimed at reducing individual car use by combining the c... more This paper introduces a mobility platform aimed at reducing individual car use by combining the car flexibility and comfort with the advantages by public transport, such as punctuality, safety and lower environmental impact. The platform, named SocialCar, delivers its services by means of a smartphone app, which performs multi-modal vehicle routing by accounting for walking, public transport and car-pooling rides. SocialCar was developed within a Horizon2020 project and was field tested in four European sites, engaging common citizens and their everyday mobility needs. In this paper we first present the app and the field test of the SocialCar platform we run in Southern Switzerland. We then discuss the outcomes of the field test, by presenting the challenges to be addressed when using real-life data (shortcomings in mapping, public transport and car-pooling data) and summarizing the strengths and weaknesses with respect to the potential large-scale diffusion of the SocialCar platform.

Miglioramento di algoritmi di elaborazione di immagini da scanner 3D tramite Simulated Annealing

by Marco Derboni and Evelina Lamma

International Conference of the Italian Association for Artificial Intelligence, 2012

Nel lavoro si descrive l'applicazione di tecniche di IA per l'elaborazione e l'allineamento di im... more Nel lavoro si descrive l'applicazione di tecniche di IA per l'elaborazione e l'allineamento di immagini provenienti da scanner 3D, in grado di generare modelli digitali tridimensionali. Al fine di allineare più correttamente i fotogrammi acquisiti, in scansioni successive, dal dispositivo e ricostruire accuratamente il modello tridimensionale digitale, si è integrata la tecnica di Simulated Annealing, con un algoritmo di elaborazione di immagini (Iterative Closest Point, ICP) che allinea un nuovo fotogramma al modello già generato tramite roto-traslazioni consecutive.

A Multi-Modal and Multi-Objective Journey Planner for Integrating Carpooling and Public Transport

Journal of Traffic and Logistics Engineering

SocialCar is a research project that aims at integrating carpooling with traditional transportati... more SocialCar is a research project that aims at integrating carpooling with traditional transportation systems in urban areas, while benefiting from social media to enhance the user's experience. The system is based on route planning and ride matching algorithms to provide the users with alternatives for their trips. In this work, we overview the multiple approaches in the literature to model transportation networks and carpooling services, and a route planning algorithm which integrates multiple transportation types together. Finally, the performance measures of the route planner are reported. 

Distributed demand side management using electric boilers

Computer Science - Research and Development, 2016

Demand side management is a promising approach towards the integration of renewable energy source... more Demand side management is a promising approach towards the integration of renewable energy sources in the electric grid, which does not require massive infrastructural investments. In this paper, we report the analysis of the performance of a demand side management algorithm for the control of electric boilers, developed within the context of the GridSense project. GridSense is a multi-objective energy management system that aims at decreasing both the end user energy costs and the congestions on the local feeder. The latter objective is minimized exploiting the existent correlation between the voltage measured at the connection point to the grid and the power flow measured at the low voltage transformer. The algorithm behavior has been firstly investigated by means of simulation, using typical water consumption profiles and a simplified thermodynamic model of the electric boiler. The simulation results show that the algorithm can effectively shift the boiler’s electric consumption based on voltage and price profiles. In the second phase, we analyzed the results from a pilot project, in which the GridSense units were controlling the boilers of four households, located in the same low voltage grid.

An optimisation-based energy disaggregation algorithm for low frequency smart meter data

Energy Informatics

An algorithm for the non-intrusive disaggregation of energy consumption into its end-uses, also k... more An algorithm for the non-intrusive disaggregation of energy consumption into its end-uses, also known as non-intrusive appliance load monitoring (NIALM), is presented. The algorithm solves an optimisation problem where the objective is to minimise the error between the total energy consumption and the sum of the individual contributions of each appliance. The algorithm assumes that a fraction of the loads present in the household is known (e.g. washing machine, dishwasher, etc.), but it also considers unknown loads, treating them as a single load. The performance of the algorithm is then compared to that obtained by two state of the art disaggregation approaches implemented in the publicly available NILMTK framework. The first one is based on Combinatorial Optimization, the second one on a Factorial Hidden Markov Model. The results show that the proposed algorithm performs satisfactorily and it even outperforms the other algorithms from some perspectives.

Miglioramento di algoritmi di elaborazione di immagini da scanner 3D tramite Simulated Annealing

Nel lavoro si descrive l’applicazione di tecniche di IA per l’elaborazione e l’allineamento di im... more Nel lavoro si descrive l’applicazione di tecniche di IA per l’elaborazione e l’allineamento di immagini provenienti da scanner 3D, in grado di generare modelli digitali tridimensionali. Al fine di allineare più correttamente i fotogrammi acquisiti, in scansioni successive, dal dispositivo e ricostruire accuratamente il modello tridimensionale digitale, si è integrata la tecnica di Simulated Annealing, con un algoritmo di elaborazione di immagini (Iterative Closest Point, ICP) che allinea un nuovo fotogramma al modello già generato tramite roto-traslazioni consecutive.

Challenges and opportunities in deploying a mobilityplatform integrating public transport andcar-pooling services

This paper introduces a new mobility platform that favours reducing individual car use, by combin... more This paper introduces a new mobility platform that favours reducing individual car use, by combining car flexibility with advantages offered by public transport, such as punctuality, comfort, safety and low environmental impact. Such platform services are delivered by means of a smartphone app that, thanks to advanced artificial intelligence algorithms, performs multimodal vehicle routing by accounting for walking, public transport and car-pooling rides. To explore citizens’ attitudes and perceptions towards SocialCar, and assess its overall business potential, we tested a prototype version in Canton Ticino (Southern Switzerland), engaging common citizens and their everyday mobility needs. In this paper we first present the app and the route planning algorithms we developed to match travel demand and offer, commenting on the challenges to be addressed when using real-life data (shortcomings in mapping, public transport and car-pooling data). Then, we describe the methodology used to...

Non intrusive load monitoring for demand side management

Energy Informatics

In the context of a pilot project, the Lugaggia Innovation Community (LIC), we address the proble... more In the context of a pilot project, the Lugaggia Innovation Community (LIC), we address the problem of non-intrusive load monitoring for the purpose of demand side management on low voltage grids in presence of distributed power generation (photovoltaic). From the power readings of smart meters, we estimate the photovoltaic production and detect the activation of major loads (heatpumps and domestic water heaters). Experiments, conducted with real data and in silico, show that exploiting meter readings only, we can estimate PV production with MAPE ranging from 4.6% (best case) to 41.9% (worst case). Even with non negligible photovoltaic production estimation errors, the proposed method is capable of detecting the activation of heatpumps and domestic water heaters.

Evaluation Of The Potential Of Electric Storage Using Decentralized Demand Side Management Algorithms

Energy Procedia

Digital pain extent is associated with pain intensity but not with pain-related cognitions and disability in people with chronic musculoskeletal pain: a cross-sectional study

BMC Musculoskeletal Disorders

Background To evaluate whether digital pain extent is associated with an array of psychological f... more Background To evaluate whether digital pain extent is associated with an array of psychological factors such as optimism, pessimism, expectations of recovery, pain acceptance, and pain self-efficacy beliefs as well as to analyse the association between digital pain extent and pain intensity and pain-related disability in people with chronic musculoskeletal pain. Methods A descriptive cross-sectional study conducted in a primary health care setting was carried out including 186 individuals with chronic musculoskeletal pain. Patient-reported outcomes were used to assess psychological factors, pain intensity, and pain-related disability. Digital pain extent was obtained from pain drawings shaded using a tablet and analysed using novel customized software. Multiple linear regression models were conducted to evaluate the association between digital pain extent and the aforementioned variables. Results Digital pain extent was statistically significantly associated with pain intensity. How...

Pain Extent Is Not Associated with Sensory-Associated Symptoms, Cognitive or Psychological Variables in COVID-19 Survivors Suffering from Post-COVID Pain

Journal of Clinical Medicine

We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sen... more We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sensory-related, cognitive and psychological variables in hospitalized COVID-19 survivors with post-COVID pain. One hundred and forty-six (67 males, 79 females) previously hospitalized COVID-19 survivors with post-COVID pain completed demographic (age, sex, height, weight), sensory-related (Central Sensitization Inventory, Self-Report Leeds Assessment of Neuropathic Symptoms), cognitive (Pain Catastrophizing Scale, Tampa Scale for Kinesiophobia) and psychological (Hospital Anxiety and Depression Scale, Pittsburgh Sleep Quality Index) variables. Pain extent and frequency maps were calculated from pain drawings using customized software. After conducting a correlation analysis to determine the relationships between variables, a stepwise linear regression model was performed to identify pain extent predictors, if available. Pain extent was significantly and weakly associated with pain intensit...

Pain Extent Is Not Associated with Sensory-Associated Symptoms, Cognitive or Psychological Variables in COVID-19 Survivors Suffering from Post-COVID Pain

by Marco Derboni and César Fernández-de-Las-Peñas

Journal of Clinical Medicine, 2022

We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sen... more We aimed to investigate the relationship between pain extent, as a sign of sensitization, and sensory-related, cognitive and psychological variables in hospitalized COVID-19 survivors with post-COVID pain. One hundred and forty-six (67 males, 79 females) previously hospitalized COVID-19 survivors with post-COVID pain completed demographic (age, sex, height, weight), sensory-related (Central Sensitization Inventory, Self-Report Leeds Assessment of Neuropathic Symptoms), cognitive (Pain Catastrophizing Scale, Tampa Scale for Kinesiophobia) and psychological (Hospital Anxiety and Depression Scale, Pittsburgh Sleep Quality Index) variables. Pain extent and frequency maps were calculated from pain drawings using customized software. After conducting a correlation analysis to determine the relationships between variables, a stepwise linear regression model was performed to identify pain extent predictors, if available. Pain extent was significantly and weakly associated with pain intensity (r = −0.201, p = 0.014): the larger the pain extent, the lower the pain intensity. No other significant association was observed between pain extent and sensory-related, cognitive, or psychological variables in individuals with post-COVID pain. Females had higher pain intensity, more sensitization-associated symptoms, higher anxiety, lower sleep quality, and higher kinesiophobia levels than males. Sex differences correlation analyses revealed that pain extent was associated with pain intensity in males, but not in females. Pain extent was not associated with any of the measured variables and was also not related to the presence of sensitization-associated symptoms in our sample of COVID-19 survivors with long-term post-COVID pain.

Digital pain extent is associated with pain intensity but not with pain-related cognitions and disability in people with chronic musculoskeletal pain: a cross-sectional study

by Marco Derboni and Vincenzo Giuffrida

BMC Musculoskeletal Disorders, 2022

Background To evaluate whether digital pain extent is associated with an array of psychological f... more Background
To evaluate whether digital pain extent is associated with an array of psychological factors such as optimism, pessimism, expectations of recovery, pain acceptance, and pain self-efficacy beliefs as well as to analyse the association between digital pain extent and pain intensity and pain-related disability in people with chronic musculoskeletal pain.

Methods
A descriptive cross-sectional study conducted in a primary health care setting was carried out including 186 individuals with chronic musculoskeletal pain. Patient-reported outcomes were used to assess psychological factors, pain intensity, and pain-related disability. Digital pain extent was obtained from pain drawings shaded using a tablet and analysed using novel customized software. Multiple linear regression models were conducted to evaluate the association between digital pain extent and the aforementioned variables.

Results
Digital pain extent was statistically significantly associated with pain intensity. However, digital pain extent was not associated with any psychological measure nor with pain-related disability.

Discussion
The results did not support an association between digital pain extent and psychological measures.

Integrating Public Transport and Car Pooling Services Evidence from a Field Test in Switzerland

This paper introduces a mobility platform aimed at reducing individual car use by combining the c... more This paper introduces a mobility platform aimed at reducing individual car use by combining the car flexibility and comfort with the advantages by public transport, such as punctuality, safety and lower environmental impact. The platform, named SocialCar, delivers its services by means of a smartphone app, which performs multi-modal vehicle routing by accounting for walking, public transport and car-pooling rides. SocialCar was developed within a Horizon2020 project and was field tested in four European sites, engaging common citizens and their everyday mobility needs. In this paper we first present the app and the field test of the SocialCar platform we run in Southern Switzerland. We then discuss the outcomes of the field test, by presenting the challenges to be addressed when using real-life data (shortcomings in mapping, public transport and car-pooling data) and summarizing the strengths and weaknesses with respect to the potential large-scale diffusion of the SocialCar platform.

Flexible Scheduling of Residential Energy Loads, the Optiflex concept

Proceedings of FTAL 2021, Lugano, Switzerland, 2021

In the context of the Optiflex project, we consider the problem of dispatching grid loads in pres... more In the context of the Optiflex project, we consider the problem of dispatching grid loads in presence of energy production coming from renewable sources. As renewables are mostly weather-dependent and therefore massively and quickly fluctuating, the imbalance between production and consumption, the over voltage and overload of grid components are just a few of implications. One of the technical measures for mastering these challenges is the intelligent management of available flexibilities in the grid. In order to let the distribution system operators face this challenge, a concept aimed to actively control heat pumps and electric heaters is proposed. This concept is concretised in four main steps: power profile disaggregation of the controllable flexibilities, photovoltaic power prediction, power demand estimation of the controllable loads, and loads actuation scheduling.

Integrating public transport and car-pooling services: Evidence from a field test in Switzerland

Proceedings of 8th Transport Research Arena TRA 2020, April 27-30, 2020, Helsinki, Finland , 2020

This paper introduces a mobility platform aimed at reducing individual car use by combining the c... more This paper introduces a mobility platform aimed at reducing individual car use by combining the car flexibility and comfort with the advantages by public transport, such as punctuality, safety and lower environmental impact. The platform, named SocialCar, delivers its services by means of a smartphone app, which performs multi-modal vehicle routing by accounting for walking, public transport and car-pooling rides. SocialCar was developed within a Horizon2020 project and was field tested in four European sites, engaging common citizens and their everyday mobility needs. In this paper we first present the app and the field test of the SocialCar platform we run in Southern Switzerland. We then discuss the outcomes of the field test, by presenting the challenges to be addressed when using real-life data (shortcomings in mapping, public transport and car-pooling data) and summarizing the strengths and weaknesses with respect to the potential large-scale diffusion of the SocialCar platform.

Miglioramento di algoritmi di elaborazione di immagini da scanner 3D tramite Simulated Annealing

by Marco Derboni and Evelina Lamma

International Conference of the Italian Association for Artificial Intelligence, 2012

Nel lavoro si descrive l'applicazione di tecniche di IA per l'elaborazione e l'allineamento di im... more Nel lavoro si descrive l'applicazione di tecniche di IA per l'elaborazione e l'allineamento di immagini provenienti da scanner 3D, in grado di generare modelli digitali tridimensionali. Al fine di allineare più correttamente i fotogrammi acquisiti, in scansioni successive, dal dispositivo e ricostruire accuratamente il modello tridimensionale digitale, si è integrata la tecnica di Simulated Annealing, con un algoritmo di elaborazione di immagini (Iterative Closest Point, ICP) che allinea un nuovo fotogramma al modello già generato tramite roto-traslazioni consecutive.

A Multi-Modal and Multi-Objective Journey Planner for Integrating Carpooling and Public Transport

Journal of Traffic and Logistics Engineering

SocialCar is a research project that aims at integrating carpooling with traditional transportati... more SocialCar is a research project that aims at integrating carpooling with traditional transportation systems in urban areas, while benefiting from social media to enhance the user's experience. The system is based on route planning and ride matching algorithms to provide the users with alternatives for their trips. In this work, we overview the multiple approaches in the literature to model transportation networks and carpooling services, and a route planning algorithm which integrates multiple transportation types together. Finally, the performance measures of the route planner are reported. 

Distributed demand side management using electric boilers

Computer Science - Research and Development, 2016

Demand side management is a promising approach towards the integration of renewable energy source... more Demand side management is a promising approach towards the integration of renewable energy sources in the electric grid, which does not require massive infrastructural investments. In this paper, we report the analysis of the performance of a demand side management algorithm for the control of electric boilers, developed within the context of the GridSense project. GridSense is a multi-objective energy management system that aims at decreasing both the end user energy costs and the congestions on the local feeder. The latter objective is minimized exploiting the existent correlation between the voltage measured at the connection point to the grid and the power flow measured at the low voltage transformer. The algorithm behavior has been firstly investigated by means of simulation, using typical water consumption profiles and a simplified thermodynamic model of the electric boiler. The simulation results show that the algorithm can effectively shift the boiler’s electric consumption based on voltage and price profiles. In the second phase, we analyzed the results from a pilot project, in which the GridSense units were controlling the boilers of four households, located in the same low voltage grid.

An optimisation-based energy disaggregation algorithm for low frequency smart meter data

Energy Informatics

An algorithm for the non-intrusive disaggregation of energy consumption into its end-uses, also k... more An algorithm for the non-intrusive disaggregation of energy consumption into its end-uses, also known as non-intrusive appliance load monitoring (NIALM), is presented. The algorithm solves an optimisation problem where the objective is to minimise the error between the total energy consumption and the sum of the individual contributions of each appliance. The algorithm assumes that a fraction of the loads present in the household is known (e.g. washing machine, dishwasher, etc.), but it also considers unknown loads, treating them as a single load. The performance of the algorithm is then compared to that obtained by two state of the art disaggregation approaches implemented in the publicly available NILMTK framework. The first one is based on Combinatorial Optimization, the second one on a Factorial Hidden Markov Model. The results show that the proposed algorithm performs satisfactorily and it even outperforms the other algorithms from some perspectives.

Miglioramento di algoritmi di elaborazione di immagini da scanner 3D tramite Simulated Annealing

Nel lavoro si descrive l’applicazione di tecniche di IA per l’elaborazione e l’allineamento di im... more Nel lavoro si descrive l’applicazione di tecniche di IA per l’elaborazione e l’allineamento di immagini provenienti da scanner 3D, in grado di generare modelli digitali tridimensionali. Al fine di allineare più correttamente i fotogrammi acquisiti, in scansioni successive, dal dispositivo e ricostruire accuratamente il modello tridimensionale digitale, si è integrata la tecnica di Simulated Annealing, con un algoritmo di elaborazione di immagini (Iterative Closest Point, ICP) che allinea un nuovo fotogramma al modello già generato tramite roto-traslazioni consecutive.

Challenges and opportunities in deploying a mobilityplatform integrating public transport andcar-pooling services

This paper introduces a new mobility platform that favours reducing individual car use, by combin... more This paper introduces a new mobility platform that favours reducing individual car use, by combining car flexibility with advantages offered by public transport, such as punctuality, comfort, safety and low environmental impact. Such platform services are delivered by means of a smartphone app that, thanks to advanced artificial intelligence algorithms, performs multimodal vehicle routing by accounting for walking, public transport and car-pooling rides. To explore citizens’ attitudes and perceptions towards SocialCar, and assess its overall business potential, we tested a prototype version in Canton Ticino (Southern Switzerland), engaging common citizens and their everyday mobility needs. In this paper we first present the app and the route planning algorithms we developed to match travel demand and offer, commenting on the challenges to be addressed when using real-life data (shortcomings in mapping, public transport and car-pooling data). Then, we describe the methodology used to...

Non intrusive load monitoring for demand side management

Energy Informatics

In the context of a pilot project, the Lugaggia Innovation Community (LIC), we address the proble... more In the context of a pilot project, the Lugaggia Innovation Community (LIC), we address the problem of non-intrusive load monitoring for the purpose of demand side management on low voltage grids in presence of distributed power generation (photovoltaic). From the power readings of smart meters, we estimate the photovoltaic production and detect the activation of major loads (heatpumps and domestic water heaters). Experiments, conducted with real data and in silico, show that exploiting meter readings only, we can estimate PV production with MAPE ranging from 4.6% (best case) to 41.9% (worst case). Even with non negligible photovoltaic production estimation errors, the proposed method is capable of detecting the activation of heatpumps and domestic water heaters.

Evaluation Of The Potential Of Electric Storage Using Decentralized Demand Side Management Algorithms

Energy Procedia