SlideShare a Scribd company logo
1 of 71
Download to read offline
Aplicación de técnicas de
Inteligencia Artificial e IoT
a la vida real
Facultad de Informática – Universidad Complutense Madrid
26 de Noviembre de 2020
José Luis Casteleiro Roca
jose.luis.casteleiro@udc.es
Índice
 Propuesta de modelado híbrido
 Métodos utilizados
 Aplicaciones
2
Índice
 Propuesta de modelado híbrido
3
Modelado híbrido
4
Modelado híbrido
5
Modelado híbrido
6
Selección de la
topología híbrida
Mejores modelos
locales
Regresión
(por grupo)
Fase de
agrupamiento
Modelo híbrido
7
Modelo híbrido
Modelos locales
Grupo 1 Grupo 2 Grupo 3 Grupo 4 Grupo 5
Global
Híbrido 2
grupos
Híbrido 3
grupos
Híbrido 4
grupos
Híbrido 5
grupos
8
9
Modelo híbrido – Errores
𝑀𝑀𝑀𝑀𝑀𝑀 =
1
𝑛𝑛
�
𝑖𝑖=1
𝑛𝑛
𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚
− 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
2
𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁 =
1
𝑛𝑛
�
𝑖𝑖=1
𝑛𝑛
𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 𝑚𝑚
− 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
2
𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 𝑚𝑚
· 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
𝑀𝑀𝑀𝑀𝑀𝑀 =
1
𝑛𝑛
�
𝑖𝑖=1
𝑛𝑛
𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚
− 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
𝑀𝑀𝑀𝑀𝑀𝑀𝑀𝑀 =
1
𝑛𝑛
�
𝑖𝑖=1
𝑛𝑛
𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 𝑚𝑚
− 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
Modelo híbrido
Modelos locales
Grupo 1 Grupo 2 Grupo 3 Grupo 4 Grupo 5
Global ANN-12
Híbrido 2
grupos
LS-SVR ANN-2
Híbrido 3
grupos
Poly-2 ANN-5 LS-SVR
Híbrido 4
grupos
ANN-5 ANN-3 ANN-4 LS-SVR
Híbrido 5
grupos
LS-SVR LS-SVR ANN-6 ANN-7 ANN-6
10
Modelo híbrido
11
Índice
 Propuesta de modelado híbrido
 Métodos utilizados
12
13
Métodos utilizados
 Agrupamiento
 Regresión
 Validación
 Elección del modelo
14
Agrupamiento – K-Means
15
Agrupamiento – K-Means
16
Agrupamiento – K-Means
Regresión
17
Regresión – Redes neuronales artificiales
18
Regresión – Redes neuronales artificiales
19
Regresión – Máquinas de vectores soporte
20
Regresión – Máquinas de vectores soporte
21
Regresión – Máquinas de vectores soporte
22
Regresión – Regresión polinomial
23
Regresión – Regresión polinomial
24
Regresión – Regresión polinomial
25
𝜃𝜃 = 𝑋𝑋 𝑇𝑇 · 𝑋𝑋 −1 · 𝑋𝑋 𝑇𝑇 · 𝑦𝑦
Validación
26
27
Validación – Hold Out
28
Validación – Cross Validation
Elección del modelo de regresión
29
Elección del modelo de regresión
 Validación con Hold Out
• Redes neuronales artificiales
– Diferente número de neuronas en la capa oculta
• Máquinas de vectores soporte
• Regresión polinomial
– Diferentes grados del polinomio
 Error de cada modelo
30
Elección del modelo de regresión
 Validación con Cross Validation
• Redes Neuronales Artificiales
– K - Diferente número de neuronas en la capa oculta
• K - Máquinas de soporte vectorial
• Regresión polinomial
– K - Diferentes grados del polinomio
 Error de cada modelo
31
Elección del modelo de regresión
 Validación
 Error de cada modelo
 Mejor modelo
 Entrenamiento del modelo con todos los datos
32
Índice
 Propuesta de modelado híbrido
 Métodos utilizados
 Aplicaciones
33
34
Aplicaciones
 Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
 Power cell SOC modelling for intelligent virtual sensor
implementation
 Prediction of the energy demand of a hotel using an
artificial intelligence-based model: Luxury hotel in Tenerife
 Fuel cell hybrid model for predicting hydrogen inflow
through energy demand
 Hybrid intelligent system to predict the individual
academic performance o engineering students
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
35
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
36
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
37
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
38
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
39
 50 pacientes
 42.788 muestras
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
40
Grupo 1 Grupo 2
Global 100%
Híbrido 2
grupos
0,8% 99,2%
Grupo 1 Grupo 2
Global 0,8531
Híbrido 2
grupos
8,1·10-4 0,4129
Grupo 1 Grupo 2
Global ANN-6
Híbrido 2
grupos
ANN-2 ANN-9
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
41
Hybrid intelligent system to perform fault detection on BIS
sensor during surgeries
42
Power cell SOC modelling for intelligent virtual sensor
implementation
43
Power cell SOC modelling for intelligent virtual sensor
implementation
44
Power cell SOC modelling for intelligent virtual sensor
implementation
45
Power cell SOC modelling for intelligent virtual sensor
implementation
46
Power cell SOC modelling for intelligent virtual sensor
implementation
47
Power cell SOC modelling for intelligent virtual sensor
implementation
48
Carga Reposo Descarga Reposo
Muestras 6.619 1.089 7.451 1.211
ANN 0,1094 0,0921 0,4767 0,0917
Poly 23,997 0,0904 17,814 0,0930
LS-SVR 0,1392 0,0902 0,5052 0,0865
ANN-10 LS-SVR ANN-8 LS-SVR
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
49
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
50
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
51
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
52
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
53
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
54
Prediction of the energy demand of a hotel using an artificial
intelligence-based model: Luxury hotel in Tenerife
55
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
56
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
57
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
58
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
59
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
60
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
61
Fuel cell hybrid model for predicting hydrogen inflow through
energy demand
62
Hybrid intelligent system to predict the individual academic
performance o engineering students
63
Hybrid intelligent system to predict the individual academic
performance o engineering students
64
Hybrid intelligent system to predict the individual academic
performance o engineering students
65
Hybrid intelligent system to predict the individual academic
performance o engineering students
66
Hybrid intelligent system to predict the individual academic
performance o engineering students
67
Hybrid intelligent system to predict the individual academic
performance o engineering students
68
Hybrid intelligent system to predict the individual academic
performance o engineering students
69
Aplicación de técnicas de
Inteligencia Artificial e IoT
a la vida real
Facultad de Informática – Universidad Complutense Madrid
26 de Noviembre de 2020
José Luis Casteleiro Roca
jose.luis.casteleiro@udc.es
Turno de preguntas
Aplicación de técnicas de
Inteligencia Artificial e IoT
a la vida real
Facultad de Informática – Universidad Complutense Madrid
26 de Noviembre de 2020
José Luis Casteleiro Roca
jose.luis.casteleiro@udc.es

More Related Content

Similar to Aplicación de técnicas de Inteligencia Artificial e IoT a la vida real.

[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...
[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...
[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...
Matteo Ferroni
 
Thesis Defense: Integration of Modeling Methods for Cyber-Physical Systems
Thesis Defense: Integration of Modeling Methods for Cyber-Physical SystemsThesis Defense: Integration of Modeling Methods for Cyber-Physical Systems
Thesis Defense: Integration of Modeling Methods for Cyber-Physical Systems
Ivan Ruchkin
 
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Luigi Vanfretti
 
Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...
Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...
Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...
OPAL-RT TECHNOLOGIES
 
Virtual Macro Site Analysis using Wireless Sensor Networks
Virtual Macro Site Analysis using Wireless Sensor NetworksVirtual Macro Site Analysis using Wireless Sensor Networks
Virtual Macro Site Analysis using Wireless Sensor Networks
luca-bencini
 

Similar to Aplicación de técnicas de Inteligencia Artificial e IoT a la vida real. (20)

Be,me ieee 2015 16 electrical electronicscommunication,tce,bio medical,diplom...
Be,me ieee 2015 16 electrical electronicscommunication,tce,bio medical,diplom...Be,me ieee 2015 16 electrical electronicscommunication,tce,bio medical,diplom...
Be,me ieee 2015 16 electrical electronicscommunication,tce,bio medical,diplom...
 
[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...
[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...
[February 2017 - Ph.D. Final Dissertation] Enabling Power-awareness For Multi...
 
DSUS_MAO_2012_Jie
DSUS_MAO_2012_JieDSUS_MAO_2012_Jie
DSUS_MAO_2012_Jie
 
Thesis Defense: Integration of Modeling Methods for Cyber-Physical Systems
Thesis Defense: Integration of Modeling Methods for Cyber-Physical SystemsThesis Defense: Integration of Modeling Methods for Cyber-Physical Systems
Thesis Defense: Integration of Modeling Methods for Cyber-Physical Systems
 
Gschwind - AI Everywhere: democratize AI with an open platform and end-to -en...
Gschwind - AI Everywhere: democratize AI with an open platform and end-to -en...Gschwind - AI Everywhere: democratize AI with an open platform and end-to -en...
Gschwind - AI Everywhere: democratize AI with an open platform and end-to -en...
 
VLSI Projects, IC Design, Low Power VLSI, Power Management, BIST, FPGA Projec...
VLSI Projects, IC Design, Low Power VLSI, Power Management, BIST, FPGA Projec...VLSI Projects, IC Design, Low Power VLSI, Power Management, BIST, FPGA Projec...
VLSI Projects, IC Design, Low Power VLSI, Power Management, BIST, FPGA Projec...
 
Call for Chapters- Edited Book: Real-World Applications of Quantum Computers ...
Call for Chapters- Edited Book: Real-World Applications of Quantum Computers ...Call for Chapters- Edited Book: Real-World Applications of Quantum Computers ...
Call for Chapters- Edited Book: Real-World Applications of Quantum Computers ...
 
cv_Md_Ariful_Islam
cv_Md_Ariful_Islamcv_Md_Ariful_Islam
cv_Md_Ariful_Islam
 
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
Model-Simulation-and-Measurement-Based Systems Engineering of Power System Sy...
 
Development Of Industrial Automatic Multi Colour Sorting and Counting Machine...
Development Of Industrial Automatic Multi Colour Sorting and Counting Machine...Development Of Industrial Automatic Multi Colour Sorting and Counting Machine...
Development Of Industrial Automatic Multi Colour Sorting and Counting Machine...
 
Geico presents Smart Paintshop
Geico presents Smart PaintshopGeico presents Smart Paintshop
Geico presents Smart Paintshop
 
Cyber Physical Systems – Collaborating Systems of Systems
Cyber Physical Systems – Collaborating Systems of SystemsCyber Physical Systems – Collaborating Systems of Systems
Cyber Physical Systems – Collaborating Systems of Systems
 
DSDT meetup July 2021
DSDT meetup July 2021DSDT meetup July 2021
DSDT meetup July 2021
 
Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...
Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...
Detailed large-scale real-time HYPERSIM EMT simulation for transient stabilit...
 
WSO2 Machine Learner - Product Overview
WSO2 Machine Learner - Product OverviewWSO2 Machine Learner - Product Overview
WSO2 Machine Learner - Product Overview
 
Powering Supply Chain Transformation Through Analytics Innovation
Powering Supply Chain Transformation Through Analytics InnovationPowering Supply Chain Transformation Through Analytics Innovation
Powering Supply Chain Transformation Through Analytics Innovation
 
Virtual Macro Site Analysis using Wireless Sensor Networks
Virtual Macro Site Analysis using Wireless Sensor NetworksVirtual Macro Site Analysis using Wireless Sensor Networks
Virtual Macro Site Analysis using Wireless Sensor Networks
 
Imagen hiperespectral en la industria cárnica
Imagen hiperespectral en la industria cárnicaImagen hiperespectral en la industria cárnica
Imagen hiperespectral en la industria cárnica
 
Energy efficiency in buildings
Energy efficiency in buildingsEnergy efficiency in buildings
Energy efficiency in buildings
 
230208 MLOps Getting from Good to Great.pptx
230208 MLOps Getting from Good to Great.pptx230208 MLOps Getting from Good to Great.pptx
230208 MLOps Getting from Good to Great.pptx
 

More from Facultad de Informática UCM

More from Facultad de Informática UCM (20)

¿Por qué debemos seguir trabajando en álgebra lineal?
¿Por qué debemos seguir trabajando en álgebra lineal?¿Por qué debemos seguir trabajando en álgebra lineal?
¿Por qué debemos seguir trabajando en álgebra lineal?
 
TECNOPOLÍTICA Y ACTIVISMO DE DATOS: EL MAPEO COMO FORMA DE RESILIENCIA ANTE L...
TECNOPOLÍTICA Y ACTIVISMO DE DATOS: EL MAPEO COMO FORMA DE RESILIENCIA ANTE L...TECNOPOLÍTICA Y ACTIVISMO DE DATOS: EL MAPEO COMO FORMA DE RESILIENCIA ANTE L...
TECNOPOLÍTICA Y ACTIVISMO DE DATOS: EL MAPEO COMO FORMA DE RESILIENCIA ANTE L...
 
DRAC: Designing RISC-V-based Accelerators for next generation Computers
DRAC: Designing RISC-V-based Accelerators for next generation ComputersDRAC: Designing RISC-V-based Accelerators for next generation Computers
DRAC: Designing RISC-V-based Accelerators for next generation Computers
 
uElectronics ongoing activities at ESA
uElectronics ongoing activities at ESAuElectronics ongoing activities at ESA
uElectronics ongoing activities at ESA
 
Tendencias en el diseño de procesadores con arquitectura Arm
Tendencias en el diseño de procesadores con arquitectura ArmTendencias en el diseño de procesadores con arquitectura Arm
Tendencias en el diseño de procesadores con arquitectura Arm
 
Formalizing Mathematics in Lean
Formalizing Mathematics in LeanFormalizing Mathematics in Lean
Formalizing Mathematics in Lean
 
Introduction to Quantum Computing and Quantum Service Oriented Computing
Introduction to Quantum Computing and Quantum Service Oriented ComputingIntroduction to Quantum Computing and Quantum Service Oriented Computing
Introduction to Quantum Computing and Quantum Service Oriented Computing
 
Computer Design Concepts for Machine Learning
Computer Design Concepts for Machine LearningComputer Design Concepts for Machine Learning
Computer Design Concepts for Machine Learning
 
Inteligencia Artificial en la atención sanitaria del futuro
Inteligencia Artificial en la atención sanitaria del futuroInteligencia Artificial en la atención sanitaria del futuro
Inteligencia Artificial en la atención sanitaria del futuro
 
Design Automation Approaches for Real-Time Edge Computing for Science Applic...
 Design Automation Approaches for Real-Time Edge Computing for Science Applic... Design Automation Approaches for Real-Time Edge Computing for Science Applic...
Design Automation Approaches for Real-Time Edge Computing for Science Applic...
 
Estrategias de navegación para robótica móvil de campo: caso de estudio proye...
Estrategias de navegación para robótica móvil de campo: caso de estudio proye...Estrategias de navegación para robótica móvil de campo: caso de estudio proye...
Estrategias de navegación para robótica móvil de campo: caso de estudio proye...
 
Fault-tolerance Quantum computation and Quantum Error Correction
Fault-tolerance Quantum computation and Quantum Error CorrectionFault-tolerance Quantum computation and Quantum Error Correction
Fault-tolerance Quantum computation and Quantum Error Correction
 
Cómo construir un chatbot inteligente sin morir en el intento
Cómo construir un chatbot inteligente sin morir en el intentoCómo construir un chatbot inteligente sin morir en el intento
Cómo construir un chatbot inteligente sin morir en el intento
 
Automatic generation of hardware memory architectures for HPC
Automatic generation of hardware memory architectures for HPCAutomatic generation of hardware memory architectures for HPC
Automatic generation of hardware memory architectures for HPC
 
Type and proof structures for concurrency
Type and proof structures for concurrencyType and proof structures for concurrency
Type and proof structures for concurrency
 
Hardware/software security contracts: Principled foundations for building sec...
Hardware/software security contracts: Principled foundations for building sec...Hardware/software security contracts: Principled foundations for building sec...
Hardware/software security contracts: Principled foundations for building sec...
 
Jose carlossancho slidesLa seguridad en el desarrollo de software implementad...
Jose carlossancho slidesLa seguridad en el desarrollo de software implementad...Jose carlossancho slidesLa seguridad en el desarrollo de software implementad...
Jose carlossancho slidesLa seguridad en el desarrollo de software implementad...
 
Do you trust your artificial intelligence system?
Do you trust your artificial intelligence system?Do you trust your artificial intelligence system?
Do you trust your artificial intelligence system?
 
Redes neuronales y reinforcement learning. Aplicación en energía eólica.
Redes neuronales y reinforcement learning. Aplicación en energía eólica.Redes neuronales y reinforcement learning. Aplicación en energía eólica.
Redes neuronales y reinforcement learning. Aplicación en energía eólica.
 
Challenges and Opportunities for AI and Data analytics in Offshore wind
Challenges and Opportunities for AI and Data analytics in Offshore windChallenges and Opportunities for AI and Data analytics in Offshore wind
Challenges and Opportunities for AI and Data analytics in Offshore wind
 

Recently uploaded

Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
Epec Engineered Technologies
 
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
DeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakesDeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakes
MayuraD1
 

Recently uploaded (20)

A Study of Urban Area Plan for Pabna Municipality
A Study of Urban Area Plan for Pabna MunicipalityA Study of Urban Area Plan for Pabna Municipality
A Study of Urban Area Plan for Pabna Municipality
 
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best ServiceTamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
 
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEGEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.ppt
 
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKARHAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
 
Engineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planesEngineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planes
 
DeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakesDeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakes
 
PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiesPE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and properties
 
Online food ordering system project report.pdf
Online food ordering system project report.pdfOnline food ordering system project report.pdf
Online food ordering system project report.pdf
 
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
 
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxWadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptx
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
DC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationDC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equation
 
Online electricity billing project report..pdf
Online electricity billing project report..pdfOnline electricity billing project report..pdf
Online electricity billing project report..pdf
 

Aplicación de técnicas de Inteligencia Artificial e IoT a la vida real.

  • 1. Aplicación de técnicas de Inteligencia Artificial e IoT a la vida real Facultad de Informática – Universidad Complutense Madrid 26 de Noviembre de 2020 José Luis Casteleiro Roca jose.luis.casteleiro@udc.es
  • 2. Índice  Propuesta de modelado híbrido  Métodos utilizados  Aplicaciones 2
  • 3. Índice  Propuesta de modelado híbrido 3
  • 6. Modelado híbrido 6 Selección de la topología híbrida Mejores modelos locales Regresión (por grupo) Fase de agrupamiento
  • 8. Modelo híbrido Modelos locales Grupo 1 Grupo 2 Grupo 3 Grupo 4 Grupo 5 Global Híbrido 2 grupos Híbrido 3 grupos Híbrido 4 grupos Híbrido 5 grupos 8
  • 9. 9 Modelo híbrido – Errores 𝑀𝑀𝑀𝑀𝑀𝑀 = 1 𝑛𝑛 � 𝑖𝑖=1 𝑛𝑛 𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 − 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟 2 𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁 = 1 𝑛𝑛 � 𝑖𝑖=1 𝑛𝑛 𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 𝑚𝑚 − 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟 2 𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 𝑚𝑚 · 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟 𝑀𝑀𝑀𝑀𝑀𝑀 = 1 𝑛𝑛 � 𝑖𝑖=1 𝑛𝑛 𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 − 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟 𝑀𝑀𝑀𝑀𝑀𝑀𝑀𝑀 = 1 𝑛𝑛 � 𝑖𝑖=1 𝑛𝑛 𝑦𝑦𝑖𝑖 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 𝑚𝑚 − 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟 𝑦𝑦𝑖𝑖𝑟𝑟𝑟𝑟𝑟𝑟𝑟𝑟
  • 10. Modelo híbrido Modelos locales Grupo 1 Grupo 2 Grupo 3 Grupo 4 Grupo 5 Global ANN-12 Híbrido 2 grupos LS-SVR ANN-2 Híbrido 3 grupos Poly-2 ANN-5 LS-SVR Híbrido 4 grupos ANN-5 ANN-3 ANN-4 LS-SVR Híbrido 5 grupos LS-SVR LS-SVR ANN-6 ANN-7 ANN-6 10
  • 12. Índice  Propuesta de modelado híbrido  Métodos utilizados 12
  • 13. 13 Métodos utilizados  Agrupamiento  Regresión  Validación  Elección del modelo
  • 18. Regresión – Redes neuronales artificiales 18
  • 19. Regresión – Redes neuronales artificiales 19
  • 20. Regresión – Máquinas de vectores soporte 20
  • 21. Regresión – Máquinas de vectores soporte 21
  • 22. Regresión – Máquinas de vectores soporte 22
  • 23. Regresión – Regresión polinomial 23
  • 24. Regresión – Regresión polinomial 24
  • 25. Regresión – Regresión polinomial 25 𝜃𝜃 = 𝑋𝑋 𝑇𝑇 · 𝑋𝑋 −1 · 𝑋𝑋 𝑇𝑇 · 𝑦𝑦
  • 29. Elección del modelo de regresión 29
  • 30. Elección del modelo de regresión  Validación con Hold Out • Redes neuronales artificiales – Diferente número de neuronas en la capa oculta • Máquinas de vectores soporte • Regresión polinomial – Diferentes grados del polinomio  Error de cada modelo 30
  • 31. Elección del modelo de regresión  Validación con Cross Validation • Redes Neuronales Artificiales – K - Diferente número de neuronas en la capa oculta • K - Máquinas de soporte vectorial • Regresión polinomial – K - Diferentes grados del polinomio  Error de cada modelo 31
  • 32. Elección del modelo de regresión  Validación  Error de cada modelo  Mejor modelo  Entrenamiento del modelo con todos los datos 32
  • 33. Índice  Propuesta de modelado híbrido  Métodos utilizados  Aplicaciones 33
  • 34. 34 Aplicaciones  Hybrid intelligent system to perform fault detection on BIS sensor during surgeries  Power cell SOC modelling for intelligent virtual sensor implementation  Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife  Fuel cell hybrid model for predicting hydrogen inflow through energy demand  Hybrid intelligent system to predict the individual academic performance o engineering students
  • 35. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 35
  • 36. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 36
  • 37. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 37
  • 38. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 38
  • 39. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 39
  • 40.  50 pacientes  42.788 muestras Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 40 Grupo 1 Grupo 2 Global 100% Híbrido 2 grupos 0,8% 99,2% Grupo 1 Grupo 2 Global 0,8531 Híbrido 2 grupos 8,1·10-4 0,4129 Grupo 1 Grupo 2 Global ANN-6 Híbrido 2 grupos ANN-2 ANN-9
  • 41. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 41
  • 42. Hybrid intelligent system to perform fault detection on BIS sensor during surgeries 42
  • 43. Power cell SOC modelling for intelligent virtual sensor implementation 43
  • 44. Power cell SOC modelling for intelligent virtual sensor implementation 44
  • 45. Power cell SOC modelling for intelligent virtual sensor implementation 45
  • 46. Power cell SOC modelling for intelligent virtual sensor implementation 46
  • 47. Power cell SOC modelling for intelligent virtual sensor implementation 47
  • 48. Power cell SOC modelling for intelligent virtual sensor implementation 48 Carga Reposo Descarga Reposo Muestras 6.619 1.089 7.451 1.211 ANN 0,1094 0,0921 0,4767 0,0917 Poly 23,997 0,0904 17,814 0,0930 LS-SVR 0,1392 0,0902 0,5052 0,0865 ANN-10 LS-SVR ANN-8 LS-SVR
  • 49. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 49
  • 50. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 50
  • 51. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 51
  • 52. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 52
  • 53. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 53
  • 54. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 54
  • 55. Prediction of the energy demand of a hotel using an artificial intelligence-based model: Luxury hotel in Tenerife 55
  • 56. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 56
  • 57. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 57
  • 58. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 58
  • 59. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 59
  • 60. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 60
  • 61. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 61
  • 62. Fuel cell hybrid model for predicting hydrogen inflow through energy demand 62
  • 63. Hybrid intelligent system to predict the individual academic performance o engineering students 63
  • 64. Hybrid intelligent system to predict the individual academic performance o engineering students 64
  • 65. Hybrid intelligent system to predict the individual academic performance o engineering students 65
  • 66. Hybrid intelligent system to predict the individual academic performance o engineering students 66
  • 67. Hybrid intelligent system to predict the individual academic performance o engineering students 67
  • 68. Hybrid intelligent system to predict the individual academic performance o engineering students 68
  • 69. Hybrid intelligent system to predict the individual academic performance o engineering students 69
  • 70. Aplicación de técnicas de Inteligencia Artificial e IoT a la vida real Facultad de Informática – Universidad Complutense Madrid 26 de Noviembre de 2020 José Luis Casteleiro Roca jose.luis.casteleiro@udc.es Turno de preguntas
  • 71. Aplicación de técnicas de Inteligencia Artificial e IoT a la vida real Facultad de Informática – Universidad Complutense Madrid 26 de Noviembre de 2020 José Luis Casteleiro Roca jose.luis.casteleiro@udc.es