SlideShare ist ein Scribd-Unternehmen logo
1 von 20
Downloaden Sie, um offline zu lesen
African Conference on Research in Computer Science and Applied Mathematics
CARI’2020 – Polytech School of Thiès, Senegal October 2020
Application of LSTM architectures for next frame
forecasting in Sentinel-1 images time series
Waytehad Rose Moskolaïa,b , Wahabou Abdoua , Albert Dipandaa , Kolyangb
a Computer Science Department, University of Burgundy, 21078 DIJON Cedex, France.
b Computer Science Department, University of Maroua, P.O. Box 46 MAROUA, Cameroon.
OUTLINE
2
• Introduction
• Methodology
• Results and Discussions
• Conclusion and Perspectives
• Definition :
 Part of data mining that allows estimating future trends of events.
 Create predictions about unknown future events.
Used in several activity sectors:
Predictive Analytics
3
Historical
Data
Predictive
Algorithms
Model
New
Data
Model Predictions
Introduction
sales
Bank
Weather
Health
Energy
Agriculture
Earth observation
Technologies used
4
• For models using remote sensing data, classical Machine Learning
algorithms are generally used: Random Forest, SVM, Regression,
Neural Networks, etc.
• But some limits exist
 The necessity to first extract the features or linearize data
 The use of auxiliary data
 performance is often subject to many physical assumptions
• Recent works use more efficient technologies to achieve better
results: Deep Learning (Jason Brownlee, 2018)
Introduction
Classical Learning
Performance
Amount of Training data
Deep Learning
Deep Learning architectures
5
• Deep Learning (DL) :
 Is a part of artificial intelligence and Machine Learning
 Mimics the workings of the human brain
 Allows computers to learn by themselves from examples…
• Several DL architectures are used for prediction in time series:
 RNN: Recurrent Neural Networks, namely the Long Short-Term
Memory (LSTM) (Sepp Hochreiter and J. Schmidhuber, 1995)
 CNN : Convolutional Neural Network, suitable for images
 ConvLSTM : Fusion of CNN architecture and LSTM architecture
(SHI Xingjian et al., 2015)
 CNN-LSTM : Combination of CNN architecture and LSTM
architecture (CNN + LSTM), (Z. Shen et al., 2019)…
Introduction
Research question
6
• In general, determining which algorithms are best for a problem is
the key to getting the most out of a predictive analytics solution.
• Main research question : which architecture is the most suitable
for prediction tasks in satellite images time series ?
• Proposed approach : the implementation and comparative study of
three architectures widely used for prediction (ConvLSTM, Stack-
LSTM and CNN-LSTM), in the context of next occurrence prediction
in a given satellite images time series.
Introduction
Objectives
7
Let 𝑋_𝑡 be a function of ℝ × ℝ of size (W, H) representing an image at
time t. Given a sequence of images 𝑋_(𝑡−𝑛), 𝑋_(𝑡−𝑛−1), … 𝑋_𝑡,
the objectives of this work are :
 The implementation of sequence-to-one models based on
Stack-LSTM, ConvLSTM and CNN-LSTM architectures, for the
prediction of the image at time t+1
 Performance evaluation of each model
time
Predicted Image at time t+1
Images time series
Methodology
Materials
8
• Used data: 158 sentinel-1 images (www.earth-explorer.usg.org),
Wildlife Reserve of Togodo, from September 2016 to May 2019
• Development tools:
 Virtual GPU, Google Colab (https://colab.research.google.com)
 Python (Programming language)
 Tensorflow and Keras libraries
 Quantum GIS (for image preprocessing)
Methodology
Data preparation
9
• Preprocessing : Radiometric and geometric corrections,
Normalization, resizing, clipping, transformation to RGB files …
• Constitution of training set (about 80%) and test set (20%)
• Transformation of the training set into the format (samples, timestep,
Wx, Hx, features)
X_train Y_train
𝑋1, 𝑋2 , 𝑋3, 𝑋4, 𝑋5 [𝑋6]
𝑋2, 𝑋3 , 𝑋4, 𝑋5, 𝑋6 [𝑋7]
𝑋3, 𝑋4 , 𝑋5, 𝑋6, 𝑋7 [𝑋8]
…
𝑋𝑡−5, 𝑋𝑡−4 , … , 𝑋𝑡−1 [𝑋𝑡]
Timestep : Number of occurrence in input sequence
Samples : Batch size for training step (t – timestep)
Features : Number of variable to predict (1)
Wx, Hx : Size of images (64X64 and 128X128)
Methodology
Structure of models
10
Layering arrangement
ConvLSTM layers Stack-LSTM layers CNN-LSTM layers
• ConvLSTM2D()
• BatchNormalization()
• Dropout()
• ConvLSTM2D()
• BatchNormalization()
• Dropout()
• ConvLSTM2D()
• BatchNormalization()
• Dropout()
• Dense()
• Flatten()
• LSTM()
• LSTM()
• LSTM()
• Dense()
• Reshape()
• Dense()
• Conv2D()
• MaxPooling2D()
• Flatten()
• LSTM()
• LSTM()
• Dense ()
• Reshape()
• Dense()
Methodology
Training parameters
11
• Optimization function: Adaptive Moment Optimization (adam)
• Loss function : Root Mean-Square-Error (RMSE) and Mean
Absolute Error (MAE))
• Training steps : 100 epochs (the number of times that the dataset
passes through the neural network)
Methodology
Evaluation parameters
12
• Evolution of loss during the training step
• Total training time
• Values of Structural SIMilarity (SSIM) between the predicted image
and the real one
Activity Recognition: Generating a textual
Methodology
Graphical display
13
Prediction results based on ConvLSTM, Stack-LSTM and CNN-
LSTM (respectively (a), (b), (c)). Timestep = 5, with (64×64) images
from test set.
Results and Discussions
Graphical display
14
Prediction results based on ConvLSTM, Stack-LSTM and CNN-LSTM
(respectively (a), (b), (c)). Timestep = 10, with (64×64) images from
test set.
Results and Discussions
Evolution of training Loss
15
Evolution of training loss (MAE) over epochs depending on timestep (vary
from 5 to 10). (a) Left: training loss with ConvLSTM, right: Training loss with
CNN-LSTM. (b) Training loss with Stack-LSTM
Results and Discussions
Evolution of training loss
16
Evolution of training loss values over epochs. (a) Left: MAE with (128×128)
images, Right: MAE with (64×64) images. (b) Left: RMSE with (128×128)
images, Right: RMSE with (64×64) images.
Results and Discussions
Evaluation criteria
17
• Due to convolutions operations, time processing is significantly higher
with ConvLSTM model than CNN-LSTM and Stack-LSTM when the
resolution of images increases.
Results and Discussions
Conclusion
18
• The use of ConvLSTM architecture for the forecasting tasks
from earth observation images time series is not advisable
(size of images, length of sequences)
• The use of CNN-LSTM architecture is recommended
• Predictions with Stack-LSTM models are done pixel by pixel
• In all situations it is necessary to choose good parameters to
achieve better results (optimization).
Conclusion and Perspectives
Perspectives
19
• What next?
 Optimize model based on CNN-LSTM architecture to
improve accuracy
 Use more date
 Test on others area
 Create a model based on different architectures to
achieve better results.
Conclusion and Perspectives
20
THANK YOU FOR YOUR ATTENTION
QUESTIONS?

Weitere ähnliche Inhalte

Was ist angesagt?

This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019Charles Martin
 
The Gaussian Process Latent Variable Model (GPLVM)
The Gaussian Process Latent Variable Model (GPLVM)The Gaussian Process Latent Variable Model (GPLVM)
The Gaussian Process Latent Variable Model (GPLVM)James McMurray
 
LCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative FilteringLCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative FilteringFabio Petroni, PhD
 
Mining at scale with latent factor models for matrix completion
Mining at scale with latent factor models for matrix completionMining at scale with latent factor models for matrix completion
Mining at scale with latent factor models for matrix completionFabio Petroni, PhD
 
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsMethods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsRyan B Harvey, CSDP, CSM
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks Charles Martin
 
Why Deep Learning Works: Dec 13, 2018 at ICSI, UC Berkeley
Why Deep Learning Works: Dec 13, 2018 at ICSI, UC BerkeleyWhy Deep Learning Works: Dec 13, 2018 at ICSI, UC Berkeley
Why Deep Learning Works: Dec 13, 2018 at ICSI, UC BerkeleyCharles Martin
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksWhy Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksCharles Martin
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksWhy Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksCharles Martin
 
Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...
Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...
Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...IOSRJECE
 
AI and Machine Learning for the Lean Start Up
AI and Machine Learning for the Lean Start UpAI and Machine Learning for the Lean Start Up
AI and Machine Learning for the Lean Start UpCharles Martin
 
Image sampling and quantization
Image sampling and quantizationImage sampling and quantization
Image sampling and quantizationBCET, Balasore
 
Dual-time Modeling and Forecasting in Consumer Banking (2016)
Dual-time Modeling and Forecasting in Consumer Banking (2016)Dual-time Modeling and Forecasting in Consumer Banking (2016)
Dual-time Modeling and Forecasting in Consumer Banking (2016)Aijun Zhang
 
Georgetown B-school Talk 2021
Georgetown B-school Talk  2021Georgetown B-school Talk  2021
Georgetown B-school Talk 2021Charles Martin
 
Self-Learning Systems for Cyber Security
Self-Learning Systems for Cyber SecuritySelf-Learning Systems for Cyber Security
Self-Learning Systems for Cyber SecurityKim Hammar
 
Dixon Deep Learning
Dixon Deep LearningDixon Deep Learning
Dixon Deep LearningSciCompIIT
 
Tutorial of topological data analysis part 3(Mapper algorithm)
Tutorial of topological data analysis part 3(Mapper algorithm)Tutorial of topological data analysis part 3(Mapper algorithm)
Tutorial of topological data analysis part 3(Mapper algorithm)Ha Phuong
 
On clustering financial time series - A need for distances between dependent ...
On clustering financial time series - A need for distances between dependent ...On clustering financial time series - A need for distances between dependent ...
On clustering financial time series - A need for distances between dependent ...Gautier Marti
 

Was ist angesagt? (20)

This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019
 
The Gaussian Process Latent Variable Model (GPLVM)
The Gaussian Process Latent Variable Model (GPLVM)The Gaussian Process Latent Variable Model (GPLVM)
The Gaussian Process Latent Variable Model (GPLVM)
 
LCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative FilteringLCBM: Statistics-Based Parallel Collaborative Filtering
LCBM: Statistics-Based Parallel Collaborative Filtering
 
Mining at scale with latent factor models for matrix completion
Mining at scale with latent factor models for matrix completionMining at scale with latent factor models for matrix completion
Mining at scale with latent factor models for matrix completion
 
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data SetsMethods of Manifold Learning for Dimension Reduction of Large Data Sets
Methods of Manifold Learning for Dimension Reduction of Large Data Sets
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks
 
Why Deep Learning Works: Dec 13, 2018 at ICSI, UC Berkeley
Why Deep Learning Works: Dec 13, 2018 at ICSI, UC BerkeleyWhy Deep Learning Works: Dec 13, 2018 at ICSI, UC Berkeley
Why Deep Learning Works: Dec 13, 2018 at ICSI, UC Berkeley
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksWhy Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks
 
Why Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural NetworksWhy Deep Learning Works: Self Regularization in Deep Neural Networks
Why Deep Learning Works: Self Regularization in Deep Neural Networks
 
Cc stat phys draft
Cc stat phys draftCc stat phys draft
Cc stat phys draft
 
Search relevance
Search relevanceSearch relevance
Search relevance
 
Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...
Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...
Investigation on the Pattern Synthesis of Subarray Weights for Low EMI Applic...
 
AI and Machine Learning for the Lean Start Up
AI and Machine Learning for the Lean Start UpAI and Machine Learning for the Lean Start Up
AI and Machine Learning for the Lean Start Up
 
Image sampling and quantization
Image sampling and quantizationImage sampling and quantization
Image sampling and quantization
 
Dual-time Modeling and Forecasting in Consumer Banking (2016)
Dual-time Modeling and Forecasting in Consumer Banking (2016)Dual-time Modeling and Forecasting in Consumer Banking (2016)
Dual-time Modeling and Forecasting in Consumer Banking (2016)
 
Georgetown B-school Talk 2021
Georgetown B-school Talk  2021Georgetown B-school Talk  2021
Georgetown B-school Talk 2021
 
Self-Learning Systems for Cyber Security
Self-Learning Systems for Cyber SecuritySelf-Learning Systems for Cyber Security
Self-Learning Systems for Cyber Security
 
Dixon Deep Learning
Dixon Deep LearningDixon Deep Learning
Dixon Deep Learning
 
Tutorial of topological data analysis part 3(Mapper algorithm)
Tutorial of topological data analysis part 3(Mapper algorithm)Tutorial of topological data analysis part 3(Mapper algorithm)
Tutorial of topological data analysis part 3(Mapper algorithm)
 
On clustering financial time series - A need for distances between dependent ...
On clustering financial time series - A need for distances between dependent ...On clustering financial time series - A need for distances between dependent ...
On clustering financial time series - A need for distances between dependent ...
 

Ähnlich wie LSTM Models for Sentinel-1 Image Forecasting

FAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETS
FAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETSFAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETS
FAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETScsandit
 
自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用Ryo Iwaki
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.bhavinecindus
 
Background Estimation Using Principal Component Analysis Based on Limited Mem...
Background Estimation Using Principal Component Analysis Based on Limited Mem...Background Estimation Using Principal Component Analysis Based on Limited Mem...
Background Estimation Using Principal Component Analysis Based on Limited Mem...IJECEIAES
 
A proposed accelerated image copy-move forgery detection-vcip2014
A proposed accelerated image copy-move forgery detection-vcip2014A proposed accelerated image copy-move forgery detection-vcip2014
A proposed accelerated image copy-move forgery detection-vcip2014SondosFadl
 
Combinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learningCombinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learning민재 정
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooJaeJun Yoo
 
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION cscpconf
 
Fractional step discriminant pruning
Fractional step discriminant pruningFractional step discriminant pruning
Fractional step discriminant pruningVasileiosMezaris
 
Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022 Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022 Charles Martin
 
Sparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image ProcessingSparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image ProcessingEswar Publications
 
Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...
Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...
Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...csandit
 
EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...
EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...
EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...cscpconf
 
Large Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate DescentLarge Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate DescentShaleen Kumar Gupta
 

Ähnlich wie LSTM Models for Sentinel-1 Image Forecasting (20)

IPT.pdf
IPT.pdfIPT.pdf
IPT.pdf
 
crowd counting.pptx
crowd counting.pptxcrowd counting.pptx
crowd counting.pptx
 
FAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETS
FAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETSFAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETS
FAST ALGORITHMS FOR UNSUPERVISED LEARNING IN LARGE DATA SETS
 
自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用自然方策勾配法の基礎と応用
自然方策勾配法の基礎と応用
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.
 
Background Estimation Using Principal Component Analysis Based on Limited Mem...
Background Estimation Using Principal Component Analysis Based on Limited Mem...Background Estimation Using Principal Component Analysis Based on Limited Mem...
Background Estimation Using Principal Component Analysis Based on Limited Mem...
 
Inverse problems in medical imaging
Inverse problems in medical imagingInverse problems in medical imaging
Inverse problems in medical imaging
 
A proposed accelerated image copy-move forgery detection-vcip2014
A proposed accelerated image copy-move forgery detection-vcip2014A proposed accelerated image copy-move forgery detection-vcip2014
A proposed accelerated image copy-move forgery detection-vcip2014
 
Combinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learningCombinatorial optimization and deep reinforcement learning
Combinatorial optimization and deep reinforcement learning
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
 
ENS Macrh 2022.pdf
ENS Macrh 2022.pdfENS Macrh 2022.pdf
ENS Macrh 2022.pdf
 
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
 
Fa19_P1.pptx
Fa19_P1.pptxFa19_P1.pptx
Fa19_P1.pptx
 
Fractional step discriminant pruning
Fractional step discriminant pruningFractional step discriminant pruning
Fractional step discriminant pruning
 
Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022 Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022
 
Sparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image ProcessingSparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image Processing
 
Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...
Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...
Efficient Approach for Content Based Image Retrieval Using Multiple SVM in YA...
 
EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...
EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...
EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING MULTIPLE SVM IN YA...
 
Large Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate DescentLarge Scale Kernel Learning using Block Coordinate Descent
Large Scale Kernel Learning using Block Coordinate Descent
 
On mesh
On meshOn mesh
On mesh
 

Mehr von Mokhtar SELLAMI

A posteriori error estimation in an adaptive multidimensional parameterizatio...
A posteriori error estimation in an adaptive multidimensional parameterizatio...A posteriori error estimation in an adaptive multidimensional parameterizatio...
A posteriori error estimation in an adaptive multidimensional parameterizatio...Mokhtar SELLAMI
 
A new approximation of the Height process of a CSBP
A new approximation of the Height process of a CSBP A new approximation of the Height process of a CSBP
A new approximation of the Height process of a CSBP Mokhtar SELLAMI
 
Effects on competition induced by periodic fluctuations in environment
Effects on competition induced by periodic fluctuations in environment Effects on competition induced by periodic fluctuations in environment
Effects on competition induced by periodic fluctuations in environment Mokhtar SELLAMI
 
E ect of the mortality on a density-dependent model with a predator-prey rela...
Eect of the mortality on a density-dependent model with a predator-prey rela...Eect of the mortality on a density-dependent model with a predator-prey rela...
E ect of the mortality on a density-dependent model with a predator-prey rela...Mokhtar SELLAMI
 
Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...
Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...
Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...Mokhtar SELLAMI
 
CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...
CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...
CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...Mokhtar SELLAMI
 
CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...
CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...
CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...Mokhtar SELLAMI
 
Federation and Promotion of Heterogeneous Domains and Services
Federation and Promotion of Heterogeneous Domains and ServicesFederation and Promotion of Heterogeneous Domains and Services
Federation and Promotion of Heterogeneous Domains and ServicesMokhtar SELLAMI
 
Cari2020 Rodrigue Aimé Djeumen Djatcha
Cari2020 Rodrigue Aimé Djeumen DjatchaCari2020 Rodrigue Aimé Djeumen Djatcha
Cari2020 Rodrigue Aimé Djeumen DjatchaMokhtar SELLAMI
 
Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...
Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...
Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...Mokhtar SELLAMI
 

Mehr von Mokhtar SELLAMI (12)

A posteriori error estimation in an adaptive multidimensional parameterizatio...
A posteriori error estimation in an adaptive multidimensional parameterizatio...A posteriori error estimation in an adaptive multidimensional parameterizatio...
A posteriori error estimation in an adaptive multidimensional parameterizatio...
 
A new approximation of the Height process of a CSBP
A new approximation of the Height process of a CSBP A new approximation of the Height process of a CSBP
A new approximation of the Height process of a CSBP
 
Effects on competition induced by periodic fluctuations in environment
Effects on competition induced by periodic fluctuations in environment Effects on competition induced by periodic fluctuations in environment
Effects on competition induced by periodic fluctuations in environment
 
E ect of the mortality on a density-dependent model with a predator-prey rela...
Eect of the mortality on a density-dependent model with a predator-prey rela...Eect of the mortality on a density-dependent model with a predator-prey rela...
E ect of the mortality on a density-dependent model with a predator-prey rela...
 
Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...
Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...
Cari2020: ALGORITHMES DE SORTIE DU PIÈGE DE LA ZONE ENNUYEUSE EN APPRENTISSAG...
 
CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...
CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...
CARI2020: RESOLUTION D’ANAPHORES NOMINALES AVEC LES SEPARATEURS À VASTES MARG...
 
CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...
CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...
CARI2020: A CGM-Based Parallel Algorithm Using the Four-Russians Speedup for ...
 
Federation and Promotion of Heterogeneous Domains and Services
Federation and Promotion of Heterogeneous Domains and ServicesFederation and Promotion of Heterogeneous Domains and Services
Federation and Promotion of Heterogeneous Domains and Services
 
Cari2020 Rodrigue Aimé Djeumen Djatcha
Cari2020 Rodrigue Aimé Djeumen DjatchaCari2020 Rodrigue Aimé Djeumen Djatcha
Cari2020 Rodrigue Aimé Djeumen Djatcha
 
Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...
Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...
Cari2020 Comparative Study of the Performance of Elliptic Curve Cryptography ...
 
CARI2020-Benaissa
CARI2020-BenaissaCARI2020-Benaissa
CARI2020-Benaissa
 
Cari2020 dembele
Cari2020 dembeleCari2020 dembele
Cari2020 dembele
 

Kürzlich hochgeladen

Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Christo Ananth
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSSIVASHANKAR N
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Dr.Costas Sachpazis
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxupamatechverse
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlysanyuktamishra911
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGMANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGSIVASHANKAR N
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdfKamal Acharya
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
 
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxBSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxfenichawla
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performancesivaprakash250
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)simmis5
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdfankushspencer015
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 

Kürzlich hochgeladen (20)

Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGMANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxBSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 

LSTM Models for Sentinel-1 Image Forecasting

  • 1. African Conference on Research in Computer Science and Applied Mathematics CARI’2020 – Polytech School of Thiès, Senegal October 2020 Application of LSTM architectures for next frame forecasting in Sentinel-1 images time series Waytehad Rose Moskolaïa,b , Wahabou Abdoua , Albert Dipandaa , Kolyangb a Computer Science Department, University of Burgundy, 21078 DIJON Cedex, France. b Computer Science Department, University of Maroua, P.O. Box 46 MAROUA, Cameroon.
  • 2. OUTLINE 2 • Introduction • Methodology • Results and Discussions • Conclusion and Perspectives
  • 3. • Definition :  Part of data mining that allows estimating future trends of events.  Create predictions about unknown future events. Used in several activity sectors: Predictive Analytics 3 Historical Data Predictive Algorithms Model New Data Model Predictions Introduction sales Bank Weather Health Energy Agriculture Earth observation
  • 4. Technologies used 4 • For models using remote sensing data, classical Machine Learning algorithms are generally used: Random Forest, SVM, Regression, Neural Networks, etc. • But some limits exist  The necessity to first extract the features or linearize data  The use of auxiliary data  performance is often subject to many physical assumptions • Recent works use more efficient technologies to achieve better results: Deep Learning (Jason Brownlee, 2018) Introduction Classical Learning Performance Amount of Training data Deep Learning
  • 5. Deep Learning architectures 5 • Deep Learning (DL) :  Is a part of artificial intelligence and Machine Learning  Mimics the workings of the human brain  Allows computers to learn by themselves from examples… • Several DL architectures are used for prediction in time series:  RNN: Recurrent Neural Networks, namely the Long Short-Term Memory (LSTM) (Sepp Hochreiter and J. Schmidhuber, 1995)  CNN : Convolutional Neural Network, suitable for images  ConvLSTM : Fusion of CNN architecture and LSTM architecture (SHI Xingjian et al., 2015)  CNN-LSTM : Combination of CNN architecture and LSTM architecture (CNN + LSTM), (Z. Shen et al., 2019)… Introduction
  • 6. Research question 6 • In general, determining which algorithms are best for a problem is the key to getting the most out of a predictive analytics solution. • Main research question : which architecture is the most suitable for prediction tasks in satellite images time series ? • Proposed approach : the implementation and comparative study of three architectures widely used for prediction (ConvLSTM, Stack- LSTM and CNN-LSTM), in the context of next occurrence prediction in a given satellite images time series. Introduction
  • 7. Objectives 7 Let 𝑋_𝑡 be a function of ℝ × ℝ of size (W, H) representing an image at time t. Given a sequence of images 𝑋_(𝑡−𝑛), 𝑋_(𝑡−𝑛−1), … 𝑋_𝑡, the objectives of this work are :  The implementation of sequence-to-one models based on Stack-LSTM, ConvLSTM and CNN-LSTM architectures, for the prediction of the image at time t+1  Performance evaluation of each model time Predicted Image at time t+1 Images time series Methodology
  • 8. Materials 8 • Used data: 158 sentinel-1 images (www.earth-explorer.usg.org), Wildlife Reserve of Togodo, from September 2016 to May 2019 • Development tools:  Virtual GPU, Google Colab (https://colab.research.google.com)  Python (Programming language)  Tensorflow and Keras libraries  Quantum GIS (for image preprocessing) Methodology
  • 9. Data preparation 9 • Preprocessing : Radiometric and geometric corrections, Normalization, resizing, clipping, transformation to RGB files … • Constitution of training set (about 80%) and test set (20%) • Transformation of the training set into the format (samples, timestep, Wx, Hx, features) X_train Y_train 𝑋1, 𝑋2 , 𝑋3, 𝑋4, 𝑋5 [𝑋6] 𝑋2, 𝑋3 , 𝑋4, 𝑋5, 𝑋6 [𝑋7] 𝑋3, 𝑋4 , 𝑋5, 𝑋6, 𝑋7 [𝑋8] … 𝑋𝑡−5, 𝑋𝑡−4 , … , 𝑋𝑡−1 [𝑋𝑡] Timestep : Number of occurrence in input sequence Samples : Batch size for training step (t – timestep) Features : Number of variable to predict (1) Wx, Hx : Size of images (64X64 and 128X128) Methodology
  • 10. Structure of models 10 Layering arrangement ConvLSTM layers Stack-LSTM layers CNN-LSTM layers • ConvLSTM2D() • BatchNormalization() • Dropout() • ConvLSTM2D() • BatchNormalization() • Dropout() • ConvLSTM2D() • BatchNormalization() • Dropout() • Dense() • Flatten() • LSTM() • LSTM() • LSTM() • Dense() • Reshape() • Dense() • Conv2D() • MaxPooling2D() • Flatten() • LSTM() • LSTM() • Dense () • Reshape() • Dense() Methodology
  • 11. Training parameters 11 • Optimization function: Adaptive Moment Optimization (adam) • Loss function : Root Mean-Square-Error (RMSE) and Mean Absolute Error (MAE)) • Training steps : 100 epochs (the number of times that the dataset passes through the neural network) Methodology
  • 12. Evaluation parameters 12 • Evolution of loss during the training step • Total training time • Values of Structural SIMilarity (SSIM) between the predicted image and the real one Activity Recognition: Generating a textual Methodology
  • 13. Graphical display 13 Prediction results based on ConvLSTM, Stack-LSTM and CNN- LSTM (respectively (a), (b), (c)). Timestep = 5, with (64×64) images from test set. Results and Discussions
  • 14. Graphical display 14 Prediction results based on ConvLSTM, Stack-LSTM and CNN-LSTM (respectively (a), (b), (c)). Timestep = 10, with (64×64) images from test set. Results and Discussions
  • 15. Evolution of training Loss 15 Evolution of training loss (MAE) over epochs depending on timestep (vary from 5 to 10). (a) Left: training loss with ConvLSTM, right: Training loss with CNN-LSTM. (b) Training loss with Stack-LSTM Results and Discussions
  • 16. Evolution of training loss 16 Evolution of training loss values over epochs. (a) Left: MAE with (128×128) images, Right: MAE with (64×64) images. (b) Left: RMSE with (128×128) images, Right: RMSE with (64×64) images. Results and Discussions
  • 17. Evaluation criteria 17 • Due to convolutions operations, time processing is significantly higher with ConvLSTM model than CNN-LSTM and Stack-LSTM when the resolution of images increases. Results and Discussions
  • 18. Conclusion 18 • The use of ConvLSTM architecture for the forecasting tasks from earth observation images time series is not advisable (size of images, length of sequences) • The use of CNN-LSTM architecture is recommended • Predictions with Stack-LSTM models are done pixel by pixel • In all situations it is necessary to choose good parameters to achieve better results (optimization). Conclusion and Perspectives
  • 19. Perspectives 19 • What next?  Optimize model based on CNN-LSTM architecture to improve accuracy  Use more date  Test on others area  Create a model based on different architectures to achieve better results. Conclusion and Perspectives
  • 20. 20 THANK YOU FOR YOUR ATTENTION QUESTIONS?