SlideShare a Scribd company logo
1 of 27
Presentation on
“Global COVID-19 cases prediction using
Long Short Term Memory”
Subash Chandra Pakhrin
PhD Student
Wichita State University
Wichita, Kansas
1
Introduction
• COVID-19 is an infectious disease caused by severe
acute respiratory syndrome coronavirus2 (SARS-COV-
2).
• The disease was first identified in December 2019 in
Wuhan.
• As of April 27 2020, more than 3 million cases have
been reported across 185 countries.
• More than 208,000 deaths and more than 878,000
recovery.
• Symptoms: fever, cough, fatigue, shortness of breath
and loss of smell.
2
COVID-19
3
Source: https://commons.wikimedia.org/wiki/File:3D_medical_animation_corona_virus.jpg
Figure 1: 3D medical animation of corona virus
COVID-19
• Flu virus travel inside a sac made from cell
membrane to our cell nucleus that has all genetic
material.
• Corona virus doesn’t enter the host cell nucleus. It
directly access Ribosome (Protein Factory).
• Polypeptide Chain made from Ribosome travels to
Golgi apparatus and combines with cell membrane
and eventually it reproduce corona virus.
• Sanche S, et al. [1] illustrated that within 6 – 7 days
number of patients affected with COVID – 19 doubles
and it has a degree of spread (R0) of 2.2 – 2.7.
4
Objective
• To predict the number of daily cases using variant of
Recurrent Neural Network: Long Short Term
Memory.
• Take preventive actions to limit the spread of
Pandemic or decrease the value of R0.
5
Literature Review
• Qiang Gao, et al. [2] has developed pilot-scale
production of a purified inactivated SARS-CoV-2 virus
vaccine candidate (PiCoVacc), and is tested in
macaques and is safe to be used for humans.
• Jiayu Qiu, et al. [3] used LSTM and an attention
mechanism, and established the prediction model of
a stock price.
6
Literature Review
• Dianbo Liu, et al., [4] have used machine-learning
methodologies, to reliably forecast COVID-19 activity
in Chinese provinces in real -time.
• Ratnabali Pal, et al. [5] have proposed a shallow Long
short-term memory (LSTM) based neural network to
predict the risk category of a country.
7
Literature Review
• Shawni Dutta, et al. [6] used machine learning
approach to evaluate how much predicted results are
close to Confirmed – Negative – Released - Death
cases of Covid-19
• Zifeng Yang, et al. [7] proposed modified susceptible
–exposed-infected-removed (SEIR) epidemiological
model to predict the epidemic progression.
8
Literature Review
• Zhiyong Cui, et al. [8] proposed a deep stacked
bidirectional and unidirectional LSTM neural network
architecture, to predict network-wide traffic speed.
• Sima Siami et al. [9] proposed BiLSTM-based model
which offers better predictions than regular LSTM-
based models. Surprisingly, They found BiLSTM
models provide better predictions compared to
ARIMA and LSTM models.
9
Methodology
• Real Time Data collected from JOHNS HOPKINS
BLOOMBERG SCHOOL of PUBLIC HEALTH
• Exploratory Data Analysis:
– Truncate the alphabet part of the dataset & Summing up the daily
cases
– Normalize the dataset
– Converting 2 dimensional (2D) dataset into 3D dataset
– Make sequential data
• Separate the data into train (90%) and test set (10%)
• Feeding the 3D data into Long Short Term Memory.
• Train the model.
• Predict the value from trained model.
• Evaluating the model. 10
Proposed framework
11
Data Collection
Exploratory Data Analysis (Truncating
alphabet features, Normalization,
conversion from 2D to 3D)
Train the LSTM Model (90% Training
Sample)
Test the model (10 % Test Sample),
predict the value from the model
Validate the model
Tune hyper
Parameters
Figure 2: Proposed Framework
Recurrent Neural Network for
Sequence Modeling
“This morning I took my dog for a _____.”
given these words predict the next word
“Nepal is where I grew up, but I now live in Wichita. I speak fluent ___.”
We need information from the distant past to accurately predict the correct word.
Figure 3: Neural network and RNN
Long Short Term Memory (LSTMs)
LSTMs networks rely on gated cell to track information throughout many
time steps.
LSTM modules contain computational blocks that control information flow
Information is added or removed through structures called gates
Figure 4: Cell of LSTM [10, 11, 12, 13]
Long Short Term Memory (LSTMs)
1) Forget 2) Store 3) Update 4) Output
LSTMs forget irrelevant parts of the previous
state
Figure 5: Forget gate of LSTM [10, 11, 12, 13]
Long Short Term Memory (LSTMs)
1) Forget 2) Store 3) Update 4) Output
LSTMs store relevant new information into the
cell state
Figure 6: Store gate of LSTM [10, 11, 12, 13]
Long Short Term Memory (LSTMs)
1)Forget 2) Store 3) Update 4) Output
LSTMs selectively update cell state values
Figure 7: Update gate of LSTM [10, 11, 12, 13]
Long Short Term Memory (LSTMs)
1)Forget 2) Store 3) Update 4) Output
The output gate controls what information is
sent to the next time step
Figure 8: Update gate of LSTM [10, 11, 12, 13]
Architecture Used
18Figure 9: Two layers of LSTM
Output: Cumulative Daily Cases
19
Figure 10: Cumulative Daily Corona Cases
As of April 22 there are more than 2,500,000 corona cases world wide.
Output: Daily Cases
20
Figure 11: Daily Corona Cases world wide
On April 10 there was around 95,000 confirmed corona cases world wide
No of epochs to train the model
21
As number of epochs increase the training and test loss gradually
decrease and eventually they become consistent at epoch 55
Figure 12: Training and Test loss w.r.t. no. of epochs
Output: Prediction vs. Real value
22
Figure 13: predicted and real values
Since COVID-19 is a pandemic its predictions is difficult and it has volatile
and mercurial pattern
Root Mean Square Error (RMSE)
23
• RMSE is the root of the mean of the squared error.
• It has same unit as Actual value.
• Varied from 15.99 to 4000
Real Value Predicted Value
70,880 88,531.305
Table 1: Real and Predicted Value
Conclusion
• The proposed model perceived some pattern from
the historical data points by remembering the
relevant facts and forgetting the irrelevant features.
• The deep learning requires huge amount of data to
be trained so the model has large RMSE.
• In order to remain safe, we should practice social
distancing.
24
Modules Used
IDE: Anaconda Navigator
Modules Used:
1. math
2. numpy
3. pandas
4. seaborn
5. keras, Sequential, Dense, LSTM
6. keras, Dropout, Activation, Flatten
7. Matplotlib
8. Sklearn
25
References:
[1] Sanche S, Lin YT, et al., “High contagiousness and rapid spread of severe acute
respiratory syndrome coronavirus 2.”, Emerg Infect Dis. 2020 Jul.
https://doi.org/10.3201/eid2607.200282
[2] Qiang Gao, Linlin Bao, et al., “Rapid development of an inactivated vaccine for
SARS-CoV-2”, bioRxiv, 2020, https://doi.org/10.1101/2020.04.17.046375
[3] Jiayu Qiu, Bin Wang, et al., “Forecasting stock prices with long-short term
memory neural network based on attention mechanism”, Jan 2020, PLOS ONE,
https://doi.org/10.1371/journal.pone.0227222
[4] Dianbo Liu, Leonardo Clemente, et al., “A machine learning methodology for real-
time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches,
news alerts, and estimates from mechanistic models”, arXiv.org stat, Apr 2020
[5] Ratnabali Pal, Arif A. Sekh, et al., “Neural Network based country wise risk
prediction of COVID-19”, IEEE, Mar 2020
[6] Shawni Dutta, et al. , “Machine Learning Approach for Confirmation of COVID-19
Cases: Positive, Negative, Death and Release”, medRxiv, Mar 2020,
https://doi.org/10.1101/2020.03.25.20043505
[7] Zifeng Yang, et al., “Modified SEIR and AI prediction of the epidemics trend of
COVID-19 in China under public health interventions”, Journal of Thoracic
Disease, Mar 2020, doi: 10.21037/jtd.2020.02.64
26
References:
[8] Zhiyong Cui, et al., “Stacked Bidirectional and Unidirectional LSTM Recurrent
Neural Network for Network-wide Traffic Speed Prediction
[9] Sima Siami, et al., “A comparative Analysis of Forecasting financial Time Series
using ARIMA, LSTM, and BiLSTM
[10]Sepp Hochreiter, Jürgen Schmidhuber et al., “LONG SHORT TERM MEMORY”,
Neural Computation, 1997
[11]Ava Soleimany, Recurrent Neural Networks, MIT Introduction to Deep Learning,
2020, 6. S191: https://youtu.be/SEnXr6v2ifU
[12]Lex Friedman, MIT 6.S094: Recurrent Neural Networks for Steering Through Time,
2017, https://youtu.be/nFTQ7kHQWtc
[13] Fei-Fei Li, Justin Johnson & Serena Young, Stanford University, Convolutional
Neural Networks for Visual Recognition, 2017,
https://youtu.be/6niqTuYFZLQ?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv
27

More Related Content

What's hot

Support vector machines (svm)
Support vector machines (svm)Support vector machines (svm)
Support vector machines (svm)Sharayu Patil
 
Digit recognition
Digit recognitionDigit recognition
Digit recognitionbtandale
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Object classification using CNN & VGG16 Model (Keras and Tensorflow)
Object classification using CNN & VGG16 Model (Keras and Tensorflow) Object classification using CNN & VGG16 Model (Keras and Tensorflow)
Object classification using CNN & VGG16 Model (Keras and Tensorflow) Lalit Jain
 
Deep Learning - Overview of my work II
Deep Learning - Overview of my work IIDeep Learning - Overview of my work II
Deep Learning - Overview of my work IIMohamed Loey
 
HANDWRITTEN DIGIT RECOGNITIONppt1.pptx
HANDWRITTEN DIGIT RECOGNITIONppt1.pptxHANDWRITTEN DIGIT RECOGNITIONppt1.pptx
HANDWRITTEN DIGIT RECOGNITIONppt1.pptxALLADURGAUMESHCHANDR
 
Image classification using CNN
Image classification using CNNImage classification using CNN
Image classification using CNNNoura Hussein
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOleg Mygryn
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningJörgen Sandig
 
Activation functions
Activation functionsActivation functions
Activation functionsPRATEEK SAHU
 
Using Machine Learning to Optimize COVID-19 Predictions
Using Machine Learning to Optimize COVID-19 PredictionsUsing Machine Learning to Optimize COVID-19 Predictions
Using Machine Learning to Optimize COVID-19 PredictionsDatabricks
 
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Gaurav Mittal
 
Classification Based Machine Learning Algorithms
Classification Based Machine Learning AlgorithmsClassification Based Machine Learning Algorithms
Classification Based Machine Learning AlgorithmsMd. Main Uddin Rony
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnnSumeraHangi
 
Yann le cun
Yann le cunYann le cun
Yann le cunYandex
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningMohamed Loey
 
Deep Learning Tutorial
Deep Learning TutorialDeep Learning Tutorial
Deep Learning TutorialAmr Rashed
 

What's hot (20)

Support vector machines (svm)
Support vector machines (svm)Support vector machines (svm)
Support vector machines (svm)
 
Digit recognition
Digit recognitionDigit recognition
Digit recognition
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Object classification using CNN & VGG16 Model (Keras and Tensorflow)
Object classification using CNN & VGG16 Model (Keras and Tensorflow) Object classification using CNN & VGG16 Model (Keras and Tensorflow)
Object classification using CNN & VGG16 Model (Keras and Tensorflow)
 
Deep Learning - Overview of my work II
Deep Learning - Overview of my work IIDeep Learning - Overview of my work II
Deep Learning - Overview of my work II
 
Transfer Learning
Transfer LearningTransfer Learning
Transfer Learning
 
HANDWRITTEN DIGIT RECOGNITIONppt1.pptx
HANDWRITTEN DIGIT RECOGNITIONppt1.pptxHANDWRITTEN DIGIT RECOGNITIONppt1.pptx
HANDWRITTEN DIGIT RECOGNITIONppt1.pptx
 
Image classification using CNN
Image classification using CNNImage classification using CNN
Image classification using CNN
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Activation functions
Activation functionsActivation functions
Activation functions
 
Using Machine Learning to Optimize COVID-19 Predictions
Using Machine Learning to Optimize COVID-19 PredictionsUsing Machine Learning to Optimize COVID-19 Predictions
Using Machine Learning to Optimize COVID-19 Predictions
 
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)
 
Classification Based Machine Learning Algorithms
Classification Based Machine Learning AlgorithmsClassification Based Machine Learning Algorithms
Classification Based Machine Learning Algorithms
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnn
 
Deep learning
Deep learningDeep learning
Deep learning
 
Recurrent Neural Network
Recurrent Neural NetworkRecurrent Neural Network
Recurrent Neural Network
 
Yann le cun
Yann le cunYann le cun
Yann le cun
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
Deep Learning Tutorial
Deep Learning TutorialDeep Learning Tutorial
Deep Learning Tutorial
 

Similar to Global COVID-19 cases prediction using LSTM

Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis IJECEIAES
 
IRJET - Detection of Malaria using Image Cells
IRJET - Detection of Malaria using Image CellsIRJET - Detection of Malaria using Image Cells
IRJET - Detection of Malaria using Image CellsIRJET Journal
 
Lung Cancer Detection using Convolutional Neural Network
Lung Cancer Detection using Convolutional Neural NetworkLung Cancer Detection using Convolutional Neural Network
Lung Cancer Detection using Convolutional Neural NetworkIRJET Journal
 
Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19IRJET Journal
 
Malaria Detection System Using Microscopic Blood Smear Image
Malaria Detection System Using Microscopic Blood Smear ImageMalaria Detection System Using Microscopic Blood Smear Image
Malaria Detection System Using Microscopic Blood Smear ImageIRJET Journal
 
Real Time Social Distance Detector using Deep learning
Real Time Social Distance Detector using Deep learningReal Time Social Distance Detector using Deep learning
Real Time Social Distance Detector using Deep learningIRJET Journal
 
Covid Face Mask Detection Using Neural Networks
Covid Face Mask Detection Using Neural NetworksCovid Face Mask Detection Using Neural Networks
Covid Face Mask Detection Using Neural NetworksIRJET Journal
 
INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...
INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...
INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...ijaia
 
Designing of Application for Detection of Face Mask and Social Distancing Dur...
Designing of Application for Detection of Face Mask and Social Distancing Dur...Designing of Application for Detection of Face Mask and Social Distancing Dur...
Designing of Application for Detection of Face Mask and Social Distancing Dur...IRJET Journal
 
Enhancing COVID-19 forecasting through deep learning techniques and fine-tuning
Enhancing COVID-19 forecasting through deep learning techniques and fine-tuningEnhancing COVID-19 forecasting through deep learning techniques and fine-tuning
Enhancing COVID-19 forecasting through deep learning techniques and fine-tuningIJECEIAES
 
Preliminary Lung Cancer Detection using Deep Neural Networks
Preliminary Lung Cancer Detection using Deep Neural NetworksPreliminary Lung Cancer Detection using Deep Neural Networks
Preliminary Lung Cancer Detection using Deep Neural NetworksIRJET Journal
 
Face Mask Detection and Contactless Body Temperature Sensing
Face Mask Detection and Contactless Body Temperature SensingFace Mask Detection and Contactless Body Temperature Sensing
Face Mask Detection and Contactless Body Temperature SensingIRJET Journal
 
Covid Mask Detection and Social Distancing Using Raspberry pi
Covid Mask Detection and Social Distancing Using Raspberry piCovid Mask Detection and Social Distancing Using Raspberry pi
Covid Mask Detection and Social Distancing Using Raspberry piIRJET Journal
 
Covid Detection Using Lung X-ray Images
Covid Detection Using Lung X-ray ImagesCovid Detection Using Lung X-ray Images
Covid Detection Using Lung X-ray ImagesIRJET Journal
 
Developing an Artificial Immune Model for Cash Fraud Detection
Developing an Artificial Immune Model for Cash Fraud Detection   Developing an Artificial Immune Model for Cash Fraud Detection
Developing an Artificial Immune Model for Cash Fraud Detection khawla Osama
 
COVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELS
COVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELSCOVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELS
COVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELSIRJET Journal
 
A Review on Covid Detection using Cross Dataset Analysis
A Review on Covid Detection using Cross Dataset AnalysisA Review on Covid Detection using Cross Dataset Analysis
A Review on Covid Detection using Cross Dataset AnalysisIRJET Journal
 
DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...
DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...
DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...gerogepatton
 

Similar to Global COVID-19 cases prediction using LSTM (20)

Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis
 
IRJET - Detection of Malaria using Image Cells
IRJET - Detection of Malaria using Image CellsIRJET - Detection of Malaria using Image Cells
IRJET - Detection of Malaria using Image Cells
 
Lung Cancer Detection using Convolutional Neural Network
Lung Cancer Detection using Convolutional Neural NetworkLung Cancer Detection using Convolutional Neural Network
Lung Cancer Detection using Convolutional Neural Network
 
Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19
 
Malaria Detection System Using Microscopic Blood Smear Image
Malaria Detection System Using Microscopic Blood Smear ImageMalaria Detection System Using Microscopic Blood Smear Image
Malaria Detection System Using Microscopic Blood Smear Image
 
323462348
323462348323462348
323462348
 
323462348
323462348323462348
323462348
 
Real Time Social Distance Detector using Deep learning
Real Time Social Distance Detector using Deep learningReal Time Social Distance Detector using Deep learning
Real Time Social Distance Detector using Deep learning
 
Covid Face Mask Detection Using Neural Networks
Covid Face Mask Detection Using Neural NetworksCovid Face Mask Detection Using Neural Networks
Covid Face Mask Detection Using Neural Networks
 
INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...
INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...
INSIGHT ABOUT DETECTION, PREDICTION AND WEATHER IMPACT OF CORONAVIRUS (COVID-...
 
Designing of Application for Detection of Face Mask and Social Distancing Dur...
Designing of Application for Detection of Face Mask and Social Distancing Dur...Designing of Application for Detection of Face Mask and Social Distancing Dur...
Designing of Application for Detection of Face Mask and Social Distancing Dur...
 
Enhancing COVID-19 forecasting through deep learning techniques and fine-tuning
Enhancing COVID-19 forecasting through deep learning techniques and fine-tuningEnhancing COVID-19 forecasting through deep learning techniques and fine-tuning
Enhancing COVID-19 forecasting through deep learning techniques and fine-tuning
 
Preliminary Lung Cancer Detection using Deep Neural Networks
Preliminary Lung Cancer Detection using Deep Neural NetworksPreliminary Lung Cancer Detection using Deep Neural Networks
Preliminary Lung Cancer Detection using Deep Neural Networks
 
Face Mask Detection and Contactless Body Temperature Sensing
Face Mask Detection and Contactless Body Temperature SensingFace Mask Detection and Contactless Body Temperature Sensing
Face Mask Detection and Contactless Body Temperature Sensing
 
Covid Mask Detection and Social Distancing Using Raspberry pi
Covid Mask Detection and Social Distancing Using Raspberry piCovid Mask Detection and Social Distancing Using Raspberry pi
Covid Mask Detection and Social Distancing Using Raspberry pi
 
Covid Detection Using Lung X-ray Images
Covid Detection Using Lung X-ray ImagesCovid Detection Using Lung X-ray Images
Covid Detection Using Lung X-ray Images
 
Developing an Artificial Immune Model for Cash Fraud Detection
Developing an Artificial Immune Model for Cash Fraud Detection   Developing an Artificial Immune Model for Cash Fraud Detection
Developing an Artificial Immune Model for Cash Fraud Detection
 
COVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELS
COVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELSCOVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELS
COVID-19 FUTURE FORECASTING USING SUPERVISED MACHINE LEARNING MODELS
 
A Review on Covid Detection using Cross Dataset Analysis
A Review on Covid Detection using Cross Dataset AnalysisA Review on Covid Detection using Cross Dataset Analysis
A Review on Covid Detection using Cross Dataset Analysis
 
DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...
DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...
DEEP LEARNING-BASED ECG CLASSIFICATION ON RASPBERRY PI USING A TENSORFLOW LIT...
 

More from Subash Chandra Pakhrin

Torsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTMTorsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTMSubash Chandra Pakhrin
 
Characterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites basedCharacterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites basedSubash Chandra Pakhrin
 
Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network Subash Chandra Pakhrin
 
Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15Subash Chandra Pakhrin
 

More from Subash Chandra Pakhrin (20)

Prismoid
PrismoidPrismoid
Prismoid
 
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTMTorsion Angles, ASA Used for prediction of Non - Enzymatic PTM
Torsion Angles, ASA Used for prediction of Non - Enzymatic PTM
 
COVID 19
COVID 19 COVID 19
COVID 19
 
Rnn & Lstm
Rnn & LstmRnn & Lstm
Rnn & Lstm
 
Characterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites basedCharacterization and identification of lysine succinylation sites based
Characterization and identification of lysine succinylation sites based
 
Cnn april 8 2020
Cnn april 8 2020Cnn april 8 2020
Cnn april 8 2020
 
Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network Deep Learning or Convolutional Neural Network
Deep Learning or Convolutional Neural Network
 
Ncit 1st ai lab
Ncit 1st ai labNcit 1st ai lab
Ncit 1st ai lab
 
Ai lab
Ai labAi lab
Ai lab
 
Constraint satisfaction problem
Constraint satisfaction problem Constraint satisfaction problem
Constraint satisfaction problem
 
Analysis
AnalysisAnalysis
Analysis
 
Planning
PlanningPlanning
Planning
 
Intelligent agents (bsc csit) lec 2
Intelligent agents (bsc csit) lec 2Intelligent agents (bsc csit) lec 2
Intelligent agents (bsc csit) lec 2
 
Final slide4 (bsc csit) chapter 4
Final slide4 (bsc csit) chapter 4Final slide4 (bsc csit) chapter 4
Final slide4 (bsc csit) chapter 4
 
Final slide (bsc csit) chapter 5
Final slide (bsc csit) chapter 5Final slide (bsc csit) chapter 5
Final slide (bsc csit) chapter 5
 
Lec 6 bsc csit
Lec 6 bsc csitLec 6 bsc csit
Lec 6 bsc csit
 
Two player games
Two player gamesTwo player games
Two player games
 
Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15Knnowledge representation and logic lec 11 to lec 15
Knnowledge representation and logic lec 11 to lec 15
 
Final slide (bsc csit) chapter 2
Final slide (bsc csit) chapter 2Final slide (bsc csit) chapter 2
Final slide (bsc csit) chapter 2
 
Final slide (bsc csit) chapter 3
Final slide (bsc csit) chapter 3Final slide (bsc csit) chapter 3
Final slide (bsc csit) chapter 3
 

Recently uploaded

SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 
Enzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdf
Enzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdfEnzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdf
Enzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdfSumit Tiwari
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxRoyAbrique
 
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting DataJhengPantaleon
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application ) Sakshi Ghasle
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
Class 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdfClass 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdfakmcokerachita
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxOH TEIK BIN
 
MENTAL STATUS EXAMINATION format.docx
MENTAL     STATUS EXAMINATION format.docxMENTAL     STATUS EXAMINATION format.docx
MENTAL STATUS EXAMINATION format.docxPoojaSen20
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...M56BOOKSTORE PRODUCT/SERVICE
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
Presiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsPresiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsanshu789521
 

Recently uploaded (20)

SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 
Enzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdf
Enzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdfEnzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdf
Enzyme, Pharmaceutical Aids, Miscellaneous Last Part of Chapter no 5th.pdf
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
 
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application )
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
Class 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdfClass 11 Legal Studies Ch-1 Concept of State .pdf
Class 11 Legal Studies Ch-1 Concept of State .pdf
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptx
 
MENTAL STATUS EXAMINATION format.docx
MENTAL     STATUS EXAMINATION format.docxMENTAL     STATUS EXAMINATION format.docx
MENTAL STATUS EXAMINATION format.docx
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
KSHARA STURA .pptx---KSHARA KARMA THERAPY (CAUSTIC THERAPY)————IMP.OF KSHARA ...
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
Presiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsPresiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha elections
 

Global COVID-19 cases prediction using LSTM

  • 1. Presentation on “Global COVID-19 cases prediction using Long Short Term Memory” Subash Chandra Pakhrin PhD Student Wichita State University Wichita, Kansas 1
  • 2. Introduction • COVID-19 is an infectious disease caused by severe acute respiratory syndrome coronavirus2 (SARS-COV- 2). • The disease was first identified in December 2019 in Wuhan. • As of April 27 2020, more than 3 million cases have been reported across 185 countries. • More than 208,000 deaths and more than 878,000 recovery. • Symptoms: fever, cough, fatigue, shortness of breath and loss of smell. 2
  • 4. COVID-19 • Flu virus travel inside a sac made from cell membrane to our cell nucleus that has all genetic material. • Corona virus doesn’t enter the host cell nucleus. It directly access Ribosome (Protein Factory). • Polypeptide Chain made from Ribosome travels to Golgi apparatus and combines with cell membrane and eventually it reproduce corona virus. • Sanche S, et al. [1] illustrated that within 6 – 7 days number of patients affected with COVID – 19 doubles and it has a degree of spread (R0) of 2.2 – 2.7. 4
  • 5. Objective • To predict the number of daily cases using variant of Recurrent Neural Network: Long Short Term Memory. • Take preventive actions to limit the spread of Pandemic or decrease the value of R0. 5
  • 6. Literature Review • Qiang Gao, et al. [2] has developed pilot-scale production of a purified inactivated SARS-CoV-2 virus vaccine candidate (PiCoVacc), and is tested in macaques and is safe to be used for humans. • Jiayu Qiu, et al. [3] used LSTM and an attention mechanism, and established the prediction model of a stock price. 6
  • 7. Literature Review • Dianbo Liu, et al., [4] have used machine-learning methodologies, to reliably forecast COVID-19 activity in Chinese provinces in real -time. • Ratnabali Pal, et al. [5] have proposed a shallow Long short-term memory (LSTM) based neural network to predict the risk category of a country. 7
  • 8. Literature Review • Shawni Dutta, et al. [6] used machine learning approach to evaluate how much predicted results are close to Confirmed – Negative – Released - Death cases of Covid-19 • Zifeng Yang, et al. [7] proposed modified susceptible –exposed-infected-removed (SEIR) epidemiological model to predict the epidemic progression. 8
  • 9. Literature Review • Zhiyong Cui, et al. [8] proposed a deep stacked bidirectional and unidirectional LSTM neural network architecture, to predict network-wide traffic speed. • Sima Siami et al. [9] proposed BiLSTM-based model which offers better predictions than regular LSTM- based models. Surprisingly, They found BiLSTM models provide better predictions compared to ARIMA and LSTM models. 9
  • 10. Methodology • Real Time Data collected from JOHNS HOPKINS BLOOMBERG SCHOOL of PUBLIC HEALTH • Exploratory Data Analysis: – Truncate the alphabet part of the dataset & Summing up the daily cases – Normalize the dataset – Converting 2 dimensional (2D) dataset into 3D dataset – Make sequential data • Separate the data into train (90%) and test set (10%) • Feeding the 3D data into Long Short Term Memory. • Train the model. • Predict the value from trained model. • Evaluating the model. 10
  • 11. Proposed framework 11 Data Collection Exploratory Data Analysis (Truncating alphabet features, Normalization, conversion from 2D to 3D) Train the LSTM Model (90% Training Sample) Test the model (10 % Test Sample), predict the value from the model Validate the model Tune hyper Parameters Figure 2: Proposed Framework
  • 12. Recurrent Neural Network for Sequence Modeling “This morning I took my dog for a _____.” given these words predict the next word “Nepal is where I grew up, but I now live in Wichita. I speak fluent ___.” We need information from the distant past to accurately predict the correct word. Figure 3: Neural network and RNN
  • 13. Long Short Term Memory (LSTMs) LSTMs networks rely on gated cell to track information throughout many time steps. LSTM modules contain computational blocks that control information flow Information is added or removed through structures called gates Figure 4: Cell of LSTM [10, 11, 12, 13]
  • 14. Long Short Term Memory (LSTMs) 1) Forget 2) Store 3) Update 4) Output LSTMs forget irrelevant parts of the previous state Figure 5: Forget gate of LSTM [10, 11, 12, 13]
  • 15. Long Short Term Memory (LSTMs) 1) Forget 2) Store 3) Update 4) Output LSTMs store relevant new information into the cell state Figure 6: Store gate of LSTM [10, 11, 12, 13]
  • 16. Long Short Term Memory (LSTMs) 1)Forget 2) Store 3) Update 4) Output LSTMs selectively update cell state values Figure 7: Update gate of LSTM [10, 11, 12, 13]
  • 17. Long Short Term Memory (LSTMs) 1)Forget 2) Store 3) Update 4) Output The output gate controls what information is sent to the next time step Figure 8: Update gate of LSTM [10, 11, 12, 13]
  • 18. Architecture Used 18Figure 9: Two layers of LSTM
  • 19. Output: Cumulative Daily Cases 19 Figure 10: Cumulative Daily Corona Cases As of April 22 there are more than 2,500,000 corona cases world wide.
  • 20. Output: Daily Cases 20 Figure 11: Daily Corona Cases world wide On April 10 there was around 95,000 confirmed corona cases world wide
  • 21. No of epochs to train the model 21 As number of epochs increase the training and test loss gradually decrease and eventually they become consistent at epoch 55 Figure 12: Training and Test loss w.r.t. no. of epochs
  • 22. Output: Prediction vs. Real value 22 Figure 13: predicted and real values Since COVID-19 is a pandemic its predictions is difficult and it has volatile and mercurial pattern
  • 23. Root Mean Square Error (RMSE) 23 • RMSE is the root of the mean of the squared error. • It has same unit as Actual value. • Varied from 15.99 to 4000 Real Value Predicted Value 70,880 88,531.305 Table 1: Real and Predicted Value
  • 24. Conclusion • The proposed model perceived some pattern from the historical data points by remembering the relevant facts and forgetting the irrelevant features. • The deep learning requires huge amount of data to be trained so the model has large RMSE. • In order to remain safe, we should practice social distancing. 24
  • 25. Modules Used IDE: Anaconda Navigator Modules Used: 1. math 2. numpy 3. pandas 4. seaborn 5. keras, Sequential, Dense, LSTM 6. keras, Dropout, Activation, Flatten 7. Matplotlib 8. Sklearn 25
  • 26. References: [1] Sanche S, Lin YT, et al., “High contagiousness and rapid spread of severe acute respiratory syndrome coronavirus 2.”, Emerg Infect Dis. 2020 Jul. https://doi.org/10.3201/eid2607.200282 [2] Qiang Gao, Linlin Bao, et al., “Rapid development of an inactivated vaccine for SARS-CoV-2”, bioRxiv, 2020, https://doi.org/10.1101/2020.04.17.046375 [3] Jiayu Qiu, Bin Wang, et al., “Forecasting stock prices with long-short term memory neural network based on attention mechanism”, Jan 2020, PLOS ONE, https://doi.org/10.1371/journal.pone.0227222 [4] Dianbo Liu, Leonardo Clemente, et al., “A machine learning methodology for real- time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models”, arXiv.org stat, Apr 2020 [5] Ratnabali Pal, Arif A. Sekh, et al., “Neural Network based country wise risk prediction of COVID-19”, IEEE, Mar 2020 [6] Shawni Dutta, et al. , “Machine Learning Approach for Confirmation of COVID-19 Cases: Positive, Negative, Death and Release”, medRxiv, Mar 2020, https://doi.org/10.1101/2020.03.25.20043505 [7] Zifeng Yang, et al., “Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions”, Journal of Thoracic Disease, Mar 2020, doi: 10.21037/jtd.2020.02.64 26
  • 27. References: [8] Zhiyong Cui, et al., “Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction [9] Sima Siami, et al., “A comparative Analysis of Forecasting financial Time Series using ARIMA, LSTM, and BiLSTM [10]Sepp Hochreiter, Jürgen Schmidhuber et al., “LONG SHORT TERM MEMORY”, Neural Computation, 1997 [11]Ava Soleimany, Recurrent Neural Networks, MIT Introduction to Deep Learning, 2020, 6. S191: https://youtu.be/SEnXr6v2ifU [12]Lex Friedman, MIT 6.S094: Recurrent Neural Networks for Steering Through Time, 2017, https://youtu.be/nFTQ7kHQWtc [13] Fei-Fei Li, Justin Johnson & Serena Young, Stanford University, Convolutional Neural Networks for Visual Recognition, 2017, https://youtu.be/6niqTuYFZLQ?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv 27

Editor's Notes

  1. Influenza degree of spread (R0) is 1.3 [Uniform]