SlideShare uma empresa Scribd logo
1 de 21
Baixar para ler offline
The KEDRI Integrated System for
         Personalised Modelling:
                Software development
                and experiment results
        Prof. Nikola Kasabov     Dr. Raphael Hu       Gary Chen
   The Knowledge Engineering and Discovery Research Institute (KEDRI)
                    Auckland University of Technology

                             www.kedri.info



23/11/2011            nkasabov@aut.ac.nz; rhu@aut.ac.nz
Overview

• Introduction
• The development of new algorithms and
  methods for personalised modelling in KEDRI
• Software prototype demo
• Conclusion and future direction




 23/11/2011      nkasabov@aut.ac.nz; rhu@aut.ac.nz
KEDRI: The Knowledge Engineering and
      Discovery Research Institute at AUT
                        (www.kedri.info)


•    Established in 2002 by Prof. Nikola Kasabov
•    Focus: novel information processing methods,
     technologies and applications for discoveries across
     different areas of science
•    Methods are mainly based on personalised
     modelling, brain information processing, evolution,
     genetics and quantum physics;




23/11/2011          nkasabov@aut.ac.nz; rhu@aut.ac.nz
KEDRI




23/11/2011   nkasabov@aut.ac.nz; rhu@aut.ac.nz
Computational Modelling Techniques

Global, local and personalized modelling are three main approaches
for modelling and pattern discovery in machine learning area [1].


Global modelling creates a model from the data which covers the entire
problem space and is represented by a single function, e.g. a regression
function, a RBF, a MLP neural network, SVM, etc.


Local modelling builds a set of local models from data, each representing a
sub-space (e.g. a cluster) of the whole problem space. These models can
be a set of rules or a set of local regressions, etc.

Personalised modelling uses transductive reasoning to create a specific
model for each single data point (e.g. a data vector, a patient record) within
a localised problem space.


23/11/2011              nkasabov@aut.ac.nz; rhu@aut.ac.nz
Why Personalised Modelling?
•   The issue of using global modelling for prediction problems:
    a global model is derived from all available data for the target and then applied
    to any new patient anywhere at anytime. Prediction and treatment based on
    global models are only effective for some patients (approx 70%) [2].

•   Personalised Modelling:
    The rationale behind personalised modeling paradigm is: since each person is
    different, the most effective treatment could be only based on the detailed
    analysis for this particular patient.

•   The availability of utilising a variety of data:
    DNA, RNA, protein expression, inheritance, disease, etc.

•   The benefits of using personalised models for medical applications
     – To produce better results for classification and prediction
     – To create the profiling for individuals
     – To provide a potential improvement scenario for individuals, if it is possible




23/11/2011                  nkasabov@aut.ac.nz; rhu@aut.ac.nz
Research Objectives of Personalised Modelling

• To create accurate personalised computational models:
  the model is specific for an individual utilising the available information from
  other individuals related to the same problem.

• To develop new algorithms and methods for personalised modelling;

• To apply the above proposed algorithms and methods on the data
  from different sources:
  gene expression data, protein data, SNPs (single-nucleotide polymorphism)
  data, clinical data, etc;




 23/11/2011               nkasabov@aut.ac.nz; rhu@aut.ac.nz
The Integrated Method for Personalised
         Modelling (IMPM) for Data Analysis


                                                          Learning
                           Feature
                                                        models, e.g.        Outcome
                          selection
                                                      risk probability    visualisation
  Data                                                  evaluation,      (personalised
Repository                                                disease         profiling, risk
                   Similarity      Neighbour           classification,     probability)
                  measurement       creation                etc.




                                       Optimisation
                             (evolutionary computation, snn)



   The proposed framework and system using IMPM biomedical data analysis [2]


23/11/2011                      nkasabov@aut.ac.nz;
Optimisation
Coevolutionary algorithm (CEA):
CEA is derived from evolutionary algorithm. The individuals in CEA
are from two or more populations and their assigned fitness values
based on their interactions between different populations.




             A sample of a simple 2-species coevolutionary model.


23/11/2011                 nkasabov@aut.ac.nz; rhu@aut.ac.nz
Software Architecture of IMPM




               An example of software architecture of ISPM




23/11/2011              nkasabov@aut.ac.nz; rhu@aut.ac.nz
An Integrated Optimisation System for
      Personalised Modelling (IOSPM)

• Cross-platform – implemented by QT which is able to be
  compiled under different platforms, such as Microsoft
  Windows, Mac OS, and Linux.

• Integrated – combine methods/functions written in different
  languages (e.g. MATLAB, Python, JAVA and C/C++ etc).

• Extensible – new methods/functions can be easily plugged in by
  editing system schema to generate dynamic GUI interface.




23/11/2011
                         nkasabov@aut.ac.nz;
An overview of the IOSPM system
                  Main GUI
                                                                                         Spiking Neural Network
                   -<<UI>>
              +Select Data file()
         +Select Optimisation Method()
          +Select Modelling Method()
                                                                                             Lib SVM
         +Select Data pre-processing()



                                            I                                                K-Nearest Neighbor
                 Data Loading               N
                                            T
                                            E
                                            R                                            DENFIS
                                            F
              Data Pre-processing           A
                                            C
                                            E
                                                    PM Optimisation                      WKNN/W KN
                                                                                               W  N

                                            1




            Visualisation GUI                                                                           INNTERFACE 2
                  -<<UI>>
        +Select Visualisation Mode()
         +Create Results Report()                                                                        Data Report Generator



                                                            Visualisation Mode 1




                                                            Visualisation Mode 2




                                                            Visualisation Mode 3




                                        MATLAB
                                                                                    Python
             QT XML GUI                Executable        OpenGL                                            C++ Code
                                                                                   Package
                                        Package




23/11/2011                                 nkasabov@aut.ac.nz; rhu@aut.ac.nz
Implementation of ISPM
    An exemplar content of the modules is given below:

•    Module for Neighbourhood Creation:
     Euclidean distance method; Hamming distance method; Cosine distance
     method; Kernel distance methods; other methods.

•    Module for Classification/Prediction:
      – Classification methods, such as: MLR, MLP, ECF, wkNN, wwkNN, TWNFI,
        SVM, eSNN.
      – Probability prediction methods, such as: DENFIS, TWNFI.

•    Module for Optimisation:
     Evolutionary computatio (EC), quantum inspired evolutionary algorithm, particle
     swarm optimisation (PSO), quantum inspired PSO, other methods.

•    Module for Task Distribution Centre:
     This module will control the whole optimisation process, will communicate with
     the user, will visualise the results.


23/11/2011                   nkasabov@aut.ac.nz; rhu@aut.ac.nz
Global Modelling vs. Personalised Modelling

  Colon cancer gene expression data


 Model                  Overall accuracy Class 1          Class 2
 MLR (global)           72.58%               75.00%       68.18%
 RBF (global)           79.03%               90.00%       59.09%
 IMPM(personalised)     87.10%               90.00%       81.82%




23/11/2011            nkasabov@aut.ac.nz; rhu@aut.ac.nz
Personalised Modelling for Bioinformatics Research

                        An example: applying PM on gene expression data for colon
                                            cancer diagnosis
                                      Compact GA Evolution                                                                       Weighted importance of selected features
             600
                                                                                                                0.08




                                                                                          Weighted importance
                                                                                  0.8
             500
                                                                                  0.7
                                                                                                                0.06
                                                                                  0.6
             400
generation




                                                                                  0.5
             300                                                                  0.4                           0.04
                                                                                  0.3
             200
                                                                                  0.2                           0.02
                                                                                  0.1
             100
                                                                                  0
                                                                                                                  0
                                                                                                                       3771285
                                                                                                                             1892419 8121843
                                                                                                                                           15743501991513 5611863814 8091069395 462 348
                       20    40         60        80        100     120    140
                                  each bit represents one feature                                                                               Index of genes


                   (a) The evolution of feature selection for                                                    (b) The weighted importance of the selected
                   sample #32 using 600 generations of GA                                                        features for sample #32 after one run of the
                   optimisation;                                                                                 method;


                                       Results from a simple experiment on colon cancer gene expression data



                   23/11/2011                                             nkasabov@aut.ac.nz; rhu@aut.ac.nz
Blue (Circle points) - actual value of this gene
                                  Visualizing the results of PFS with 3 features                                                      Green Upward Triangle -Healthy Red Downward Triangle-Diseased
                                 Blue (Circle points) - actual value of this gene
                                                                                                                           1400
                        Green Upward Triangle -Healthy; Red Downward Triangle-Diseased




                                                                                                   Gene Expression Level
                                                                                                                           1200

                                                                                                                           1000
            0.8
                                                                                                                           800
            0.6
    f1892




                                                                                                                           600
            0.4

            0.2                                                                                                            400

                                                                                                                           200
                  0.2                                                                    0.8
                           0.4                                                 0.6
                                 0.6                                  0.4                                                    0
                                        0.8                 0.2                                                                      377 12851892 419 812 18431574 350 1991 513 561 1863 814 809 1069 395 462 348
                                                1
                                                                    f1285                                                                                    Index of Selected Genes
                                    f377
                  15                                                                                                         1
                                                                                                                                          Colon cancer data - area under Curve: 0.87727

                                                                                                                           0.9

                                                                                                                           0.8




                                                                                               Classification Accuracy
                  10                                                                                                       0.7

                                                                                                                           0.6

                                                                                                                           0.5

                                                                                                                           0.4
                  5                                                                                                                                       ROC Curve
                                                                                                                           0.3                            Overall Accuracy
                                                                                                                                                          Class 1 Accuracy
                                                                                                                           0.2                            Class 2 Accuracy

                                                                                                                           0.1
                  0
                        419 377 1423 132 105818921982 350 79110601495 49 824 892129618631924                                 0
                                                                                                                                 0               0.2              0.4              0.6              0.8             1
                                                                                                                                                                     Threshold

(c) Sample 32 (a blue dot) is plotted with its neighbouring samples (red triangles represent cancer samples and green
triangles - control) in the 3D space of the top 3 gene variables from (b);
(d) The profile of sample #32 (blue dots) versus the average local profile of the control (green) and cancer (red triangles)
using the features from (b)
(e) The 17 most frequently selected features for all samples - the method is run 20 times for each sample;
(f)The accuracy of personalised diagnosis across all 60 samples when the 17 markers from (e) are used in a leave-one-
out cross validation; in case of ROC curve x axis represents false positive rate (1-specificity), while y axis is true
positive rate (sensitivity); the area under curve is 0.87727 and the overall accuracy - 87.10%;

             23/11/2011                                                     nkasabov@aut.ac.nz; rhu@aut.ac.nz
Personalised Modelling (PM) for CVD Diagnosis and
                     Risk Prognosis
This study aims at personalised modelling for cardiovascular diseases
(CVD) diagnosis.

                                           The dependency of classification accuracy on number of neighbors
                                 0.9
                                                                                              overallAcc
                                                                                              class 1 acc
                                0.85                                                          class 2 acc
      Classification accuracy




                                 0.8



                                0.75



                                 0.7



                                0.65
                                       5        10           15           20             25         30        35
                                                                  Num of neighbors (k)

            The PM method optimises automatically the number of the neighbouring samples K,
            which can be unique for every input sample or chosen as an optimal for all.



 23/11/2011                                                 nkasabov@aut.ac.nz; rhu@aut.ac.nz
Software Demo




23/11/2011   nkasabov@aut.ac.nz; rhu@aut.ac.nz
Conclusion
•   The proposed IMPM has a major advantage: the modelling process
    starts with all relevant variables available for a person, rather than with
    a fixed set of variables required by a global model.
•   The proposed IMPM leads to a better prognostic accuracy and a
    computed personalised profile;
•   With global optimisation using IMPM, a small set of variables (potential
    markers) can be identified from the selected variable set across the
    whole population
•   The proposed algorithms and models of IMPM are generic which can
    be potentially incorporated into a variety of applications for data
    analysis and knowledge discovery with certain constraints, such as
    financial risk analysis, time series data prediction, etc
•   We hope that this study will motivate the applications of personalised
    modelling research in different research areas.




23/11/2011                 nkasabov@aut.ac.nz; rhu@aut.ac.nz
Reference List:

1.    Kasabov, N.: Global, local and personalized modelling and pattern discovery in
     bioinformatics: An integrated approach. Pattern Recognition Letters 28(6) (2007) 673–685.
2.   Amnon Shabo. Health record banks: integrating clinical and genomic data into patientcentric
     longitudinal and cross-institutional health records. Personalised Medicine, 4(4):453–455,
     2007.
3.   Kasabov, N and Hu, Y (2011) Integrated optimisation method for personalised modelling
     and case study applications, Int. J. Functional Informatics and Personalised Medicine, vol. 3,
     no.3, pp. 236-256, 2010.




23/11/2011                        nkasabov@aut.ac.nz; rhu@aut.ac.nz
Questions?




23/11/2011   nkasabov@aut.ac.nz; rhu@aut.ac.nz

Mais conteúdo relacionado

Semelhante a The KEDRI Integrated System for Personalised Modelling

Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...
Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...
Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...IJCSIS Research Publications
 
Deep Learning in Text Recognition and Text Detection : A Review
Deep Learning in Text Recognition and Text Detection : A ReviewDeep Learning in Text Recognition and Text Detection : A Review
Deep Learning in Text Recognition and Text Detection : A ReviewIRJET Journal
 
Distributed Database practicals
Distributed Database practicals Distributed Database practicals
Distributed Database practicals Vrushali Lanjewar
 
Aplications for machine learning in IoT
Aplications for machine learning in IoTAplications for machine learning in IoT
Aplications for machine learning in IoTYashesh Shroff
 
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...CSCJournals
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learningpratik pratyay
 
Real-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for SurveillanceReal-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for SurveillanceIRJET Journal
 
Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Vidyut Singhania
 
Presentation1.2.pptx
Presentation1.2.pptxPresentation1.2.pptx
Presentation1.2.pptxpranaykusuma
 
MICE: Monitoring and modelIng of Context Evolution
MICE: Monitoring and modelIng of Context EvolutionMICE: Monitoring and modelIng of Context Evolution
MICE: Monitoring and modelIng of Context EvolutionLuca Berardinelli
 
A hybrid approach for face recognition using a convolutional neural network c...
A hybrid approach for face recognition using a convolutional neural network c...A hybrid approach for face recognition using a convolutional neural network c...
A hybrid approach for face recognition using a convolutional neural network c...IAESIJAI
 
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...IJERD Editor
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET Journal
 
Software effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN networkSoftware effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN networkIOSR Journals
 
Massif cluster meeting
Massif cluster meetingMassif cluster meeting
Massif cluster meetingfcleary
 
I/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue SimulationI/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue Simulationinside-BigData.com
 
SVM-KNN Hybrid Method for MR Image
SVM-KNN Hybrid Method for MR ImageSVM-KNN Hybrid Method for MR Image
SVM-KNN Hybrid Method for MR ImageIRJET Journal
 

Semelhante a The KEDRI Integrated System for Personalised Modelling (20)

Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...
Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...
Using K-Nearest Neighbors and Support Vector Machine Classifiers in Personal ...
 
Deep Learning in Text Recognition and Text Detection : A Review
Deep Learning in Text Recognition and Text Detection : A ReviewDeep Learning in Text Recognition and Text Detection : A Review
Deep Learning in Text Recognition and Text Detection : A Review
 
Distributed Database practicals
Distributed Database practicals Distributed Database practicals
Distributed Database practicals
 
Aplications for machine learning in IoT
Aplications for machine learning in IoTAplications for machine learning in IoT
Aplications for machine learning in IoT
 
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
Semantic Concept Detection in Video Using Hybrid Model of CNN and SVM Classif...
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learning
 
36575
3657536575
36575
 
slide-171212080528.pptx
slide-171212080528.pptxslide-171212080528.pptx
slide-171212080528.pptx
 
Real-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for SurveillanceReal-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for Surveillance
 
Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Final Report on Optical Character Recognition
Final Report on Optical Character Recognition
 
Presentation1.2.pptx
Presentation1.2.pptxPresentation1.2.pptx
Presentation1.2.pptx
 
Sensor Data Management
Sensor Data ManagementSensor Data Management
Sensor Data Management
 
MICE: Monitoring and modelIng of Context Evolution
MICE: Monitoring and modelIng of Context EvolutionMICE: Monitoring and modelIng of Context Evolution
MICE: Monitoring and modelIng of Context Evolution
 
A hybrid approach for face recognition using a convolutional neural network c...
A hybrid approach for face recognition using a convolutional neural network c...A hybrid approach for face recognition using a convolutional neural network c...
A hybrid approach for face recognition using a convolutional neural network c...
 
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
IJERD (www.ijerd.com) International Journal of Engineering Research and Devel...
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
 
Software effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN networkSoftware effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN network
 
Massif cluster meeting
Massif cluster meetingMassif cluster meeting
Massif cluster meeting
 
I/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue SimulationI/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue Simulation
 
SVM-KNN Hybrid Method for MR Image
SVM-KNN Hybrid Method for MR ImageSVM-KNN Hybrid Method for MR Image
SVM-KNN Hybrid Method for MR Image
 

Mais de Health Informatics New Zealand

The Austin Health Diabetes Discovery Initiative: Using technology to support ...
The Austin Health Diabetes Discovery Initiative: Using technology to support ...The Austin Health Diabetes Discovery Initiative: Using technology to support ...
The Austin Health Diabetes Discovery Initiative: Using technology to support ...Health Informatics New Zealand
 
Shaping Informatics for Allied Health - Refining our voice
Shaping Informatics for Allied Health - Refining our voiceShaping Informatics for Allied Health - Refining our voice
Shaping Informatics for Allied Health - Refining our voiceHealth Informatics New Zealand
 
Laptop computers enhancing clinical care in community allied health service
Laptop computers enhancing clinical care in community allied health serviceLaptop computers enhancing clinical care in community allied health service
Laptop computers enhancing clinical care in community allied health serviceHealth Informatics New Zealand
 
Safe IT Practices: making it easy to do the right thing
Safe IT Practices: making it easy to do the right thingSafe IT Practices: making it easy to do the right thing
Safe IT Practices: making it easy to do the right thingHealth Informatics New Zealand
 
Reducing hospitalisations and arrests of mental health patients through the u...
Reducing hospitalisations and arrests of mental health patients through the u...Reducing hospitalisations and arrests of mental health patients through the u...
Reducing hospitalisations and arrests of mental health patients through the u...Health Informatics New Zealand
 
Using the EMR in early recognition and management of sepsis
Using the EMR in early recognition and management of sepsisUsing the EMR in early recognition and management of sepsis
Using the EMR in early recognition and management of sepsisHealth Informatics New Zealand
 
Allied Health and informatics: Identifying our voice - can you hear us?
Allied Health and informatics: Identifying our voice - can you hear us?Allied Health and informatics: Identifying our voice - can you hear us?
Allied Health and informatics: Identifying our voice - can you hear us?Health Informatics New Zealand
 
Change in the data collection landscape: opportunity, possibilities and poten...
Change in the data collection landscape: opportunity, possibilities and poten...Change in the data collection landscape: opportunity, possibilities and poten...
Change in the data collection landscape: opportunity, possibilities and poten...Health Informatics New Zealand
 
Overview of the New Zealand Maternity Clinical Information System
Overview of the New Zealand Maternity Clinical Information SystemOverview of the New Zealand Maternity Clinical Information System
Overview of the New Zealand Maternity Clinical Information SystemHealth Informatics New Zealand
 
Electronic prescribing system medication errors: Identification, classificati...
Electronic prescribing system medication errors: Identification, classificati...Electronic prescribing system medication errors: Identification, classificati...
Electronic prescribing system medication errors: Identification, classificati...Health Informatics New Zealand
 
Global trends in technology for retailers and how they are impacting the phar...
Global trends in technology for retailers and how they are impacting the phar...Global trends in technology for retailers and how they are impacting the phar...
Global trends in technology for retailers and how they are impacting the phar...Health Informatics New Zealand
 
"Not flying under the radar": Developing an App for Patient-led Management of...
"Not flying under the radar": Developing an App for Patient-led Management of..."Not flying under the radar": Developing an App for Patient-led Management of...
"Not flying under the radar": Developing an App for Patient-led Management of...Health Informatics New Zealand
 
The quantified self: Does personalised monitoring change everything?
The quantified self: Does personalised monitoring change everything?The quantified self: Does personalised monitoring change everything?
The quantified self: Does personalised monitoring change everything?Health Informatics New Zealand
 

Mais de Health Informatics New Zealand (20)

The Austin Health Diabetes Discovery Initiative: Using technology to support ...
The Austin Health Diabetes Discovery Initiative: Using technology to support ...The Austin Health Diabetes Discovery Initiative: Using technology to support ...
The Austin Health Diabetes Discovery Initiative: Using technology to support ...
 
Shaping Informatics for Allied Health - Refining our voice
Shaping Informatics for Allied Health - Refining our voiceShaping Informatics for Allied Health - Refining our voice
Shaping Informatics for Allied Health - Refining our voice
 
Surveillance of social media: Big data analytics
Surveillance of social media: Big data analyticsSurveillance of social media: Big data analytics
Surveillance of social media: Big data analytics
 
The Power of Surface Modelling
The Power of Surface ModellingThe Power of Surface Modelling
The Power of Surface Modelling
 
Laptop computers enhancing clinical care in community allied health service
Laptop computers enhancing clinical care in community allied health serviceLaptop computers enhancing clinical care in community allied health service
Laptop computers enhancing clinical care in community allied health service
 
Making surgical practice improvement easy
Making surgical practice improvement easyMaking surgical practice improvement easy
Making surgical practice improvement easy
 
Safe IT Practices: making it easy to do the right thing
Safe IT Practices: making it easy to do the right thingSafe IT Practices: making it easy to do the right thing
Safe IT Practices: making it easy to do the right thing
 
Beyond EMR - so you've got an EMR - what next?
Beyond EMR - so you've got an EMR - what next?Beyond EMR - so you've got an EMR - what next?
Beyond EMR - so you've got an EMR - what next?
 
Empowered Health
Empowered HealthEmpowered Health
Empowered Health
 
Reducing hospitalisations and arrests of mental health patients through the u...
Reducing hospitalisations and arrests of mental health patients through the u...Reducing hospitalisations and arrests of mental health patients through the u...
Reducing hospitalisations and arrests of mental health patients through the u...
 
Using the EMR in early recognition and management of sepsis
Using the EMR in early recognition and management of sepsisUsing the EMR in early recognition and management of sepsis
Using the EMR in early recognition and management of sepsis
 
Allied Health and informatics: Identifying our voice - can you hear us?
Allied Health and informatics: Identifying our voice - can you hear us?Allied Health and informatics: Identifying our voice - can you hear us?
Allied Health and informatics: Identifying our voice - can you hear us?
 
Change in the data collection landscape: opportunity, possibilities and poten...
Change in the data collection landscape: opportunity, possibilities and poten...Change in the data collection landscape: opportunity, possibilities and poten...
Change in the data collection landscape: opportunity, possibilities and poten...
 
Overview of the New Zealand Maternity Clinical Information System
Overview of the New Zealand Maternity Clinical Information SystemOverview of the New Zealand Maternity Clinical Information System
Overview of the New Zealand Maternity Clinical Information System
 
Nhitb wednesday 9am plenary (sadhana first)
Nhitb wednesday 9am plenary (sadhana first)Nhitb wednesday 9am plenary (sadhana first)
Nhitb wednesday 9am plenary (sadhana first)
 
Oncology treatment patterns in the South Island
Oncology treatment patterns in the South IslandOncology treatment patterns in the South Island
Oncology treatment patterns in the South Island
 
Electronic prescribing system medication errors: Identification, classificati...
Electronic prescribing system medication errors: Identification, classificati...Electronic prescribing system medication errors: Identification, classificati...
Electronic prescribing system medication errors: Identification, classificati...
 
Global trends in technology for retailers and how they are impacting the phar...
Global trends in technology for retailers and how they are impacting the phar...Global trends in technology for retailers and how they are impacting the phar...
Global trends in technology for retailers and how they are impacting the phar...
 
"Not flying under the radar": Developing an App for Patient-led Management of...
"Not flying under the radar": Developing an App for Patient-led Management of..."Not flying under the radar": Developing an App for Patient-led Management of...
"Not flying under the radar": Developing an App for Patient-led Management of...
 
The quantified self: Does personalised monitoring change everything?
The quantified self: Does personalised monitoring change everything?The quantified self: Does personalised monitoring change everything?
The quantified self: Does personalised monitoring change everything?
 

Último

VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋TANUJA PANDEY
 
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...chandars293
 
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...chandars293
 
All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...Arohi Goyal
 
Bangalore Call Girls Nelamangala Number 9332606886 Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 9332606886  Meetin With Bangalore Esc...Bangalore Call Girls Nelamangala Number 9332606886  Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 9332606886 Meetin With Bangalore Esc...narwatsonia7
 
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...
♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...
♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...astropune
 
Call Girls Haridwar Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Haridwar Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Haridwar Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Haridwar Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Call Girls Bareilly Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bareilly Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bareilly Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bareilly Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...tanya dube
 
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...parulsinha
 
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...Dipal Arora
 
(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...
(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...
(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...indiancallgirl4rent
 
Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...Dipal Arora
 
Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...Dipal Arora
 
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 

Último (20)

VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
VIP Hyderabad Call Girls Bahadurpally 7877925207 ₹5000 To 25K With AC Room 💚😋
 
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
The Most Attractive Hyderabad Call Girls Kothapet 𖠋 6297143586 𖠋 Will You Mis...
 
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...Top Rated  Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
Top Rated Hyderabad Call Girls Erragadda ⟟ 6297143586 ⟟ Call Me For Genuine ...
 
All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...
All Time Service Available Call Girls Marine Drive 📳 9820252231 For 18+ VIP C...
 
Bangalore Call Girls Nelamangala Number 9332606886 Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 9332606886  Meetin With Bangalore Esc...Bangalore Call Girls Nelamangala Number 9332606886  Meetin With Bangalore Esc...
Bangalore Call Girls Nelamangala Number 9332606886 Meetin With Bangalore Esc...
 
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bangalore Just Call 9907093804 Top Class Call Girl Service Available
 
♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...
♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...
♛VVIP Hyderabad Call Girls Chintalkunta🖕7001035870🖕Riya Kappor Top Call Girl ...
 
Call Girls Haridwar Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Haridwar Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Haridwar Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Haridwar Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Siliguri Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Dehradun Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Gwalior Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Tirupati Just Call 9907093804 Top Class Call Girl Service Available
 
Call Girls Bareilly Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bareilly Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Bareilly Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Bareilly Just Call 9907093804 Top Class Call Girl Service Available
 
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
 
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
(Low Rate RASHMI ) Rate Of Call Girls Jaipur ❣ 8445551418 ❣ Elite Models & Ce...
 
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
 
(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...
(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...
(Rocky) Jaipur Call Girl - 09521753030 Escorts Service 50% Off with Cash ON D...
 
Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...
Best Rate (Guwahati ) Call Girls Guwahati ⟟ 8617370543 ⟟ High Class Call Girl...
 
Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Bhubaneswar Just Call 9907093804 Top Class Call Girl Service Avail...
 
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Kochi Just Call 9907093804 Top Class Call Girl Service Available
 

The KEDRI Integrated System for Personalised Modelling

  • 1. The KEDRI Integrated System for Personalised Modelling: Software development and experiment results Prof. Nikola Kasabov Dr. Raphael Hu Gary Chen The Knowledge Engineering and Discovery Research Institute (KEDRI) Auckland University of Technology www.kedri.info 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 2. Overview • Introduction • The development of new algorithms and methods for personalised modelling in KEDRI • Software prototype demo • Conclusion and future direction 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 3. KEDRI: The Knowledge Engineering and Discovery Research Institute at AUT (www.kedri.info) • Established in 2002 by Prof. Nikola Kasabov • Focus: novel information processing methods, technologies and applications for discoveries across different areas of science • Methods are mainly based on personalised modelling, brain information processing, evolution, genetics and quantum physics; 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 4. KEDRI 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 5. Computational Modelling Techniques Global, local and personalized modelling are three main approaches for modelling and pattern discovery in machine learning area [1]. Global modelling creates a model from the data which covers the entire problem space and is represented by a single function, e.g. a regression function, a RBF, a MLP neural network, SVM, etc. Local modelling builds a set of local models from data, each representing a sub-space (e.g. a cluster) of the whole problem space. These models can be a set of rules or a set of local regressions, etc. Personalised modelling uses transductive reasoning to create a specific model for each single data point (e.g. a data vector, a patient record) within a localised problem space. 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 6. Why Personalised Modelling? • The issue of using global modelling for prediction problems: a global model is derived from all available data for the target and then applied to any new patient anywhere at anytime. Prediction and treatment based on global models are only effective for some patients (approx 70%) [2]. • Personalised Modelling: The rationale behind personalised modeling paradigm is: since each person is different, the most effective treatment could be only based on the detailed analysis for this particular patient. • The availability of utilising a variety of data: DNA, RNA, protein expression, inheritance, disease, etc. • The benefits of using personalised models for medical applications – To produce better results for classification and prediction – To create the profiling for individuals – To provide a potential improvement scenario for individuals, if it is possible 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 7. Research Objectives of Personalised Modelling • To create accurate personalised computational models: the model is specific for an individual utilising the available information from other individuals related to the same problem. • To develop new algorithms and methods for personalised modelling; • To apply the above proposed algorithms and methods on the data from different sources: gene expression data, protein data, SNPs (single-nucleotide polymorphism) data, clinical data, etc; 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 8. The Integrated Method for Personalised Modelling (IMPM) for Data Analysis Learning Feature models, e.g. Outcome selection risk probability visualisation Data evaluation, (personalised Repository disease profiling, risk Similarity Neighbour classification, probability) measurement creation etc. Optimisation (evolutionary computation, snn) The proposed framework and system using IMPM biomedical data analysis [2] 23/11/2011 nkasabov@aut.ac.nz;
  • 9. Optimisation Coevolutionary algorithm (CEA): CEA is derived from evolutionary algorithm. The individuals in CEA are from two or more populations and their assigned fitness values based on their interactions between different populations. A sample of a simple 2-species coevolutionary model. 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 10. Software Architecture of IMPM An example of software architecture of ISPM 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 11. An Integrated Optimisation System for Personalised Modelling (IOSPM) • Cross-platform – implemented by QT which is able to be compiled under different platforms, such as Microsoft Windows, Mac OS, and Linux. • Integrated – combine methods/functions written in different languages (e.g. MATLAB, Python, JAVA and C/C++ etc). • Extensible – new methods/functions can be easily plugged in by editing system schema to generate dynamic GUI interface. 23/11/2011 nkasabov@aut.ac.nz;
  • 12. An overview of the IOSPM system Main GUI Spiking Neural Network -<<UI>> +Select Data file() +Select Optimisation Method() +Select Modelling Method() Lib SVM +Select Data pre-processing() I K-Nearest Neighbor Data Loading N T E R DENFIS F Data Pre-processing A C E PM Optimisation WKNN/W KN W N 1 Visualisation GUI INNTERFACE 2 -<<UI>> +Select Visualisation Mode() +Create Results Report() Data Report Generator Visualisation Mode 1 Visualisation Mode 2 Visualisation Mode 3 MATLAB Python QT XML GUI Executable OpenGL C++ Code Package Package 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 13. Implementation of ISPM An exemplar content of the modules is given below: • Module for Neighbourhood Creation: Euclidean distance method; Hamming distance method; Cosine distance method; Kernel distance methods; other methods. • Module for Classification/Prediction: – Classification methods, such as: MLR, MLP, ECF, wkNN, wwkNN, TWNFI, SVM, eSNN. – Probability prediction methods, such as: DENFIS, TWNFI. • Module for Optimisation: Evolutionary computatio (EC), quantum inspired evolutionary algorithm, particle swarm optimisation (PSO), quantum inspired PSO, other methods. • Module for Task Distribution Centre: This module will control the whole optimisation process, will communicate with the user, will visualise the results. 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 14. Global Modelling vs. Personalised Modelling Colon cancer gene expression data Model Overall accuracy Class 1 Class 2 MLR (global) 72.58% 75.00% 68.18% RBF (global) 79.03% 90.00% 59.09% IMPM(personalised) 87.10% 90.00% 81.82% 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 15. Personalised Modelling for Bioinformatics Research An example: applying PM on gene expression data for colon cancer diagnosis Compact GA Evolution Weighted importance of selected features 600 0.08 Weighted importance 0.8 500 0.7 0.06 0.6 400 generation 0.5 300 0.4 0.04 0.3 200 0.2 0.02 0.1 100 0 0 3771285 1892419 8121843 15743501991513 5611863814 8091069395 462 348 20 40 60 80 100 120 140 each bit represents one feature Index of genes (a) The evolution of feature selection for (b) The weighted importance of the selected sample #32 using 600 generations of GA features for sample #32 after one run of the optimisation; method; Results from a simple experiment on colon cancer gene expression data 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 16. Blue (Circle points) - actual value of this gene Visualizing the results of PFS with 3 features Green Upward Triangle -Healthy Red Downward Triangle-Diseased Blue (Circle points) - actual value of this gene 1400 Green Upward Triangle -Healthy; Red Downward Triangle-Diseased Gene Expression Level 1200 1000 0.8 800 0.6 f1892 600 0.4 0.2 400 200 0.2 0.8 0.4 0.6 0.6 0.4 0 0.8 0.2 377 12851892 419 812 18431574 350 1991 513 561 1863 814 809 1069 395 462 348 1 f1285 Index of Selected Genes f377 15 1 Colon cancer data - area under Curve: 0.87727 0.9 0.8 Classification Accuracy 10 0.7 0.6 0.5 0.4 5 ROC Curve 0.3 Overall Accuracy Class 1 Accuracy 0.2 Class 2 Accuracy 0.1 0 419 377 1423 132 105818921982 350 79110601495 49 824 892129618631924 0 0 0.2 0.4 0.6 0.8 1 Threshold (c) Sample 32 (a blue dot) is plotted with its neighbouring samples (red triangles represent cancer samples and green triangles - control) in the 3D space of the top 3 gene variables from (b); (d) The profile of sample #32 (blue dots) versus the average local profile of the control (green) and cancer (red triangles) using the features from (b) (e) The 17 most frequently selected features for all samples - the method is run 20 times for each sample; (f)The accuracy of personalised diagnosis across all 60 samples when the 17 markers from (e) are used in a leave-one- out cross validation; in case of ROC curve x axis represents false positive rate (1-specificity), while y axis is true positive rate (sensitivity); the area under curve is 0.87727 and the overall accuracy - 87.10%; 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 17. Personalised Modelling (PM) for CVD Diagnosis and Risk Prognosis This study aims at personalised modelling for cardiovascular diseases (CVD) diagnosis. The dependency of classification accuracy on number of neighbors 0.9 overallAcc class 1 acc 0.85 class 2 acc Classification accuracy 0.8 0.75 0.7 0.65 5 10 15 20 25 30 35 Num of neighbors (k) The PM method optimises automatically the number of the neighbouring samples K, which can be unique for every input sample or chosen as an optimal for all. 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 18. Software Demo 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 19. Conclusion • The proposed IMPM has a major advantage: the modelling process starts with all relevant variables available for a person, rather than with a fixed set of variables required by a global model. • The proposed IMPM leads to a better prognostic accuracy and a computed personalised profile; • With global optimisation using IMPM, a small set of variables (potential markers) can be identified from the selected variable set across the whole population • The proposed algorithms and models of IMPM are generic which can be potentially incorporated into a variety of applications for data analysis and knowledge discovery with certain constraints, such as financial risk analysis, time series data prediction, etc • We hope that this study will motivate the applications of personalised modelling research in different research areas. 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 20. Reference List: 1. Kasabov, N.: Global, local and personalized modelling and pattern discovery in bioinformatics: An integrated approach. Pattern Recognition Letters 28(6) (2007) 673–685. 2. Amnon Shabo. Health record banks: integrating clinical and genomic data into patientcentric longitudinal and cross-institutional health records. Personalised Medicine, 4(4):453–455, 2007. 3. Kasabov, N and Hu, Y (2011) Integrated optimisation method for personalised modelling and case study applications, Int. J. Functional Informatics and Personalised Medicine, vol. 3, no.3, pp. 236-256, 2010. 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz
  • 21. Questions? 23/11/2011 nkasabov@aut.ac.nz; rhu@aut.ac.nz