University of Jyväskylä | JYX Digital Repository

  • English  | Give feedback |
    • suomi
    • English
 
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
View Item 
  • JYX
  • Opinnäytteet
  • Väitöskirjat
  • View Item
JYX > Opinnäytteet > Väitöskirjat > View Item

Convolutional neural networks and stochastic modelling in hyperspectral data analysis

Thumbnail
View/Open
36. Mb

Downloads:  
Show download detailsHide download details  
Published in
JYU dissertations
Authors
Annala, Leevi
Date
2020

 
Hyperspectral imaging is relatively new and rapidly growing field of research. The datasets produced by hyperspectral imaging are large, and handling such data requires large computational resources. Therefore, there is a need for developing machine learning methods that can cope with the data, and methods to reduce the necessary amount of data gathering missions. For the latter, problem the author and his co-authors have developed stochastic modelling and generative adversarial neural networks for data augmentation. In machine learning, they have experimented with using convolutional neural network in conjunction with said stochastic model in order to retrieve useful information from hyperspectral data. Additionally, the author lists useful Python packages for hyperspectral data analysis. Keywords: Hyperspectral imaging, Convolutional neural network, Stochastic modelling, Biophysical parameter retrieval, Data augmentation
 
Hyperspektrikuvantaminen on kasvava ala. Hyperspektrikuvantaminen on resurssien ja datan määrän suhteen vaativaa, ja siksi on tarpeen kehittää koneoppimismenetelmiä, jotka pystyvät käsittelemään dataa, ja menetelmiä tarvittavan datan keräämisen vähentämiseksi. Viimeksi mainittua ongelmaa varten kirjoittaja ja hänen kanssakirjoittajansa ovat kehittäneet stokastista mallintamista ja generatiivisia kilpailevia neuroverkkoja datan määrän kasvattamiseksi mitatun datan rinnalla. Koneoppimisessa he ovat käyttäneet konvoluutioneuroverkkoa mainitun stokastisen mallin kanssa saadakseen hyödyllistä tietoa hyperperspektridatasta. Lisäksi työssä etsittiin ja ja testattiin hyödyllisiä Python-paketteja hyperspektridatan analysointiin. Avainsanat: Hyperspektrikuvantaminen, Konvoluutioneuroverkko, Stokastinen mallintaminen, biofysikaalisen parametrin palauttaminen, Datan lisääminen
 
ISBN
978-951-39-8453-3
Contains publications
  • Artikkeli I: Annala, L., Eskelinen, M., Hämäläinen, J., Riihinen, A., & Pölönen, I. (2018). Practical Approach for Hyperspectral Image Processing in Python. In J. Jiang, A. Shaker, H. Zhang, X. Liang, B. Osmanoglu, U. Soergel, . . . K. Komp (Eds.), ISPRS TC III Mid-term Symposium “Developments, Technologies and Applications in Remote Sensing” (pp. 45-52). International Society for Photogrammetry and Remote Sensing. DOI: 10.5194/isprs-archives-XLII-3-45-2018
  • Artikkeli II: Pölönen, I., Annala, L., Rahkonen, S., Nevalainen, O., Honkavaara, E., Tuominen, S., . . . , & Hakala, T. (2019). Tree Species Identification Using 3D Spectral Data and 3D Convolutional Neural Network. In WHISPERS 2018 : 9th Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing. IEEE. DOI: 10.1109/WHISPERS.2018.8747253
  • Artikkeli III: Pölönen, I., Rahkonen, S., Annala, L., & Neittaanmäki, N. (2019). Convolutional neural networks in skin cancer detection using spatial and spectral domain. In B. Choi, & H. Zeng (Eds.), Proceedings of SPIE Volume 10851 : Photonics in Dermatology and Plastic Surgery 2019 (pp. 108510B). SPIE, The International Society for Optical Engineering. DOI: 10.1117/12.2509871
  • Artikkeli IV: Annala, Leevi; Honkavaara, Eija; Tuominen, Sakari; Pölönen, Ilkka (2020). Chlorophyll Concentration Retrieval by Training Convolutional Neural Network for Stochastic Model of Leaf Optical Properties (SLOP) Inversion. Remote Sensing, 12 (2), 283. DOI: 10.3390/rs12020283
  • Artikkeli V: Annala, Leevi and Pölönen, Ilkka. (2020). Kubelka-Munk Model and Stochastic Model Comparison in Skin Physical Parameter Retrieval. Computational Sciences and Artificial Intelligence in Industry – New digital technologies for solving future societal and economical challenges. In press.
  • Artikkeli VI: Annala, Leevi; Äyrämö, Sami; Pölönen, Ilkka (2020). Comparison of Machine Learning Methods in Stochastic Skin Optical Model Inversion. Applied Sciences, 10 (20), 7097. DOI: 10.3390/app10207097
  • Artikkeli VII: Annala, Leevi; Neittaanmäki, Noora; Paoli, John; Zaar, Oscar; Pölönen, Ilkka (2020). Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network. In EMBC 2020 : Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 1600-1603. DOI: 10.1109/EMBC44109.2020.9176292
Keywords
spektrikuvaus kuvantaminen tiedonlouhinta koneoppiminen stokastiset prosessit neuroverkot hyperspectral imaging convolutional neural network stochastic modelling biophysical parameter retrieval data augmentation
URI

http://urn.fi/URN:ISBN:978-951-39-8453-3

Metadata
Show full item record
Collections
  • Väitöskirjat [3178]

Related items

Showing items with similar title or keywords.

  • Chlorophyll Concentration Retrieval by Training Convolutional Neural Network for Stochastic Model of Leaf Optical Properties (SLOP) Inversion 

    Annala, Leevi; Honkavaara, Eija; Tuominen, Sakari; Pölönen, Ilkka (MDPI AG, 2020)
    Miniaturized hyperspectral imaging techniques have developed rapidly in recent years and have become widely available for different applications. Combining calibrated hyperspectral imagery with inverse physically based ...
  • Using Aerial Platforms in Predicting Water Quality Parameters from Hyperspectral Imaging Data with Deep Neural Networks 

    Hakala, Taina; Pölönen, Ilkka; Honkavaara, Eija; Näsi, Roope; Hakala, Teemu; Lindfors, Antti (Springer, 2020)
    In near future it is assumable that automated unmanned aerial platforms are coming more common. There are visions that transportation of different goods would be done with large planes, which can handle over 1000 kg payloads. ...
  • Tree species classification of drone hyperspectral and RGB imagery with deep learning convolutional neural networks 

    Nezami, Somayeh; Khoramshahi, Ehsan; Nevalainen, Olli; Pölönen, Ilkka; Honkavaara, Eija (MDPI AG, 2020)
    Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include ...
  • Comparison of Machine Learning Methods in Stochastic Skin Optical Model Inversion 

    Annala, Leevi; Äyrämö, Sami; Pölönen, Ilkka (MDPI AG, 2020)
    In this study, we compare six different machine learning methods in the inversion of a stochastic model for light propagation in layered media, and use the inverse models to estimate four parameters of the skin from the ...
  • Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours : A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and Convolutional Neural Networks 

    Lindholm, Vivian; Raita-Hakola, Anna-Maria; Annala, Leevi; Salmivuori, Mari; Jeskanen, Leila; Saari, Heikki; Koskenmies, Sari; Pitkänen, Sari; Pölönen, Ilkka; Isoherranen, Kirsi; Ranki, Annamari (MDPI AG, 2022)
    Several optical imaging techniques have been developed to ease the burden of skin cancer disease on our health care system. Hyperspectral images can be used to identify biological tissues by their diffuse reflected spectra. ...
  • Browse materials
  • Browse materials
  • Articles
  • Conferences and seminars
  • Electronic books
  • Historical maps
  • Journals
  • Tunes and musical notes
  • Photographs
  • Presentations and posters
  • Publication series
  • Research reports
  • Research data
  • Study materials
  • Theses

Browse

All of JYXCollection listBy Issue DateAuthorsSubjectsPublished inDepartmentDiscipline

My Account

Login

Statistics

View Usage Statistics
  • How to publish in JYX?
  • Self-archiving
  • Publish Your Thesis Online
  • Publishing Your Dissertation
  • Publication services

Open Science at the JYU
 
Data Protection Description

Accessibility Statement

Unless otherwise specified, publicly available JYX metadata (excluding abstracts) may be freely reused under the CC0 waiver.
Open Science Centre