Now showing items 21-40 of 51

    • Housing unit price prediction system 

      Eronen, Juuso (2018-11-07)
      The objective of this thesis was to compare different regression methods for predicting the price of housing unit, to design and develop a price estimation software and to determine which features are most important when ...
    • Improvements for Projection-based Point Cloud Compression 

      Sheikhi pour, Nahid (2018-12-05)
      Point clouds for immersive media technology have received substantial interest in recent years. Such representation of three-dimensional (3D) scenery provides freedom of movement for the viewer. However, transmitting and/or ...
    • Kasvojen etsintä kuva-aineistosta 

      Tommola, Janne (2018-08-15)
      Tässä työssä tarkastellaan erilaisia koneoppimisen menetelmiä kasvojen etsintään kuva-aineistosta. Työn tavoitteena on saada käsitys alan menetelmistä ja kehityksestä tällä vuosituhannella. Työssä vertailtiin ensimmäisiä ...
    • Kielen tunnistus koneoppimismenetelmillä 

      Koskimies, Aino (2018-01-10)
      Koneoppimismenetelmien avulla aineistosta voidaan irrottaa piirteitä ja luokitella se eri luokkiin näiden piirteiden perusteella. Erilaisia piirteenirrotus- ja luokittelumenetelmiä hyödyntämällä on mahdollista esimerkiksi ...
    • Kuusentaimen automaattinen tunnistus kamerasovelluksena 

      Usenius, Olli (2017-06-07)
      Yksi nuorenmetsänhoidon koneellistamisen haasteista on koneiden työtehokkuus ja tuntikustannus verrattuna metsurin tekemään raivaussahatyöhön. Koneiden työtehon parantamiseksi vastuuta työskentelystä voisi tulevaisuudessa ...
    • Lens Array Based Techniques for 3D Scene Capture and Display 

      Akpinar, Ugur (2017-10-04)
      This thesis discusses the use of lens arrays for both capture and display of 3D visual scenes while utilizing the ray optics formalism for modeling the propagation of light. In 3D capture, the use of lens arrays brings the ...
    • Lifestyle Analysis Using Digital footprints 

      Das, Soumya (2018-10-03)
      Digital Revolution has changed how the world used to function. Using digital devices and se sors every activity we do in our daily life can be tracked and can be stored as data. This thesis work aims to search how digital ...
    • Low Latency High-definition Video Streaming for Real-time Teleoperation Platform 

      Laine, Joona (2017-06-07)
      Teleoperation is the remote controlling of machines using a real-time video stream to support the controlling decisions. The key components of a teleoperation system are video streaming through a network to enable the ...
    • Microsoft HoloLens yhdistetyn todellisuuden välineenä 

      Mansikka, Mikael (2018-08-15)
      Yhdistetty todellisuus on digitaalisen datan ja reaalimaailman yhdistämistä toisiinsa. Yhdistetyn todellisuuden ominaispiirre on saada digitaalinen data reagoimaan reaalimaailman kanssa. Yhdistetyn todellisuuden havainnointiin ...
    • Multilingual Sentiment Analysis as Product Reputation Insight 

      Mushtaq, Muhammad Adnan (2018-01-10)
      A vast amount of textual data is continually being generated every day and available across the internet. By utilizing this ‘big data’ we can deduct meaningful information from its contents. One of the major tasks of Natural ...
    • Natural Language Syntactic Parsing with Neural Networks 

      Pasanen, Jaakko (2017-12-07)
      Conversational user interfaces have made strong appearance during the last couple of years. Most growth with conversational UIs can be seen with customer service moving from phone to chat. As big as the hype surrounding ...
    • Neuroverkkokiihdytystä käyttävän konenäkösovelluksen toteutus 

      Yrjänäinen, Jukka (2019-02-15)
      Tässä työssä tarkastellaan syviä neuroverkkoja käyttävän konenäkösovelluksen toteuttamista. Tutkimuksen käytettiin Raspberry Pi pienoistietokone ympäristöä, johon on liitetty neuroverkkolaskentaa nopeuttava erillinen laite: ...
    • Object Recognition for Maritime Application Using Deep Neural Networks 

      Hakala, Jarmo (2018-11-07)
      The aim of this thesis was to study object recognition with the state of the art methods in order to evaluate their potential for the sector of autonomous maritime logistics. In autonomous maritime transportation, object ...
    • Object Tracking in Video Sequences 

      Rintala, Sebastian (2017-05-03)
      Tässä diplomityössä vertaillaan konenäössä käytettyjen SIFT-, SURF- ja ORB-algoritmia objektin seurannassa. Tutkimuksen tavoitteena on tarkastella algoritmien soveltuvuutta erityyppisille videoille ja erilaisiin ...
    • Physical size of microphone arrays in ad-hoc beamforming 

      Tinakari, Aki (2017-12-07)
      Microphone arrays can be used to record an event, for example speech during a meeting in meeting room setting. Besides the wanted signal, the speech, these audio recordings also have noise in them that is caused by various ...
    • Prediction and detection of abnormal usage of an elevator 

      Hayati, Saboktakin (2019-01-09)
      In this thesis we used machine learning to detect the anomalous use of elevators by measuring the behavior at any specific time. We examined the data for unusual patterns in comparison with observed samples from the history ...
    • Predictive model for breast cancer sub-stage classification 

      Azam, MD. Facihul (2017-06-07)
      Prediction accuracy of sub-stage classification varies with different staging methods of breast-cancer. In this Master’s thesis we investigate whether there are differences in the performance of machine learning models ...
    • Real-time Target Tracking and Following with UR5 Collaborative Robot Arm 

      Teke, Burak (2018-06-06)
      The rise of the camera usage and their availability give opportunities for developing robotics applications and computer vision applications. Especially, recent development in depth sensing (e.g., Microsoft Kinect) allows ...
    • Recurrent Neural Networks for Modeling Motion Capture Data 

      Mir Abdul Rasool Khan, Mir A. (2017-06-07)
      This thesis introduces a Recurrent Neural Network (RNN) framework as a generative model for synthesizing human motion capture data. The skeleton model of the data used is a complex human skeleton model with 64 joints, ...
    • Recurrent neural networks for multi-microphone speech separation 

      Nandakumar, Shriram (2018-01-10)
      This thesis takes the classical signal processing problem of separating the speech of a target speaker from a real-world audio recording containing noise, background interference — from competing speech or other non-speech ...