Search for dissertations about: "KNN"

Showing result 1 - 5 of 7 swedish dissertations containing the word KNN.

  2. 1. Automated Traffic Time Series Prediction

    Author : Bin Sun; Wei Cheng; Prashant Goswami; Guohua Bai; Slawomir Nowaczyk; Blekinge Tekniska Högskola; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Machine Learning; Time Series; Traffic Engineering;

    Abstract : Intelligent transportation systems (ITS) are becoming more and more effective. Robust and accurate short-term traffic prediction plays a key role in modern ITS and demands continuous improvement. READ MORE

  4. 2. Classification and Computational Methods in Gene Expression Data Analysis

    Author : Cecilia Ritz; Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Bioinformatik; medicinsk informatik; Bioinformatics; medical informatics; biomathematics biometrics; missing values; leukemia; cDNA microarray data; supervised classification; breast cancer; prognostic markers; biomatematik;

    Abstract : The technology of cDNA microarrays has given us the possibility to monitor the state of cells by measuring the activity of thousands of genes simultaneously. This high-throughput techniqe has in cancer research allowed exploratory studies of molecular mechanisms behind for example metastasis and response to therapy. READ MORE

  5. 3. Nearest Neighbor Classification in High Dimensions

    Author : Sampath Deegalla; Henrik Boström; Slawomir Nowaczyk; Stockholms universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Nearest Neighbor; High-Dimensional Data; Curse of Dimensionality; Dimensionality Reduction; data- och systemvetenskap; Computer and Systems Sciences;

    Abstract : The simple k nearest neighbor (kNN) method can be used to learn from high dimensional data such as images and microarrays without any modification to the original version of the algorithm. However, studies show that kNN's accuracy is often poor in high dimensions due to the curse of dimensionality; a large number of instances are required to maintain a given level of accuracy in high dimensions. READ MORE

  6. 4. Multispectral Remote Sensing and Deep Learning for Wildfire Detection

    Author : Xikun Hu; Yifang Ban; Ioannis Gitas; KTH; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; active fire detection; biome; multi-criteria; Sentinel-2; Landsat-8; burned area mapping; deep learning; semantic segmentation; machine learning.; aktiv branddetektering; biom; multikriterietillvägagångssätt; Sentinel-2; Landsat-8; kartläggning av bränt område; djupinlärning; semantisk segmentering; maskininlärningsmetoderna; Geoinformatik; Geoinformatics;

    Abstract : Remote sensing data has great potential for wildfire detection and monitoring with enhanced spatial resolution and temporal coverage. Earth Observation satellites have been employed to systematically monitor fire activity over large regions in two ways: (i) to detect the location of actively burning spots (during the fire event), and (ii) to map the spatial extent of the burned scars (during or after the event). READ MORE

  7. 5. Identification, validation and clinical application of a three-gene signature for accurate prognosis prediction and treatment selection of newly diagnosed prostate cancer

    Author : Zhuochun Peng; Karolinska Institutet; Karolinska Institutet; []
    Keywords : ;

    Abstract : This thesis presents a complete, comprehensive and stepwise approach of translational molecular research. Starting from whole-genome bioinformatics analyses based on the embryonic stem (ES) cell hypothesis, a three-gene signature was identified, validated with the goal of clinical application in order to optimize treatment decision based on improvement of overall survival estimation. READ MORE