Sort by: Order: Results:

Now showing items 1-2 of 2
  • Wang, Aimei; Islam, Md Nahidul; Johansen, Anders; Haapalainen, Minna; Latvala, Satu; Edelenbos, Merete (2019)
    Diseases develop during the storage of onions. To minimize losses, new methods are needed to identify diseased bulbs early in storage. Volatile organic compounds (VOCs), the respiration rate, weight loss, and the dry matter content were investigated for 1-7 weeks post inoculation of bulbs with water (control) and two strains (Fox006 or Fox260) of Fusarium oxysporum f. sp. cepae. Photos, multispectral image analysis, and real-time polymerase chain reaction (PCR) showed no infection in the control onions, weak pathogenic infection in Fox006-onions, and strong pathogenic infection in Fox260-onions at week 7 post inoculation. Infected bulbs exhibited increased respiration rate, increased VOC emission rate, and increased weight loss. The control and Fox006-onions did not respond to inoculation and had similar reaction pattern. Forty-three different VOCs were measured, of which 17 compounds had sulfur in their chemical structure. 1-Propanethiol, methyl propyl sulfide, and styrene were emitted in high concentrations and were positively correlated with the extent of infection (r = 0.82 - 0.89). Therefore, these compounds were the most promising volatile markers of Fusarium basal rot infection. For the first time, we show that the extent of fungal infection determined by real-time PCR in onion bulbs is related with VOC emission.
  • Kauppi, Jukka-Pekka; Hahne, Janne; Müller, Klaus-Robert; Müller, Klaus-Robert (2015)
    Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.