ABSTRACT In this paper a new method for the automatic classification of bird sounds is presented. Our method is based on acoustic parameters (features) taken from the first harmonic component computed from the sound spectrogram. The features are based on a line segment approximation of the first harmonic component. The final feature vectors, consisting of 16 real numbers, are then classified using a self-organizing map (SOM) neural network. Flight calls of four crossbill species (Loxia spp.) are used as a test example. In the first phase, an unsupervised network was trained and tested using common crossbill L. curvirostra flight calls recorded mainly in the Netherlands. The network was tested using two-barred L. leucoptera, Scottish L. scotica and parrot L. pytyopsittacus crossbill flight calls in the second phase. Finally, the results were validated applying the same network to flight calls of common crossbills and parrot crossbills recorded in Finland. The method automatically separated common crossbill flight calls from those of parrot crossbills. The classification accuracy of the Dutch recordings was 58% in the first phase and 54% in the second phase. The Finnish recordings were classified with 54% accuracy. 相似文献
Atrial fibrillation (AF) and atrial flutter (AFL) are the two common atrial arrhythmia encountered in the clinical practice. In order to diagnose these abnormalities the electrocardiogram (ECG) is widely used. The conventional linear time and frequency domain methods cannot decipher the hidden complexity present in these signals. The ECG is inherently a non-linear, non-stationary and non-Gaussian signal. The non-linear models can provide improved results and capture minute variations present in the time series. Higher order spectra (HOS) is a non-linear dynamical method which is highly rugged to noise. In the present study, the performances of two methods are compared: (i) 3rd order HOS cumulants and (ii) HOS bispectrum. The 3rd order cumulant and bispectrum coefficients are subjected to dimensionality reduction using independent component analysis (ICA) and classified using classification and regression tree (CART), random forest (RF), artificial neural network (ANN) and k-nearest neighbor (KNN) classifiers to select the best classifier. The ICA components of cumulant coefficients have provided the average accuracy, sensitivity, specificity and positive predictive value of 99.50%, 100%, 99.22% and 99.72% respectively using KNN classifier. Similarly, the ICA components of HOS bispectrum coefficients have yielded the average accuracy, sensitivity, specificity and PPV of 97.65%, 98.16%, 98.75% and 99.53% respectively using KNN. So, the ICA performed on the 3rd order HOS cumulants coupled with KNN classifier performed better than the HOS bispectrum method. The proposed methodology is robust and can be used in mass screening of cardiac patients. 相似文献
The 13/12C ratio in plant roots is likely dynamic depending on root function (storage versus uptake), but to date, little is known about the effect of season and root order (an indicator of root function) on the isotopic composition of C‐rich fractions in roots. To address this, we monitored the stable isotopic composition of one evergreen (Picea abies) and one deciduous (Fagus sylvatica), tree species' roots by measuring δ13C of bulk, respired and labile C, and starch from first/second and third/fourth order roots during spring and fall root production periods. In both species, root order differences in δ13C were observed in bulk organic matter, labile, and respired C fractions. Beech exhibited distinct seasonal trends in δ13C of respired C, while spruce did not. In fall, first/second order beech roots were significantly depleted in 13C, whereas spruce roots were enriched compared to higher order roots. Species variation in δ 13C of respired C may be partially explained by seasonal shifts from enriched to depleted C substrates in deciduous beech roots. Regardless of species identity, differences in stable C isotopic composition of at least two root order groupings (first/second, third/fourth) were apparent, and should hereafter be separated in belowground C‐supply‐chain inquiry. 相似文献
The natural flow regime of rivers across the world has been largely modified. Understanding the extent to which the flow regime deviates from natural conditions is necessary for designing sound management and restoration measures. In this regard, ‘Indicators of Hydrologic Alteration’ is currently considered one of the most effective approaches for assessing hydrologic alteration (HA). However, several generalized drawbacks such as the climatic variability between the pre- and post-impacted series and the scarcity of hydrological data in many impaired rivers should be addressed. In this study, a protocol with the following five alternative designs based on data availability is presented: (1) Paired-Before–After Control–Impact (BACIP), (2) Before–After (BA), (3) Control–Impact (CI), (4) Hydrological Classification (HC) and (5) Predicted Hydrological indices (HP). BACIP compares the status of the impacted gauge before and after the perturbation is started, in addition to controlling for natural climatic changes. Hence, it has been considered as the reference benchmark for all other designs. When this protocol was applied to 11 reservoirs situated in the northern third of the Iberian Peninsula, the BA design was able to correctly identify most of the non-significant HA but failed in almost one quarter of the significant alterations. Similarly, BACIP and CI showed an agreement of >80%. This suggests that the method is suitable when proper data are unavailable for BACIP or BA. In addition, our results indicated that the critical thresholds for HA varied depending on the hydrological index being considered. Significant HAs ranged from <5% for the number of days with increasing and decreasing flows to >64% for the duration of low-flow pulses. To delineate adequate thresholds, further research combining hydrological analyses with the biological response to the HA is warranted. Finally, the application of HC and HP designs revealed a significant degree of uncertainty related to the intra-class variability and the predictive error of the models. Therefore, 25% of the analysis could not be evaluated. However, in the evaluable cases, the HC and HP designs correctly assessed >75% of the HA, which highlighted the potential of this method in cases of scarce streamflow data. 相似文献
Introduction: Despite the unquestionable advantages of Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry Imaging in visualizing the spatial distribution and the relative abundance of biomolecules directly on-tissue, the yielded data is complex and high dimensional. Therefore, analysis and interpretation of this huge amount of information is mathematically, statistically and computationally challenging.
Areas covered: This article reviews some of the challenges in data elaboration with particular emphasis on machine learning techniques employed in clinical applications, and can be useful in general as an entry point for those who want to study the computational aspects. Several characteristics of data processing are described, enlightening advantages and disadvantages. Different approaches for data elaboration focused on clinical applications are also provided. Practical tutorial based upon Orange Canvas and Weka software is included, helping familiarization with the data processing.
Expert commentary: Recently, MALDI-MSI has gained considerable attention and has been employed for research and diagnostic purposes, with successful results. Data dimensionality constitutes an important issue and statistical methods for information-preserving data reduction represent one of the most challenging aspects. The most common data reduction methods are characterized by collecting independent observations into a single table. However, the incorporation of relational information can improve the discriminatory capability of the data. 相似文献