AUTOMATIC FEATURE EXTRACTION AND CLASSIFICATION OF CROSSBILL (LOXIA SPP.) FLIGHT CALLS

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.     

Application of higher order statistics for atrial arrhythmia classification

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.     

高敏C-反应蛋白在紫癜性肾炎患儿中的应用

目的：探讨血清高敏C-反应蛋白（hs-CRP）在儿童紫癜性肾炎（HSPN）临床分型与病理分级中的应用价值,为基层医院提供一个可评价HSPN患儿病情严重程度的实验室相关指标。方法：应用免疫比浊法检测210例HSPN患儿不同临床分型与病理分级中的血清hs-CRP的水平,并与住院的70例的正常儿童作对照组进行比较。采用Pearson秩相关分析得出HSPN患儿血清hs-CRP水平临床分型与及病理分级的关系。结果：HSPN患儿血清hs-CRP水平明显高于对照组（HSPN组6.4±3.5 mg/L,对照组0.7±0.1mg/L）,差异有统计学意义（t=1.021,P=0.003）。HSPN患儿的血清hs-CRP水平与其临床分型的严重程度存在正相关（r=0.913,P〈0.05）。而HSPN患儿血清hs-CRP水平与其病理分级的关系也呈正相关（r=0.901,P〈0.05）。结论：随着HSPN患儿临床分型与病理分级的增高,其血清hs-CRP水平显著升高,HSPN患儿血清hs-CRP水平与其临床分型和病理分级之间均呈显著正相关,检测HSPN患儿血清hs-CRP水平可预测其临床分型和病理分级的程度,即HSPN患儿血清hs-CRP水平越高提示其临床分型和病理分级越重,因此检测HSPN患儿血清hs-CRP水平有助于评估HSPN患儿的病情、治疗效果和预后情况。     

云南地方辣椒品种涮辣和雀辣的植物学分类

涮辣和雀辣是我国云南地区有特色的两个地方品种。本文分别基于园艺性状和90份不同类型的辣椒资源利用均匀覆盖12条染色体的29个SSR标记进行聚类分析。研究结果表明,园艺性状以及分子水平上涮辣归属于中国辣椒(C.chinese),雀辣更倾向归属于灌木辣椒(C.frutescens)。     

Evolution of trichomes and its systematic significance in Salvia (Mentheae; Nepetoideae; Lamiaceae)

We have investigated the trichome characteristics in representative species of Salvia and Pleudia in order to evaluate this source of morphological evidence for addressing problems regarding generic delimitation and subgeneric classification. Trichomes of 46 Salvia spp., representing three subgenera in Iran, were investigated using light microscopy and scanning electron microscopy. General trichome characteristics were constant among different populations of a certain species, but showed a degree of variability useful in the delimitation of taxa, specifically at lower taxonomic levels. Trichome characters of taxonomic interest are as follows: types of glandular hair; number of composing cells (uni‐, bi‐ or multicellular); size and thickness; branching pattern; and presence of papillae on the surface. Non‐glandular trichomes can be simple and branched. Glandular trichomes can be stalked, subsessile or sessile. Our investigation reveals the usefulness of such characters in providing fundamental taxonomic criteria for taxon delimitation in these genera at various levels, especially at the specific rank. Furthermore, the data presented here indicate the potential applicability of such characters in the determination of evolutionary trends in Salvia and allies. © 2015 The Linnean Society of London, Botanical Journal of the Linnean Society, 2016, 180 , 241–257.     

Integrative insect taxonomy based on morphology,mitochondrial DNA,and hyperspectral reflectance profiling

Integrative taxonomy is considered a reliable taxonomic approach of closely related and cryptic species by integrating different sources of taxonomic data (genetic, ecological, and morphological characters). In order to infer the boundaries of seven species of the evacanthine leafhopper genus Bundera Distant, 1908 (Hemiptera: Cicadellidae), an integrated analysis based on morphology, mitochondrial DNA, and hyperspectral reflectance profiling (37 spectral bands from 411–870 nm) was conducted. Despite their morphological similarities, the genetic distances of the cytochrome c oxidase subunit I (COI) gene among the tested species are relatively large (5.8–17.3%). The species‐specific divergence of five morphologically similar species (Bundera pellucida and Bundera spp. 1–4) was revealed in mitochondrial DNA data and reflectance profiling. A key to identifying males is provided, and their morphological characters are described. Average reflectance profiles from the dorsal side of specimens were classified based on linear discriminant analysis. Cross‐validation of reflectance‐based classification revealed that the seven species could be distinguished with 91.3% classification accuracy. This study verified the feasibility of using hyperspectral imaging data in insect classification, and our work provides a good example of using integrative taxonomy in studies of closely related and cryptic species. © 2015 The Linnean Society of London     

Seasonal dynamics of δ13C of C‐rich fractions from Picea abies (Norway spruce) and Fagus sylvatica (European beech) fine roots

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.     

Assessing hydrologic alteration: Evaluation of different alternatives according to data availability

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.     

Machine learning approaches in MALDI-MSI: clinical applications

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.