Classification Of Candidates Research Articles

LBV Candidates in M31 and M33. Overview of 20 Years of the 6-m Telescope: Observations and Results

An ongoing SAO RAS program for the 6-m telescope to search for and study luminous blue variable (LBV) candidates in the M31 and M33 galaxies was started in 1997. This paper summarizes the results of our observations over the last 20 years. Over this time, we have a general lists of candidates and obtained photometry and spectroscopy for approximately one hundred stars from the list. A detailed study and classification of LBV candidates were carried out.We alsomonitored spectrally and photometrically the confirmed LBV stars in these galaxies. Based on these results, the spectral energy distributions (SEDs) of LBVs and LBV candidates were computed, and the interstellar extinction values, temperature, and luminosity were derived. We propose a new method of confirming the nature of LBV stars. It is based on a special property exhibited only by LBV stars—the constancy of the bolometric luminosity, with except of a rare phase of giant eruption, registered for two historical LBVs in our galaxy and about few dozen extragalactic LBVs. Using this method, we determine the fundamental parameters of these stars: temperature, radius, luminosity, and interstellar extinction. We discuss the nature of several individual LBV stars discovered by us in M33 and the classification of the LBV candidates in M31. Thus, for 20 years of observations we have found four LBV stars in M33; in the M31 galaxy with different methods, we have confirmed seven objects as a LBV class.

Crack detection based on the mesoscale geometric features for visual concrete bridge inspection

False cracks, such as split joints and scratches, have macroscopic geometry that is similar to real cracks, which can influence the crack detection efficiency for a concrete bridge. To solve this problem, a crack detection algorithm based on the mesoscale geometric features of cracks is proposed. Through the mesoscale analysis of concrete crack formation and propagation mechanisms, it is found that a concrete crack propagates at the interface between aggregates and mortar and usually has a meandering path, whereas a false crack’s path is usually smooth or even straight. Thus the path smoothness of a crack candidate is chosen as the detection basis. The algorithm extracts a crack candidate with conventional methods, and also its skeleton for representing the path. In addition, the feature parameters are designed to quantify the path smoothness. Moreover, a back propagation neural network (BPNN) and a support vector machine (SVM) for the classification of crack candidates are trained using the proposed feature parameters as the input. Experimental results show that the classification rate of the BPNN trained by new features is 91.7%, which is better than the BPNNs trained by conventional features. The classification rate of the SVM is 93.3%, which is more suitable for engineering in small size samples.

The STRong lensing Insights into the Dark Energy Survey (STRIDES) 2016 follow-up campaign – I. Overview and classification of candidates selected by two techniques

The primary goals of the STRong lensing Insights into the Dark Energy Survey (STRIDES) collaboration are to measure the dark energy equation of state parameter and the free streaming length of dark matter. To this aim, STRIDES is discovering strongly lensed quasars in the imaging data of the Dark Energy Survey and following them up to measure time delays, high resolution imaging, and spectroscopy sufficient to construct accurate lens models. In this paper, we first present forecasts for STRIDES. Then, we describe the STRIDES classification scheme, and give an overview of the Fall 2016 follow-up campaign. We continue by detailing the results of two selection methods, the Outlier Selection Technique and a morphological algorithm, and presenting lens models of a system, which could possibly be a lensed quasar in an unusual configuration. We conclude with the summary statistics of the Fall 2016 campaign. Including searches presented in companion papers (Anguita et al.; Ostrovski et al.), STRIDES followed up 117 targets identifying 7 new strongly lensed systems, and 7 nearly identical quasars (NIQs), which could be confirmed as lenses by the detection of the lens galaxy. 76 candidates were rejected and 27 remain otherwise inconclusive, for a success rate in the range 6-35\%. This rate is comparable to that of previous searches like SQLS even though the parent dataset of STRIDES is purely photometric and our selection of candidates cannot rely on spectroscopic information.

A robust automated flower estimation system for grape vines

Automated flower counting systems have recently been developed to process images of grapevine inflorescences, which assist in the critical tasks of determining potential yields early in the season and measurement of fruit-set ratios without arduous manual counting. In this paper, we introduce a robust flower estimation system comprised of an improved flower candidate detection algorithm, flower classification and finally flower estimation using calibration models. These elements of the system have been tested in eight aspects across 533 images with associated manual counts to determine the overall accuracy and how it is affected by experimental conditions. The proposed algorithm for flower candidate detection and classification is superior to all existing methods in terms of accuracy and robustness when compared with images where visible flowers are manually identified. For flower estimation, an accuracy of 84.3% against actual manual counts was achieved both in-vivo and ex-vivo and found to be robust across the 12 datasets used for validation. A single-variable linear model trained on 13 images outperformed other estimation models and had a suitable balance between accuracy and manual counting effort. Although accurate flower counting is dependent on the stage of inflorescence development, we found that once they reach approximately EL16 this dependency decreases and the same estimation model can be used within a range of about two EL stages. A global model can be developed across multiple cultivars if they have inflorescences with a similar size and structure.

Diabetic macular edema grading in retinal images using vector quantization and semi-supervised learning

BACKGROUND: Diabetic macular edema (DME) is one of the severe complication of diabetic retinopathy causing severe vision loss and leads to blindness in severe cases if left untreated.OBJECTIVE:To grade the severity of DME in retinal images.METHODS:Firstly, the macular is localized using its anatomical features and the information of the macula location with respect to the optic disc. Secondly, a novel method for the exudates detection is proposed. The possible exudate regions are segmented using vector quantization technique and formulated using a set of feature vectors. A semi-supervised learning with graph based classifier is employed to identify the true exudates. Thirdly, the disease severity is graded into different stages based on the location of exudates and the macula coordinates.RESULTS:The results are obtained with the mean value of 0.975 and 0.942 for accuracy and F1-scrore, respectively.CONCLUSION:The present work contributes to macula localization, exudate candidate identification with vector quantization and exudate candidate classification with semi-supervised learning. The proposed method and the state-of-the-art approaches are compared in terms of performance, and experimental results show the proposed system overcomes the challenge of the DME grading and demonstrate a promising effectiveness.

Convolutional neural network-based PSO for lung nodule false positive reduction on CT images

Background and objectiveDetection of lung nodules is critical in CAD systems; this is because of their similar contrast with other structures and low density, which result in the generation of numerous false positives (FPs). Therefore, this study proposes a methodology to reduce the FP number using a deep learning technique in conjunction with an evolutionary technique. MethodThe particle swarm optimization (PSO) algorithm was used to optimize the network hyperparameters in the convolutional neural network (CNN) in order to enhance the network performance and eliminate the requirement of manual search. ResultsThe methodology was tested on computed tomography (CT) scans from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) with the highest accuracy of 97.62%, sensitivity of 92.20%, specificity of 98.64%, and area under the receiver operating characteristic (ROC) curve of 0.955. ConclusionThe results demonstrate the high performance-potential of the PSO algorithm in the identification of optimal CNN hyperparameters for lung nodule candidate classification into nodules and non-nodules, increasing the sensitivity rates in the FP reduction step of CAD systems.

Detection of white matter lesion regions in MRI using SLIC0 and convolutional neural network

Background and Objective: White matter lesions are non-static brain lesions that have a prevalence rate up to 98% in the elderly population. Because they may be associated with several brain diseases, it is important that they are detected as soon as possible. Magnetic Resonance Imaging (MRI) provides three-dimensional data with the possibility to detect and emphasize contrast differences in soft tissues, providing rich information about the human soft tissue anatomy. However, the amount of data provided for these images is far too much for manual analysis/interpretation, representing a difficult and time-consuming task for specialists. This work presents a computational methodology capable of detecting regions of white matter lesions of the brain in MRI of FLAIR modality. The techniques highlighted in this methodology are SLIC0 clustering for candidate segmentation and convolutional neural networks for candidate classification. Methods: The methodology proposed here consists of four steps: (1) images acquisition, (2) images preprocessing, (3) candidates segmentation and (4) candidates classification. Results: The methodology was applied on 91 magnetic resonance images provided by DASA, and achieved an accuracy of 98.73%, specificity of 98.77% and sensitivity of 78.79% with 0.005 of false positives, without any false positives reduction technique, in detection of white matter lesion regions. Conclusions: It is demonstrated the feasibility of the analysis of brain MRI using SLIC0 and convolutional neural network techniques to achieve success in detection of white matter lesions regions.

An international delphi survey for the definition of the variables for the development of new classification criteria for periodic fever aphtous stomatitis pharingitis cervical adenitis (PFAPA)

BackgroundDiagnosis of Periodic fever, aphthous stomatitis, pharyngitis and cervical adenitis (PFAPA) is currently based on a set of criteria proposed in 1999 modified from Marshall’s criteria. Nevertheless no validated evidence based set of classification criteria for PFAPA has been established so far. The aim of this study was to identify candidate classification criteria PFAPA syndrome using international consensus formation through a Delphi questionnaire survey.MethodsA first open-ended questionnaire was sent to adult and pediatric clinicians/researchers, asking to identify the variables thought most likely to be helpful and relevant for the diagnosis of PFAPA. In a second survey, respondents were asked to select, from the list of variables coming from the first survey, the 10 features that they felt were most important, and to rank them in descending order from most important to least important.ResultsThe response rate to the first and second Delphi was respectively 109/124 (88%) and 141/162 (87%). The number of participants that completed the first and second Delphi was 69/124 (56%) and 110/162 (68%). From the first Delphi we obtained a list of 92 variables, of which 62 were selected in the second Delphi. Variables reaching the top five position of the rank were regular periodicity, aphthous stomatitis, response to corticosteroids, cervical adenitis, and well-being between flares.ConclusionOur process led to identification of features that were felt to be the most important as candidate classification criteria for PFAPA by a large sample of international rheumatologists. The performance of these items will be tested further in the next phase of the study, through analysis of real patient data.

Computer-aided discovery of debris disk candidates: A case study using the Wide-Field Infrared Survey Explorer (WISE) catalog

Abstract Debris disks around stars other than the Sun have received significant attention in studies of exoplanets, specifically exoplanetary system formation. Since debris disks are major sources of infrared emissions, infrared survey data such as the Wide-Field Infrared Survey (WISE) catalog potentially harbors numerous debris disk candidates. However, it is currently challenging to perform disk candidate searches for over 747 million sources in the WISE catalog due to the high probability of false positives caused by interstellar matter, galaxies, and other background artifacts. Crowdsourcing techniques have thus started to harness citizen scientists for debris disk identification since humans can be easily trained to distinguish between desired artifacts and irrelevant noises. With a limited number of citizen scientists, however, increasing data volumes from large surveys will inevitably lead to analysis bottlenecks. To overcome this scalability problem and push the current limits of automated debris disk candidate identification, we present a novel approach that uses citizen science results as a seed to train machine learning based classification. In this paper, we detail a case study with a computer-aided discovery pipeline demonstrating such feasibility based on WISE catalog data and NASA’s Disk Detective project. Our approach of debris disk candidates classification was shown to be robust under a wide range of image quality and features. Our hybrid approach of citizen science with algorithmic scalability can facilitate big data processing for future detections as envisioned in future missions such as the Transiting Exoplanet Survey Satellite (TESS) and the Wide-Field Infrared Survey Telescope (WFIRST).

A Novel Fitness Computation Framework for Nature Inspired Classification Algorithms

Nature inspired algorithms have become popular for discovering classification rules due to their ability to effectively handle large and complex search spaces. However, nature inspired algorithms have to compute the fitness of individuals (candidate classification rules) over successive generations repeatedly. Each fitness computation requires scanning the training data. Since the database scan is computationally expensive operation, the execution time for nature inspired algorithms for discovering classification rules grows unreasonably faster for bulky datasets. This paper proposes a novel fitness computation framework for nature inspire algorithms by using a list structure. The indices of instances, covered by every possible attribute-value pair with respect to each class in the training data, are stored in the suggested list structure. The list is prepared only once in advance and stores all information to compute the fitness of any rule that may come up in the life time of the nature inspired algorithm. The existence of the pre-maintained list eliminates the need of scanning training data again and again for fitness computation. We have conducted experiments on 12 datasets from UCI machine learning repository. The results show that the suggested fitness computational framework brings significant speed gain without compromising predictive accuracy. Although, a Genetic Algorithm is used for classification rule discovery as the nature inspired algorithm in this paper, the fitness computation framework is general and can be used with any other nature inspired algorithm.

Object-based detection of vehicles using combined optical and elevation data

The detection of vehicles is an important and challenging topic that is relevant for many applications. In this work, we present a workflow that utilizes optical and elevation data to detect vehicles in remotely sensed urban data. This workflow consists of three consecutive stages: candidate identification, classification, and single vehicle extraction. Unlike in most previous approaches, fusion of both data sources is strongly pursued at all stages. While the first stage utilizes the fact that most man-made objects are rectangular in shape, the second and third stages employ machine learning techniques combined with specific features. The stages are designed to handle multiple sensor input, which results in a significant improvement. A detailed evaluation shows the benefits of our workflow, which includes hand-tailored features; even in comparison with classification approaches based on Convolutional Neural Networks, which are state of the art in computer vision, we could obtain a comparable or superior performance (F1 score of 0.96–0.94).

Ensemble candidate classification for the LOTAAS pulsar survey

One of the biggest challenges arising from modern large-scale pulsar surveys is the number of candidates generated. Here, we implemented several improvements to the machine learning (ML) classifier previously used by the LOFAR Tied-Array All-Sky Survey (LOTAAS) to look for new pulsars via filtering the candidates obtained during periodicity searches. To assist the ML algorithm, we have introduced new features which capture the frequency and time evolution of the signal and improved the signal-to-noise calculation accounting for broad profiles. We enhanced the ML classifier by including a third class characterizing RFI instances, allowing candidates arising from RFI to be isolated, reducing the false positive return rate. We also introduced a new training data set used by the ML algorithm that includes a large sample of pulsars misclassified by the previous classifier. Lastly, we developed an ensemble classifier comprised of five different Decision Trees. Taken together these updates improve the pulsar recall rate by 2.5 per cent, while also improving the ability to identify pulsars with wide pulse profiles, often misclassified by the previous classifier. The new ensemble classifier is also able to reduce the percentage of false positive candidates identified from each LOTAAS pointing from 2.5 per cent (∼500 candidates) to 1.1 per cent (∼220 candidates).

Cost-effective screening of DNMT3A coding sequence identifies somatic mutation in pediatric T-cell acute lymphoblastic leukemia.

In pediatric T-cell acute lymphoblastic leukemia (T-ALL), risk assignment schemes preclude reliable prediction of outcome, and thus, new prognostic factors are needed. Mutations inDNMT3A are candidate prognostic and classification markers in adults with acute myeloid leukemia (AML) and T-ALL and thus were considered as candidates prognostic markers in pediatric T-ALL. DNMT3A mutational status was investigated in 74 pediatric T-ALL samples collected at diagnosis. We applied high-resolution melt (HRM) analysis and Sanger sequencing to study the hotspot position (R882) within catalytic MTase domain and exons coding for other functional domains of the protein, known to be mutated in the wide spectrum of hematological malignancies. We demonstrate a low frequency of mutations in DNMT3A coding sequence in pediatric T-ALL (1.4%, n=1/74). We identified missense mutation, p.Ala644Thr, which has not been described previously in pediatric T-ALL, but is recurrent in adults with T-ALL and AML. Low frequency of DNMT3A mutations in pediatric T-ALL is in striking contrast to adult T-ALL and renders the necessity for the search of other candidate prognostic markers. Combined Sanger sequencing-HRM approach offers a cost-effective option for genotyping DNMT3A coding sequence, with potential clinical application in other hematological malignancies.

An Insight into State-of-the-Art Techniques for Big Data Classification

This article describes how classification algorithms have emerged as strong meta-learning techniques to accurately and efficiently analyze the masses of data generated from the widespread use of internet and other sources. In particular, there is need of some mechanism which classifies unstructured data into some organized form. Classification techniques over big transactional database may provide required data to the users from large datasets in a more simplified way. With the intention of organizing and clearly representing the current state of classification algorithms for big data, present paper discusses various concepts and algorithms, and also an exhaustive review of existing classification algorithms over big data classification frameworks and other novel frameworks. The paper provides a comprehensive comparison, both from a theoretical as well as an empirical perspective. The effectiveness of the candidate classification algorithms is measured through a number of performance metrics such as implementation technique, data source validation, and scalability etc.

Feasibility Study of a Generalized Framework for Developing Computer-Aided Detection Systems—a New Paradigm

We propose a generalized framework for developing computer-aided detection (CADe) systems whose characteristics depend only on those of the training dataset. The purpose of this study is to show the feasibility of the framework. Two different CADe systems were experimentally developed by a prototype of the framework, but with different training datasets. The CADe systems include four components; preprocessing, candidate area extraction, candidate detection, and candidate classification. Four pretrained algorithms with dedicated optimization/setting methods corresponding to the respective components were prepared in advance. The pretrained algorithms were sequentially trained in the order of processing of the components. In this study, two different datasets, brain MRA with cerebral aneurysms and chest CT with lung nodules, were collected to develop two different types of CADe systems in the framework. The performances of the developed CADe systems were evaluated by threefold cross-validation. The CADe systems for detecting cerebral aneurysms in brain MRAs and for detecting lung nodules in chest CTs were successfully developed using the respective datasets. The framework was shown to be feasible by the successful development of the two different types of CADe systems. The feasibility of this framework shows promise for a new paradigm in the development of CADe systems: development of CADe systems without any lesion specific algorithm designing.

In silico screening of dicarboxylic acids for cocrystallization with phenylpiperazine derivatives based on both cocrystallization propensity and solubility advantage

In silico screening was performed to search for binary solids in which a phenylpiperazine-derivative drug was cocrystallized with a dicarboxylic acid. The phenylpiperazine derivative could be any of 61 such drugs, while the dicarboxylic acid could be any of nine such acids. The uniqueness of this approach was that two criteria had to be fulfilled simultaneously, namely a high propensity for cocrystallization and a sufficient solubility advantage. Using the mixing enthalpies of selected pairs of crystal formers with high affinities for one another permitted the classification of candidates with a high probability of cocrystallization. Further modeling of the solubility advantage allowed the identification of many binary solids that potentially exhibit significantly enhanced solubility in water. Based on the computed values for the mixing enthalpies and solubility advantage factors, it was concluded that dicarboxylic acids are both excellent coformers for cocrystallization with phenylpiperazines and very good solubility enhancers; indeed, the use of dicarboxylic acids as coformers would allow the degree of dissolution to be tuned for many of the studied drugs. The observed similarities of the cocrystallization landscapes of the studied drugs and excipients were also explored.

Automatic Detection of Pulmonary Embolism in CTA Images Using Machine Learning

In this study, a novel computer-aided detection (CAD) method is introduced to detect pulmonary embolism (PE) in computed tomography angiography (CTA) images. This method consists of lung vessel segmentation, PE candidate detection, feature extraction, feature selection and classification of PE. PE candidates are determined in lung vessel tree. Then, feature extraction is carried out based on morphological properties of PEs. Stepwise feature selection method is used to find the best set of the features. Artificial neural network (ANN), k-nearest neighbours (KNN) and support vector machines (SVM) are used as classifiers. The CAD system is evaluated for 33 CTA datasets with 10 fold cross-validation. The sensitivities of these classifiers are obtained as 98.3 %, 57.3 % and 73 % at 10.2, 5.7 and 8.2 false positives per dataset respectively. DOI: http://dx.doi.org/10.5755/j01.eie.23.1.17585

High HCV subtype heterogeneity in a chronically infected general population revealed by high-resolution hepatitis C virus subtyping

ObjectivesThis study aimed to characterize the chronically infected general hepatitis C virus (HCV) population in Barcelona using a highly sensitive subtyping method that can identify the 67 recognized HCV subtypes and diagnose mixed infection by various genotypes/subtypes in a single individual. The resulting information has implications for selecting optimal direct-acting antiviral (DAA) treatment for each patient and establishing public healthcare policies in our setting. MethodsConsecutive HCV patients (treatment-naïve or interferon-based failures) attending Vall d'Hebron Hospital outpatient clinics from February 2015 to May 2016 (N=1473) were included in the study. Patient samples were characterized using HCV subtyping by next-generation ultra-deep pyrosequencing. ResultsThe following genotypes (G) were found: G1 (1126/1473 (76.4%)), G4 (145/1473 (9.8%)), G3 (135/1473 (9.2%)), G2 (51/1473 (3.5%)), and G5 (1/1473 (0.1%)). Twenty-two subtypes were seen: 1b (790/1473 (53.6%)), 1a (332/1473 (22.5%)), 3a (133/1473 (9.0%)), 4d (105/1473 (7.1%)), 4a (29/1473 (2.0%)), and 2c (25/1473 (1.7%)), with 16 low-prevalence subtypes accounting for the remaining 3.0% (44/1473). There was a worrisome 1.0% (15/1473) of mixed infections. G2 (51/1473 (3.5%)) showed a high level of heterogeneity. Analyses by age groups showed a predominance of G1b over G1a (428/506 (84.6%) vs. 24/506 (4.7%)) in patients born before 1950 (N=506/1473), and similar percentages of these subtypes in those born between 1951 and 1975 (N=834/1473) (315/834, 37.8% vs. 266/834, 31.9%) and after 1976 (N=133/1473) (47/133, 35.3% vs. 42/133, 31.6%). ConclusionsSubtype distribution showed a higher level of heterogeneity than was expected, particularly for G2. Prevalence of mixed infections was around 1%. HCV subtype distribution related to patient age group suggested that patients born from 1936 to 1975 in our setting should undergo screening for the infection. Next-generation sequencing enabled better classification of candidates for DAA-based treatment.

The suppression of tomato defence response genes upon potato cyst nematode infection indicates a key regulatory role of miRNAs

Potato cyst nematode Globodera rostochiensis is an obligate parasite of solanaceous plants, triggering metabolic and morphological changes in roots which may result in substantial crop yield losses. Previously, we used the cDNA-AFLP to study the transcriptional dynamics in nematode infected tomato roots. Now, we present the rescreening of already published, upregulated transcript-derived fragment dataset using the most current tomato transcriptome sequences. Our reanalysis allowed to add 54 novel genes to 135, already found as upregulated in tomato roots upon G. rostochiensis infection (in total - 189). We also created completely new catalogue of downregulated sequences leading to the discovery of 76 novel genes. Functional classification of candidates showed that the ‘wound, stress and defence response’ category was enriched in the downregulated genes. We confirmed the transcriptional dynamics of six genes by qRT-PCR. To place our results in a broader context, we compared the tomato data with Arabidopsis thaliana, revealing similar proportions of upregulated and downregulated genes as well as similar enrichment of defence related transcripts in the downregulated group. Since transcript suppression is quite common in plant–nematode interactions, we assessed the possibility of miRNA-mediated inverse correlation on several tomato sequences belonging to NB-LRR and receptor-like kinase families. The qRT-PCR of miRNAs and putative target transcripts showed an opposite expression pattern in 9 cases. These results together with in silico analyses of potential miRNA targeting to the full repertoire of tomato R-genes show that miRNA mediated gene suppression may be a key regulatory mechanism during nematode parasitism.

Single versus concurrent systems: Nominal classification in Mian

AbstractThe Papuan language Mian allows us to refine the typology of nominal classification. Mian has two candidate classification systems, differing completely in their formal realization but overlapping considerably in their semantics. To determine whether to analyse Mian as a single system or concurrent systems we adopt a canonical approach. Our criteria – orthogonality of the systems (we give a precise measure), semantic compositionality, morphosyntactic alignment, distribution across parts of speech, exponence, and interaction with other features – point mainly to an analysis as concurrent systems. We thus improve our analysis of Mian and make progress with the typology of nominal classification.