Unsupervised Procedures Research Articles

Automated Open Cotton Boll Detection for Yield Estimation Using Unmanned Aircraft Vehicle (UAV) Data

Unmanned aerial vehicle (UAV) images have great potential for various agricultural applications. In particular, UAV systems facilitate timely and precise data collection in agriculture fields at high spatial and temporal resolutions. In this study, we propose an automatic open cotton boll detection algorithm using ultra-fine spatial resolution UAV images. Seed points for a region growing algorithm were generated hierarchically with a random base for computation efficiency. Cotton boll candidates were determined based on the spatial features of each region growing segment. Spectral threshold values that automatically separate cotton bolls from other non-target objects were derived based on input images for adaptive application. Finally, a binary cotton boll classification was performed using the derived threshold values and other morphological filters to reduce noise from the results. The open cotton boll classification results were validated using reference data and the results showed an accuracy higher than 88% in various evaluation measures. Moreover, the UAV-extracted cotton boll area and actual crop yield had a strong positive correlation (0.8). The proposed method leverages UAV characteristics such as high spatial resolution and accessibility by applying automatic and unsupervised procedures using images from a single date. Additionally, this study verified the extraction of target regions of interest from UAV images for direct yield estimation. Cotton yield estimation models had R2 values between 0.63 and 0.65 and RMSE values between 0.47 kg and 0.66 kg per plot grid.

Digital pathology imaging and computer-aided diagnostics as a novel tool for standardization of evaluation of aganglionic megacolon (Hirschsprung disease) histopathology.

Based on a recently introduced immunohistochemical panel (Bachmann et al. 2015) for aganglionic megacolon (AM), also known as Hirschsprung disease, histopathological diagnosis, we evaluated whether the use of digital pathology and 'machine learning' could help to obtain a reliable diagnosis. Slides were obtained from 31 specimens of 27 patients immunohistochemically stained for MAP2, calretinin, S100β and GLUT1. Slides were digitized by whole slide scanning. We used a Definiens Developer Tissue Studios as software for analysis. We configured necessary parameters in combination with 'machine learning' to identify pathological aberrations. A significant difference between AM- and non-AM-affected tissues was found for calretinin (AM 0.55% vs. non-AM 1.44%) and MAP2 (AM 0.004% vs. non-AM 0.07%) staining measurements and software-based evaluations. In contrast, S100β and GLUT1 staining measurements and software-based evaluations showed no significant differences between AM- and non-AM-affected tissues. However, no difference was found in comparison of suction biopsies with resections. Applying machine learning via an ensemble voting classifier, we achieved an accuracy of 87.5% on the test set. Automated diagnosis of AM by applying digital pathology on immunohistochemical panels was successful for calretinin and MAP2, whereas S100β and GLUT1 were not effective in diagnosis. Our method suggests that software-based approaches are capable of diagnosing AM. Our future challenge will be the improvement of efficiency by reduction of the time-consuming need for large pre-labelled training data. With increasing technical improvement, especially in unsupervised training procedures, this method could be helpful in the future.

Systematic clustering method to identify and characterise spatiotemporal congestion on freeway corridors

Many analytical procedures, technical methods, and tools have been developed to facilitate manual inspection of traffic congestion and support the decision-making process for traffic authorities. However, lacking an automatic mechanism, it would be a time-consuming and labour-intensive process for day-to-day and location-by-location analyses. This study presents a method based on a three-stage framework that is capable of automatically identifying and characterising spatiotemporal congested areas (STCAs) by parsing, extracting, analysing and quantifying the knowledge contained in traffic heatmaps. The key components of the proposed method are two unsupervised clustering procedures: (i) a mini-batch k-means clustering algorithm to separate the congested and non-congested areas and (ii) a graph-theory-based clustering algorithm to distinguish between different STCAs. Twenty weekdays of dual loop detector data collected from a 26-mile stretch of Interstate 10 in Phoenix, Arizona was analysed for the case study. The new method identified and quantified 102 STCAs without the need for human intervention. Based on 14 traffic measures calculated for each STCA, 19 active bottlenecks along the study corridor were identified. Top-ranked bottlenecks identified in this study were consistent with those reported in previous studies but were produced with less effort, demonstrating the new method's potential utility for traffic congestion management systems.

Selection of informative hyperspectral band subsets based on entropy and correlation

ABSTRACTThe article proposes two novel and relatively simple unsupervised procedures for the selection of informative small subsets of spectral bands in hyperspectral images. To ensure the informativeness of the subsets, bands featuring higher entropy are included. The correlation of band images is restricted to avoid redundancy of the subsets. The entropy multiple correlation ratio procedure employs the entropy-correlation ratio for the selection of spectral bands. The entropy-based correlated band grouping (ECBG) procedure divides the spectrum into groups of bands featuring highly correlated images. The subsets obtained were characterized by the performance of classifiers using only data from included bands. The ECBG procedure provided better results than the alternatives if the number of selected bands was low. Another advantage of this procedure is the possibility of averaging the images obtained for spectral bands within the groups found. It is shown that classification results are significantly improved if such an averaging is used. In the data acquisition practice, it can be used for a purposeful merging of spectral bands in the configuration of hyperspectral imagers, which allows one to reduce the amount of data to be saved in real time and thus helps one to improve the achievable spatial resolution.

Unsupervised Atmospheric Compensation of Airborne Hyperspectral Images in the VNIR Spectral Range

Atmospheric compensation (AC) is a fundamental and critical step for quantitative exploitation of hyperspectral data. It is the means by which the reflectance of an object/material is estimated from the measured at-sensor radiance. Such reflectance is the inherent signature that is used to identify various materials in a monitored scene. AC is quite complex and is hampered by the large amount of uncontrollable variables that play a role: just think about the spatial variability of some atmospheric constituents such as water vapor and aerosols, or to the rapidly spatially varying effects of the radiation coming from adjacent areas. Though, in principle, some atmospheric parameters and radiometric quantities such as solar irradiance and sky irradiance can be measured during the flight, in practice such measures are rarely available in an operational framework or are taken at a single point of the surface ignoring their spatial variation. Thus, a prompt quantitative exploitation of hyperspectral data for operational purposes, such as material identification and object detection, requires unsupervised and accurate AC procedures that can learn from the image itself the parameters of the inversion model and follow their variability within the scene. In this framework, we present a new unsupervised methodology for AC of airborne hyperspectral images in the visible and near-infrared spectral range. The proposed methodology relies on a radiative transfer model accounting for the adjacency effect and allows the estimation of relevant atmospheric parameters. Specifically, it embeds two new algorithms for the estimation of: 1) aerosol and atmospheric visibility and 2) the water vapor content of the atmosphere accounting for the spatial variability of such a parameter. The two algorithms significantly differ from those adopted by existing state-of-the-art approaches or in commercial packages such as fast line-of-sight atmospheric analysis of spectral hypercubes and airborne atmospheric and topographic correction algorithm. In this paper, we present the detailed description of the new AC methodology, and we analyze the results provided by the algorithm over real data.

A cross-sectional study of confidence in minor surgical skills amongst junior dentists.

To work in the National Health Service (NHS) as a dentist, the practitioner needs to be on the UK dental "performer's list". To apply for access to this list and work as a General Dental Practitioner (GDP), dentists must be qualified from the European Economic Area (EEA) or, those trained in the UK, must undertake Dental Foundation Training (DFT). Dentists interested in further taught learning or pursuing specialist training must continue working as "Dental Core Trainees" (DCTs). Most of these jobs are available in Oral and Maxillofacial Surgery (OMFS) Units and require dentists to undertake unsupervised surgical procedures. It is currently estimated that over 400 "junior dentists" undertake DCT a year. It is the aim of this study to ascertain whether confidence in simple surgical procedures improves when compared to GDPs of similar experience. One hundred and two junior dentists, 34 DFTs, 20 DCT1s, 21 DCT2s and 27second and third year post-DFT GDPs all working across the Midlands, UK, had Likert scale responses about confidence in 14 minor surgical skills assessed. Results were analysed to ascertain whether gender, year group and number of extractions had any effect on confidence. We conclude that confidence in minor surgical procedures improves significantly when undertaking DCT OMFS posts, with the most significant improvement in confidence occurring within the first 6months. Dental Core Trainees become significantly more confident in their surgical ability within the first 6months when compared to GDPs with longer postgraduate experience.

Programming Fault Prediction Using Quad Tree-Based Fluffy C-Means Clustering Algorithm

Software measurements and blame information having a place with a past programming form are utilized to construct the product blame expectation show for the following arrival of the product. Unsupervised procedures like bunching might be utilized for blame expectation as a part of programming modules, all the more so in those situations where blame marks are not accessible. In this paper a Quad Tree-based Fuzzy C-Means calculation has been connected for anticipating deficiencies in program modules. The points of this paper are twofold. In the first place, Quad Trees are connected for observing the underlying group focuses to be contribution to the Fuzzy C-Means Algorithm. An information edge parameter oversees the quantity of introductory bunch focuses and by shifting the limit the client can create wanted beginning group focuses. The idea of grouping increase has been utilized to decide the nature of bunches for assessment of the Quad Tree-based introduction calculation when contrasted with other instatement procedures. These bunches got by Quad Tree-based calculation were found to have most extreme pick up qualities. Second, the Quad Tree based calculation is connected for anticipating shortcomings in program modules. The general blunder rates of this forecast approach are contrasted with other existing calculations and are observed to be better in the vast majority of the cases.

A combined change detection procedure to study desertification using opensource tools

Background and MethodsThe paper presents a combination of two unsupervised techniques for change detection studies in arid and semi-arid areas. Among Remote Sensing change detection techniques, unsupervised approaches have the advantage of promptly producing a map of the change between two dates, but often the interpretation of the results is not straightforward, and requires further processing of the image. The aim of the research is to propose a new time effective and semi-automated reproducible technique in order to reduce the weakness of the unsupervised approach in change detection. Two techniques, Change Vector Analysis (CVA) and Maximum Autocorrelation Factor transform of Multivariate Alteration Detector components (MAD/MAF) are chosen to serve the purpose.Results and ConclusionsThe results of the research, applied to two case studies in the Middle East region, indicate that the chosen techniques complement each other, since MAD/MAF gives a detailed spatial extent while CVA gives the semantic interpretation of the output. The research brings further understanding to the use of both unsupervised procedures and the methodology can be used as a fast semi-automatic preliminary step for more accurate change detection studies. A further output is a new add-on implementing CVA for the GFOSS (Geospatial Free and Open Source Software) project Grass GIS.

A comparison of unsupervised segmentation parameter optimization approaches using moderate- and high-resolution imagery

Unsupervised segmentation optimization methods have been proposed to aid in selecting an “optimal” set of scale parameters quickly and objectively for object-based image analysis. The goal of this study was to qualitatively assess three unsupervised approaches using both moderate-resolution Landsat and high-resolution Ikonos imagery from two study sites with different landscape characteristics to demonstrate the continued need for analyst intervention during the segmentation process. The results demonstrate that these methods selected parameters that were optimal for the scene which varied with method, image type, and site complexity. Several takeaways from this exercise are as follows: (1) some methods do not work as intended, (2) single-scale unsupervised optimization procedures cannot be expected to properly segment all the features of interest in the image every time, and (3) many multi-scale approaches require subjectively chosen weights or thresholds or additional testing to determine those values that meet the objective. Visual inspection of segmentation results is still required in order to assess over and under-segmentation as no method can be expected to select the best parameters for land cover classifications every time. These approaches should instead be used to narrow down parameter values in order to save time.

Shadow detection and removal in RGB VHR images for land use unsupervised classification

Nowadays, high resolution aerial images are widely available thanks to the diffusion of advanced technologies such as UAVs (Unmanned Aerial Vehicles) and new satellite missions. Although these developments offer new opportunities for accurate land use analysis and change detection, cloud and terrain shadows actually limit benefits and possibilities of modern sensors.Focusing on the problem of shadow detection and removal in VHR color images, the paper proposes new solutions and analyses how they can enhance common unsupervised classification procedures for identifying land use classes related to the CO2 absorption.To this aim, an improved fully automatic procedure has been developed for detecting image shadows using exclusively RGB color information, and avoiding user interaction. Results show a significant accuracy enhancement with respect to similar methods using RGB based indexes.Furthermore, novel solutions derived from Procrustes analysis have been applied to remove shadows and restore brightness in the images. In particular, two methods implementing the so called “anisotropic Procrustes” and the “not-centered oblique Procrustes” algorithms have been developed and compared with the linear correlation correction method based on the Cholesky decomposition.To assess how shadow removal can enhance unsupervised classifications, results obtained with classical methods such as k-means, maximum likelihood, and self-organizing maps, have been compared to each other and with a supervised clustering procedure.

Automated monitoring of high-temperature volcanic features: from high-spatial to very-high-temporal resolution

Abstract Developments in spaceborne Earth Observation (EO) sensor technology over the last decade, combined with well-tested physical models and multispectral data-processing techniques developed from the early 1980s, have paved the way to the global monitoring of volcanoes by sensors of metric, decametric, kilometric and multi-kilometric spatial resolution. Such variable geometries provide for revisit intervals ranging from about monthly – at high-spatial resolution in Low-Earth Orbit – to less than 5 min – at low-spatial resolution, from geostationary platforms. There are currently about 20 spacecrafts available for carrying out 24/7 quantitative observations of volcanic unrest, at all resolutions and as close as possible to real-time. We show some successful examples of synergetic EO on volcanoes on three continents from 10 different payloads, automatically processed with three, end-to-end unsupervised procedures, on eight major eruptions and a lava lake between 2006 and 2014.

Exploring Geographical Differentiation of the Hoelen Medicinal Mushroom, Wolfiporia extensa (Agaricomycetes), Using Fourier-Transform Infrared Spectroscopy Combined with Multivariate Analysis.

In this study the geographical differentiation of dried sclerotia of the medicinal mushroom Wolfiporia extensa, obtained from different regions in Yunnan Province, China, was explored using Fourier-transform infrared (FT-IR) spectroscopy coupled with multivariate data analysis. The FT-IR spectra of 97 samples were obtained for wave numbers ranging from 4000 to 400 cm-1. Then, the fingerprint region of 1800-600 cm-1 of the FT-IR spectrum, rather than the full spectrum, was analyzed. Different pretreatments were applied on the spectra, and a discriminant analysis model based on the Mahalanobis distance was developed to select an optimal pretreatment combination. Two unsupervised pattern recognition procedures- principal component analysis and hierarchical cluster analysis-were applied to enhance the authenticity of discrimination of the specimens. The results showed that excellent classification could be obtained after optimizing spectral pretreatment. The tested samples were successfully discriminated according to their geographical locations. The chemical properties of dried sclerotia of W. extensa were clearly dependent on the mushroom's geographical origins. Furthermore, an interesting finding implied that the elevations of collection areas may have effects on the chemical components of wild W. extensa sclerotia. Overall, this study highlights the feasibility of FT-IR spectroscopy combined with multivariate data analysis in particular for exploring the distinction of different regional W. extensa sclerotia samples. This research could also serve as a basis for the exploitation and utilization of medicinal mushrooms.

Learning endoscopic resection in the esophagus

Endoscopic resection is the cornerstone of endoscopic management of esophageal early neoplasia. However, endoscopic resection is a complex technique requiring knowledge and expertise. Our aims were to identify the most important learning points in performing endoscopic resection in a training setting and to provide information on how to improve endoscopic resection technique. Six gastroenterologists at centers with multidisciplinary expertise in upper gastrointestinal oncology participated in a structured endoscopic resection training program, consisting of four training days with lectures and hands-on training on live pigs, further one-to-one hands-on training days, and written feedback (by an expert) on videos of unsupervised endoscopic resection procedures. The first 20 endoscopic resections of each participant were prospectively registered. Ninety learning points were independently identified by participants using a standardized questionnaire and by an expert providing written feedback on 33 unsupervised endoscopic resection videos. Three expert endoscopists selected and ranked the most important learning points in a consensus meeting. Results. The top 10 tips (illustrated by unique videos of three perforations) were: (1) allow time for inspection and use a high-definition endoscope; (2) create a preprocedural plan by placing electrocoagulation markings; (3) know the management of bleeding; (4) optimize the endoscopic view by repeatedly cleaning out stomach and target area; (5) use a therapeutic endoscope during resection; (6) always perform a test suction; (7) keep instruments close to the tip; (8) lift edges in piecemeal endoscopic cap resections; (9) know the management of perforation; (10) pin specimens down. This study summarized the most important learning points for performing endoscopic resection encountered during a structured endoscopic resection training program.

Boosting diagnosis accuracy of Alzheimer's disease using high dimensional recognition of longitudinal brain atrophy patterns

ObjectiveBoosting accuracy in automatically discriminating patients with Alzheimer's disease (AD) and normal controls (NC), based on multidimensional classification of longitudinal whole brain atrophy rates and their intermediate counterparts in analyzing magnetic resonance images (MRI). MethodLongitudinal percentage of brain volume changes (PBVC) in two-year follow up and its intermediate counterparts in early 6-month and late 18-month are used as features in supervised and unsupervised classification procedures based on K-mean, fuzzy clustering method (FCM) and support vector machine (SVM). The most relevant features for classification are selected using discriminative analysis (DA) of features and their principal components (PC). Accuracy of the proposed method is evaluated in a group of 30 patients with AD (16 males, 14 females, age±standard-deviation (SD)=75±1.36 years) and 30 normal controls (15 males, 15 females, age±SD=77±0.88 years) using leave-one-out cross-validation. ResultsResults indicate superiority of supervised machine learning techniques over unsupervised ones in diagnosing AD and withal, predominance of RBF kernel over lineal one. Accuracies of 83.3%, 83.3%, 90% and 91.7% are achieved in classification by K-mean, FCM, linear SVM and SVM with radial based function (RBF) respectively. ConclusionEvidence that SVM classification of longitudinal atrophy rates may results in high accuracy is given. Additionally, it is realized that use of intermediate atrophy rates and their principal components improves diagnostic accuracy.

A Comparison of Statistics for Assessing Model Invariance in Latent Class Analysis

Latent class analysis (LCA) is a widely used statistical technique for identifying subgroups in the population based upon multiple indicator variables. It has a number of advantages over other unsupervised grouping procedures such as cluster analysis, including stronger theoretical underpinnings, more clearly defined measures of model fit, and the ability to conduct confirmatory analyses. In addition, it is possible to ascertain whether an LCA solution is equally applicable to multiple known groups, using invariance assessment techniques. This study compared the effectiveness of multiple statistics for detecting group LCA invariance, including a chi-square difference test, a bootstrap likelihood ratio test, and several information indices. Results of the simulation study found that the bootstrap likelihood ratio test was the optimal invariance assessment statistic. In addition to the simulation, LCA group invariance assessment was demonstrated in an application with the Youth Risk Behavior Survey (YRBS). Implications of the simulation results for practice are discussed.

Taking Contrast Coverage Seriously

RADIOLOGY RESIDENT MOONLIGHTING Most residents graduate from medical school with significant debt. As such, moonlighting is a desirable and common aspect of many residency programs. Radiology residency moonlighting opportunities vary in intensity, from the simpler contrast coverage— monitoring for contrast reactions after the administration of contrast agents—to interpreting diagnostic imaging studies, to performing unsupervised invasive procedures [1]. Radiology residents often begin their moonlighting careers with contrast coverage opportunities. In a recent survey of US radiology residency programs, 73% of programs actively encouraged or condoned moonlighting. Of these programs, 73% had contrast coverage opportunities for residents [2]. For contrast coverage, residents are paid to be on site to monitor and treat patients for contrast reactions after the administration of contrast agents. Given the rarity of contrast reactions, most contrast coverage shifts involve little to no stress for moonlighting residents. Unfortunately, this has led to a widespread misconception that a contrast coverage shift involves little to no work. In reality, contrast reactions can be life threatening, and providing contrast coverage is a serious clinical responsibility for which one should be prepared.

Differentiation of Anatolian honey samples from different botanical origins by ATR-FTIR spectroscopy using multivariate analysis

Botanical origin of the nectar predominantly affects the chemical composition of honey. Analytical techniques used for reliable honey authentication are mostly time consuming and expensive. Additionally, they cannot provide 100% efficiency in accurate authentication. Therefore, alternatives for the determination of floral origin of honey need to be developed. This study aims to discriminate characteristic Anatolian honey samples from different botanical origins based on the differences in their molecular content, rather than giving numerical information about the constituents of samples. Another scope of the study is to differentiate inauthentic honey samples from the natural ones precisely. All samples were tested via unsupervised pattern recognition procedures like hierarchical clustering and Principal Component Analysis (PCA). Discrimination of sample groups was achieved successfully with hierarchical clustering over the spectral range of 1800–750cm−1 which suggests a good predictive capability of Fourier Transform Infrared (FTIR) spectroscopy and chemometry for the determination of honey floral source.

Prediction of rare single-nucleotide causative mutations for muscular diseases in pooled next-generation sequencing experiments.

Next-generation sequencing (NGS) is a new approach for biomedical research, useful for the diagnosis of genetic diseases in extremely heterogeneous conditions. In this work, we describe how data generated by high-throughput NGS experiments can be analyzed to find single nucleotide polymorphisms (SNPs) in DNA samples of patients affected by neuromuscular disorders. In particular, we consider untagged pooled NGS data, where DNA samples of different individuals are combined in a single experiment, still providing information with an uncertainty limited to only two patients. At the moment, only few publications address the problem of SNPs detection in pooled experiments, and existing tools are often inaccurate. We propose a computational procedure consisting of two parts. In the first, data are filtered by means of decision rules. The second phase is based on a supervised classification technique. In the present work, we compare different de facto standard supervised and unsupervised procedures to identify and classify variants potentially related to muscular diseases, and we discuss results in terms of statistical and biological validation.

Internal versus External Moonlighting by Radiology Trainees: Differences in Roles and Responsibilities

Recent survey data have suggested that the paid extracurricular activities of radiology trainees (known as "moonlighting") are more diverse than has been previously recognized. The purpose of this study is to examine these activities in further detail and to assess for differences between clinical duties performed at institutions affiliated with residents' training programs ("internal moonlighting") versus those performed at unaffiliated institutions ("external moonlighting").Electronic survey data were collected from trainee members of the Association of University Radiologists regarding their extracurricular clinical work, with an emphasis on their responsibilities when working in institutions that are affiliated with their training program versus work done in unaffiliated institutions. Descriptive and analytic statistics were used to examine these data.Survey respondents represented 61 unique institutions (of 173 Association of University Radiologists member-programs, a 35% institutional response rate). Trainees engage in moonlighting activities at nearly three-fourths of these programs. Although the incidence of duty hour violations appears to be low ("probably" or "definitely" occurring at three of 44, or 7%, of represented programs with moonlighting trainees), these violations go largely undocumented. Residents participating in external moonlighting were significantly more likely to provide final interpretations of diagnostic imaging studies when compared with residents moonlighting internally (odds ratio 13.84, P < .05). Of the 27 programs with residents that moonlight externally, five respondents (19%) indicated that their external moonlighting duties include the unsupervised performance of invasive procedures. There were no reports of unsupervised procedures performed by trainees moonlighting internally.Many resident physicians view moonlighting as a highly desirable, or even financially necessary, component of their clinical training. Although external moonlighting may be a useful means of garnering additional experience and income, certain ethical and medicolegal implications must be considered. The moonlighting trainee should seek opportunities for extracurricular work that do not compromise patient safety or the trainee's own long-term professional interests. Department administrators might facilitate this process by providing opportunities for internal moonlighting, while simultaneously developing competency-based systems for assessing trainee readiness for progressive clinical independence.

Hijamat in Traditional Persian Medicine

Traditional Persian medicine is based on humoral medical concepts. In the case of abundant blood in the body, tabi'at (body nature) deals with this imbalance by elimination of the morbid substances via some controlling mechanisms. If tabi'at could not react properly, the physician should prescribe an intervention to let the extra blood out. This can be done through phlebotomy, wet cupping, and the use of leech or scarification of the ears. Cupping with scarification may eliminate the morbid substance through the scarified skin, and cupping without scarification evacuates the morbid materials from the compromised organs. Wet cupping in health state is meant to be applied for preventing the blood humor dominance in susceptible individuals. In disease condition, wet cupping is defined as a treatment in which the patients confront the abundance of blood. Wet cupping may have harmful complications in extremely thin or obese patients. Wet cupping should be postponed in patients compromised by diseases especially in the thick phlegm abundance. In Asia, Iranian people, because of religious beliefs, are very interested in cupping therapy. Many unsupervised cupping procedures are performed in Iran, whereas benefits and risks of these procedures are undetermined by providers and clients. In this study, the most important indications and contraindications of wet cupping have been reviewed based on the traditional Persian medicine resources.