Contributions to Ensemble Classifiers with Image Analysis Applications

134 p.

Semi-supervised video segmentation using tree structured graphical models

We present a novel, implementation friendly and occlusion aware semi-supervised video segmentation algorithm using tree structured graphical models, which delivers pixel labels alongwith their uncertainty estimates. Our motivation to employ supervision is to tackle a task-specific segmentation problem where the semantic objects are pre-defined by the user. The video model we propose for this problem is based on a tree structured approximation of a patch based undirected mixture model, which includes a novel time-series and a soft label Random Forest classifier participating in a feedback mechanism. We demonstrate the efficacy of our model in cutting out foreground objects and multi-class segmentation problems in lengthy and complex road scene sequences. Our results have wide applicability, including harvesting labelled video data for training discriminative models, shape/pose/articulation learning and large scale statistical analysis to develop priors for video segmentation. © 2011 IEEE.

Computação da Seleção Genômica Ampla (GWS).

Métodos para GWS; Teoria dos métodos de regressão; Computação do método Random (Ridge) Regression BLUP (RR-BLUP/GWS); Fenótipos corrigidos; Frequências alélicas, variância dos marcadores e herdabilidade; Marcadores codominantes (SNP) ? Modelo genotípico; Marcadores dominantes (DArT) - Modelo genotípico; Marcadores codominantes (SNP) ? Modelo gamético ou alélico; Número de marcadores com efeitos significativos; Populações de estimação, validação e seleção; População de validação e Jacknife; Correlação e regressão entre valores genéticos preditos e fenótipos na população de validação; Análise de associação na GWAS; Software Selegen Genômica: Random (Ridge) Regression BLUP: RR-BLUP/GWS; Exemplo aplicado ao melhoramento do eucalipto.

Predicting interpretability of metabolome models based on behavior, putative identity, and biological relevance of explanatory signals

Enot, D. P., Beckmann, M., Overy, D., Draper, J. (2006). Predicting interpretability of metabolome models based on behavior, putative identity, and biological relevance of explanatory signals. Proceedings of the National Academy of Sciences of the USA, 103(40), 14865-14870. Sponsorship: BBSRC RAE2008

Representation, comparison, and interpretation of metabolome fingerprint data for total composition analysis and quality trait investigation in potato cultivars

Manfred Beckmann, David P. Enot, David P. Overy, and John Draper (2007). Representation, comparison, and interpretation of metabolome fingerprint data for total composition analysis and quality trait investigation in potato cultivars. Journal of Agricultural and Food Chemistry, 55 (9) pp.3444-3451 RAE2008

The impact of structured support groups for pregnant South African women recently diagnosed HIV positive.

The authors of this study evaluated a structured 10-session psychosocial support group intervention for newly HIV-diagnosed pregnant South African women. Participants were expected to display increases in HIV disclosure, self-esteem, active coping and positive social support, and decreases in depression, avoidant coping, and negative social support. Three hundred sixty-one pregnant HIV-infected women were recruited from four antenatal clinics in Tshwane townships from April 2005 to September 2006. Using a quasi-experimental design, assessments were conducted at baseline and two and eight months post-intervention. A series of random effects regression analyses were conducted, with the three assessment points treated as a random effect of time. At both follow-ups, the rate of disclosure in the intervention group was significantly higher than that of the comparison group (p<0.001). Compared to the comparison group at the first follow-up, the intervention group displayed higher levels of active coping (t=2.68, p<0.05) and lower levels of avoidant coping (t=-2.02, p<0.05), and those who attended at least half of the intervention sessions exhibited improved self-esteem (t=2.11, p<0.05). Group interventions tailored for newly HIV positive pregnant women, implemented in resource-limited settings, may accelerate the process of adjusting to one's HIV status, but may not have sustainable benefits over time.

Raman microscopy in the diagnosis and prognosis of surgically resected nonsmall cell lung cancer

The main curative therapy for patients with nonsmall cell lung cancer is surgery. Despite this, the survival rate is only 50%, therefore it is important to more efficiently diagnose and predict prognosis for lung cancer patients. Raman spectroscopy is useful in the diagnosis of malignant and premalignant lesions. The aim of this study is to investigate the ability of Raman microscopy to diagnose lung cancer from surgically resected tissue sections, and predict the prognosis of these patients. Tumor tissue sections from curative resections are mapped by Raman microscopy and the spectra analzsed using multivariate techniques. Spectra from the tumor samples are also compared with their outcome data to define their prognostic significance. Using principal component analysis and random forest classification, Raman microscopy differentiates malignant from normal lung tissue. Principal component analysis of 34 tumor spectra predicts early postoperative cancer recurrence with a sensitivity of 73% and specificity of 74%. Spectral analysis reveals elevated porphyrin levels in the normal samples and more DNA in the tumor samples. Raman microscopy can be a useful technique for the diagnosis and prognosis of lung cancer patients receiving surgery, and for elucidating the biochemical properties of lung tumors. (C) 2010 Society of Photo-Optical Instrumentation Engineers. [DOI: 10.1117/1.3323088]

Detecting sequence dependent transcriptional pauses from RNA and protein number time series

Background: Evidence suggests that in prokaryotes sequence-dependent transcriptional pauses a?ect the dynamics of transcription and translation, as well as of small genetic circuits. So far, a few pause-prone sequences have been identi?ed from in vitro measurements of transcription elongation kinetics.

Results: Using a stochastic model of gene expression at the nucleotide and codon levels with realistic parameter values, we investigate three di?erent but related questions and present statistical methods for their analysis. First, we show that information from in vivo RNA and protein temporal numbers is su?cient to discriminate between models with and without a pause site in their coding sequence. Second, we demonstrate that it is possible to separate a large variety of models from each other with pauses of various durations and locations in the template by means of a hierarchical clustering and a random forest classi?er. Third, we introduce an approximate likelihood function that allows to estimate the location of a pause site.

Conclusions: This method can aid in detecting unknown pause-prone sequences from temporal measurements of RNA and protein numbers at a genome-wide scale and thus elucidate possible roles that these sequences play in the dynamics of genetic networks and phenotype.

Predicting organic acid concentration from UV/vis spectrometry measurements - A comparison of machine learning techniques

The concentration of organic acids in anaerobic digesters is one of the most critical parameters for monitoring and advanced control of anaerobic digestion processes. Thus, a reliable online-measurement system is absolutely necessary. A novel approach to obtaining these measurements indirectly and online using UV/vis spectroscopic probes, in conjunction with powerful pattern recognition methods, is presented in this paper. An UV/vis spectroscopic probe from S::CAN is used in combination with a custom-built dilution system to monitor the absorption of fully fermented sludge at a spectrum from 200 to 750 nm. Advanced pattern recognition methods are then used to map the non-linear relationship between measured absorption spectra to laboratory measurements of organic acid concentrations. Linear discriminant analysis, generalized discriminant analysis (GerDA), support vector machines (SVM), relevance vector machines, random forest and neural networks are investigated for this purpose and their performance compared. To validate the approach, online measurements have been taken at a full-scale 1.3-MW industrial biogas plant. Results show that whereas some of the methods considered do not yield satisfactory results, accurate prediction of organic acid concentration ranges can be obtained with both GerDA and SVM-based classifiers, with classification rates in excess of 87% achieved on test data.

Collectives of diagnostic biomarkers identify high-risk subpopulations of hematuria patients: exploiting heterogeneity in large-scale biomarker data

Background: Ineffective risk stratification can delay diagnosis of serious disease in patients with hematuria. We applied a systems biology approach to analyze clinical, demographic and biomarker measurements (n = 29) collected from 157 hematuric patients: 80 urothelial cancer (UC) and 77 controls with confounding pathologies.

Methods: On the basis of biomarkers, we conducted agglomerative hierarchical clustering to identify patient and biomarker clusters. We then explored the relationship between the patient clusters and clinical characteristics using Chi-square analyses. We determined classification errors and areas under the receiver operating curve of Random Forest Classifiers (RFC) for patient subpopulations using the biomarker clusters to reduce the dimensionality of the data.

Results: Agglomerative clustering identified five patient clusters and seven biomarker clusters. Final diagnoses categories were non-randomly distributed across the five patient clusters. In addition, two of the patient clusters were enriched with patients with ‘low cancer-risk’ characteristics. The biomarkers which contributed to the diagnostic classifiers for these two patient clusters were similar. In contrast, three of the patient clusters were significantly enriched with patients harboring ‘high cancer-risk” characteristics including proteinuria, aggressive pathological stage and grade, and malignant cytology. Patients in these three clusters included controls, that is, patients with other serious disease and patients with cancers other than UC. Biomarkers which contributed to the diagnostic classifiers for the largest ‘high cancer- risk’ cluster were different than those contributing to the classifiers for the ‘low cancer-risk’ clusters. Biomarkers which contributed to subpopulations that were split according to smoking status, gender and medication were different.

Conclusions: The systems biology approach applied in this study allowed the hematuric patients to cluster naturally on the basis of the heterogeneity within their biomarker data, into five distinct risk subpopulations. Our findings highlight an approach with the promise to unlock the potential of biomarkers. This will be especially valuable in the field of diagnostic bladder cancer where biomarkers are urgently required. Clinicians could interpret risk classification scores in the context of clinical parameters at the time of triage. This could reduce cystoscopies and enable priority diagnosis of aggressive diseases, leading to improved patient outcomes at reduced costs. © 2013 Emmert-Streib et al; licensee BioMed Central Ltd.

Laughter Type Recognition from Whole Body Motion

Despite the importance of laughter in social interactions it remains little studied in affective computing. Respiratory, auditory, and facial laughter signals have been investigated but laughter-related body movements have received almost no attention. The aim of this study is twofold: first an investigation into observers' perception of laughter states (hilarious, social, awkward, fake, and non-laughter) based on body movements alone, through their categorization of avatars animated with natural and acted motion capture data. Significant differences in torso and limb movements were found between animations perceived as containing laughter and those perceived as nonlaughter. Hilarious laughter also differed from social laughter in the amount of bending of the spine, the amount of shoulder rotation and the amount of hand movement. The body movement features indicative of laughter differed between sitting and standing avatar postures. Based on the positive findings in this perceptual study, the second aim is to investigate the possibility of automatically predicting the distributions of observer's ratings for the laughter states. The findings show that the automated laughter recognition rates approach human rating levels, with the Random Forest method yielding the best performance.

COD and NH4-N Estimation in the Inflow of Wastewater Treatment Plants using Machine Learning Techniques

The in-line measurement of COD and NH4-N in the WWTP inflow is crucial for the timely monitoring of biological wastewater treatment processes and for the development of advanced control strategies for optimized WWTP operation. As a direct measurement of COD and NH4-N requires expensive and high maintenance in-line probes or analyzers, an approach estimating COD and NH4-N based on standard and spectroscopic in-line inflow measurement systems using Machine Learning Techniques is presented in this paper. The results show that COD estimation using Radom Forest Regression with a normalized MSE of 0.3, which is sufficiently accurate for practical applications, can be achieved using only standard in-line measurements. In the case of NH4-N, a good estimation using Partial Least Squares Regression with a normalized MSE of 0.16 is only possible based on a combination of standard and spectroscopic in-line measurements. Furthermore, the comparison of regression and classification methods shows that both methods perform equally well in most cases.

Perception and Automatic Recognition of Laughter from Whole-Body Motion: Continuous and Categorical Perspectives

Despite its importance in social interactions, laughter remains little studied in affective computing. Intelligent virtual agents are often blind to users’ laughter and unable to produce convincing laughter themselves. Respiratory, auditory, and facial laughter signals have been investigated but laughter-related body movements have received less attention. The aim of this study is threefold. First, to probe human laughter perception by analyzing patterns of categorisations of natural laughter animated on a minimal avatar. Results reveal that a low dimensional space can describe perception of laughter “types”. Second, to investigate observers’ perception of laughter (hilarious, social, awkward, fake, and non-laughter) based on animated avatars generated from natural and acted motion-capture data. Significant differences in torso and limb movements are found between animations perceived as laughter and those perceived as non-laughter. Hilarious laughter also differs from social laughter. Different body movement features were indicative of laughter in sitting and standing avatar postures. Third, to investigate automatic recognition of laughter to the same level of certainty as observers’ perceptions. Results show recognition rates of the Random Forest model approach human rating levels. Classification comparisons and feature importance analyses indicate an improvement in recognition of social laughter when localized features and nonlinear models are used.

Machine learning for transient discovery in Pan-STARRS1 difference imaging

Efficient identification and follow-up of astronomical transients is hindered by the need for humans to manually select promising candidates from data streams that contain many false positives. These artefacts arise in the difference images that are produced by most major ground-based time-domain surveys with large format CCD cameras. This dependence on humans to reject bogus detections is unsustainable for next generation all-sky surveys and significant effort is now being invested to solve the problem computationally. In this paper, we explore a simple machine learning approach to real-bogus classification by constructing a training set from the image data of similar to 32 000 real astrophysical transients and bogus detections from the Pan-STARRS1 Medium Deep Survey. We derive our feature representation from the pixel intensity values of a 20 x 20 pixel stamp around the centre of the candidates. This differs from previous work in that it works directly on the pixels rather than catalogued domain knowledge for feature design or selection. Three machine learning algorithms are trained (artificial neural networks, support vector machines and random forests) and their performances are tested on a held-out subset of 25 per cent of the training data. We find the best results from the random forest classifier and demonstrate that by accepting a false positive rate of 1 per cent, the classifier initially suggests a missed detection rate of around 10 per cent. However, we also find that a combination of bright star variability, nuclear transients and uncertainty in human labelling means that our best estimate of the missed detection rate is approximately 6 per cent.

Effectiveness of a Multifaceted Intervention for Potentially Inappropriate Prescribing in Older Patients in Primary Care: A Cluster-Randomized Controlled Trial (OPTI-SCRIPT Study)

PURPOSE Potentially inappropriate prescribing (PIP) is common in older people and can result in increased morbidity, adverse drug events, and hospitalizations. The OPTI-SCRIPT study (Optimizing Prescribing for Older People in Primary Care, a cluster-randomized controlled trial) tested the effectiveness of a multifaceted intervention for reducing PIP in primary care.

METHODS We conducted a cluster-randomized controlled trial among 21 general practitioner practices and 196 patients with PIP. Intervention participants received a complex, multifaceted intervention incorporating academic detailing; review of medicines with web-based pharmaceutical treatment algorithms that provide recommended alternative-treatment options; and tailored patient information leaflets. Control practices delivered usual care and received simple, patient-level PIP feedback. Primary outcomes were the proportion of patients with PIP and the mean number of potentially inappropriate prescriptions. We performed intention-to-treat analysis using random-effects regression.

RESULTS All 21 practices and 190 patients were followed. At intervention completion, patients in the intervention group had significantly lower odds of having PIP than patients in the control group (adjusted odds ratio = 0.32; 95% CI, 0.15–0.70; P = .02). The mean number of PIP drugs in the intervention group was 0.70, compared with 1.18 in the control group (P = .02). The intervention group was almost one-third less likely than the control group to have PIP drugs at intervention completion, but this difference was not significant (incidence rate ratio = 0.71; 95% CI, 0.50–1.02; P = .49). The intervention was effective in reducing proton pump inhibitor prescribing (adjusted odds ratio = 0.30; 95% CI, 0.14–0.68; P = .04).

CONCLUSIONS The OPTI-SCRIPT intervention incorporating academic detailing with a pharmacist, and a review of medicines with web-based pharmaceutical treatment algorithms, was effective in reducing PIP, particularly in modifying prescribing of proton pump inhibitors, the most commonly occurring PIP drugs nationally.