Uncontrolled face recognition by individual stable neural network

There usually exist diverse variations in face images taken under uncontrolled conditions. Most previous work on face recognition focuses on particular variations and usually assume the absence of others. Such work is called controlled face recognition. Instead of the ‘divide and conquer’ strategy adopted by controlled face recognition, this paper presents one of the first attempts directly aiming at uncontrolled face recognition. The solution is based on Individual Stable Neural Network (ISNN) proposed in this paper. ISNN can map a face image into the so-called Individual Stable Space (ISS), the feature space that only expresses personal characteristics, which is the only useful information for recognition. There are no restrictions for the face images fed into ISNN. Moreover, unlike many other robust face recognition methods, ISNN does not require any extra information (such as view angle) other than the personal identities during training. These advantages of ISNN make it a very practical approach for uncontrolled face recognition. In the experiments, ISNN is tested on two large face databases with vast variations and achieves the best performance compared with several popular face recognition techniques.

Comparing methods for prescribing exercise for individuals with chronic heart failure

This study examined the accuracy of current recommended guidelines for prescribing exercise intensity using the methods of percentage of heart rate reserve (%HRR), percentage of VO₂ peak (%VO₂peak) and percentage of VO₂ reserve (%VO₂R) in a clinical population of chronic heart failure (CHF) patients. The precision of prescription of exercise intensity for 45 patients with stable CHF (39:6 M:F, 65±9 yrs (mean±SD)) was investigated. VO₂peak testing is relatively common among patients with cardiac disease, but the assessment of VO₂rest is not common practice and the accepted standard value of 3.5 mL/kg/min is assumed in the application of %VO2R (%VO₂R_3.5). In this study, VO₂rest was recorded for 3 min prior to the start of a symptom-limited exercise test on a cycle ergometer. Target exercise intensities were calculated using the VO₂ corresponding to 50 or 80 %HRR, VO₂peak and VO₂R. The VO₂ values were then converted into prescribed speeds on a treadmill in km/hr at 1 %grade using ACSM’s metabolic equation for walking. Target intensities and prescribed treadmill speeds were also calculated with the %VO₂R method using the mean VO₂rest value of participants (3.9 mL/kg/min) (%VO₂R_3.9). This was then compared to the exercise intensities and prescribed treadmill speeds using patient’s measured VO₂rest. Error in prescription correlates the difference between %VO₂R_3.5 and %VO₂R_3.9 compared to %VO₂R with measured VO₂rest. Prescription of exercise intensity through the %HRR method is imprecise for patients on medications that blunt the HR response to exercise. %VO₂R method offers a significant improvement in exercise prescription compared to %VO₂peak. However, a disparity of 10 % still exists in the %VO₂R method using the standard 3.5 mL/kg/min for VO₂rest in the %VO₂R equation. The mean measured VO₂rest in the 45 CHF patients was 11 % higher (3.9±0.8 mL/kg/min) than the standard value provided by ACSM. Applying the mean measured VO₂rest value of 3.9 mL/kg/min rather than the standard assumed value of 3.5 mL/kg/min proved to be closer to the prescribed intensity determined by the actual measured resting VO₂. These results suggest that the %HRR method should not be used to prescribe exercise intensity for CHF patients. Instead, VO₂ should be used to prescribe exercise intensity and be expressed as %VO₂R with measured variables (VO₂rest and VO₂peak).

Measurement of stable changes of self-management skills after rehabilitation: a latent state–trait analysis of the Health Education Impact Questionnaire (heiQ™)

Methods: Subjects were N = 580 patients with rheumatism, asthma, orthopedic conditions or inflammatory bowel disease, who filled out the heiQ™ at the beginning, the end of and 3 months after a disease-specific inpatient rehabilitation program in Germany. Structural equation modeling techniques were used to estimate latent trait-change models and test for measurement invariance in each heiQ™ scale. Coefficients of consistency, occasion specificity and reliability were computed.

Stable feature selection for clinical prediction: Exploiting ICD tree structure using Tree-Lasso

Modern healthcare is getting reshaped by growing Electronic Medical Records (EMR). Recently, these records have been shown of great value towards building clinical prediction models. In EMR data, patients' diseases and hospital interventions are captured through a set of diagnoses and procedures codes. These codes are usually represented in a tree form (e.g. ICD-10 tree) and the codes within a tree branch may be highly correlated. These codes can be used as features to build a prediction model and an appropriate feature selection can inform a clinician about important risk factors for a disease. Traditional feature selection methods (e.g. Information Gain, T-test, etc.) consider each variable independently and usually end up having a long feature list. Recently, Lasso and related l1-penalty based feature selection methods have become popular due to their joint feature selection property. However, Lasso is known to have problems of selecting one feature of many correlated features randomly. This hinders the clinicians to arrive at a stable feature set, which is crucial for clinical decision making process. In this paper, we solve this problem by using a recently proposed Tree-Lasso model. Since, the stability behavior of Tree-Lasso is not well understood, we study the stability behavior of Tree-Lasso and compare it with other feature selection methods. Using a synthetic and two real-world datasets (Cancer and Acute Myocardial Infarction), we show that Tree-Lasso based feature selection is significantly more stable than Lasso and comparable to other methods e.g. Information Gain, ReliefF and T-test. We further show that, using different types of classifiers such as logistic regression, naive Bayes, support vector machines, decision trees and Random Forest, the classification performance of Tree-Lasso is comparable to Lasso and better than other methods. Our result has implications in identifying stable risk factors for many healthcare problems and therefore can potentially assist clinical decision making for accurate medical prognosis.

From video recordings to whisker stable isotopes: a critical evaluation of timescale in assessing individual foraging specialisation in Australian fur seals

Estimating the degree of individual specialisation is likely to be sensitive to the methods used, as they record individuals' resource use over different time-periods. We combined animal-borne video cameras, GPS/TDR loggers and stable isotope values of plasma, red cells and sub-sampled whiskers to investigate individual foraging specialisation in female Australian fur seals (Arctocephalus pusillus doriferus) over various timescales. Combining these methods enabled us to (1) provide quantitative information on individuals' diet, allowing the identification of prey, (2) infer the temporal consistency of individual specialisation, and (3) assess how different methods and timescales affect our estimation of the degree of specialisation. Short-term inter-individual variation in diet was observed in the video data (mean pairwise overlap = 0.60), with the sampled population being composed of both generalist and specialist individuals (nested network). However, the brevity of the temporal window is likely to artificially increase the level of specialisation by not recording the entire diet of seals. Indeed, the correlation in isotopic values was tighter between the red cells and whiskers (mid- to long-term foraging ecology) than between plasma and red cells (short- to mid-term) (R (2) = 0.93-0.73 vs. 0.55-0.41). δ(13)C and δ(15)N values of whiskers confirmed the temporal consistency of individual specialisation. Variation in isotopic niche was consistent across seasons and years, indicating long-term habitat (WIC/TNW = 0.28) and dietary (WIC/TNW = 0.39) specialisation. The results also highlight time-averaging issues (under-estimation of the degree of specialisation) when calculating individual specialisation indices over long time-periods, so that no single timescale may provide a complete and accurate picture, emphasising the benefits of using complementary methods.

Stable feature selection with support vector machines

The support vector machine (SVM) is a popular method for classification, well known for finding the maximum-margin hyperplane. Combining SVM with l1-norm penalty further enables it to simultaneously perform feature selection and margin maximization within a single framework. However, l1-norm SVM shows instability in selecting features in presence of correlated features. We propose a new method to increase the stability of l1-norm SVM by encouraging similarities between feature weights based on feature correlations, which is captured via a feature covariance matrix. Our proposed method can capture both positive and negative correlations between features. We formulate the model as a convex optimization problem and propose a solution based on alternating minimization. Using both synthetic and real-world datasets, we show that our model achieves better stability and classification accuracy compared to several state-of-the-art regularized classification methods.

Exploiting feature relationships towards stable feature selection

Feature selection is an important step in building predictive models for most real-world problems. One of the popular methods in feature selection is Lasso. However, it shows instability in selecting features when dealing with correlated features. In this work, we propose a new method that aims to increase the stability of Lasso by encouraging similarities between features based on their relatedness, which is captured via a feature covariance matrix. Besides modeling positive feature correlations, our method can also identify negative correlations between features. We propose a convex formulation for our model along with an alternating optimization algorithm that can learn the weights of the features as well as the relationship between them. Using both synthetic and real-world data, we show that the proposed method is more stable than Lasso and many state-of-the-art shrinkage and feature selection methods. Also, its predictive performance is comparable to other methods.

Microencapsulation of omega-3 fatty acids: a review of microencapsulation and characterization methods

To improve consumption of omega-3 fatty acids, foods can be enriched with omega-3 rich oils. Microencapsulation of omega-3 oils minimizes oxidative deterioration and allows their use in stable and easy-to-handle form. Microencapsulation of omega-3 fatty acids can be achieved by using a variety of methods, with the two most commonly used commercial processes being complex coacervation and spray dried emulsions. A variety of other methods are in development including spray chilling, extrusion coating and liposome entrapment. The key parameter in any of these processes is the selection of wall material. For spray dried emulsions and complex coacervates protein or polysaccharides are primarily used as shell material, although complex coacervation is currently commercially limited to gelatin. Here we review the need for microencapsulation of omega-3 oils, methods of microencapsulation and analysis, and the selection of shell material components. In particular, we discuss the method of complex coacervation, including its benefits and limitations. This review highlights the need for research on the fundamentals of interfacial and complexation behaviour of various proteins, gums and polyphenols to encapsulate and deliver omega-3 fatty acids, particularly with regard to broadening the range of shell materials that can be used in complex coacervation of omega-3 rich oils.

Strategies for extending metabolomics studies with stable isotope labelling and fluxomics

This is a perspective from the peer session on stable isotope labelling and fluxomics at the Australian & New Zealand Metabolomics Conference (ANZMET) held from 30 March to 1 April 2016 at La Trobe University, Melbourne, Australia. This report summarizes the key points raised in the peer session which focused on the advantages of using stable isotopes in modern metabolomics and the challenges in conducting flux analyses. The session highlighted the utility of stable isotope labelling in generating reference standards for metabolite identification, absolute quantification, and in the measurement of the dynamic activity of metabolic pathways. The advantages and disadvantages of different approaches of fluxomics analyses including flux balance analysis, metabolic flux analysis and kinetic flux profiling were also discussed along with the use of stable isotope labelling in in vivo dynamic metabolomics. A number of crucial technical considerations for designing experiments and analyzing data with stable isotope labelling were discussed which included replication, instrumentation, methods of labelling, tracer dilution and data analysis. This report reflects the current viewpoint on the use of stable isotope labelling in metabolomics experiments, identifying it as a great tool with the potential to improve biological interpretation of metabolomics data in a number of ways.