Hidden Biases Research Articles

Comparing the impact of older age on outcome in chronic kidney disease of different etiologies: a prospective cohort study

BackgroundIn older patients with chronic kidney disease (CKD), the risk of progression to end stage renal disease and cardiovascular death both differ compared to younger patients. This likely reflects differences in case mix and co-morbid burdens. We sought to establish the extent to which age itself is an independent biomarker of adverse outcome in CKD.MethodsThis was an analysis of the Salford Kidney Study, a prospective, longitudinal, observational study of 2,667 patients with eGFR < 60 ml/min/1.73 m2. Patients were divided into four age groups (< 55, 55–65, 65–75 and > 75 years). Within group adjusted hazard ratios for death in older compared to younger patients were calculated for different primary renal diseases. A competing risk model of death and renal replacement therapy (RRT) as outcomes was performed.ResultsThe median age of the cohort was 67.1 years [interquartile range (IQR): 55.6–75.3] and median eGFR 30.8 ml/min/1.73 m2 (IQR: 20.6–43.2). Follow up was 3.5 ± 2.9 years. Overall, the adjusted HR for death in patients aged > 75 years compared to those < 55 years was 4.4 (95% CI 3.4–5.9), p < 0.001. The HR for death differed between primary renal diseases and CKD stages. In diabetic nephropathy, the HR was 3.0 (1.8–5.3, p < 0.001), in glomerulonephritis the HR was 12.2 (5.6–25.5, p < 0.001). The cumulative incidence of RRT was < 0.1 at 10 years for patients > 75 years, compared with 0.50 in those < 55 years. Death was more likely at 20 months in those aged 75 years or older (0.17) than at 10 years in those aged < 55 years (0.10).ConclusionThis study demonstrates that the risk associated with older age shows significant variability between primary renal diseases. This is whilst acknowledging that observational studies carry the risk of hidden bias not adjusted for in the statistical model.

A multiobjective optimization-based sparse extreme learning machine algorithm

Abstract Extreme Learning Machine (ELM) is a popular machine learning method and has been widely applied to real-world problems due to its fast training speed and good generalization performance. However, in ELM, the randomly assigned input weights and hidden biases usually degrade the generalization performance. Furthermore, ELM is considered as an empirical risk minimization model and easily leads to overfitting when dataset exists some outliers. In this paper, we proposed a novel algorithm named Multiobjective Optimization-based Sparse Extreme Learning Machine (MO-SELM), where parameter optimization and structure learning are integrated into the learning process to simultaneously enhance the generalization performance and alleviate the overfitting problem. In MO-SELM, the training error and the connecting sparsity are taken as two conflicting objectives of the multiobjective model, which aims to find sparse connecting structures with optimal weights and biases. Then, a hybrid encoding-based MOEA/D is used to optimize the multiobjective model. In addition, ensemble learning is embedded into this algorithm to make decisions after multiobjective optimization. Experimental results of several classification and regression applications demonstrate the effectiveness of the proposed MO-SELM.

Metaheuristic-based extreme learning machines: a review of design formulations and applications

Extreme learning machine (ELM) is a novel and recent machine learning algorithm which was first proposed by Huang et al. (Proceedings of 2004 IEEE international joint conference on, pp 985–990, 2004). Over the last decade, ELM has gained a remarkable research interest with tremendous audiences from different domains in a short period of time due to its impressive characteristics over other single hidden-layer feedforward neural networks. Although ELM enjoys powerful advantages, it still has some potential weaknesses like performance sensitivity to the initial condition of the input weights, number of hidden neurons, and the selection of activation functions. In order to overcome the limitations of classical ELM, many metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, memetic and trajectory algorithms have been proposed for optimizing the different components of ELM by researchers aiming to improve the generalization performance of ELM networks for different types of complex problems and applications. Therefore our review paper intent to conduct a deep study of the important aspects of applying metaheuristic algorithms for optimizing ELM networks. Three main streams of research lines are identified: the optimization of input weights and hidden biases, selection of hidden neurons, and optimization of activation functions. Furthermore, this paper will discuss a wide spectrum of applications of metaheuristic-based ELM models. We will highlight the strengths of these models and the improvements that are suggested in the literature to overcome their weaknesses. We touch upon several interesting and challenging open issues in optimizing ELM using metaheuristics.

Development of hybrid extreme learning machine based chemo-metrics for precise quantitative analysis of LIBS spectra using internal reference pre-processing method

Laser induced breakdown spectroscopy (LIBS) is a versatile spectroscopic technique that requires little or no sample preparation and capable of simultaneous elemental sample analysis. Quantitative analysis of its spectra has been a major challenge due to self-absorption of the emitted radiation during plasma cooling and inadequate description of non-linear complex interactions taking place in the laser induced plasma. This work presents a novel chemo-metric tool, extreme learning machine (ELM) and its hybrid HHELM (homogenously hybridized ELM), for the first time in modeling the complex interactions of laser induced plasma and quantification of LIBS spectra. Internal reference preprocessing (IRP) method is also proposed as a novel method of enhancing the performance of ELM based chemo-metrics. Since the proposed chemo-metrics (ELM and HHELM) determine their input weights as well as their hidden biases in a random manner, ELM and HHELM are respectively hybridized with gravitational search algorithm (GSA) for optimization of the number of hidden neurons. Effect of IRP, obtained by normalizing the emission spectra intensities with the emission intensity that has highest upper level excitation energy and lowest transition probability, on the performance of the proposed GSA-ELM and GSA-HHELM chemo-metrics is investigated. The proposed models are implemented using spectra of seven bronze standard samples. Chemo-metrics with IRP (GSA-ELM-IRP and GSA-HHELM-IRP) show better generalization performance than those without IRP (GSA-ELM-WIRP and GSA-HHELM-WIRP) while GSA-HHELM based chemo-metrics perform better than their counterparts. The outstanding performance demonstrated by the proposed chemo-metrics and their self-absorption correction ability would definitely widen the applicability of LIBS and improve its precision for the quantitative analysis.

An improved learning algorithm for random neural networks based on particle swarm optimization and input-to-output sensitivity

Extreme learning machine (ELM) for random single-hidden-layer feedforward neural networks (RSLFN) has been widely applied in many fields in the past ten years because of its fast learning speed and good generalization performance. But because traditional ELM randomly selects the input weights and hidden biases, it typically requires high number of hidden neurons and thus decreases its convergence performance. It is necessary to select optimal input weights and hidden biases to improve the convergence performance of the traditional ELM. Generally, the single-hidden-layer feedforward neural networks (SLFN) with low input-to-output sensitivity will cause good robustness of the network, which may further lead into good generalization performance. Moreover, particle swarm optimization (PSO) has no complicated evolutionary operators and fewer parameters need to adjust, and is easy to implement. In this study, an improved ELM based on PSO and input-to-output sensitivity information is proposed to improve RSLFN’s convergence performance. In the improved ELM, PSO encoding the input to output sensitivity information of the SLFN is used to optimize the input weights and hidden biases. The improved ELM could obtain better generalization performance as well as improve the conditioning of the SLFN by decreasing the input-to-output sensitivity of the network. Finally, experiment results on the regression and classification problems verify the improved performance the proposed ELM.

Ergodicity, hidden bias and the growth rate gain

Many single-cell observables are highly heterogeneous. A part of this heterogeneity stems from age-related phenomena: the fact that there is a nonuniform distribution of cells with different ages. This has led to a renewed interest in analytic methodologies including use of the ‘von Foerster equation’ for predicting population growth and cell age distributions. Here we discuss how some of the most popular implementations of this machinery assume a strong condition on the ergodicity of the cell cycle duration ensemble. We show that one common definition for the term ergodicity, ‘a single individual observed over many generations recapitulates the behavior of the entire ensemble’ is implied by the other, ‘the probability of observing any state is conserved across time and over all individuals’ in an ensemble with a fixed number of individuals but that this is not true when the ensemble is growing. We further explore the impact of generational correlations between cell cycle durations on the population growth rate. Finally, we explore the ‘growth rate gain’—the phenomenon that variations in the cell cycle duration leads to an improved population-level growth rate—in this context. We highlight that, fundamentally, this effect is due to asymmetric division.

A Bayes Factor for Bounding the Treatment Effect to Address Hidden Bias in Linear Regression

A Bayes factor is introduced for the normal linear regression model, which can be used to estimate bounds of the treatment effect on the dependent variable, from the data. This is done while accounting for hidden omitted-variable bias, due to an unobserved covariate, and adjusting for any other observed covariates. The Bayes factor measures how much the data have changed the odds for some specified hidden bias versus no hidden bias, and is defined by a ratio of residual sums-of-squares raised to a power proportional to half the sample size. Therefore, the estimated bounds for the treatment effect can be determined by values of the hidden bias parameter that attain non-small Bayes factors, while the Bayes factor can be quickly computed in closed-form. The Bayes factor is illustrated through the analysis of real data and simulated data sets. Software code for the Bayes factor method is provided as Supplemental Material (available upon request of the author).

Radar HRRP Target Recognition Based on Stacked Autoencoder and Extreme Learning Machine.

A novel radar high-resolution range profile (HRRP) target recognition method based on a stacked autoencoder (SAE) and extreme learning machine (ELM) is presented in this paper. As a key component of deep structure, the SAE does not only learn features by making use of data, it also obtains feature expressions at different levels of data. However, with the deep structure, it is hard to achieve good generalization performance with a fast learning speed. ELM, as a new learning algorithm for single hidden layer feedforward neural networks (SLFNs), has attracted great interest from various fields for its fast learning speed and good generalization performance. However, ELM needs more hidden nodes than conventional tuning-based learning algorithms due to the random set of input weights and hidden biases. In addition, the existing ELM methods cannot utilize the class information of targets well. To solve this problem, a regularized ELM method based on the class information of the target is proposed. In this paper, SAE and the regularized ELM are combined to make full use of their advantages and make up for each of their shortcomings. The effectiveness of the proposed method is demonstrated by experiments with measured radar HRRP data. The experimental results show that the proposed method can achieve good performance in the two aspects of real-time and accuracy, especially when only a few training samples are available.

Balancing Confounding and Generalizability Using Observational, Real-world Data: 17-gene Genomic Prostate Score Assay Effect on Active Surveillance.

Randomized, controlled trials can provide high-quality, unbiased evidence for therapeutic interventions but are not always a practical or viable study design for certain healthcare decisions, such as those involving prognostic or predictive testing. Studies using large, real-world databases may be more appropriate and more generalizable to the intended target population of physicians and patients to answer these questions but carry potential for hidden bias. We illustrate several emerging methods of analyzing observational studies using propensity score matching (PSM) and coarsened exact matching (CEM). These advanced statistical methods are intended to reveal a "hidden experiment" within an observational database, and so refute or confirm a potential causal effect of assignment to an intervention and study outcome. We applied these methods to the Optum™ Research Database (ORD; Eden Prairie, MN) of electronic health records and administrative claims data to assess the effect of the 17-gene Genomic Prostate Score® (GPS™; Genomic Health, Redwood City, CA) assay on use of active surveillance (AS). In a traditional multivariable logistic regression, the GPS assay increased the use of AS by 29% (95% CI, 24%-33%). Upon applying the matching methods, the effect of the GPS assay on AS use varied between 27% and 80% and the matched data were significant among all algorithms. All matching algorithms performed well in identifying matched data that improved the imbalance in baseline covariates. By using different matching methods to assess causal inference in an observational database, we provide further confidence that the effect of the GPS assay on AS use is statistically significant and unlikely to be a result of confounding due to differences in baseline characteristics of the patients or the settings in which they were seen.

Discrete ripplet-II transform and modified PSO based improved evolutionary extreme learning machine for pathological brain detection

Recently there has been remarkable advances in computer-aided diagnosis (CAD) system development for detection of the pathological brain through MR images. Feature extractors like wavelet and its variants, and classifiers like feed-forward neural network (FNN) and support vector machine (SVM) are very often used in these systems despite the fact that they suffer from many limitations. This paper presents an efficient and improved pathological brain detection system (PBDS) that overcomes the problems faced by other PBDSs in the recent literature. First, we support the use of contrast limited adaptive histogram equalization (CLAHE) to enhance the quality of the input MR images. Second, we use discrete ripplet-II transform (DR2T) with degree 2 as the feature extractor. Third, in order to reduce the huge number of coefficients obtained from DR2T, we employ PCA+LDA approach. Finally, an improved hybrid learning algorithm called MPSO-ELM has been proposed that combines modified particle swarm optimization (MPSO) and extreme learning machine (ELM) for segregation of MR images as pathological or healthy. In MPSO-ELM, MPSO is utilized to optimize the hidden node parameters (input weights and hidden biases) of single-hidden-layer feedforward neural networks (SLFN) and the output weights are determined analytically. The proposed method is contrasted with the current state-of-the-art methods on three benchmark datasets. Experimental results indicate that our proposed scheme brings potential improvements in terms of classification accuracy and number of features. Additionally, it is observed that the proposed MPSO-ELM algorithm achieves higher accuracy and obtains compact network architecture compared to conventional ELM and BPNN classifier.

An evolutionary extreme learning machine based on chemical reaction optimization

This paper considers an evolutionary extreme learning machine (ELM) based on chemical reaction optimization (CRO) to overcome the drawbacks of ELM, such as the unavoidable existence of a set of unnecessary or non-optimal hidden biases and input weights. By using CRO algorithm to determine the hidden biases and input weights according to both the norm of output weights and the root mean squared error, the classification performance of optimized ELM can be improved. The experimental results on some real benchmark problems show that the proposed method can achieve higher classification accuracy than both other compared evolutionary ELMs and original ELM.

Particle swarm optimized extreme learning machine for feature classification in power quality data mining

ABSTRACTThis paper proposes enhanced particle swarm optimization (PSO) with craziness factor based extreme learning machine (ELM) for feature classification of single and combined power quality disturbances. In the proposed method, an S-transform technique is applied for feature extraction. PSO with craziness factor is applied to adjust the input weight and hidden biases of ELM. To test the effectiveness of the proposed approach, eight possible combinations of single and combined power quality disturbances are assumed in the sampled form and the performance of the proposed approach is investigated. In addition white gaussian noise of different signal-to-noise ratio is added to the signals and the performance of the algorithm is analysed. The results indicate that the proposed approach can be effectively applied for classification of power quality disturbances.

Hidden Bias in Cost-Analysis Research: What Is the Prevalence of Under-Reporting Cost Perspective in the General Surgical Literature?

Hidden Bias in Cost-Analysis Research: What Is the Prevalence of Under-Reporting Cost Perspective in the General Surgical Literature?

The hidden appeal and aversion to political conspiracies as revealed in the response dynamics of partisans

In this study, we used a mouse-tracking paradigm to capture subtle processing dynamics that may occur when people spontaneously endorse or disavow political conspiracies. Rather than exclusively focus on explicit, endpoint responses, we examined the underlying temptation to respond opposite of what is overtly reported. Our results revealed such tendencies in participants' arm movements as they provided “true” or “false” answers to political conspiracy statements relative to baseline statements. These effects were strongly modulated by whether participants identified with the Republican or Democratic parties. To interpret our findings, we argue that political conspiracies tap into hidden biases that may be at odds with each other, such that, even for nonbelievers of a particular conspiracy, there is an implicit appeal for ideologically-aligned conspiracies driven by motivated reasoning biases, and for believers, an implicit aversion to the same conspiracies driven by accuracy and self-presentation needs.

How Costly Are Stale Prices? Illiquidity in Hedge Fund Returns and Its Implications for Asset Allocation

Diversification and low correlation are the primary reasons institutional investors cite for choosing to include hedge funds in a portfolio. However, there are a number of hidden biases in the reported returns which may overstate the attractiveness of hedge funds as an asset class. We review the literature on the stale pricing bias in hedge fund returns, propose an improved model for assessing the existence and extent of the stale pricing bias, and discuss potential causes of the pricing bias. We show how correcting hedge fund returns for stale pricing has a meaningful impact on the estimated volatility and correlation with other asset classes. From this, we demonstrate the degree to which asset allocation decisions relying on standard mean-variance optimization will mis-allocate to hedge funds when the stale pricing bias is not corrected.

Social Media Engagement and Performance of E-Tailers: An Empirical Study

While prior literature mainly focuses on user-generated content (UGC), we study the impact of marketer-generated content (MGC) on sales revenue. Specifically, we quantify the sales effect at the firm level, and examine how the effect varies with firm characteristics. We collect data from taobao.com and its microblogging platform WeiTao. Using Propensity Score Matching (PSM) and Difference-in-Differences (DID) methods, we find that MGC significantly promotes sales at firm level. Meanwhile, firms selling low-involvement products benefit more from MGC efforts, compared to those selling high-involvement products. Specifically, sales elasticity is 27.89% for firms selling low-involvement products (stationery stores in our data) whereas that for firms selling high-involvement products (cosmetics stores in our data) is 19.84%. We also find that MGC with more followers and more blog postings improves firm sales more. Furthermore, we apply control function model to remove possible hidden bias in the matching process. Results hold for various robustness checks. Overall, our findings suggest that MGC plays an important role in firm marketing activities, and firms need suitable strategy to gain from their social media efforts.

Two swarm intelligence approaches for tuning extreme learning machine

Extreme learning machine (ELM) is a new algorithm for training single-hidden layer feedforward neural networks which provides good performance as well as fast learning speed. ELM tends to produce good generalization performance with large number of hidden neurons as the input weights and hidden neurons biases are randomly initialized and remain unchanged during the learning process, and the output weights are analytically determined. In this paper, two swarm intelligence based metaheuristic techniques, viz. Artificial Bee Colony (ABC) and Invasive Weed Optimization (IWO) are proposed for tuning the input weights and hidden biases. The proposed approaches are called ABC-ELM and IWO-ELM in which the input weights and hidden biases are selected using ABC and IWO respectively and the output weights are computed using the Moore-Penrose (MP) generalized inverse. The proposed approaches are tested on different benchmark classification data sets and simulations show that the proposed approaches obtain good generalization performance in comparison to the other techniques available in the literature.

Dolphin Swarm Extreme Learning Machine

As a novel learning algorithm for a single hidden-layer feedforward neural network, the extreme learning machine has attracted much research attention for its fast training speed and good generalization performances. Instead of iteratively tuning the parameters, the extreme machine can be seen as a linear optimization problem by randomly generating the input weights and hidden biases. However, the random determination of the input weights and hidden biases may bring non-optimal parameters, which have a negative impact on the final results or need more hidden nodes for the neural network. To overcome the above drawbacks caused by the non-optimal input weights and hidden biases, we propose a new hybrid learning algorithm named dolphin swarm algorithm extreme learning machine adopting the dolphin swarm algorithm to optimize the input weights and hidden biases efficiently. Each set of input weights and hidden biases is encoded into one vector, namely the dolphin. The dolphins are evaluated by root mean squared error and updated by the four pivotal phases of the dolphin swarm algorithm. Eventually, we will obtain an optimal set of input weights and hidden biases. To evaluate the effectiveness of our method, we compare the proposed algorithm with the standard extreme learning machine and three state-of-the-art methods, which are the particle swarm optimization extreme learning machine, evolutionary extreme learning machine, and self-adaptive evolutionary extreme learning machine, under 13 benchmark datasets obtained from the University of California Irvine Machine Learning Repository. The experimental results demonstrate that the proposed method can achieve superior generalization performances than all the compared algorithms.

A Global Orientation Map in the Primary Visual Cortex (V1): Could a Self Organizing Model Reveal Its Hidden Bias?

A remarkable accomplishment of self organizing models is their ability to simulate the development of feature maps in the cortex. Additionally, these models have been trained to tease out the differential causes of multiple feature maps, mapped on to the same output space. Recently, a Laterally Interconnected Synergetically Self Organizing Map (LISSOM) model has been used to simulate the mapping of eccentricity and meridional angle onto orthogonal axes in the primary visual cortex (V1). This model is further probed to simulate the development of the radial bias in V1, using a training set that consists of both radial (rectangular bars of random size and orientation) as well as non-radial stimuli. The radial bias describes the preference of the visual system toward orientations that match the angular position (meridional angle) of that orientation with respect to the point of fixation. Recent fMRI results have shown that there exists a coarse scale orientation map in V1, which resembles the meridional angle map, thereby providing a plausible neural basis for the radial bias. The LISSOM model, trained for the development of the retinotopic map, on probing for orientation preference, exhibits a coarse scale orientation map, consistent with these experimental results, quantified using the circular cross correlation (rc). The rc between the orientation map developed on probing with a thin annular ring containing sinusoidal gratings with a spatial frequency of 0.5 cycles per degree (cpd) and the corresponding meridional map for the same annular ring, has a value of 0.8894. The results also suggest that the radial bias goes beyond the current understanding of a node to node correlation between the two maps.

Radar Target Classification Using an Evolutionary Extreme Learning Machine Based on Improved Quantum-Behaved Particle Swarm Optimization

A novel evolutionary extreme learning machine (ELM) based on improved quantum-behaved particle swarm optimization (IQPSO) for radar target classification is presented in this paper. Quantum-behaved particle swarm optimization (QPSO) has been used in ELM to solve the problem that ELM needs more hidden nodes than conventional tuning-based learning algorithms due to the random set of input weights and hidden biases. But the method for calculating the characteristic length of Delta potential well of QPSO may reduce the global search ability of the algorithm. To solve this issue, a new method to calculate the characteristic length of Delta potential well is proposed in this paper. Experimental results based on the benchmark functions validate the better performance of IQPSO against QPSO in most cases. The novel algorithm is also evaluated by using real-world datasets and radar data; the experimental results indicate that the proposed algorithm is more effective than BP, SVM, ELM, QPSO-ELM, and so on, in terms of real-time performance and accuracy.