Binary Discrimination Research Articles

Kernel extreme learning machine‐based general solution to forward kinematics of parallel robots

AbstractThe forward kinematics of parallel robots is a challenging issue due to its highly coupled non‐linear relation among branch chains. This paper presents a novel approach to forward kinematics of parallel robots based on kernel extreme learning machine (KELM). To tackle with the forward kinematics solution of fully parallel robots, the forward kinematics solution of parallel robots is equivalently transformed into a machine learning model first. On this basis, a computational model combining sparrow search algorithm and KELM is then established, which can serve as both regression and classification. Based on SSA‐optimised KELM (SSA‐KELM) established in this study, a binary discriminator for judging the existence of the forward kinematics solution and a multi‐label regression model for predicting the forward kinematics solution are built to obtain the forward kinematics general solution of parallel robots with different structural configurations and parameters. To evaluate the proposed model, a numerical case on this dataset collected by the inverse kinematics model of a typical 6‐DOF parallel robot is conducted, followed by the results manifesting that the binary discriminator with the discriminant accuracy of 88.50% is superior over ELM, KELM, support vector machine and logistic regression. The multi‐label regression model, with the root mean squared error of 0.06 mm for the position and 0.15° for the orientation, outperforms the double‐hidden‐layer back propagation (2‐BP), ELM, KELM and genetic algorithm‐optimised KELM. Furthermore, numerical cases of parallel robots with different structural configurations and parameters are compared with state‐of‐the‐art models. Moreover, these results of numerical simulation and experiment on the host computer demonstrate that the proposed model displays its high precision, high robustness and rapid convergence, which provides a candidate for the forward kinematics of parallel robots.

Gender Nonconformity Leads to Identity Denial for Cisgender and Transgender Individuals

In modern Western cultures, gender is largely viewed as binary, and individuals who challenge the gender/sex binary face discrimination and marginalization. Across three preregistered studies ( N = 1,096), we examine gender discrimination against gender-nonconforming people. Studies 1 and 2 show that behavioral and appearance-based gender nonconformity leads to the misgendering of cisgender and transgender women and men. This was true for the gendered perception of these targets and the binary assignment to gender/sex-based spaces and policies (e.g., access to bathrooms or gender/sex-based leadership training). Surprisingly, whether the target was transgender or cisgender did not affect these results. Study 3 replicated findings for transgender targets and showed that adherence to gender stereotypes is seen as a necessity for transgender individuals who want their gender identity recognized by others (e.g., on official documents or through pronoun use).

Comparison of Race-Based and Non-Race-Based Glomerular Filtration Rate Equations for the Assessment of Renal Functional Risk Before Nephrectomy

To compare the performance of race-based and race-neutral estimated glomerular filtration rate (eGFR) calculators in patients undergoing kidney surgery. Analysis of institutional kidneys surgeries from 2006-2021 was conducted. Demographics, serum creatinine (SCr), protein dipstick, and creatinine clearance (CrCl) were assessed within 1 week prior to surgery. SCr was used to calculate eGFR using 3 models: Modification of Diet in Renal Disease (MDRD), Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI 2009), and CKD-EPI 2021. Patients were classified based on Kidney Disease: Improving Global Outcomes (KDIGO) criteria for CKD staging and prognosis, with urine CrCl treated as benchmark for analysis. Receiver operating characteristic (ROC) analysis evaluated accuracy of eGFR calculators' binary discrimination of eGFR less than 60 mL/min. CKD stage agreement between eGFR and urine CrCl was assessed. A total of 554 kidney surgeries in 336 patients had necessary laboratory data for analysis. The cohort was 62% male, with a median age of 47. Within this cohort, 8.1% (n=45) were Black, and 80% (n=441) were White. glomerular filtration rate (GFR) from 24-hour urine CrCl normalized by BSA did not vary significantly from eGFR by SCr based calculators. The proportion of patients with eGFR <60 significantly differed when using Modification of Diet in Renal Disease, CKD-EPI 2009, and CKD-EPI 2021 equations when compared to CrCl (P<.001). Still, they performed equivalently in the staging of CKD, as well as in predicting GFR of less than 60, and classifying CKD prognosis of "moderately increased or higher". A race-neutral eGFR calculator can perform equivalently to established eGFR calculators, with the added benefit of mitigating biases that account for racial disparities in nephrectomy decision making.

PSGAN: Revisit the binary discriminator and an alternative for face frontalization

Generative adversarial network (GAN) based face frontalization is a cheap and convenient way to eliminate the impact of pose variance on face recognition. The sigmoid cross-entropy loss function is usually employed for the discriminator in those GAN based face synthesis methods. There are two disadvantages for this loss function: 1) The discriminator always wins the generator easily at the beginning of training because the convergence of the discriminator and the generator is unbalanced; 2) The training of GANs becomes unstable due to the prediction boundary uncertainty and massive parameters of the traditional binary discriminator. In order to eliminate the impacts caused by the traditional discriminator in the general GANs, a Bayesian induced perceptual self-representation discriminator (i.e.PSD) is proposed, which can also maintain the identity information, and simultaneously reduce the model parameters and training difficulty. There are three key contributions in this work: 1) On the basis of PSD, a perceptual self-representation GAN (i.e.PSGAN) with a new architecture is proposed, which reduces the training difficulty without lowering the synthetic quality; 2) In order to further improve the performance of our method, multiple features extracted from different layers are adopted to constitute a multi-perceptual self-representation discriminator (i.e.MPSD); 3) The proposed PSD discriminator is more lightweight with fewer parameters and can also be easily plugged and played in various GANs. Extensive qualitative and quantitative experiments on both restricted and unrestricted face databases and non-facial datasets demonstrate its superiority.

Risk factors for hypoxic-ischemic encephalopathy or neonatal death in placental abruption

ObjectiveTo identify risk factors for moderate or severe hypoxic-ischemic encephalopathy (HIE), or neonatal death in clinical placental abruption. Material and methodsA nested case-control study within a cohort of singleton pregnancies complicated by placental abruption with a live born infant at two academic reference centers in France, from 2006 to 2019. Cases were patients who gave birth to an infant with moderate or severe HIE or death within 28 days (HIE/death group), and controls were patients whose infant did not have any of these outcomes (no-HIE group). Independent risk factors were identified by logistic regression. Binary decision tree discriminant (CART) analysis was performed to define high-risk subgroups of HIE or death. ResultsAmong 152 patients, the infants of 44 (29%) had HIE or death. Out-of-hospital placental abruption and fetal bradycardia at admission were more frequent in cases than in controls: 39 (89%) vs 61 (56%), p < .01 and 24 (59%) vs 19 (18%), p < .01, respectively. In multivariate analysis, out-of-hospital placental abruption (aOR, 7.05; 95% CI, 1.94-25.66) and bradycardia at admission (aOR, 8.60; 95% CI, 2.51-29.42) were independently associated with an increased risk of HIE or death. The combination of out-of-hospital placental abruption and bradycardia was the highest risk situation associated with HIE or death (67%). The decision-to-delivery interval was 15 [12-20] minutes among cases. ConclusionOut-of-hospital placental abruption combined with bradycardia at admission was associated with a major risk of moderate or severe HIE or death. An optimal decision-to-delivery interval does not guarantee the absence of an adverse neonatal outcome.

Comparison of Bayesian, Frequentist and Machine learning models for predicting the two-year mortality of patients diagnosed with squamous cell carcinoma of the oral cavity

BackgroundStatistical models developed in frequentist and Bayesian context along with machine learning algorithms can encompass the multifactorial effect of the prognostic factors in predicting the outcome. This paper is aimed to compare the effect estimates and predictive performance of Bayesian, frequentist and machine learning algorithm in predicting the two-year mortality of patients diagnosed with squamous cell carcinoma (SCC) of oral cavity. Materials and methodsLogistic regression (LR), Binary Discriminant analysis (BDA), Naïve Bayes (NB), Bayesian regression (BLR), K nearest neighbor (KNN), Artificial neural network (ANN) and Random Forest (RF) models were built. The effect estimate of each prognostic factor was estimated and compared by LR and BLR model. 10-fold cross-validation was performed for internal validation of the models. The predictive performance of the models was assessed and compared. ResultsBLR model had lower and narrower effect estimates in comparison to LR model. Age and smoking are the biggest prognostic risk factors for SCC whereas surgery had the best response amongst the mode of treatment. Random forest had an AUROC of 0.86 (0.82, 0.90) whereas it was estimated to be 0.77 (0.71, 0.82) for both BLR and LR models. ConclusionsBLR model had better precision in estimating the effect size of prognostic factors and can be an alternative for predicting mortality in patients with SCC of oral cavity. Machine learning classifiers had the best predictive ability as compared to statistical models.

Hierarchical Graphene‐Dye Bilayers for Multimodal Optoelectronic Sensing and Decoupling of Complex Stimuli

AbstractSignals obtained by chemical or calorimetric sensors are highly coupled and complex, making it very challenging to precisely detect and discriminate between simultaneous stimuli. The development of sensors that provide multiple sensory outputs is a good way to tackle such a long‐lasting challenge. Herein, a new design of multimodal sensors capable of generating both colorimetric and electrical sensory outputs is introduced. This is achieved by coupling two functional nanolayers, graphene (electrically active) and dyes (colorimetric) in which each layer can work either autonomously or in conjugation with the other sensing layer. It is shown that the interfacial interaction of graphene with the wide variety of dyes creates unique interfacial sensing sites for the detection of chemicals. This endows each sensor or sensor array, in the format of (opto)electronic nose, with a “fingerprint” of varying bonding possibilities, enlarging the spectrum of gas–sensor interactions. Furthermore, it is shown that the hierarchical nanobilayer structure allows the separation and discrimination of volatile organic compounds (VOCs) based on their diffusion kinetics. Taken together, the bilayer design qualifies as a superior sensor compared to unimodal devices by offering improved detection limits, wider dynamic ranges, and higher sensitivity and selectivity in the binary discrimination of a wide range of stimuli (temperature, relative humidity, and VOCs).

Lithofacies of early Jurassic successions derived from spectral gamma ray logging in the Mandawa Basin, SE Tanzania

Spectral gamma ray log (SGRL) data has been widely employed to derive subsurface lithological information and to perform well correlation when the core is not available. Previous studies mainly targeted homogenous facies whereas few attempts addressed heterolithic successions. The SGRL investigation here aimed at deriving lithofacies and further constrain conditions of deposition prevailing during the early Jurassic (Mbuo, Nondwa, and Mihambia Fms.) in the Mandawa Basin, onshore Tanzania, where core and outcrop data is rare. By use of binary discrimination diagrams of U, Th, and K, composition fields were defined for various lithofacies types (black shale, red shale, siltstone, sandstone, chert, anhydrite, halite, and carbonate) compiled from literature data. Sediment composition for two wells in the Mandawa Basin was then deduced from cuttings and SGRL data and compared with literature-derived geochemical provenance data from adjacent regions and strata. Binary discrimination diagrams revealed the presence of multi-mineral components in the heterolithic facies type, which in concert with diagenetic and detrital mineral dilution effects, led to low compositional contrasts between provenance fields and to overlap of different lithofacies types, complicating interpretation and limiting the effectiveness of the SGRL-based facies differentiation. For the early Jurassic strata, an upward increase in the Th/K ratio suggests an enhanced terrigenous influx into the basin due to intensified weathering. High Th/U and Th/K in the study region indicate a relatively shallow, well mixed, and oxic depositional setting in proximity to the source area opposing the more distal, deeper, and reduced depositional settings that prevailed in the southern central part of the basin. Th/U and Th/K excursions in the Nondwa and Mihambia formations suggest a shift towards less oxic depositional conditions upon two major marine incursions, corroborated by a decline in the clastic fraction and concomitant increase in carbonate.

Terrain matching positioning method for underwater vehicles based on curvature discrimination

Terrain matching positioning technology is used to locate underwater vehicles by the terrain information. The traditional method uses all real-time bathymetric points to traverse the underwater prior map, which has a large calculation amount and high complexity. To improve computational efficiency while ensuring accuracy, we represent the terrain matching positioning method based on the local terrain features and the global search technology in this paper. Firstly, the Moving Least Square (MLS) method is used to construct the MLS surface of the multi-beam bathymetric terrain. Then, a shape operator related to the principal curvatures is employed to reflect the curvedness of the MLS surface at each bathymetric point. Next, a Local Curvature Binary Discrimination (LCBD) method is proposed to describe the shape of local MLS surface with a LCBD descriptor, and divide the points satisfying the LCBD situations into the sampling point set. Finally, the Genetic Algorithm (GA) is introduced to replace the traditional traversal method (TM) to search the optimal estimated position of vehicle from the underwater prior map. The experimental results show that the proposed method can quickly locate the vehicle without affecting the accuracy, and the efficiency is improved by more than 80% compared with the traditional method.

Perceiving Body Height From Connected Speech: Higher Fundamental Frequency Is Associated With the Speaker's Height.

To a certain degree, human listeners can perceive a speaker's body size from their voice. The speaker's voice pitch or fundamental frequency (Fo) and the vocal formant frequencies are the voice parameters that have been most intensively studied in past body size perception research (particularly for body height). Artificially lowering the Fo of isolated vowels from male speakers improved listeners' accuracy of binary (i.e., tall vs not tall) body height perceptions. This has been explained by the theory that a denser harmonic spectrum provided by a low pitch improved the perceptual resolution of formants that aid formant-based size assessments. In the present study, we extended this research using connected speech (i.e., words and sentences) pronounced by speakers of both sexes. Unexpectedly, we found that raising Fo, not lowering it, increased the participants' perceptual performance in two binary discrimination tasks of body size. We explain our new finding in the temporal domain by the dynamic and time-varying acoustic properties of connected speech. Increased Fo might increase the sampling density of sound wave acoustic cycles and provide more detailed information, such as higher resolution, on the envelope shape.

Imputation methods on retrospective breast cancer data in Tanzania: A comparative study

Background: Clinical datasets are at risk of having missing data for several reasons including patients’ failure to attend clinical measurements and measurement recorder’s defects. Missing data can significantly affect the analysis and results might be doubtful due to bias caused by omission incomplete records during analysis especially if a dataset is small. This study aims to compare several imputation methods in terms of efficiency in filling-in missing data so as to increase prediction and classification accuracy in breast cancer dataset. Methodology: Five imputation methods namely series mean, k-nearest neighbour, hot deck, predictive mean matching, expected maximisation via bootstrapping, and multiple imputation by chained equations were applied to replace the missing values to the real breast cancer dataset. The efficiency of imputation methods was compared by using the Root Mean Square Errors and Mean Absolute Errors to obtain a suitable complete dataset. Binary logistic regression and linear discrimination classifiers were applied to the imputed dataset to compare their efficacy on classification and discrimination. Results: The evaluation of imputation methods revealed that the predictive mean matching method was better off compared to other imputation methods. In addition, the binary logistic regression and linear discriminant analyses yield almost similar values on overall classification rates, sensitivity and specificity. Conclusion: The predictive mean matching imputation showed higher accuracy in estimating and replacing missing data values in a real breast cancer dataset under the study. It is a more effective and good approach to handle missing data. We recommend replacing missing data by using predictive mean matching since it is a plausible approach toward multiple imputations for numerical variables. It improves estimation and prediction accuracy over the use complete-case analysis especially when percentage of missing data is not very small.

An Active Sensing Paradigm for Studying Human Auditory Perception.

Our perception is based on active sensing, i.e., the relationship between self-motion and resulting changes to sensory inputs. Yet, traditional experimental paradigms are characterized by delayed reactions to a predetermined stimulus sequence. To increase the engagement of subjects and potentially provide richer behavioral responses, we developed Sensory Island Task for humans (SITh), a freely-moving search paradigm to study auditory perception. In SITh, subjects navigate an arena in search of an auditory target, relying solely on changes in the presented stimulus frequency, which is controlled by closed-loop position tracking. A “target frequency” was played when subjects entered a circular sub-area of the arena, the “island”, while different frequencies were presented outside the island. Island locations were randomized across trials, making stimulus frequency the only informative cue for task completion. Two versions of SITh were studied: binary discrimination, and gradual change of the stimulus frequency. The latter version allowed determining frequency discrimination thresholds based on the subjects’ report of the perceived island location (i.e., target frequency). Surprisingly, subjects exhibited similar thresholds as reported in traditional “stationary” forced-choice experiments after performing only 30 trials, highlighting the intuitive nature of SITh. Notably, subjects spontaneously employed a small variety of stereotypical search patterns, and their usage proportions varied between task versions. Moreover, frequency discrimination performance depended on the search pattern used. Overall, we demonstrate that the use of an ecologically driven paradigm is able to reproduce established findings while simultaneously providing rich behavioral data for the description of sensory ethology.

General analysis for observing quantum interference at colliders

Despite their inextricable quantum mechanical nature, events at a high energy particle collider experiment typically have very few unambiguous quantum signatures, due the type of data and the manner in which they are collected. We present a general analysis of one feature of quantum mechanics, interference between two orthogonal states on Hilbert space, projected onto the basis of states that span a collider experiment observable space. Identification of quantum interference can be considered as a binary discrimination between a pure state and a mixed state, and we introduce several statistical measures that quantify the amplitude of interference in a pure state with respect to a mixed state that exhibits no interference. Two explicit examples from particle physics are provided to demonstrate features of the general formalism.

State Classification via a Random-Walk-Based Quantum Neural Network

In quantum information technology, crucial information is regularly encoded in different quantum states. To extract information, the identification of one state from the others is inevitable. However, if the states are non-orthogonal and unknown, this task will become awesomely tricky, especially when our resources are also limited. Here, we introduce the quantum stochastic neural network (QSNN), and show its capability to accomplish the binary discrimination of quantum states. After a handful of optimizing iterations, the QSNN achieves a success probability close to the theoretical optimum, no matter whether the states are pure or mixed. Other than binary discrimination, the QSNN is also applied to classify an unknown set of states into two types: entangled ones and separable ones. After training with four samples, it can classify a number of states with acceptable accuracy. Our results suggest that the QSNN has the great potential to process unknown quantum states in quantum information.

Experimental multi-state quantum discrimination through optical networks

Developing strategies to effectively discriminate between different quantum states is a fundamental issue in quantum information and communication. The actual realization of generally optimal protocols in this task is often limited by the need of supplemental resources and very complex receivers. We have experimentally implemented two discrimination schemes in a minimum-error scenario based on a receiver featured by a network structure and a dynamical processing of information. The first protocol implemented in our experiment, directly inspired to a recent theoretical proposal, achieves binary optimal discrimination, while the second one provides a novel approach to multi-state quantum discrimination, relying on the dynamical features of the network-like receiver. This strategy exploits the arrival time degree of freedom as an encoding variable, achieving optimal results, without the need for supplemental systems or devices. Our results further reveal the potential of dynamical approaches to quantum state discrimination tasks, providing a possible starting point for efficient alternatives to current experimental strategies.

Decreased imaging time of amyloid PET using [18F]florbetapir can maintain quantitative accuracy.

Shortening the amount of time required to acquire amyloid positron emission tomography (PET) brain images while maintaining the accuracy of quantitative evaluation would help to overcome motion artifacts associated with Alzheimer's disease patients. The present study aimed to validate the quantitative accuracy of [18F]florbetapir ([18F]FBP) imaging over a shorter acquisition duration. Forty participants were injected with [18F]FBP, and PET images were acquired for 50-55, 50-60, and 50-70min after injection. Three physicians visually assessed the reprocessed [18F]FBP images using a binary scale to classify them as amyloid β (Aβ) negative or positive. A mean composite standard uptake value ratio (cSUVR) > 1.075 was defined as Aβ-positive based on receiver operating characteristic curves. Inter-reader and inter-acquisition duration agreements with visual assessment were evaluated using Cohen's kappa (κ). Binary visual discrimination of 102 for the 120 [18F]FBP images, was consistent among the three readers. Sixteen, sixteen, and fourteen of the 40 [18F]FBP images acquired for 50-55, 50-60, and 50-70min after injection, respectively, were deemed Aβ-positive by visual assessment. The inter-rater agreement was high, and the inter-acquisition duration agreement was almost perfect. The cSUVR did not change significantly among the acquisition durations, and the acquisition duration did not affect the outcome of discrimination based on the cSUVR cutoff. A shorter acquisition duration changed the visual assessment outcomes. Stable quantitative values were derived from [18F]FBP images acquired within 5min. cSUVR helped to improve the performance and confidence in the outcomes of visual assessment.

Red Queen and Red King Effects in cultural agent-based modeling: Hawk Dove Binary and Systemic Discrimination

ABSTRACT What endogenous factors contribute to minority (Red Queen) or majority (Red King) domination under conditions of coercive bargaining? We build on previous work demonstrating minority disadvantage in non-coercive bargaining games to show that under neutral initial conditions, majorities are advantaged in high conflict situations, and minorities are advantaged in low conflict games. These effects are a function of the relationship between (1) relative proportions of the majority and minority groups and (2) costs of conflict. Although both Red King and Red Queen effects can occur, we further show that agents’ increased initial propensity toward conflict advantages majorities.

On the Error Exponents of Binary State Discrimination With Composite Hypotheses

The trade-off between the two types of error probabilities in binary state discrimination may be quantified in the asymptotics by various error exponents. In the composite case, where the hypotheses consist of sets of states, any such exponent is upper bounded by the infimum of the corresponding pairwise exponents of discriminating individual members of the two sets. Attainability of this upper bound may depend on the type of exponents considered; whether the problem is classical or quantum; the cardinality and the geometric properties of the sets representing the hypotheses; and also on the dimensionality of the underlying Hilbert space. Our main contribution is clarifying this landscape considerably. We show that in the quantum case unattainability is the general behaviour for all the exponents, already in finite dimension, for a simple null-hypothesis and an alternative hypothesis consisting of only two states. Moreover, the upper bound may be strict even in the infinite-dimensional classical case if the alternative hypothesis contains at least countably infinitely many states. We also prove general attainability results, e.g., for classical adversarial and arbitrarily varying hypothesis testing, and for the quantum case where all states are pure, or the states commute with every state in the opposite hypothesis.

Beyond binary discrimination: wading our way through the pool of equality jurisprudence

Beyond binary discrimination: wading our way through the pool of equality jurisprudence

A Semi-Supervised Modulation Identification in MIMO Systems: A Deep Learning Strategy

Accurate modulation identification of the received signals is undoubtedly a central component in multiple-input multiple-output (MIMO) communication systems, facilitating the demodulation task. This study presents a flexible and semi-supervised deep learning-driven strategy for automatic modulation identification. To this end, the multiclass classification problem is treated as multiple binary discrimination problems to address modulation identification challenges. Here, we merge the features extraction ability of the Generative Adversarial Network (GAN) model and the semi-supervised anomaly detection scheme, the one-class Support Vector Machine (1SVM). Essentially, a single GAN-based 1SVM detector is trained using training data of each class, with the samples of that class as inlier and all other samples as anomalies (i.e., one-vs.-rest). The 1SVM is trained using the features learned by the GAN model. A dataset consisting of three digital modulations (i.e., BFSK, CPFSK, and PAM4) and three analog modulations (i.e., AM-DSB, AM-SSB, and WB-FM), widely used in wireless communications systems, is employed to demonstrate the performance of the considered deep learning-based methods. Compared to Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN)-based 1SVM, the conventional GAN, DBN, and RBM with softmax layer as discriminator layer, the proposed GAN-based 1SVM detector offers superior discrimination performance of modulation types by achieving an averaged accuracy of 0.951 and F1-Score of 0.954. Results also showed that the GAN-1SVM detector dominates the state-of-the-art modulation classification techniques.