Binary Discrimination Research Articles

Machine Learning-Based Tectonic Discrimination Using Basalt Element Geochemical Data: Insights into the Carboniferous–Permian Tectonic Regime of Western Tianshan Orogen

Identifying the tectonic setting of rocks is essential for gaining insights into the geological contexts in which these rocks were formed, aiding in tectonic plate reconstruction and enhancing our comprehensive understanding of the Earth’s history. The application of machine learning algorithms helps identify complex patterns and relationships between big data that may be overlooked by binary or ternary tectonomagmatic discrimination diagrams based on basalt compositions. In this study, three machine learning algorithms, i.e., Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost), were employed to classify the basalts from seven diverse settings, including intraplate basalts, island arc basalts, ocean island basalts, mid-ocean ridge basalts, back-arc basin basalts, oceanic flood basalts, and continental flood basalts. Specifically, for altered and fresh basalt samples, we utilized 22 immobile elements and 35 major and trace elements, respectively, to construct discrimination models. The results indicate that XGBoost demonstrates the best performance in discriminating basalts into seven tectonic settings, achieving accuracies of 85% and 89% for the altered and fresh basalt samples, respectively. A key innovation of our newly developed tectonic discrimination model is the establishment of tailored models for altered and fresh basalts. Moreover, by omitting isotopic features during model construction, the new models offer broader applicability in predicting a wider range of basalt samples in practical scenarios. The classification models were applied to investigate the Carboniferous to Permian evolution in the Western Tianshan Orogen (WTO), revealing that the subduction of Tianshan Ocean ceased at the end of Carboniferous and the WTO evolved into a post-collisional orogenesis during the Permian.

Detection of tea seed oil adulteration based on near-infrared and Raman spectra information fusion

The adulteration of tea seed oil severely harms consumer interests, such as affecting the taste experience and economic losses, creating an urgent need for a rapid, efficient, and non-destructive detection method. In this study, near-infrared and Raman spectroscopy were used to detect the adulteration of tea seed oil with four common edible vegetable oils. After preprocessing the raw spectral data, three variable selection methods namely uninformative variable elimination, competitive adaptive reweighted sampling, and successive projections algorithm were used individually and consecutively to select key spectral variables. And the NIR and Raman characteristic variables were then fused to develop a discrimination model. The results indicate that normalization is the superior preprocessing method and consecutive variable selection methods are generally superior to single ones. The best NIR and Raman models, based on consecutive variable selection methods, achieve accuracy and F1 score of the prediction set of 95.652%, 97.479% and 92.754%, 95.868%, respectively. Spectral information fusion can fully utilize the spectral information, the accuracy and F1 score of the optimal binary adulteration discrimination model based on information fusion for calibration and prediction sets are all 100%. Meanwhile, the accuracy and F1 score of the multiple adulteration discrimination model are 98.225% and 98.932%, respectively. Therefore, the fusion of NIR and Raman spectral information can enable highly accurate discrimination of adulterated oil. The proposed method in this study will aid in developing portable detection devices for tea seed oil adulteration.

DELINEATE-Regurgitation: deep learning for automated assessment of aortic, mitral, and tricuspid regurgitation from echocardiography

Abstract Background Valvular heart diseases, including aortic regurgitation (AR), mitral regurgitation (MR), and tricuspid regurgitation (TR) are significant contributors to cardiovascular morbidity and mortality worldwide. Artificial intelligence (AI) may improve echocardiographic assessment, but no models to date have successfully evaluated valvular regurgitation. Purpose The goal of this study was to develop an AI system to improve the accuracy of echocardiographic AR, MR, and TR interpretation. Methods Complete transthoracic echocardiogram (TTE) studies performed at a single center were split into train (n=65,301), validation (14,018), and test sets (13,746). The Deep Learning for Echo Analysis, Tracking, and Evaluation of Valvular Regurgitation (DELINEATE-Regurgitation) system intakes entire TTE studies, identifies color Doppler clips showing each valve, and yields a study level classification of AR, MR, and TR on a 6-grade scale (none/trace, mild, mild-moderate, moderate, moderate-severe, severe) using the cardiologist interpretation as a reference standard. This system used a hybrid neural network, leveraging the spatiotemporal feature learning capabilities of convolutional neural networks with the sequential processing strengths of transformer networks. The end-to-end hybrid approach allows the model to learn nuanced representations of the data including features within and across color Doppler videos. Model accuracy was assessed using quadratically weighted Cohen’s kappa (k), area under the receiver operator characteristic curve (AUROC) for the detection of both "moderate or greater" and "severe" regurgitation, and AI-cardiologist agreement the 6-grade scale. Additionally, an analysis was conducted using a 4-grade regurgitation scale (none/trace, mild, moderate, and severe) by rolling up intermediate classes (mild-moderate and moderate-severe) into the next higher class for both cardiologist determinations and model predictions. Results The DELINEATE-Regurgitation system demonstrated a high accuracy in the classification of AR (k=0.857), MR (k=0.867), and TR (k=0.847) (Figure 1). DELINEATE predicted the same severity as cardiologists (AR 91.8%, MR 79.9%, TR 77.7%) or within ±1 grade accuracy (AR 99.5%, MR 98.6%, TR 98.6%). The models had excellent binary discrimination in the detection of moderate or greater (AR AUROC 99.4, MR 98.6, TR 98.1) and severe (AR 99.7, MR 99.3, TR 99.6) regurgitation (Figure 2). In the 4-grade scale, the model had exact agreement with cardiologists in 92.3% of AR, 82.4% of MR, and 80.6% of TR cases. Panel adjudication of AI-cardiologist disagreement and correlation with quantitative metrics at higher levels of regurgitation will be presented. Conclusions The DELINEATE-Regurgitation AI system demonstrates a high level of accuracy in the assessment of AR, MR, and TR using color Doppler TTE videos. Future work will focus on automating quantification and developing strategies for optimal clinical deployment.Figure 1 - Confusion MatricesFigure 2 - ROC Curves

Deep-learning model accurately classifies multi-label lung ultrasound findings, enhancing diagnostic accuracy and inter-reader agreement.

Despite the increasing use of lung ultrasound (LUS) in the evaluation of respiratory disease, operators' competence constrains its effectiveness. We developed a deep-learning (DL) model for multi-label classification using LUS and validated its performance and efficacy on inter-reader variability. We retrospectively collected LUS and labeled as normal, B-line, consolidation, and effusion from patients undergoing thoracentesis at a tertiary institution between January 2018 and January 2022. The development and internal testing involved 7580 images fromJanuary 2018and December2020, andthe model's performance was validated on a temporally separated test set (n = 985 imagescollected after January 2021) and two external test sets (n = 319 and 54 images). Two radiologists interpreted LUS with and without DL assistance and compared diagnostic performance and agreement. The model demonstrated robust performancewith AUCs: 0.93 (95% CI 0.92-0.94) for normal, 0.87 (95% CI 0.84-0.89) for B-line, 0.82 (95% CI 0.78-0.86) for consolidation, and 0.94 (95% CI 0.93-0.95) for effusion.The model improved reader accuracy for binary discrimination (normal vs. abnormal; reader 1: 87.5-95.6%, p = 0.004;reader 2: 95.0-97.5%, p = 0.19), and agreement(k = 0.73-0.83, p = 0.01). In conclusion,the DL-based model may assist interpretation, improving accuracy and overcoming operator competence limitationsin LUS.

The Two Word Test as a semantic benchmark for large language models

Large language models (LLMs) have shown remarkable abilities recently, including passing advanced professional exams and demanding benchmark tests. This performance has led many to suggest that they are close to achieving humanlike or “true” understanding of language, and even artificial general intelligence (AGI). Here, we provide a new open-source benchmark, the Two Word Test (TWT), that can assess semantic abilities of LLMs using two-word phrases in a task that can be performed relatively easily by humans without advanced training. Combining multiple words into a single concept is a fundamental linguistic and conceptual operation routinely performed by people. The test requires meaningfulness judgments of 1768 noun-noun combinations that have been rated as meaningful (e.g., baby boy) or as having low meaningfulness (e.g., goat sky) by human raters. This novel test differs from existing benchmarks that rely on logical reasoning, inference, puzzle-solving, or domain expertise. We provide versions of the task that probe meaningfulness ratings on a 0–4 scale as well as binary judgments. With both versions, we conducted a series of experiments using the TWT on GPT-4, GPT-3.5, Claude-3-Optus, and Gemini-1-Pro-001. Results demonstrated that, compared to humans, all models performed relatively poorly at rating meaningfulness of these phrases. GPT-3.5-turbo, Gemini-1.0-Pro-001 and GPT-4-turbo were also unable to make binary discriminations between sensible and nonsense phrases, with these models consistently judging nonsensical phrases as making sense. Claude-3-Opus made a substantial improvement in binary discrimination of combinatorial phrases but was still significantly worse than human performance. The TWT can be used to understand and assess the limitations of current LLMs, and potentially improve them. The test also reminds us that caution is warranted in attributing “true” or human-level understanding to LLMs based only on tests that are challenging for humans.

Geochemical Characterization and Constraints on Provenance, Tectonic setting and Paleoweathering of the Miocene Bhuban Sandstone Exposed in Sakhan Anticline, Tripura Fold Belt, Surma Basin, India

ABSTRACT The petrography of sandstone, major oxides, trace and REE compositions of the Bhuban formation, exposed in the Sakhan Anticline of Tripura Frontal Fold Belt have been studied to determine the source rock, depositional tectonic setup and paleoweathering conditions. The average modal composition of the Bhuban Sandstone (Q89.27F4.40L6.33) classified them as quartz arenite and sub litharenite types. The modal composition data (Q-F-L) indicates a craton interior and recycled source for these sediments and deposited in an active continental basin margin as suggested by the bivariate plot of SiO2 vs. K2O/Na2O. The binary discrimination plot of Hf vs. La/Th suggests acidic and older sedimentary component as source for the studied sandstone. The ternary plot of V-Ni-Th×10 pointed towards felsic igneous provenance. Trace and rare earth elemental ratios, chondrite-normalize REE plot suggests the source of the Bhuban sediments are derived from felsic terrain. The CIA values (66.48-75.41), A-CN-K plot (A=Al2O3, CN=CaO+ Na2O, K=K2O) and distinct depletion of Na2O, CaO, U, Sr and Ba suggests moderate degree of chemical weathering of the source rocks which may indicate humid climatic conditions in the source area.

Multiscale feature-based robust secure diffusion estimation with noisy input over adversarial networks

This paper studies secure distributed estimation over wireless sensor networks in adversarial and noisy environments where a subset of sensors may be invaded by malicious attacks. We build a system model for the problem and prove that the bias-compensation method can resist noisy input but fails in attack defence. To alleviate the impact of attacks, a multiscale feature-based attack detection algorithm is proposed consisting of two main steps. Firstly, a binary discrimination mechanism is proposed to split neighbors of each node into two groups by their relative-state whose perception explores and exploits delicate element-wised features of attack vector. To reduce computational costs, the classifier is designed in a tree shape. Specifically, at each internal tree-node, a generalized correntropy based similarity metric function is developed and compared with an optimal threshold. Secondly, based on features of the classified groups, an absolute-state decider is presented to detect the trust neighbors and thus secure information sharing can be achieved. Simulation results reveal the effectiveness and robustness of our proposed method compared with some state-of-the-art algorithms under various attack forms.

Source depth estimation based on the higher‐order sound field in the deep ocean

AbstractLloyd's mirror effect is a spatial interference phenomenon that results from the coherent combination of direct and surface‐reflected propagation paths. The higher‐order vertical sound intensities of the interference sound field contain source depth information, and the relationship between these higher‐order sound intensities can be employed to estimate the source depth. A method for source depth estimation and qualitative binary source depth discrimination using the 0th‐order sound pressure, as well as the 1st‐ and 2nd‐order sound intensities, was proposed. The numerical simulation results confirmed the ability of the proposed method to approximate the source depth and discriminate between surface and submerged sources without requiring long‐term tracking or knowledge of the ocean environment.

Asymptotic behavior of some multicategory classification methods for high-dimensional data

We consider multicategory extensions of binary discrimination methods via one-versus-one (OVO) or one-versus-rest (OVR) methodologies, focusing on extensions of the binary classification by linear mean difference (MD), support vector machine (SVM), maximal data piling (MDP), and distance weighted discrimination (DWD) via OVO, and the multicategory extension of MD via OVR, in the context of high-dimensional and low sample size (HDLSS) data. The asymptotic behavior of OVO-MD, OVO-SVM, OVO-MDP and OVO-DWD is described when the dimension of the data increases and the sample size is fixed, in terms of the probabilities of correct classification of a new data point, finding sufficient conditions for the correct classification probabilities to converge to one as the dimension approaches infinity. As in the binary case, OVO-MD, OVO-SVM and OVO-MDP have the same asymptotic behavior while OVO-DWD could behave differently. We also consider the asymptotic behavior of the OVR-MD methodology providing necessary and sufficient conditions for a new data point of a given class to be correctly classified with probability tending to one. A simulation experiment is conducted to further compare the methodologies, and consider the four binary methods in the OVR case. We evaluate the performance of the considered methods using a microarray data set.

Characterising the motion and cardiorespiratory interaction of preterm infants can improve the classification of their sleep state.

This study aimed to classify quiet sleep, active sleep and wake states in preterm infants by analysing cardiorespiratory signals obtained from routine patient monitors. We studied eight preterm infants, with an average postmenstrual age of 32.3 ± 2.4 weeks, in a neonatal intensive care unit in the Netherlands. Electrocardiography and chest impedance respiratory signals were recorded. After filtering and R-peak detection, cardiorespiratory features and motion and cardiorespiratory interaction features were extracted, based on previous research. An extremely randomised trees algorithm was used for classification and performance was evaluated using leave-one-patient-out cross-validation and Cohen's kappa coefficient. A sleep expert annotated 4731 30-second epochs (39.4 h) and active sleep, quiet sleep and wake accounted for 73.3%, 12.6% and 14.1% respectively. Using all features, and the extremely randomised trees algorithm, the binary discrimination between active and quiet sleep was better than between other states. Incorporating motion and cardiorespiratory interaction features improved the classification of all sleep states (kappa 0.38 ± 0.09) than analyses without these features (kappa 0.31 ± 0.11). Cardiorespiratory interactions contributed to detecting quiet sleep and motion features contributed to detecting wake states. This combination improved the automated classifications of sleep states.

Binary discrimination through next-to-leading order

Binary discrimination between well-defined signal and background datasets is a problem of fundamental importance in particle physics. With detailed event simulation and the advent of extensive deep learning tools, identification of the likelihood ratio has typically been reserved as a computational problem. However, this approach can obscure overtraining or excessive sensitivity to tuned features of the simulation that may not be well-defined theoretically. Here, we present the first analysis of binary discrimination for signal and background distributions for which their likelihood ratio is infrared and collinear safe, and can therefore be calculated order-by-order in perturbation theory. We present explicit, general formulas for receiver operator characteristic curves and the area under it through next-to-leading order. These results can then establish absolute upper bounds on discrimination performance because any realistic implementation will have measurement errors, undetected particles, or restrictions on fiducial phase space. As a demonstration of this formalism, we apply it to discrimination of highly-boosted Higgs decays from gluon splitting to bottom quarks. Effects at next-to-leading order are first sensitive to the flow of color in the jet and significantly modify discrimination performance at leading-order. In the limit of infinite boost, these events can be perfectly discriminated because only the gluon will radiate at finite angles from the bottom quarks, and we find that large effects persist at energies accessible at the Large Hadron Collider. Next-to-leading order is therefore required to qualitatively understand results using machine-learning methods.

OpenGAN: Open-Set Recognition Via Open Data Generation.

Real-world machine learning systems need to analyze test data that may differ from training data. In K-way classification, this is crisply formulated as open-set recognition, core to which is the ability to discriminate open-set data outside the K closed-set classes. Two conceptually elegant ideas for open-set discrimination are: 1) discriminatively learning an open-vs-closed binary discriminator by exploiting some outlier data as the open-set, and 2) unsupervised learning the closed-set data distribution with a GAN, using its discriminator as the open-set likelihood function. However, the former generalizes poorly to diverse open test data due to overfitting to the training outliers, which are unlikely to exhaustively span the open-world. The latter does not work well, presumably due to the unstable training of GANs. Motivated by the above, we propose OpenGAN, which addresses the limitation of each approach by combining them with several technical insights. First, we show that a carefully selected GAN-discriminator on some real outlier data already achieves the state-of-the-art. Second, we augment the available set of real open training examples with adversarially synthesized "fake" data. Third and most importantly, we build the discriminator over the features computed by the closed-world K-way networks. This allows OpenGAN to be implemented via a lightweight discriminator head built on top of an existing K-way network. Extensive experiments show that OpenGAN significantly outperforms prior open-set methods.

Performance evaluation of brain state discrimination using near-infrared spectroscopy for brain-computer interface: an exploratory case study

<abstract> <p>A new method of environmental control that does not depend on motor functions is eagerly awaited to support independent living for people with severe quadriplegia. In this study, we conducted an exploratory case study of brain state discrimination in a quadriplegic subject to develop a brain-computer interface controlled by a mental task execution. We measured near-infrared spectroscopy (NIRS) signals in a patient with a cervical spinal cord injury while performing mental tasks. A block design with a task and a rest separated by 30 seconds was used to measure brain function. The utilized mental tasks were mental arithmetic and Japanese word chains. Seventeen trials of the NIRS signal were acquired for each task, and 52 samples with 24-dimensional features per trial data were extracted. Random forest was used as the classifier, and the number of correct responses in the binary discrimination of the brain states were calculated by cross-validation. The exact binomial test was used for the statistical analysis, and a two-tailed test with a significance level of 5% was performed. The results showed that the number of correct responses was 15 out of 17 (p = 0.002) for the mental arithmetic task and 14 out of 17 (p = 0.013) for the Japanese word chains task, for an overall accuracy of 85%. These results indicate that this method can discriminate the brain state of a patient with quadriplegia from the NIRS signal. By applying these findings to a brain-computer interface, it will be possible to provide a new means of environmental control for individuals with quadriplegia.</p> </abstract>

Quantifying channel coherence via the norm distance

Quantifying the number of resources contained in a physical object has been one of the core topics in the resource theory of coherence. In this paper, we introduce the dynamical coherence measures based on a class of norms in the classical channel setting. It is proved that it satisfies faithfulness, decreases monotonically under the maximally incoherent superchannels, and is convex. Moreover, we show that it satisfies subadditivity under both the composition and tensor product of channels. Especially, the diamond measure as a special case is discussed in detail, it can reduce to trace norm of coherence, satisfies amortization inequality, and can be calculated efficiently using a semidefinite program. In addition, we introduce the creation-coherent diamond measure and find that neither the detection coherence nor the creation coherence of a channel exceeds the coherence of the channel, which does not exceed the purity of the channel. Second, we introduce the corresponding dephasing measure, which is a dynamical coherence measure under the dephasing-covariant incoherent superchannels. Meanwhile, we also introduce the dephasing diamond measure as a special case. Third, we use the dephasing diamond measure to accurately calculate the coherence values of some important noisy channels such as amplitude damping channel, phase damping channel, and depolarizing channel, respectively, and give the sufficient and necessary conditions for an unital qubit channel with a parameter probability vector to be a coherent channel. Finally, the operational interpretation of our diamond measure in the binary channel discrimination task is investigated.

How far can I extrapolate my species distribution model? Exploring shape, a novel method

Species distribution and ecological niche models (hereafter SDMs) are popular tools with broad applications in ecology, biodiversity conservation, and environmental science. Many SDM applications require projecting models in environmental conditions non‐analog to those used for model training (extrapolation), giving predictions that may be statistically unsupported and biologically meaningless. We introduce a novel method, Shape, a model‐agnostic approach that calculates the extrapolation degree for a given projection data point by its multivariate distance to the nearest training data point. Such distances are relativized by a factor that reflects the dispersion of the training data in environmental space. Distinct from other approaches, Shape incorporates an adjustable threshold to control the binary discrimination between acceptable and unacceptable extrapolation degrees. We compared Shape's performance to five extrapolation metrics based on their ability to detect analog environmental conditions in environmental space and improve SDMs suitability predictions. To do so, we used 760 virtual species to define different modeling conditions determined by species niche tolerance, distribution equilibrium condition, sample size, and algorithm. All algorithms had trouble predicting species niches. However, we found a substantial improvement in model predictions when model projections were truncated independently of extrapolation metrics. Shape's performance was dependent on extrapolation threshold used to truncate models. Because of this versatility, our approach showed similar or better performance than the previous approaches and could better deal with all modeling conditions and algorithms. Our extrapolation metric is simple to interpret, captures the complex shapes of the data in environmental space, and can use any extrapolation threshold to define whether model predictions are retained based on the extrapolation degrees. These properties make this approach more broadly applicable than existing methods for creating and applying SDMs. We hope this method and accompanying tools support modelers to explore, detect, and reduce extrapolation errors to achieve more reliable models.Keywords: environmental novelty, extrapolation, Mahalanobis distance, model prediction, non‐analog environmental data, transferability

Impaired ability to smile in Alzheimer’s disease is associated with reduced brain volume of nucleus accumbens and pallidum, revealed by artificial intelligence

AbstractBackgroundPatients tend to lose the ability to smile during the clinical course of dementia. However, details of such impairment remain obscure presumably due to difficulty of quantifying facial expression. Feature extraction is now automated as a result of recent developments in artificial intelligence (AI). The authors applied a model to quantify impaired smile expression in patients with Alzheimer disease (AD). The relationship between the expression of a smile and subcortical volumes was also investigated.MethodThis study included 280 and 190 participants with AD and with normal cognition (NC), respectively. The faces of the participants were photographed as they smiled or maintained a neutral expression. Subcortical brain volume was assessed in 210 and 90 of those with AD and NC, respectively, using MRI and the FSL‐FIRST algorithm. Datasets of the photographs were prepared with combinations of smiling and neutral expression in NC and AD, smiling in AD and NC, and neutral expression in AD and NC, then binary discrimination proceeded using the VGG‐Face convolutional neural network (CNN).ResultThe accuracy of discriminating a smile from a neutral expression was of 92.3% in NC, and 61.2% in AD, indicating that a considerable proportion of patients with AD have difficulties forming a natural smile. 48.5% of smile AD were classified as negative in NC dataset. The smile/neutral‐NC scores for AD were robustly associated with the volume of the bilateral nucleus accumbens (right, r = 0.51, p = 2.59 × 10−15; left, r = 0.493, p = 2.89 × 10−14) and the bilateral pallidum (right, r = 0.266, p = 0.0000981; left, r = 0.256, p = 0.000174). The accuracy of discriminating between AD and NC was 95.2% with smile and 90.1% with a neutral expression, respectively (p = 0.0045). The neutral‐AD/NC score inversely correlated with the results of the MMSE (p = 1.62 × 10−7), but not with smile/neutral‐NC or smile‐AD/NC scores.ConclusionThe ability to form smile was impaired in AD and associated with nucleus accumbens and pallidum shrinkage. Such impairment enhanced the accuracy of facial discrimination between AD and NC, whereas a neutral expression was associated with cognitive function.

No Sex-Specific Effects of Artificial Selection for Relative Telencephalon Size during Detour Learning and Spatial Discrimination in Guppies (Poecilia reticulata)

Over recent decades, substantial research has focused on fish cognitive evolution to increase our understanding of the evolution of the enormous diversity of cognitive abilities that exists in fishes. One important but understudied aspect of cognitive evolution is sexual dimorphism in cognitive abilities. Sex-specific variation in brain region morphology has been proposed to be an important mechanism in this context. However, it is also common to find sex-specific variation in behavior and cognition without associated differences in brain morphology among the sexes. The telencephalon is the major cognitive center in the vertebrate brain and variation in telencephalon size has been associated with variation in cognition. Here, we utilize recently developed guppy artificial selection lines with ca. 10% differences in relative telencephalon size to investigate whether similar responses to selection of the size of this region may affect cognitive abilities differently in males and females. To that end, we compared two ecologically relevant aspects of cognition, detour learning and binary spatial discrimination. We tested the significance of the interaction between telencephalon size and sex, and we found no sex-specific effects of evolutionary increases in telencephalon size in the cognitive abilities tested. This study indicates that no clear cognitive sex-specific effects occur in response to rapid selection of telencephalon size. We suggest that future research on sexual dimorphism in cognitive abilities in fish could use various cognitive tests and examine telencephalic sub-regions to gain a more comprehensive understanding of their evolution.

Body Perception From Connected Speech: Speaker Height Discrimination from Natural Sentences and Sine-Wave Replicas with and without Pitch.

In addition to language, the human voice carries information about the physical characteristics of speakers, including their body size (height and weight). The fundamental speaking frequency, perceived as voice pitch, and the formant frequencies, or resonators of the vocal tract, are the acoustic speech parameters that have been most intensely studied for perceiving a speaker's body size. In this study, we created sine-wave (SW) replicas of connected speech (sentences) uttered by 20 male and 20 female speakers, consisting of three time-varying sinusoidal waves matching the frequency pattern of the first three formants of each sentence. These stimuli only provide information about the formant frequencies of a speech signal. We also created a new experimental condition by adding a sinusoidal replica of the voice pitch of each sentence. Results obtained from a binary discrimination task revealed that (a) our SW replicas provided sufficient useful information to accurately judge the speakers' body height at an above chance level; (b) adding the sinusoidal replica about the voice pitch did not significantly increase accuracy; and (c) stimuli from female speakers were more informative for body height detection and allowed higher perceptual accuracy, due to a stronger correlation between formant frequencies and actual body height than stimuli from male speakers.

Discriminating chert origins using machine‐learning approaches

Automatic techniques have not been applied in the geochemical discrimination of marine, terrestrial and hydrothermal cherts, which is critical to retrieving the paleoenvironmental information of ancient sedimentary basins. Here, we applied three supervised machine‐learning methods to analyse the labelled geochemical compositional data (32 major and trace elements) of cherts, including the support vector machine (SVM), sparse multinomial regression and linear discrimination analysis. Our results show that these machine‐learning methods can successfully discriminate different chert types, as the lowest classification score is 79%. Among the methods, the SVM is the most powerful approach (classification score 88%, on average), even though it is hard to be geochemically interpreted. Sparse multinomial regression and linear discrimination analysis are also efficient approaches (mean classification score 84%), which can be used to extract the important elements and the most representative sample for each chert type. Especially, the linear discrimination analysis can construct binary discrimination diagram superposed with biplot rays and posterior probability‐based decision boundaries, which could be quickly applied and explained by other researchers. Furthermore, the successful discrimination of different chert types indicates that cherts derived from different silica sources have different geochemical signatures, albeit mixing between different sources of silica during chert formation is common. Last, the general geochemical features of each chert type were summarised based on geochemical information extracted by machine‐learning methods and previous geochemical studies.

Near infrared spectroscopy discriminates glutinous and non-glutinous sorghum using an approach based on typical samples and direct calibration

Sorghum has a long history of cultivation and is an important food and economic crop. It can be divided into glutinous and non-glutinous varieties according to the starch structure and content. Rapid discrimination between the two would help the winemaking, feed, and food industries complete purchase pricing, ingredients, and quality control. In this study, 38 different samples were acquired, including 14 glutinous and 24 non-glutinous sorghum samples. Near infrared (NIR) spectra of glutinous and non-glutinous sorghum, pre-treated using the standard normal variable (SNV) transformation were found to have slightly different absorbances in the combination and first overtone bands. Based on the distribution of the starch-related and hydrogen-containing groups in the NIR region, it was concluded that glutinous sorghum has more C-O and C-C groups than non-glutinous sorghum. This study proposes an approach based on typical samples and direct calibration (TSDC) for binary discrimination. The TSDC approach consists of three functions. First, typical samples of two types of samples were selected. Second, typical type samples are used as dependent variables, predicted samples are used as independent variables, and formula regression is used to obtain fitted coefficients. Finally, if the formula regression model has no solution or the fitted coefficient is 1, typical type samples are reselected. Using the TSDC approach, discrimination accuracy can achieve 100% accuracy at 0.5 threshold. A larger threshold can be set to select better type characteristic predicted samples for discrimination. The TSDC approach can build excellent model through real relevance between the NIR spectra and the properties of interest, and the use of typical type samples greatly reduces modeling work compared with complex pattern recognition methods, especially for highly varied agricultural products. Therefore, it can efficiently propel the application and development of NIR detection technology. More research is required to apply the TSDC approach to three types of samples.