Linear Discriminant Analysis Model Research Articles

Non-Destructive Assessment of Stone Heritage Weathering Types Based on Machine Learning Method Using Hyperspectral Data

Abstract. Stone cultural heritage is exposed to various environments, resulting in a diverse range of weathering types. The identification of these weathering types is vital for targeted conservation efforts. In this paper, a weathering type classification method based on hyperspectral imaging technology is proposed. Firstly, fresh sandstones are collected from Yungang Grottoes to carry out the simulated weathering experiments, including freeze-thaw cycles and wet-dry cycles with acid, alkali and salt solutions. Subsequently, the hyperspectral imaging system was used to collect the visible-near-infrared (VNIR) and short-wave infrared (SWIR) images of the sandstone samples with different weathering types and degrees. The surface spectral reflectance of sandstone samples with different weathering types were used as training data, with weathering types serving as the labels. Support vector machine (SVM), K-nearest neighbour (KNN), linear discriminant analysis (LDA) and random forest (RF) were used to establish weathering type classification models. The results show that the SVM model and LDA model based on both VNIR and SWIR spectra exhibit outstanding performance, with a best accuracy of 0.994. The framework proposed in this paper facilitates rapid and non-contact assessment of the weathering types of the superficial layers of stone cultural heritage, thereby supporting more targeted conservation work.

Breaking the Barriers: Machine-Learning-Based c-RASAR Approach for Accurate Blood-Brain Barrier Permeability Prediction.

The intricate nature of the blood-brain barrier (BBB) poses a significant challenge in predicting drug permeability, which is crucial for assessing central nervous system (CNS) drug efficacy and safety. This research utilizes an innovative approach, the classification read-across structure-activity relationship (c-RASAR) framework, that leverages machine learning (ML) to enhance the accuracy of BBB permeability predictions. The c-RASAR framework seamlessly integrates principles from both read-across and QSAR methodologies, underscoring the need to consider similarity-related aspects during the development of the c-RASAR model. It is crucial to note that the primary goal of this research is not to introduce yet another model for predicting BBB permeability but rather to showcase the refinement in predicting the BBB permeability of organic compounds through the introduction of a c-RASAR approach. This groundbreaking methodology aims to elevate the accuracy of assessing neuropharmacological implications and streamline the process of drug development. In this study, an ML-based c-RASAR linear discriminant analysis (LDA) model was developed using a dataset of 7807 compounds, encompassing both BBB-permeable and -nonpermeable substances sourced from the B3DB database (freely accessible from https://github.com/theochem/B3DB), for predicting BBB permeability in lead discovery for CNS drugs. The model's predictive capability was then validated using three external sets: one containing 276,518 natural products (NPs) from the LOTUS database (accessible from https://lotus.naturalproducts.net/download) for data gap filling, another comprising 13,002 drug-like/drug compounds from the DrugBank database (available from https://go.drugbank.com/), and a third set of 56 FDA-approved drugs to assess the model's reliability. Further diversifying the predictive arsenal, various other ML-based c-RASAR models were also developed for comparison purposes. The proposed c-RASAR framework emerged as a powerful tool for predicting BBB permeability. This research not only advances the understanding of molecular determinants influencing CNS drug permeability but also provides a versatile computational platform for the rapid assessment of diverse compounds, facilitating informed decision-making in drug development and design.

A New Sub-Class Linear Discriminant for Miniature Spectrometer Based Food Analysis

The well-known and extensively studied Linear Discriminant Analysis (LDA) can have its performance lowered in scenarios where data is not homoscedastic or not Gaussian. That is, the classical assumptions when LDA models are built are not applicable, and consequently LDA projections would not be able to extract the needed features to explain the intrinsic structure of data and for classes to be separated. As with many real word data sets, data obtained using miniature spectrometers can suffer from such drawbacks which would limit the deployment of such technology needed for food analysis. The solution presented in the paper is to divide classes into subclasses and to use means of sub classes, classes, and data in the suggested between classes scatter metric. Further, samples belonging to the same subclass are used to build a measure of within subclass scatterness. Such a solution solves the shortcoming of the classical LDA. The obtained results when using the proposed solution on food data and on general machine learning datasets show that the work in this paper compares well to and is very competitive with similar sub-class LDA algorithms in the literature. An extension to a Hilbert space is also presented; and the kernel version of the presented solution can be fused with its linear counter parts to yield improved classification rates.

Early detection of infestation by mustard aphid, vegetable thrips and two-spotted spider mite in bok choy with deep neural network (DNN) classification model using hyperspectral imaging data

Although exclusion measures (e.g., air filters, biosecurity practices) can be employed to prevent occurrence of pest outbreaks, indoors vegetable farms in Singapore are still susceptible to various arthropod pests. Due to strong interest from the industry to pursue pesticide-free production, indoors pest management is often focused on early detection for timely containment and eradication, implying the importance of robust and vigorous pest monitoring programs. In recent years, application of machine vision technologies, especially hyperspectral imaging (HSI), has been studied for their capacity to early detect pest infestation. However, there is a lack of studies conducted in actual indoor environments and on multiple arthropod pests. Thus, this study aimed to non-destructively collect hyperspectral data of bok choy Brassica rapa subspecies chinensis which were healthy or infested with either mustard aphids Lipaphis erisymi, vegetable thrips Echinothrips americanus or two-spotted spider mites Tetranichus urticae in indoor environment to build deep neural network (DNN) classification model for early detection. Based on HSI data of control and infested plants collected daily over a period of two weeks, we found that point percentage change (PPC) values associated with leaf reflectance in 420–440 nm, 500–520 nm, 620–637 nm, 720–800 nm, and 850 nm were sensitive to infestation by the mentioned arthropod pests. Deep Neural Network (DNN) classification models trained on collected HSI data were found to outperform Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) classification models. DNN models achieved 92.8 ± 0.4 % overall classification accuracy across all days. As early as two days after infestation, DNN models could achieved classification precision values of 96.4 %, 96.9 %, 93.9 % and 100 % for control plants and plants infested with either aphids, spider mites or thrips respectively. These results highlight the feasibility of multiclass early detection of different arthropod pests and the potential of HSI system coupled with DNN classification as an autonomous plant health monitoring tool in indoor crop production.

Detection of Maize Mold Based on a Nanocomposite Colorimetric Sensor Array under Different Substrates.

This study developed a novel nanocomposite colorimetric sensor array (CSA) to distinguish between fresh and moldy maize. First, the headspace solid-phase microextraction gas chromatography-mass spectrometry (HS-SPME-GC/MS) method was used to analyze volatile organic compounds (VOCs) in fresh and moldy maize samples. Then, principal component analysis and orthogonal partial least-squares discriminant analysis (OPLS-DA) were used to identify 2-methylbutyric acid and undecane as key VOCs associated with moldy maize. Furthermore, colorimetric sensitive dyes modified with different nanoparticles were employed to enhance the dye properties used in the nanocomposite CSA analysis of key VOCs. This study focused on synthesizing four types of nanoparticles: polystyrene acrylic (PSA), porous silica nanospheres (PSNs), zeolitic imidazolate framework-8 (ZIF-8), and ZIF-8 after etching. Additionally, three types of substrates, qualitative filter paper, polyvinylidene fluoride film, and thin-layer chromatography silica gel, were comparatively used to fabricate nanocomposite CSA combining with linear discriminant analysis (LDA) and K-nearest neighbor (KNN) models for real sample detection. All moldy maize samples were correctly identified and prepared to characterize the properties of the CSA. Through initial testing and nanoenhancement of the chosen dyes, four nanocomposite colorimetric sensitive dyes were confirmed. The accuracy rates for LDA and KNN models in this study reached 100%. This work shows great potential for grain quality control using CSA methods.

Rethinking Sweetener Discovering: Multiparameter Modeling of Molecular Docking Results between the T1R2-T1R3 Receptor and Compounds with Different Tastes.

Molecular docking has been widely applied in the discovery of new sweeteners, yet the interpretation of computational results sometimes remains difficult. Here, the interaction between the T1R2-T1R3 sweet taste receptor and 66 tasting compounds, including 26 sweet, 19 bitter, and 21 sour substances was investigated by batch molecular docking processes. Statistical analysis of the docking results generated two novel methods of interpreting taste properties. Quantitative correlation between relative sweetness (RS) and docking results created a multiparameter model to predict sweetness intensity, whose correlation coefficient r = 0.74 is much higher than r = 0.17 for the linear correlation model between sweetness and binding energy. The improved correlation indicated that docking results besides binding energy contain undiscovered information about the ligand-protein interaction. Qualitative discriminant analysis of different tasting molecules generated an uncorrelated linear discriminant analysis (UDLA) model, which achieved an overall 93.1% accuracy in discriminating the taste of molecules, with specific accuracy for verifying sweet, bitter, and sour compounds reaching 88.0%, 92.1%, and 100%. These unprecedented models provide a unique perspective for interpreting computational results and may inspire future research on sweetener discovery.

Near-infrared spectroscopy and multivariate analysis as real-time monitoring strategy of TEMPO-mediated oxidation of cellulose fibers from different feedstocks

The regioselective oxidation of the primary hydroxyl groups of cellulose, usually mediated by the (2,2,6,6-tetramethylpiperidin-1-yl)oxyl radical (TEMPO), is highly popular in the scientific literature. However, the lack of efficient monitoring techniques imposes a severe limitation to its upscaling. This work involves a portable, user-friendly near-infrared spectroscopy device, optimized preprocessing techniques, and multivariate calibration to quickly estimate the carboxyl group content of modified cellulose (i.e., the extent of the oxidation). For that, bleached pulps from eucalyptus, pine, hemp, and sisal were submitted to TEMPO-mediated oxidation, varying the dosage of spent oxidizer (NaClO) and thus attaining samples of different values of carboxyl group content. These values were related to near-infrared spectra (908–1676 nm) by Partial Least Squares regression, yielding cross-validation coefficients (RCV2) above 0.97 for wood pulps, 0.95 for sisal pulp, and 0.91 for hemp pulp. Based on the residual prediction deviation, the model for each pulp was found to show good predictability. Nonetheless, the overall regression model, comprising the four different materials, was unreliable. In light of this, spectra were submitted to principal components analysis (PCA), hinting that pulps could be classified in terms of their hemicellulose to cellulose ratio. Considering all the statistical parameters, the overall proposal presented here begins with a PCA—Linear Discriminant Analysis model to classify the sample by its fiber type, subsequently selecting a specific regression model for that class. Overall, the presented models in this work allow the determination of the extent of oxidation of different cellulosic feedstocks, expressed as carboxyl content, in a fast and simple approach using a benchtop near-infrared equipment.

Field-based measurement tools to distinguish clonal Typha taxa and estimate biomass: a resource for conservation and restoration.

Two species of clonal Typha [T. latifolia (native) and T. angustifolia (exotic)] hybridize to form the highly invasive, heterotic (high vigor) T. × glauca in North American wetlands leading to increased primary production, litter accumulation, and biodiversity loss. Conservation of T. latifolia has become critical as invasive Typha has overwhelmed wetlands. In the field, Typha taxa identification is difficult due to subtle differences in morphology, and molecular identification is often unfeasible for managers. Furthermore, improved methods to non-destructively estimate Typha biomass is imperative to enhance ecological impact assessments. To address field-based Typha ID limitations, our study developed a predictive model from 14 Typha characters in 7 northern Michigan wetlands to accurately distinguish Typha taxa (n = 33) via linear discriminant analysis (LDA) of molecularly identified specimens. In addition, our study developed a partial least squares regression (PLS) model to predict Typha biomass from field collected measurements (n = 75). Results indicate that two field measurements [Leaf Counts, Longest Leaf] can accurately differentiate the three Typha taxa and advanced-generation hybrids. The LDA model had a 100% correct prediction rate of T. latifolia. The selected PLS biomass prediction model (sqrt[Typha Dry Mass] ~ log[Ramet Area at 30 cm] + Inflorescence Presence + Total Ramet Height + sqrt[Organic Matter Depth]) improved upon existing simple linear regression (SLR) height-to-biomass predictions. The rapid field-based Typha identification and biomass assessment tools presented in this study advance targeted management for regional conservation of T. latifolia and ecological restoration of wetlands impacted by invasive Typha taxa.

In-Database Data Imputation

Missing data is a widespread problem in many domains, creating challenges in data analysis and decision making. Traditional techniques for dealing with missing data, such as excluding incomplete records or imputing simple estimates (e.g., mean), are computationally efficient but may introduce bias and disrupt variable relationships, leading to inaccurate analyses. Model-based imputation techniques offer a more robust solution that preserves the variability and relationships in the data, but they demand significantly more computation time, limiting their applicability to small datasets. This work enables efficient, high-quality, and scalable data imputation within a database system using the widely used MICE method. We adapt this method to exploit computation sharing and a ring abstraction for faster model training. To impute both continuous and categorical values, we develop techniques for in-database learning of stochastic linear regression and Gaussian discriminant analysis models. Our MICE implementations in PostgreSQL and DuckDB outperform alternative MICE implementations and model-based imputation techniques by up to two orders of magnitude in terms of computation time, while maintaining high imputation quality.

A Study of High-Frequency Noise for Microplastics Classification Using Raman Spectroscopy and Machine Learning.

Given the growing urge for plastic management and regulation in the world, recent studies have investigated the problem of plastic material identification for correct classification and disposal. Recent works have shown the potential of machine learning techniques for successful microplastics classification using Raman signals. Classification techniques from the machine learning area allow the identification of the type of microplastic from optical signals based on Raman spectroscopy. In this paper, we investigate the impact of high-frequency noise on the performance of related classification tasks. It is well-known that classification based on Raman is highly dependent on peak visibility, but it is also known that signal smoothing is a common step in the pre-processing of the measured signals. This raises a potential trade-off between high-frequency noise and peak preservation that depends on user-defined parameters. The results obtained in this work suggest that a linear discriminant analysis model cannot generalize properly in the presence of noisy signals, whereas an error-correcting output codes model is better suited to account for inherent noise. Moreover, principal components analysis (PCA) can become a must-do step for robust classification models, given its simplicity and natural smoothing capabilities. Our study on the high-frequency noise, the possible trade-off between pre-processing the high-frequency noise and the peak visibility, and the use of PCA as a noise reduction technique in addition to its dimensionality reduction functionality are the fundamental aspects of this work.

On-chip growth of one-dimensional In2O3 nanostructures by vapor trapping method and their comparative gas-sensing performance

In this study, we use the chemical vapour deposition trapping method to grow various one-dimensional (1D) indium oxide (In2O3) nanostructures, namely nanorods (NRs), nanoneedles (NNs), and nanowires (NWs). The structural and morphological characteristics of the synthesised nanostructures are analysed using x-ray diffraction and scanning electron microscopy. By comparing the morphology of In2O3 under different growth conditions with previous research findings, we investigate the growth mechanism and the role of gold catalysts. The In2O3 sensor presented a good selection for C2H5OH gas. The NWs-based sensor exhibits a superior response and faster response-recovery rates (50%, and 49 s/343 s) in comparison to the NRs- (45%, and 35 s/339 s) and NNs-based sensors (8%, and 70 s/496 s) when exposed to 200 ppm C2H5OH at 400 °C. Besides, the sensors exhibited good stability under the switch-off reversible cycle. The linear discriminant analysis (LDA) model was effectively used in classifying target gases such as 25–200 ppm C2H5OH, NH3, and CO at the temperature of 350 °C–450 °C. We attribute the NWs-based sensor’s better gas-sensing performance to its favourable morphology for gas diffusion and modulation of depletion depth.

Vegetation and Dormancy States Identification in Coniferous Plants Based on Hyperspectral Imaging Data

Conifers are a common type of plant used in ornamental horticulture. The prompt diagnosis of the phenological state of coniferous plants using remote sensing is crucial for forecasting the consequences of extreme weather events. This is the first study to identify the “Vegetation” and “Dormancy” states in coniferous plants by analyzing their annual time series of spectral characteristics. The study analyzed Platycladus orientalis, Thuja occidentalis and T. plicata using time series values of 81 vegetation indices and 125 spectral bands. Linear discriminant analysis (LDA) was used to identify “Vegetation” and “Dormancy” states. The model contained three to four independent variables and achieved a high level of correctness (92.3 to 96.1%) and test accuracy (92.1 to 96.0%). The LDA model assigns the highest weight to vegetation indices that are sensitive to photosynthetic pigments, such as the photochemical reflectance index (PRI), normalized PRI (PRI_norm), the ratio of PRI to coloration index 2 (PRI/CI2), and derivative index 2 (D2). The random forest method also diagnoses the “Vegetation” and “Dormancy” states with high accuracy (97.3%). The vegetation indices chlorophyll/carotenoid index (CCI), PRI, PRI_norm and PRI/CI2 contribute the most to the mean decrease accuracy and mean decrease Gini. Diagnosing the phenological state of conifers throughout the annual cycle will allow for the effective planning of management measures in conifer plantations.

Qingxiangxing Baijiu sensory quality grade classification by 1H NMR and GC combined with multivariate statistical analysis

The traditional uniform artificial sensory evaluation makes it difficult to standardize the classification of different sensory quality grades of Baijiu. In this study, a total of 92 authentic Qingxiangxing Baijiu samples with 3 sensory quality grades were carefully collected. Gas chromatography (GC) was used to determine 46 main flavor components and proton nuclear magnetic resonance (1H NMR) spectroscopy was employed to obtain hydrogen atom characteristic information of organic compounds. The principal component analysis (PCA), k-nearest neighbor (KNN) and linear discriminant analysis (LDA) models were conducted and fully validated by internal leave-one-out cross validation (LOOCV) and external repeated double random cross validation (RDRCV). The sensory quality grades of Qingxiangxing Baijiu were effectively classified by using GC and 1H NMR techniques coupled with PCA/KNN analysis with the averaged accuracy higher than 80%. In addition, synthetic minority oversampling technique (SMOTE) algorithm was successfully used to address the model overfitting problem caused by an unbalanced sample composition. This study demonstrated that 1H NMR and GC combined with multivariate statistical analysis were effective for sensory quality classification of Qingxiangxing Baijiu.

Discriminant analysis using MRI asymmetry indices and cognitive scores of women with temporal lobe epilepsy or schizophrenia.

This study aims to assess the diagnostic power of brain asymmetry indices and neuropsychological tests for differentiating mesial temporal lobe epilepsy (MTLE) and schizophrenia (SCZ). We studied a total of 39 women including 13 MTLE, 13 SCZ, and 13 healthy individuals (HC). A neuropsychological test battery (NPT) was administered and scored by an experienced neuropsychologist, and NeuroQuant (CorTechs Labs Inc., San Diego, California) software was used to calculate brain asymmetry indices (ASI) for 71 different anatomical regions of all participants based on their 3D T1 MR imaging scans. Asymmetry indices measured from 10 regions showed statistically significant differences between the three groups. In this study, a multi-class linear discriminant analysis (LDA) model was built based on a total of fifteen variables composed of the most five significantly informative NPT scores and ten significant asymmetry indices, and the model achieved an accuracy of 87.2%. In pairwise classification, the accuracy for distinguishing MTLE from either SCZ or HC was 94.8%, while the accuracy for distinguishing SCZ from either MTLE or HC was 92.3%. The ability to differentiate MTLE from SCZ using neuroradiological and neuropsychological biomarkers, even within a limited patient cohort, could make a substantial contribution to research in larger patient groups using different machine learning techniques.

Vibration-based structural damage localization through a discriminant analysis strategy with cepstral coefficients

Over the past decades, Vibration-Based Methods (VBMs) have consistently exhibited exceptional effectiveness in the field of Structural Health Monitoring when it comes to assessing structural damage in both civil and mechanical structures. Recently, the progress made in data-driven strategies for localizing structural damage through the VBMs has resulted in substantial benefits. These advanced strategies not only enable an efficient decision-making process but also provide precise identification of repair locations for monitored structures. Importantly, they achieve this without the inherent complexity and computational burden typically associated with traditional model-based methods. In this study, an innovative data-driven method for localizing and quantifying structural damage is proposed. The method is developed on the basis of the principles of Linear Discriminant Analysis (LDA) and a newly devised modeling strategy that utilizes the power cepstral coefficients extracted from the structural acceleration response. The developed LDA model is able to highlight the local structural characteristics (i.e., mode shape-related information) embedded in the cepstral coefficients in the LDA latent space. Based on the highlighted local characteristics of the cepstral coefficients, a statistical pattern recognition strategy is proposed to effectively conduct the quantification and localization of structural damage. The proposed damage localization method is designed to function in a completely unsupervised-learning manner, which eliminates the requirement for the model to have access to any prior knowledge or information regarding structural damage during the training phase. The proposed method has been validated by both numerical simulations and experimental data.

Classification of English vowels in terms of Cypriot Greek categories: The role of acoustic similarity between L1 and L2 sounds

Abstract Previous evidence has suggested that acoustic similarity between first language (L1) and second language (L2) sounds is an accurate indicator of the speakers’ L2 classification patterns. This study investigates this assumption by examining how speakers of an under-researched language, namely Cypriot Greek, classify L2 English vowels in terms of their L1 categories. The experimental protocol relied on a perception and a production study. For the purpose of the production study, two linear discriminant analysis (LDA) models, one with both formants and duration (FD) and one with only formants (F) as input, were used to predict this classification; the models included data from both English and Cypriot Greek speakers. The perception study consisted of a classification task performed by adult Cypriot Greek advanced speakers of English who permanently resided in Cyprus. The results demonstrated that acoustic similarity was a relatively good predictor of speakers’ classification patterns as the majority of L2 vowels classified with the highest proportion were predicted with success by the LDA models. In addition, the F model was better than the FD model in predicting the full range of responses. This shows that duration features were less important than formant features for the prediction of L2 vowel classification.

Directly Self-Assembly of Aligned Ag NWs Films at the Air-Water Interface for the Detection of Pathogens in Artificial Breath Aerosols.

Exhaled aerosols from humans, containing various pathogens, are crucial for early disease diagnosis. However, the traditional pathogen detection methods, such as polymerase chain reaction, are often slow and cumbersome due to complex sampling and procedures. This study introduces a novel, direct, and label-free detection method for pathogens in respiratory aerosols, utilizing a highly aligned silver nanowire (Ag NW) film combined with a filter membrane (Ag NWs@filter) as a surface-enhanced Raman spectroscopy-active substrate. A large-scale, ordered silver nanowire film was developed through a simplified self-assembly process. This process eliminates the need for an organic phase and complex surface modifications of Ag NWs, which are common in other preparation methods. Subsequently, the fabricated Ag NWs@filter demonstrated its capability to continuously capture and efficiently preconcentrate pathogens from aerosols, achieving a remarkable detection limit of 3 × 103 CFU/mL, demonstrated using Escherichia coli (E. coli) as a model pathogen. Moreover, the classification between E. coli and Pseudomonas aeruginosa achieved an overall accuracy of 96.5% by the principal component analysis with linear discriminant analysis models. The success of this sensing strategy illustrates its potential in detecting and identifying a variety of biomarkers present in respiratory aerosols, marking a significant step forward in the field of pathogen detection.

Testing the accuracy of the SexEst software for sex estimation in a modern Greek sample

AbstractSex estimation from human skeletal remains is fundamental in osteoarcheology and forensic anthropology. The increasing availability of reference skeletal collections across the world has allowed the development of morphological and metric methods for skeletal sex estimation, some of which may be implemented in specialized computer software. The present study aims to evaluate the freely available SexEst software, which utilizes cranial and postcranial measurements, and different classification models for sex estimation, on a contemporary Greek population comprising of 227 (126 males and 101 females) adult individuals. After the calculation of intra‐observer error to assess the repeatability of the measurements, the proposed variables were tested for classification accuracy individually and in different combinations. Based on the results, the postcranial models outperformed the cranial ones in all cases and can be adequately applied on a Greek population sample. The light gradient boosting (LGB) algorithm yielded the highest correct classification rates when no missing values exist, while the linear discriminant analysis (LDA) models should only be used when dealing with missing data. The highest classification accuracy for a 0.65 posterior probability threshold was reached when utilizing a combination of postcranial variables (89.67%), while the lowest was achieved with the cranial measurement “Glabella‐occipital length” (45.00%). The same models yielded the highest and lowest accuracy for a 0.5 probability threshold, with values of 92.96% and 67.73%, respectively. Combining variables yielded higher accuracies in both skeletal regions, suggesting that the software would be more helpful in cases of intact skeletons. The loss of classification accuracy due to population specificity further corroborates the need to include different ancestries in sex estimation software.

One-shot random forest model calibration for hand gesture decoding

Objective. Most existing machine learning models for myoelectric control require a large amount of data to learn user-specific characteristics of the electromyographic (EMG) signals, which is burdensome. Our objective is to develop an approach to enable the calibration of a pre-trained model with minimal data from a new myoelectric user. Approach. We trained a random forest (RF) model with EMG data from 20 people collected during the performance of multiple hand grips. To adapt the decision rules for a new user, first, the branches of the pre-trained decision trees were pruned using the validation data from the new user. Then new decision trees trained merely with data from the new user were appended to the pruned pre-trained model. Results. Real-time myoelectric experiments with 18 participants over two days demonstrated the improved accuracy of the proposed approach when compared to benchmark user-specific RF and the linear discriminant analysis models. Furthermore, the RF model that was calibrated on day one for a new participant yielded significantly higher accuracy on day two, when compared to the benchmark approaches, which reflects the robustness of the proposed approach. Significance. The proposed model calibration procedure is completely source-free, that is, once the base model is pre-trained, no access to the source data from the original 20 people is required. Our work promotes the use of efficient, explainable, and simple models for myoelectric control.

Rapid determination of alprazolam in gin tonic cocktails based on the coupling of IR spectroscopy and chemometrics: A feasibility study

“Drug-facilitated sexual assault" (DFSA) is a sexual assault perpetrated against a person rendered unconscious by a substance that changes her/his physical and/or mental condition, such as ethanol or drugs. Several active pharmaceutical ingredients, whether used alone or with alcoholic beverages, can produce anterograde amnesia and loss of inhibition. The most common pharmaceuticals found in DFSAs are GHB (-hydroxybutyric acid), benzodiazepines (Valium, Xanax, or Roipnol), antidepressants (Venlafaxine), muscle relaxants (cyclobenzaprine), antihistamines, sleeping pills (diphenhydramines), hallucinogens, and opioids. Biological samples are typically examined in cases of suspected DFSA; however, occasionally, samples are sent to labs a long period after being collected, jeopardizing the accuracy of the analysis. As a result, in recent years, the focus has shifted to directly detecting the presence of drugs in alcoholic beverages. In light of this, the purpose of the current study is to build a FT-IR-based approach for the determination of alprazolam in a common long drink (gin and tonic). To achieve this goal, pure (Class Pure) and spiked gin tonics (Class Spiked) were analyzed by Fourier-transform infrared spectroscopy (FT-IR). Afterward, two classifiers were used: Sequential preprocessing through ORThogonalization Linear Discriminant Analysis (SPORT-LDA) and Soft Independent Modeling of Class Analogies (SIMCA). Both approaches provided good results: SPORT-LDA achieved a 95% and a 98% accuracy rate (on the external test set of samples) for spiked and pure cocktails, respectively. This corresponds to the misclassification of 5 spiked and 1 pure drinks. The SIMCA model of class pure achieved 98.2% and 91.7% of specificity and sensitivity, respectively, coinciding with 55 pure samples (over 60) correctly accepted and 2 (over 110) erroneously rejected by the model. In conclusion, the SIMCA model of class pure seems preferable, because it minimizes the type II error. Eventually, the study was circumscribed to the spiked cocktails and a novel SPORT model was used to quantify alprazolam in spiked cocktails. This provided noteworthy results, in fact, it led to a Root Mean Square Error in Prediction (RMSEP) of 0.95, and a R2pred of 0.98.