Classification Rate Research Articles

Enhancement of loop-mediated isothermal amplification (LAMP) with guanidine hydrochloride for the detection of Streptococcus equi subspecies equi (Strangles).

Streptococcus equi subspecies equi, commonly referred to as "strangles", poses a significant biosecurity challenge across equine farms worldwide. The continuous prevalence and highly transmissibility of strangles necessitates a rapid and accurate diagnostic procedure. However, current "gold-standard" techniques, such as cultures and quantitative polymerase chain reaction (qPCR), are unreliable or inaccessible, and require lengthy periods between sample collection and results. Moreover, the lack of a standardized detection protocol can lead to variations in results. This study aimed to develop a reproducible and field-deployable diagnostic assay to detect strangles in real-time. Utilising the rapid technique loop-mediated isothermal amplification (LAMP), we developed an assay targeting a conserved region of the S. equi-specific M gene (SeM). Additionally, we optimised our assay with guanidine hydrochloride (GuHCl) to enhance the assay's performance and detection capabilities. The Str-LAMP was able to detect S. equi within 13 minutes and 20 seconds for both synthetic DNA and clinical isolates, with a limit of detection (LOD) of 53 copies/µl. Our assay demonstrated high repeatability with the inter-coefficient of variation ranging from 0.17% to 3.93%. Furthermore, the clinical sensitivity and specificity was calculated at 91.3% and 93.3%, respectively, with a correct classification rate of 91.8%. The implementation of this newly developed strangles assay can be employed as an efficient aid for in-field surveillance programs. The assay's reproducibility can allow for equine managers to undertake routine self-surveillance on their properties, without the requirement of specialised training. The Str-LAMP assay has the potential to be a valuable tool to help mitigate potential strangles outbreaks.

HCO-RLF: Hybrid classification optimization using recurrent learning and fuzzy for COVID-19 detection on CT images

COVID-19 infection detection through initial lesion classification provides early diagnosis and prevents breathing difficulties. Detecting the infectious part of the lungs using computerized tomography (CT) images has become an instantaneous detection method. In this article, a Hybrid Classification Optimization (HCO) using Recurrent Leaning and Fuzzy (RLF) is proposed. The neural network classifies infected and non-infected regions using pixel distributions and their variations. This is performed by identifying missing features and training the recurrent network using regional differences. Based on the feature availability, recurrent learning classifies the region through the input dataset and recurrent training correlation. The fuzzy predicts missing features through substituted derivatives obtained between wide ranges of variations. In this process, the maximum fuzzy derivatives for feature substitution are used for infected region prediction. The least fuzzy derivatives are prevented from the training layer to reduce false rates in region classification. This joint process improves the training consistency to leverage the detection and region classification accuracies. The proposed HCO-RLF improves detection and classification accuracy, and precision by 11.96 %, 9.98 %, and 13.42 % for the varying classification rates. Besides, the results are obtained in comparison with the existing DR-MIL, DSAE, and BS-FSA methods discussed later in the article.

Fractal properties of 4-point interpolatory subdivision schemes and wavelet scattering transform for signal classification

Wavelet scattering is a recent time-frequency transform that shares the convolutional architecture with convolutional neural networks, but it allows for a faster training and it often requires smaller training sets. It consists of a multistage non-linear transform that allows us to compute the deep spectrum of a signal by cascading convolution, non-linear operator and pooling at each stage, resulting a powerful tool for signal classification when embedded in machine learning architectures. One of the most delicate parameters in convolutional architectures is the temporal sampling that strongly affects the computational load as well as the classification rate. In this paper the role of sampling in the wavelet scattering transform is studied for signal classification purposes. In particular, the role of subdivision schemes in properly compensating the information lost when using sampling at each stage of the transform is investigated. Preliminary experimental results show that, starting from coarse grids, interpolatory subdivision schemes reproduce copies of the original scattering coefficients at a fixed full grid that still represent distinctive features for signal classes. In fact, thanks to the ability of the scheme in reproducing similar fractal properties of the transform through an efficient iterative refinement procedure, the reproduced coefficients enable to obtain classification rates similar to those provided by the native wavelet scattering transform. The relationships between the tension parameter of the scheme and the fractal dimension of its limit curve are also investigated.

Discrimination between the facial gestures of vocalising and non-vocalising lemurs and small apes using deep learning

Facial expression studies in animal communication are essential. However, manual inspection methods are only practical for small datasets. Deep learning techniques can help discriminate facial configurations associated with vocalisations over large datasets. We extracted and labelled frames of different primate species, trained deep-learning models to identify key points on their faces, and computed distances between them to identify facial gestures. We used machine learning algorithms to classify vocalised and non-vocalised gestures across different species. The algorithms showed higher-than-chance correct classification rates, with some exceeding 90 %. Our work employs deep learning to map primate facial gestures and offers an innovative application of pose estimation systems. Our approach facilitates the investigation of facial repertoire across primate species and behavioural contexts, enabling comparative research in primate communication.

Enhancing testing efficacy of high-density SNP microarrays to distinguish pedigrees belonging to the same kinship class

Kinship testing, which involves genotyping genetic markers and comparing their profiles between individuals, holds significant applications in forensic science. However, the prevalent use of independent markers often lacks the discriminatory power to distinguish pedigrees belong to the same kinship class. While numerous studies have attempted to address this challenge through diverse approaches, the testing efficacy of high-density SNP microarrays in combination with the likelihood approach remains unclear.In this study, we further explored the utilization of linked autosomal SNPs derived from microarrays with the likelihood approach. Several SNP panels with differing numbers of loci were developed and putative pedigrees were constructed to evaluated to test their efficacy in distinguishing second-degree relationships, including grandparent-grandchild, half-siblings, and avuncular. Our findings indicate that the use of high-density SNP microarrays is theoretically feasible for discriminating second-degree relationships, with balanced classification rates ranging from 0.444 to 0.853.Moreover, to optimize the practical effectiveness of discriminating pedigrees belonging to the same kinship class, several other aspects such as adding additional SNPs or an additional relative and examining the effects of genotype errors and population selection were discussed. Our results revealed that the employment of denser marker sets with more accurate genotyping methods may be beneficial. Additionally, the inclusion of additional relatives and the selection of an appropriate reference population also appear to be crucial factors for enhancing the accuracy of kinship testing.In conclusion, our study provides insights into the potential of high-density SNPs in kinship testing and highlights the need for further optimization and examination into various factors that may contribute to enhancing testing efficacy.

Acoustic encoding of vocally expressed confidence and doubt in Chinese bidialectics.

Language communicators use acoustic-phonetic cues to convey a variety of social information in the spoken language, and the learning of a second language affects speech production in a social setting. It remains unclear how speaking different dialects could affect the acoustic metrics underlying the intended communicative meanings. Nine Chinese Bayannur-Mandarin bidialectics produced single-digit numbers in statements of both Standard Mandarin and the Bayannur dialect with different levels of intended confidence. Fifteen listeners judged the intention presence and confidence level. Prosodically unmarked and marked stimuli exhibited significant differences in perceived intention. A higher intended level was perceived as more confident. The acoustic analysis revealed the segmental (third and fourth formants, center of gravity), suprasegmental (mean fundamental frequency, fundamental frequency range, duration), and source features (harmonic to noise ratio, cepstral peak prominence) can distinguish between confident and doubtful expressions. Most features also distinguished between dialect and Mandarin productions. Interactions on fourth formant and mean fundamental frequency suggested that speakers made greater use of acoustic parameters to encode confidence and doubt in the Bayannur dialect than in Mandarin. In machine learning experiments, the above-chance-level overall classification rates for confidence and doubt and the in-group advantage supported the dialect theory.

Texture Analysis and Classification using Local Binary Patterns and Statistical Features

Texture analysis and classification are crucial in many applications such as medical applications, satellite imagery analysis, and so on. This paper presents a new technique that incorporates the LBP with the HOG to improve the texture analysis and classification. LBP is famous for finding out the local texture descriptors by comparing the pixel intensities it deals with and can challenge light variations and image transformations. On the other hand, there is HOG which emphasizes edge and gradient information to detect the orientation and shape of a texture in a given image. While LBP describes the local micro-patterns HOG gives the perspective of the global gradient orientation. The combined use of local and global texture information is helpful in the presented problem when prioritizing the recognition of complex texture patterns that cannot be deciphered by a single algorithm. To demonstrate the efficiency of the proposed hybrid method, several experiments are performed on several texture databases. According to the findings, the proposed LBP-HOG strategy proves more beneficial than basic LBP and HOG techniques concerning the classification rate and computing time. The combination method shows improved performance in terms of agreement with the reference of fine and coarse level of texture descriptions along with providing large-scale description of the texture which results in the improved discriminatory power of the texture classes.

Perception of urban green space among university students in Bangladesh.

Public parks and other green areas are crucial components of urban development. Urban management in emerging countries such as Bangladesh faces major challenges, especially because of the socio-environmental impacts of urbanization. Urban management initiatives in developing countries sometimes neglect crucial services for university students, such as study environments and recreational facilities. This study aimed to investigate students' perceptions of urban green space (UGS) and its potential benefits to our daily lives at Shahjalal University of Science and Technology (SUST) in Sylhet, Bangladesh, We collected data from 438 respondents by using a survey questionnaire-based stated preference approach as a methodological tool, using non-monetary assertions as the basis for the method. The survey included questions about respondents' social background, the frequency with which they visited green spaces, the benefits of urban green spaces and their perception of urban green spaces. We performed statistical analysis both descriptive and inferential statistics. Our findings suggest that 71.7% of students primarily use street trees and peace gardens as their main sites for urban green spaces. The study suggests that the advantages of urban green spaces, which include physical, mental, and environmental benefits, are strongly associated with criteria such as gender, academic level, and vulnerable to home locality for climate change (CC) or extreme weather events (EWEs). The Binary Logistic regression analysis identified urban life as the most influential factor. The correct classification rate was approximately 74.7%, indicating the model's strong accuracy in classification. Students who have lived in urban areas for more than 20 years have a reduced awareness of urban green spaces at 5% level of significance. Planning and policymaking for the creation and administration of urban green spaces, considering aspects like land use and environmental sustainability, could benefit from this study.

Impacts of Backcalculation Software Selection on Airport Flexible Pavements Using the Aircraft Classification Rating/Pavement Classification Rating Method

From November 2024, the aircraft classification rating/pavement classification rating (ACR/PCR) method will be accepted by civil aviation authorities to notify the bearing capacity of airport pavements. Structural characteristics are necessary to calculate the parameters relating to this method, such as the modulus of elasticity which, in the case of existing pavements, can be obtained by backcalculation. However, the results of this procedure may vary depending on the type of method and algorithms used to minimize adjustment errors between the deflection basins adopted in the software. Given the above, this article aims to evaluate whether the choice of backcalculation software affects the resistance classification and admissibility of aircraft on airport pavements using the ACR/PCR method based on the backcalculated elastic moduli. The elastic modulus values of the materials from two runways were backcalculated using BAKFAA, BackCAP, BackMedina, and ELMOD software, and then used to calculate the PCR. The results of the backcalculation showed differences in the elastic moduli obtained by the software, mainly in the subgrade. It was found that the backcalculation software used can limit the type of aircraft and the runway resistance. Therefore, the choice of software for backcalculation of deflection basins can influence the results of the ACR/PCR method because of divergences in determining the resistance of the pavement’s bearing capacity and the admissibility of aircraft operations in the analyzed structures.

Utilizing machine learning and hemagglutinin sequences to identify likely hosts of influenza H3Nx viruses

Influenza is a disease that represents both a public health and agricultural risk with pandemic potential. Among the subtypes of influenza A virus, H3 influenza virus can infect many avian and mammalian species and is therefore a virus of interest to human and veterinary public health. The primary goal of this study was to train and validate classifiers for the identification of the most likely host species using the hemagglutinin gene segment of H3 viruses. A five-step process was implemented, which included training four machine learning classifiers, testing the classifiers on the validation dataset, and further exploration of the best-performing model on three additional datasets. The gradient boosting machine classifier showed the highest host-classification accuracy with a 98.0 % (95 % CI [97.01, 98.73]) correct classification rate on an independent validation dataset. The classifications were further analyzed using the predicted probability score which highlighted sequences of particular interest. These sequences were both correctly and incorrectly classified sequences that showed considerable predicted probability for multiple hosts. This showed the potential of using these classifiers for rapid sequence classification and highlighting sequences of interest. Additionally, the classifiers were tested on a separate swine dataset composed of H3N2 sequences from 1998 to 2003 from the United States of America, and a separate canine dataset composed of canine H3N2 sequences of avian origin. These two datasets were utilized to look at the applications of predicted probability and host convergence over time. Lastly, the classifiers were used on an independent dataset of environmental sequences to explore the host identification of environmental sequences. The results of these classifiers show the potential for machine learning to be used as a host identification technique for viruses of unknown origin on a species-specific level.

Geographical origin identification of cinnamon using HPLC-DAD fingerprints and chemometrics

The commercial value of cinnamon depends largely on its geographical origin. This study proposed high-performance liquid chromatography-diode array detection (HPLC-DAD) fingerprints combined with chemometrics to identify geographical origins of cinnamons. Alternating trilinear decomposition (ATLD) algorithm was applied to extract meaningful chemical information from the HPLC fingerprint data. Then, non-targeted HPLC fingerprints and chemical component information were used as chemical descriptors to distinguish geographical origins using principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA)/N-way partial least squares-discriminant analysis (NPLS-DA). Satisfactory classification results were acquired for each discriminant model and the correct classification rates (CCRs) of training and test sets were 100%. Moreover, four characteristic variables were screened by variable importance in projection (VIP) method, three of which were reasonably identified as cinnamic acid, cinnamaldehyde and 2-methoxycinnamaldehyde, which can be regarded as potential markers to distinguish cinnamon from different geographical origins. The results indicated that HPLC-DAD fingerprints combined with chemometrics can be a promising means to identify the geographical origins and screen potential markers of cinnamon samples, especially in the absence of high-cost and sophisticated analytical instrumentals (e.g., high-resolution mass spectrometry and nuclear magnetic resonance spectroscopy). This work can help to prevent cinnamon fraud practices and maintain the normal order of the cinnamon market.

Polyphenolic profiling of coffee beverages by Liquid Chromatography-High-Resolution mass Spectrometry for classification and characterization

The importance of monitoring the presence of bioactive compounds as food attributes for sample classification and characterization is increasing. In this study, targeted Liquid Chromatography coupled with High-Resolution Mass Spectrometry (LC-HRMS) was employed to analyze the chemical profile of polyphenolic compounds as the source of information for the characterization and classification of 306 commercial coffee samples. Coffee holds a distinguished position as one of the most widely popular beverages globally but also one of the most easily adulterated. Regrettably, in recent times, instances of coffee adulteration have been on the rise. Consequently, implementing rigorous quality control measures for coffee becomes imperative to guarantee its quality. The results obtained in this work confirm that the proposed chemical profiles serve as excellent descriptors for sample characterization and classification through the implementation of principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA), achieving classification rates higher than 83.3% in PLS-DA validation. Moreover, the proposed LC-HRMS polyphenolic approach was employed to identify and measure adulteration levels in coffee samples using partial least squares (PLS) regression with prediction errors below 7.8%.

Which jump test is most sensitive for classifying ACL injury history in fatigued or non-fatigued athletes?

Introduction & Purpose In fast-paced clinical decision-making, jump-landing movement assessments are rarely used to guide return-to-sport (RTS) decisions after an anterior cruciate ligament (ACL) injury. While these tests are crucial for identifying deficits in movement execution (e.g., dynamic valgus, extended knee, knee internal rotation) that could predispose to ACL re-rupture (Kaplan & Witvrouw, 2019), identifying these deficits can be challenging. To integrate RTS movement assessments into clinical practice, the first step is to identify the most sensitive jump-landing test that can best expose remaining deficits in neuromuscular control and resulting landing kinematics associated with ACL injury. Further, RTS tests are mostly performed in a non-fatigued state although fatigued individuals often fail to reach the RTS criteria (Dingenen & Gokeler, 2017). This exploratory study aimed to rank common jump-landing tests in their ability to identify (sensitivity and classification rate) deficits in whole-body landing kinematics following ACL injury, under both fatigued and non-fatigued conditions. Methods A total of 43 volunteers were recruited into ACL group (n = 21, 11 females, 3.9 years post ACL injury) and control group (n = 22, 12 females). 3D motion data (Vicon, 250 Hz) were recorded during a single-leg forward hop (SH), single-leg countermovement jump (CMJ), single-leg triple crossover hop (COH), and single-leg 90° medial rotation hop (MRH) before and after a fatigue-inducing intervention (single-leg squats and step-ups). Thirteen joint angles (50 ms after initial contact) from the lower body, trunk, and pelvis representing the landing kinematics were calculated in OpenSim. A correlation analysis was performed to check for multicollinearity issues. Eight distinct logistic regression models (four jumps, fatigued/non-fatigued, α = .05) were computed to predict ACL injury history based on a combination of joint angles. For each model, a backward stepwise method was employed to determine which combination of joint angles resulted in the highest classification rates. Results ACL injury history was successfully predicted in seven (χ² > 4.4, p < .036) of the eight logistic regression models (Figure 1). The SH in the fatigued condition (χ² = 22.5, p = .008) demonstrated the highest sensitivity of 85.7% and a classification rate of 86%. Significant predictors for this model were knee rotation (Odds ratios [OR] = 1.537), hip abduction (OR = 1.385), hip rotation (OR = 1.525), and ankle flexion (OR = 0.771). The CMJ (non-fatigued) showed the second-highest sensitivity of 81% and a classification rate of 81.4% (p = .027). Significant predictors were knee rotation (OR = 1.440), hip abduction (OR = 1.428), hip rotation (OR = 1.297), and pelvis rotation (OR = 0.664). The MRH in the non-fatigued condition exhibited the lowest sensitivity, and no classification was possible in the non-fatigued COH model (χ² = 3.6, p = .056). Discussion & Conclusion The fatigued SH was the most sensitive jump-landing test for classifying groups and detecting kinematic differences due to previous ACL injury. Thus, we recommended the SH over other tests for RTS decision-making, as it is most likely to reveal kinematic abnormalities. Higher classification rates in the fatigued condition support RTS testing in fatigued states to better identify movement deficits. To integrate jump-landing assessments into RTS decisions in a feasible way, our future work will involve 3D motion capture using pose estimation algorithms on video data.

Tone classification of online medical services based on 1DCNN-BiLSTM

In order to improve the recognition rate of the tone classification of doctors in online medical services scenarios, we propose a model that integrates a one-dimensional convolutional neural network (1DCNN) with a bidirectional long short-term memory network (BiLSTM). Firstly, significant tone types within online medical services scenarios were identified through a survey questionnaire. Secondly, 68 features in both the time and frequency domains of doctors’ tone were extracted using Librosa, serving as the initial input for the model. We utilize the 1DCNN branch to extract local features in the time and frequency domains, while the BiLSTM branch captures the global sequential features of the audio, and a feature-level fusion is performed to enhance tone classification effectiveness. When applied in online medical services scenarios, experimental results show that the model achieved an average recognition rate of 84.4% and an F1 score of 84.4%, significantly outperforming other models and effectively improving the efficiency of doctor-patient communication. Additionally, a series of ablation experiments were conducted to validate the effectiveness of the 1DCNN and BiLSTM modules and the parameter settings.

Contrast-Enhanced Intraoperative Ultrasound Shows Excellent Performance in Improving Intraoperative Decision-Making.

The aim of this study was to evaluate the performance and the impact of contrast-enhanced intraoperative ultrasound (CE-IOUS) on intraoperative decision-making, as there is still no standardized protocol for its use. Therefore, we retrospectively analyzed multiple CE-IOUS performed in hepato-pancreatic-biliary surgery with respect to pre- and postoperative imaging and histopathological findings. Data of 50 patients who underwent hepato-pancreatic-biliary surgery between 03/2022 and 03/2024 were retrospectively collected. CE-IOUS was performed with a linear 6-9 MHz multifrequency probe connected to a high-resolution device. The ultrasound contrast agent used was a stabilized aqueous suspension of sulphur hexafluoride microbubbles. In total, all 50 lesions indicated for surgery were correctly identified. In 30 cases, CE-IOUS was used to localize the primary lesion and to define the resection margins. In the remaining 20 cases, CE-IOUS identified an additional lesion. Fifteen of these findings were identified as malignant. In eight of these cases, the additional malignant lesion was subsequently resected. In the remaining seven cases, CE-IOUS again revealed an inoperable situation. In summary, CE-IOUS diagnostics resulted in a high correct classification rate of 95.7%, with positive and negative predictive values of 95.2% and 100.0%, respectively. CE-IOUS shows excellent performance in describing intraoperative findings in hepato-pancreatic-biliary surgery, leading to a substantial impact on intraoperative decision-making.

Abstract A008: Proof-of-Concept: A machine learning classifier to impute nativity status in Hispanic/Latino/a/x cancer patients in the California Cancer Registry

Abstract Background: Cancer disparities exist within the Hispanic/Latino/a/x (H/L) population by nativity status. Non-US born H/L colorectal cancer (CRC) patients and Prostate Cancer (PCa) patients in California have a statistically significant lower risk of cancer-specific survival when compared to Non-Hispanic White patients after controlling for confounders. However, birthplace information is largely incomplete in population-based cancer registries. For example, more than 40% of H/L patients have missing information on nativity in the California Cancer Registry (CCR) database. With the goal of better imputing missing birthplace, we built a Machine Learning (ML) model to predict nativity among CCR H/L cancer patients. Methods: H/L cases with primary invasive CRC (n = 75,613) and PCa (n = 93,042) at least 18 years old, diagnosed between 1988 and 2021 contained in the CCR research file were analyzed (46.36% had missing birthplace). A binary indicator variable assigning cases with known birthplace to US-born vs. Non-US born was constructed as the target for prediction. A stratified split by levels of the outcome was used to generate training (70%, n = 63,323) and testing (30%, n = 27,139) datasets. We used a pruned classification tree to perform feature selection, with the 10 features with the highest importance (measured by the overall reduction in impurity for any split containing each feature) used to predict nativity. Missing observations of the quantitative and qualitative features were mean, or mode imputed, respectively. The classification methods considered were classification trees, Random Forest (RF), and Boosting. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and the rate of correctly classified observations. Results: The top three features with the highest importance were the NHIA (NAACCR Hispanic/Latino Identification Algorithm) label, the Hispanic/Spanish identity, and the year of social security number issuance (SSN); the latter is part of a current SSN-based algorithm used to impute nativity status in this population. Classification models showed similar prediction performance. The highest AUC was reported by the RF (AUC = 0.9822), followed by Boosting (AUC = 0.9785), and the pruned classification tree (AUC = 0.9647). A similar rate of correctly classified observations was reported for the Boosting and RF models (∼94%). The RF model ranked feature importance in a similar order as the pruned classification tree. Ultimately, the RF model was the best performing classifier with a sensitivity and specificity of 0.61 and 0.90, respectively. This classifier substantially outperforms the SSN-based algorithm, which reported a correct classification rate of 81%, a sensitivity = 0.54, and a specificity = 0.41 in this dataset. Conclusions: This proof-of-concept analysis showcases a potential for developing a ML model to overcome missing nativity status in H/L cancer patients to enable more accurate classification by nativity in future research using CCR data. Citation Format: Proof-of-Concept: A machine learning classifier to impute nativity status in Hispanic/Latino/a/x cancer patients in the California Cancer Registry. Joel Sanchez Mendez, Lihua Liu, Juan P. Lewinger, Laura Fejerman, Mariana C. Stern [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A008.

Authentication of Pacific white shrimp (Litopenaeus vannamei) reared in freshwater and seawater areas using fatty acid profiles combined with chemometrics

Fatty acid (FA) profiling in muscle and hepatopancreas of Litopenaeus vannamei was combined with k-nearest neighbor (KNN), and random forest (RF) to differentiate L. vannamei raised in freshwater and seawater areas. The FA profiles of the two tissues differed between L. vannamei cultured in freshwater and seawater. Moreover, six (C22:6n3, C20:3n3, C17:0, C18:3n3, C20:5n3, and C20:2) and seven (C22:6n3, C16:0, C18:3n3, C18:2n6, C20:2, C20:1, and C18:1n9) variables in muscle and hepatopancreas, respectively, were selected by orthogonal partial least squares-discriminant analysis (OPLS-DA) to create models for distinguishing L. vannamei cultured in freshwater and seawater. The most selected variables in muscle and hepatopancreas were related to salinity. Furthermore, using FA profiles from the two tissues, both KNN and RF had initial and cross-validated classification rates >93%, while the predictive classification rates of the models based on muscle FA profiles were higher than that of the models based on hepatopancreas FA profiles. Therefore, FA profiles in muscle were more effective than hepatopancreas FAs for identifying shrimps. FA profiling in muscle tissue represents a promising method for discriminating between L. vannamei cultured in freshwater and seawater.

Non-Targeted Nuclear Magnetic Resonance Analysis for Food Authenticity: A Comparative Study on Tomato Samples.

Non-targeted NMR is widely accepted as a powerful and robust analytical tool for food control. Nevertheless, standardized procedures based on validated methods are still needed when a non-targeted approach is adopted. Interlaboratory comparisons carried out in recent years have demonstrated the statistical equivalence of spectra generated by different instruments when the sample was prepared by the same operator. The present study focused on assessing the reproducibility of NMR spectra of the same matrix when different operators performed individually both the sample preparation and the measurements using their spectrometer. For this purpose, two independent laboratories prepared 63 tomato samples according to a previously optimized procedure and recorded the corresponding 1D 1H NMR spectra. A classification model was built using the spectroscopic fingerprint data delivered by the two laboratories to assess the geographical origin of the tomato samples. The performance of the optimized statistical model was satisfactory, with a 97.62% correct sample classification rate. The results of this work support the suitability of NMR techniques in food control routines even when samples are prepared by different operators by using their equipment in independent laboratories.

Data-driven approach for identifying the factors related to debt collector performance

The company's success and growth heavily rely on its workforce's performance, yet the evaluation of employees has been only partially and inconclusively executed so far. The primary goal of this research is to build an open innovation framework for analyzing the performance of the debt collector. We have developed the Reinforcement Learning based Continual Learning (RLC) approach for evaluating the performance by analyzing the metrics such as visit patterns and collection percentage. We have used the private debt collection dataset to assess the debt collector's performance. We formulated hypotheses derived from insights gained during exploratory data analysis and subsequently validated them through statistical testing. Whether there are noticeable distinctions among debt collectors in terms of visitation frequency, collection rates, and collection modes. This proposed open innovation framework for analyzing the debt collector performance provides significant variation in terms of collection rate. The proposed EDQN-CL achieved a 13.56 % higher classification rate than the existing algorithm for categorizing the debt collector performance.

Safe and Reliable Movement of Fast LiDAR-based Self-driving Vehicle

Classification of objects is an important technique for autonomous ground vehicles to identify a surrounding environment and execute safe path planning. In this paper, a method based on horizontal segmentation is proposed to detect cone-shaped objects in vehicle’s vicinity using a LiDAR sensor. A captured point cloud is divided into five layers based on height information, and the division of detected objects into two groups, cones and others, has been made using classifiers available in MATLAB toolboxes. To separate the classified conical objects into four types used to mark the route, an algorithm for their recognition was developed and used. The proposed solution, verified by navigation experiments in real conditions using an unmanned racing car, has gave good results, i.e., a high rate of cone-shaped objects classification, a short processing time and a low computational load. The performed tests have allowed also to diagnose the causes of incorrect classification of objects. Thus, the experimental results indicated that the approach presented in this work can be used in real time for autonomous, collision-free driving along marked routes.