Bayesian Classification Model Research Articles

OUCH: Oversampling and Undersampling Cannot Help Improve Accuracy in Our Bayesian Classifiers That Predict Preeclampsia

Unbalanced data can have an impact on the machine learning (ML) algorithms that build predictive models. This manuscript studies the influence of oversampling and undersampling strategies on the learning of the Bayesian classification models that predict the risk of suffering preeclampsia. Given the properties of our dataset, only the oversampling and undersampling methods that operate with numerical and categorical attributes will be taken into consideration. In particular, synthetic minority oversampling techniques for nominal and continuous data (SMOTE-NC), SMOTE—Encoded Nominal and Continuous (SMOTE-ENC), random oversampling examples (ROSE), random undersampling examples (UNDER), and random oversampling techniques (OVER) are considered. According to the results, when balancing the class in the training dataset, the accuracy percentages do not improve. However, in the test dataset, both positive and negative cases of preeclampsia were accurately classified by the models, which were built on a balanced training dataset. In contrast, models built on the imbalanced training dataset were not good at detecting positive cases of preeclampsia. We can conclude that while imbalanced training datasets can be addressed by using oversampling and undersampling techniques before building prediction models, an improvement in model accuracy is not always guaranteed. Despite this, the sensitivity and specificity percentages improve in binary classification problems in most cases, such as the one we are dealing with in this manuscript.

Study on canopy extraction method for narrowband spectral images based on superpixel color gradation skewness distribution features

BackgroundCrop phenotype extraction devices based on multiband narrowband spectral images can effectively detect the physiological and biochemical parameters of crops, which plays a positive role in guiding the development of precision agriculture. Although the narrowband spectral image canopy extraction method is a fundamental algorithm for the development of crop phenotype extraction devices, developing a highly real-time and embedded integrated narrowband spectral image canopy extraction method remains challenging owing to the small difference between the narrowband spectral image canopy and background.MethodsThis study identified and validated the skewed distribution of leaf color gradation in narrowband spectral images. By introducing kurtosis and skewness feature parameters, a canopy extraction method based on a superpixel skewed color gradation distribution was proposed for narrowband spectral images. In addition, different types of parameter combinations were input to construct two classifier models, and the contribution of the skewed distribution feature parameters to the proposed canopy extraction method was evaluated to confirm the effectiveness of introducing skewed leaf color skewed distribution features.ResultsLeaf color gradient skewness verification was conducted on 4200 superpixels of different sizes, and 4190 superpixels conformed to the skewness distribution. The intersection over union (IoU) between the soil background and canopy of the expanded leaf color skewed distribution feature parameters was 90.41%, whereas that of the traditional Otsu segmentation algorithm was 77.95%. The canopy extraction method used in this study performed significantly better than the traditional threshold segmentation method, using the same training set, Y1 (without skewed parameters) and Y2 (with skewed parameters) Bayesian classifier models were constructed. After evaluating the segmentation effect of introducing skewed parameters, the average classification accuracies Acc_Y1 of the Y1 model and Acc_Y2 of the Y2 model were 72.02% and 91.76%, respectively, under the same test conditions. This indicates that introducing leaf color gradient skewed parameters can significantly improve the accuracy of Bayesian classifiers for narrowband spectral images of the canopy and soil background.ConclusionsThe introduction of kurtosis and skewness as leaf color skewness feature parameters can expand the expression of leaf color information in narrowband spectral images. The narrowband spectral image canopy extraction method based on superpixel color skewness distribution features can effectively segment the canopy and soil background in narrowband spectral images, thereby providing a new solution for crop canopy phenotype feature extraction.

Prediction of Drug-Induced Liver Injury: From Molecular Physicochemical Properties and Scaffold Architectures to Machine Learning Approaches.

The process of developing new drugs is widely acknowledged as being time-intensive and requiring substantial financial investment. Despite ongoing efforts to reduce time and expenses in drug development, ensuring medication safety remains an urgent problem. One of the major problems involved in drug development is hepatotoxicity, specifically known as drug-induced liver injury (DILI). The popularity of new drugs often poses a significant barrier during development and frequently leads to their recall after launch. In silico methods have many advantages compared with traditional invivo and invitro assays. To establish a more precise and reliable prediction model, it is necessary to utilize an extensive and high-quality database consisting of information on drug molecule properties and structural patterns. In addition, we should also carefully select appropriate molecular descriptors that can be used to accurately depict compound characteristics. The aim of this study was to conduct a comprehensive investigation into the prediction of DILI. First, we conducted a comparative analysis of the physicochemical properties of extensively well-prepared DILI-positive and DILI-negative compounds. Then, we used classic substructure dissection methods to identify structural pattern differences between these two different types of chemical molecules. These findings indicate that it is not feasible to establish property or substructure-based rules for distinguishing between DILI-positive and DILI-negative compounds. Finally, we developed quantitative classification models for predicting DILI using the naïve Bayes classifier (NBC) and recursive partitioning (RP) machine learning techniques. The optimal DILI prediction model was obtained using NBC, which combines 21 physicochemical properties, the VolSurf descriptors and the LCFP_10 fingerprint set. This model achieved a global accuracy (GA) of 0.855 and an area under the curve (AUC) of 0.704 for the training set, while the corresponding values were 0.619 and 0.674 for the test set, respectively. Moreover, indicative substructural fragments favorable or unfavorable for DILI were identified from the best naïve Bayesian classification model. These findings may help prioritize lead compounds in the early stage of drug development pipelines.

Ranking Search Results Based on User Preferences in the Absence of Personalized Statistics

The article considers the algorithm of search results ranking according to the compliance with user's expectations due to the feedback on the data of search results pre-release, which allowed to reduce the time of search for the necessary information. A numerical experiment aimed at evaluating the effectiveness of the proposed approach on the example of real estate objects is presented. Aggregated data of real estate listings were used as data, and the results of user surveys were used to evaluate the relevance. TOPSIS and PROMETHEE methods were used as pre-ranking algorithms. The ranking results were combined considering their order in the output of both methods. To implement the next step of the algorithm, the pre-release list was partitioned into classes for which users selected a few objects they liked. Machine learning models were trained on the partitioned data. Based on their average accuracy and variance estimates, a naive Bayesian classifier model was selected and used for subsequent computations. The results of further experiments showed the possibility of taking into account personal preferences when organizing search and selection of objects of interest in the absence of personalized statistics on the example of real estate objects. As a result of the experiments, the time of searching a group of results of interest was reduced by 74 % on average.

Integration of Multicomplex‐Based Pharmacophore Modeling and Molecular Docking in Machine Learning‐Based Virtual Screening: Toward the Discovery of Novel PI3K Inhibitors

AbstractThe phosphatidylinositol‐3 kinase (PI3K) pathway is a crucial intracellular signaling pathway within living cells. The hyperactivation of PI3K signaling cascades is a common occurrence in human cancers, rendering PI3K a promising therapeutic target. Although several PI3K inhibitors are already available on the market, the adverse side effects of current therapies continue to highlight the necessity for the development of novel PI3K inhibitors. In this study, a virtual screening strategy employing naïve Bayesian classification (NBC) models, based on multicomplex‐based molecular docking and pharmacophore modeling, is developed. First, the docking accuracy and scoring reliability of four docking software are assessed, and Glide demonstrated higher predictability for PI3K inhibitors. Second, pharmacophore models are generated based on the current reported PI3K‐inhibitor interactions, and five pharmacophore hypotheses displayed significant capability in discriminating active PI3K molecules from inactive ones. Subsequently, three NBC models are constructed based on molecular docking and/or pharmacophore models, and the validation results showed that the NBC model, combining multicomplex‐based molecular docking and pharmacophore, significantly improved the hit rate of virtual screening against PI3K. Finally, the optimal NBC model is employed for virtual screening against the ChEMBL database, leading to the identification of multiple molecules with high potential as active PI3K inhibitors.

Exploring different classification-dependent QSAR modelling strategies for HDAC3 inhibitors in search of meaningful structural contributors.

Histone deacetylase 3 (HDAC3), a Zn2+-dependent class I HDACs, contributes to numerous disorders such as neurodegenerative disorders, diabetes, cardiovascular disease, kidney disease and several types of cancers. Therefore, the development of novel and selective HDAC3 inhibitors might be promising to combat such diseases. Here, different classification-based molecular modelling studies such as Bayesian classification, recursive partitioning (RP), SARpy and linear discriminant analysis (LDA) were conducted on a set of HDAC3 inhibitors to pinpoint essential structural requirements contributing to HDAC3 inhibition followed by molecular docking study and molecular dynamics (MD) simulation analyses. The current study revealed the importance of hydroxamate function for Zn2+ chelation as well as hydrogen bonding interaction with Tyr298 residue. The importance of hydroxamate function for higher HDAC3 inhibition was noticed in the case of Bayesian classification, recursive partitioning and SARpy models. Also, the importance of substituted thiazole ring was revealed, whereas the presence of linear alkyl groups with carboxylic acid function, any type of ester function, benzodiazepine moiety and methoxy group in the molecular structure can be detrimental to HDAC3 inhibition. Therefore, this study can aid in the design and discovery of effective novel HDAC3 inhibitors in the future.

Machine learning-aided algorithm design for prediction of severity from clinical, demographic, biochemical and immunological parameters: Our COVID-19 experience from the pandemic.

The severity of laboratory and imaging finding was found to be inconsistent with clinical symptoms in COVID-19 patients, thereby increasing casualties. As compared to conventional biomarkers, machine learning algorithms can learn nonlinear and complex interactions and thus improve prediction accuracy. This study aimed at evaluating role of biochemical and immunological parameters-based machine learning algorithms for severity indexing in COVID-19. Laboratory biochemical results of 5715 COVID-19 patients were mined from electronic records including 509 admitted in COVID-19 ICU. Random Forest Classifier (RFC), Support Vector Machine (SVM), Naive Bayesian Classifier (NBC) and K-Nearest Neighbours (KNN) classifier models were used. Lasso regression helped in identifying the most influential parameter. A decision tree was made for subdivided data set, based on randomization. Accuracy of SVM was highest with 94.18% and RFC with 94.04%. SVM had highest PPV (1.00), and NBC had highest NPV (0.95). QUEST modelling ignored age, urea and total protein, and only C-reactive protein and lactate dehydrogenase were considered to be a part of decision-tree algorithm. The overall percentage of correct classification was 78.31% in the overall algorithm with a sensitivity of 87.95% and an AUC of 0.747. C-reactive protein and lactate dehydrogenase being routinely performed tests in clinical laboratories in peripheral setups, this algorithm could be an effective predictive tool. SVM and RFC models showed significant accuracy in predicting COVID-19 severity and could be useful for future pandemics.

Monitoring Soil Salinity Classes through Remote Sensing-Based Ensemble Learning Concept: Considering Scale Effects

Remote sensing (RS) technology can rapidly obtain spatial distribution information on soil salinization. However, (1) the scale effects resulting from the mismatch between ground-based “point” salinity data and remote sensing pixel-based “spatial” data often limit the accuracy of remote sensing monitoring of soil salinity, and (2) the same salinity RS monitoring model usually provides inconsistent or sometimes conflicting explanations for different data. Therefore, based on Landsat 8 imagery and synchronously collected ground-sampling data of two typical study regions (denoted as N and S, respectively) of the Yichang Irrigation Area in the Hetao Irrigation District for May 2013, this study used geostatistical methods to obtain “relative truth values” of salinity corresponding to the Landsat 8 pixel scale. Additionally, based on Landsat 8 multispectral data, 14 salinity indices were constructed. Subsequently, the Correlation-based Feature Selection (CFS) method was used to select sensitive features, and a strategy similar to the concept of ensemble learning (EL) was adopted to integrate the single-feature-sensitive Bayesian classification (BC) model in order to construct an RS monitoring model for soil salinization (Nonsaline, Slightly saline, Moderately saline, Strongly saline, and Solonchak). The research results indicated that (1) soil salinity exhibits moderate to strong variability within a 30 m scale, and the spatial heterogeneity of soil salinity needs to be considered when developing remote sensing models; (2) the theoretical models of salinity variance functions in the N and S regions conform to the exponential model and the spherical model, with R2 values of 0.817 and 0.967, respectively, indicating a good fit for the variance characteristics of salinity and suitability for Kriging interpolation; and (3) compared to a single-feature BC model, the soil salinization identification model constructed using the concept of EL demonstrated better potential for robustness and effectiveness.

Image segmentation of mouse eye invivo with optical coherence tomography based on Bayesian classification.

Optical coherence tomography (OCT) is a new imaging technology that uses an optical analog of ultrasound imaging for biological tissues. Image segmentation plays an important role in dealing with quantitative analysis of medical images. We have proposed a novel framework to deal with the low intensity problem, based on the labeled patches and Bayesian classification (LPBC) model. The proposed method includes training and testing phases. During the training phase, firstly, we manually select the sub-images of background and Region of Interest (ROI) from the training image, and then extract features by patches. Finally, we train the Bayesian model with the features. The segmentation threshold of each patch is computed by the learned Bayesian model. In addition, we have collected a new dataset of mouse eyes invivo with OCT, named MEVOCT, which can be found at URL https://17861318579.github.io/LPBC. MEVOCT consists of 20 high-resolution images. The resolution of every image is 2048×2048 pixels. The experimental results demonstrate the effectiveness of the LPBC method on the new MEVOCT dataset. The ROI segmentation is of great importance for the distortion correction.

Optimization of virtual screening against phosphoinositide 3-kinase delta: Integration of common feature pharmacophore and multicomplex-based molecular docking

Extensive research has accumulated which suggests that phosphatidylinositol 3-kinase delta (PI3Kδ) is closely related to the occurrence and development of various human diseases, making PI3Kδ a highly promising drug target. However, PI3Kδ exhibits high homology with other members of the PI3K family, which poses significant challenges to the development of PI3Kδ inhibitors. Therefore, in the present study, a hybrid virtual screening (VS) approach based on a ligand-based pharmacophore model and multicomplex-based molecular docking was developed to find novel PI3Kδ inhibitors. 13 crystal structures of the human PI3Kδ-inhibitor complex were collected to establish models. The inhibitors were extracted from the crystal structures to generate the common feature pharmacophore. The crystallographic protein structures were used to construct a naïve Bayesian classification model that integrates molecular docking based on multiple PI3Kδ conformations. Subsequently, three VS protocols involving sequential or parallel molecular docking and pharmacophore approaches were employed. External predictions demonstrated that the protocol combining molecular docking and pharmacophore resulted in a significant improvement in the enrichment of active PI3Kδ inhibitors. Finally, the optimal VS method was utilized for virtual screening against a large chemical database, and some potential hit compounds were identified. We hope that the developed VS strategy will provide valuable guidance for the discovery of novel PI3Kδ inhibitors.

A Study on the Methods of Improving Writing Skills by Bayesian Classifier in English Teaching and Learning

Abstract Teachers have been researching how to effectively improve the English writing ability of contemporary college students. The article utilizes web crawler technology to establish an English writing knowledge database and preprocesses the data through a word division algorithm, lexical annotation, and word form reduction. The article employs Bayesian classification algorithms to model the English writing style of students. The English writing grammar error correction model was constructed based on the BiGRU model, combined with the BERT pre-training task, fused with the attention mechanism. The English writing knowledge database was used to analyze the data for the model mentioned above. The sentence length of English written text fluctuates between -0.095 and 0.436, and the Bayesian classification model’s AUC value is 0.814. The grammar error correction model for English writing text has a GLEU value of 63.24, with an automatic scoring mean of 26.69, which is only 0.35 higher than manual scoring and a scoring error of only 1.29%. Through the English writing text style and grammar error correction model, teachers can optimize the English writing teaching mode and help students improve their English writing abilities.

The Innovative Integration of College Students’ Mental Health Education and Civic Education Paths in the Age of Artificial Intelligence

Abstract This article takes personalized education as the starting point, discusses the application in mental health education, and uses the plain Bayesian classification model to classify college students’ mental health in a refined way. The article proposes an evidential reasoning timeliness evaluation model for calculating the total assessment value of ideological and political education in colleges and universities and its actual effect to evaluate the ideological and political education quality. In addition, combining mental health education and ideological and political education, this study constructs an innovative collaborative parenting education model. The empirical analysis shows that the overall level of students’ mental health and Civic and Political learning quality in college L exceeds 2.5 points. By building a model of coupling and coordination degree of mental health and civic education, the study found that the integration benefit index of the two showed an upward trend in 10 years, growing to 0.97852. The coupling and coordination degrees in 2022 reached 0.996332 and 0.911752, respectively, which showed a reasonable level. Through the educational model proposed in this paper, the integration of mental health education and ideological education is more effective, which provides an effective educational method for colleges and universities to improve the overall quality of students.

Probabilistic Nearest Neighbors Classification.

Analysis of the currently established Bayesian nearest neighbors classification model points to a connection between the computation of its normalizing constant and issues of NP-completeness. An alternative predictive model constructed by aggregating the predictive distributions of simpler nonlocal models is proposed, and analytic expressions for the normalizing constants of these nonlocal models are derived, ensuring polynomial time computation without approximations. Experiments with synthetic and real datasets showcase the predictive performance of the proposed predictive model.

Characterization of Unplasticized Polyvinyl Chloride Windows by Confocal Raman Microspectroscopy and Chemometrics

In order to nondestructively and accurately identify unplasticized polyvinyl chloride windows, a classification method based on multi-feature algorithm selection modeling was developed. Confocal Raman microspectroscopy was used to obtain the spectral profiles of 150 samples from five brands. The differences in model recognition accuracy were compared among three preprocessing methods: Savitzky-Golay filtering, Hilbert transform, and wavelet transform. The best preprocessing method was selected, and the competitive adaptive reweighted sampling was used to extract feature wavelengths. Furthermore, a Bayesian classification model was constructed to classify and differentiate each sample. The results showed that confocal Raman microspectroscopy can reflect the differences in physicochemical information among different samples. Preprocessing can improve the model’s recognition accuracy, with wavelet transform (96%) > Hilbert transform (90%) > Savitzky-Golay filtering (76%) > untreated (72%). Wavelet transform can remove noise from spectral data without changing the peak region and its absorbance. Based on wavelet transform processing and competitive adaptive reweighted sampling (CARS) combined with Bayesian discriminant analysis, a 100% accurate classification of 150 samples was successfully achieved.

Fault Diagnosis of Rotating Machinery Using Kernel Neighborhood Preserving Embedding and a Modified Sparse Bayesian Classification Model.

Fault diagnosis of rotating machinery plays an important role in modern industrial machines. In this paper, a modified sparse Bayesian classification model (i.e., Standard_SBC) is utilized to construct the fault diagnosis system of rotating machinery. The features are extracted and adopted as the input of the SBC-based fault diagnosis system, and the kernel neighborhood preserving embedding (KNPE) is proposed to fuse the features. The effectiveness of the fault diagnosis system of rotating machinery based on KNPE and Standard_SBC is validated by utilizing two case studies: rolling bearing fault diagnosis and rotating shaft fault diagnosis. Experimental results show that base on the proposed KNPE, the feature fusion method shows superior performance. The accuracy of case1 and case2 is improved from 93.96% to 99.92% and 98.67% to 99.64%, respectively. To further prove the superiority of the KNPE feature fusion method, the kernel principal component analysis (KPCA) and relevance vector machine (RVM) are utilized, respectively. This study lays the foundation for the feature fusion and fault diagnosis of rotating machinery.

A - 121 Psychosocial and Neurocognitive Correlates of Suicidal Thoughts and Behaviours Amongst Siblings of Persons with and without Neurodevelopmental Conditions.

Siblings of individuals with neurodevelopmental conditions (NDCs) have greater incidence of psychiatric diagnoses and neurocognitive difficulties compared to siblings of persons without NDCs. Despite suicidality being labelled a global health crisis, and NDC siblings experiencing risk factors implicated in suicidality, no previous studies examined suicidality amongst adolescent and young adult siblings of persons with NDCs. Our study aimed to bridge this gap. The present study used Bayesian analyses and risk classification models to examine individual and environmental risk factors associated with suicidal thoughts and behaviour amongst siblings of persons with and without NDCs (n = 267; 132 NDC, 135 control group, mean age 20.61, range 14-27, 76.40% female, 76.78% White Caucasian), as measured using self-report survey data and remote self-administered cognitive tests. NDC siblings had higher rates of current nonsuicidal self-injury (NSSI; 18.94% versus 14.07%, δ= -0.32), suicidal ideation (25.76% versus 8.89%, δ= -0.40) and history of suicide attempts (18.18% versus 4.44%, δ= -0.43) compared to controls. Classification models using boosting and random forest demonstrated adequate performance: positive predictive value 0.86-0.91, negative predictive value 0.81-0.90, false negative rates 0.11-0.24. Cognitive inflexibility, alexithymia, inattention, bullying, depression, NSSI, and eating or psychotic disorder history had the highest relative importance in predicting lifetime suicidality. Poorer executive functioning (measured by the Wisconsin Card Sorting Task, Sustained Attention to Response Task, Stop Signal Task, and N-Back 2-back task) was strongly correlated with suicidality. Screening for proximal and modifiable risk factors is critical to inform suicidal behaviour intervention and prevention programs for at-risk siblings.

Anomaly prediction of CT equipment based on IoMT data

BackgroundLarge-scale medical equipment, which is extensively implemented in medical services, is of vital importance for diagnosis but vulnerable to various anomalies and failures. Most hospitals that conduct regular maintenance have been suffering from medical equipment-related incidents for years. Currently, the Internet of Medical Things (IoMT) has emerged as a crucial tool in monitoring the real-time status of the medical equipment. In this paper, we develop an IoMT system of Computed Tomography (CT) equipment in the West China Hospital, Sichuan University and collected the system status time-series data. Novel multivariate time-series classification models and frameworks are proposed to predict the anomalies of CT equipment. The important features that are closely related to the equipment anomalies are identified with the model.MethodsWe extracted the real-time CT equipment status time-series data of 11 equipment between May 19, 2020 and May 19, 2021 from the IoMT, which includes the equipment oil temperature, anode voltage, etc. The arcs are identified as labels of anomalies due to their relationship with decreased imaging quality and CT equipment failures. To improve prediction accuracy, the statistics and transformations of the raw historical time-series data segment in the sliding time window are used to construct new features. Due to the particularity of time-series data, two frameworks are proposed for splitting the training and test sets. Then the Decision Tree, Support Vector Machine, Logistic Regression, Naive Bayesian, and K-Nearest Neighbor classification models are used to classify the system status. We also compare our model to state-of-the-art models.ResultsThe results show that the anomaly prediction accuracy and recall of our method are 79% and 77%, respectively. The oil temperature and anode voltage are identified as the decisive features that may lead to anomalies. The proposed model outperforms the others when predicting the anomalies of the CT equipment based on our dataset.ConclusionsThe proposed method could predict the state of CT equipment and be used as a reference for practical maintenance, where unexpected anomalies of medical equipment could be reduced. It also brings new insights into how to handle non-uniform and imbalanced time series data in practical cases.

MEASURING VULNERABILITY TO MULTIDIMENSIONAL POVERTY IN LATIN AMERICA

AbstractIn this paper, we perform estimates of vulnerability to multidimensional poverty for 17 Latin American countries at three points of time: 2005/2006, 2012, and 2017. We use a Multidimensional Bayesian Network Classifier model to estimate the conditional probability of being multidimensionally poor and then we use these probabilities and the standard downside semi‐deviation as the risk parameter to identify the vulnerable households. Despite significant reductions over the study period, in 2017 approximately 150 million people—excluding Guatemala, Nicaragua and Venezuela for which we do not have recent data—remained vulnerable to multidimensional poverty. We also observe that vulnerability to poverty is reduced at a much slower rate than poverty itself, revealing that achievements in SDG1 can be quite fragile. We perform a decomposition and find that as poverty decreases, risk‐induced vulnerability becomes relatively more important than poverty‐induced vulnerability. However, the poor‐vulnerable still constitute the core vulnerability group.

Vehicle Target Recognition Method Based on Visible and Infrared Image Fusion Using Bayesian Inference

The accuracy of single-mode optical imaging systems for vehicle target recognition is limited by external ambient illumination or imaging equipment resolution. In this paper, a vehicle target recognition method based on visible and infrared image fusion using Bayesian inference is proposed. Based on the significance area detection combined with Spectral Residual (SR) and EdgeBox algorithms, the target area is marked on the visible light image, and the maximum between-class variance method and GrabCut algorithm are used to segment vehicle targets in marked images. The open operation filter is employed to extract the vehicle target features in the infrared image, and the fusion result of the visible light image and the infrared image is obtained by introducing the Intersection Over Union (IOU), and as the parameter of Bayesian inference, the class and attribute of the parameter are defined and substituted into the established naive Bayesian classification model, and the probability of the class is calculated to determine whether the vehicle target is recognized. Experiments under different test conditions were carried out, and the experimental results were as follows: the accuracy of image target recognition reached 77% when the vehicle target was not occluded; when the vehicle target was partially occluded, the accuracy of image target recognition reached 74%; the results verified that the proposed method can recognize vehicle targets in different scenarios.

Non-destructive recognition of copy paper based on advanced spectral fusion and feature optimization

In order to provide more clues for ongoing investigations and case handling, as well as achieve fast, non-destructive, and accurate identification of copy paper found at crime scenes, this study aims to utilize advanced spectral fusion technology to characterize and identify the three-dimensional features of the “origin-manufacturer-brand” of copy paper. Confocal Raman Microscopic and Fourier transform infrared spectroscopy were employed to collect spectral data from 200 samples from four regions (Shandong, Henan, Shaanxi, Jiangsu). The effects of different preprocessing methods, such as Hilbert transformation and deconvolution, on the model's ability to distinguish were compared. Feature variables were extracted using principal component analysis, and Bayesian discriminant classification models were constructed based on single infrared spectroscopy, Raman spectroscopy, and three types of spectral fusion datasets. By comparing the classification accuracy of different models, the primary fusion based on the full spectrum dataset was selected as the optimal model for the three-dimensional feature classification of copy paper. The accuracy achieved for origin (96%), manufacturer (100%), and brand (100%) was satisfactory, and the classification results were highly accurate. This study provides valuable insights and serves as a reference for its application in forensic science research.