The goal of this study was to use Fourier transform mid-infrared （FTIR） spectroscopy for discrimination of samples of pods and seeds of carob from three Moroccan regions. The origin of samples Pods and seeds of caro...The goal of this study was to use Fourier transform mid-infrared （FTIR） spectroscopy for discrimination of samples of pods and seeds of carob from three Moroccan regions. The origin of samples Pods and seeds of carob could be distinguished from their IR spectra and this measurement was used for discriminate analysis. A multivariate analysis procedure based on the combined use of Hierarchical Cluster Aanalysis （HCA） and Partial Least Squares-Discriminant Analysis （PLS-DA） was tested and provided good classification results. Three distinctive clusters were recognised, related to the three Moroccan regions. Afterwards, PLS-DA was used for the discrimination and classification of the origin of the various Pods and seeds of carob samples. The results demonstrated that the combined use of FTIR and chemometric analysis （cluster analysis and discrimination by PLS- DA） can be used to rapidly and simply determine the origin of carob pulpe samples.展开更多
China is not only one of the origin centers of Pyrus L.,but also the earliest birthplace of Pyrus L.in the world.This paper reviews the evolution of Pyrus L.from the aspects of leaf edge morphology,inflorescence and f...China is not only one of the origin centers of Pyrus L.,but also the earliest birthplace of Pyrus L.in the world.This paper reviews the evolution of Pyrus L.from the aspects of leaf edge morphology,inflorescence and fruit type,and summarizes the research progress of classification and species distribution of Pyrus L.,which is of great significance for the protection,evaluation and utilization of germplasm resources.展开更多
Combined with tectonic evolution, a multi-isotopic method （δD, δ^18O, ^87Sr/^86Sr and ^14C） and hydrochemistry data have been used to study the origin and classification of geothermal water in the Guanzhong Basin....Combined with tectonic evolution, a multi-isotopic method （δD, δ^18O, ^87Sr/^86Sr and ^14C） and hydrochemistry data have been used to study the origin and classification of geothermal water in the Guanzhong Basin. The study shows that geothermal water of Xianli terrace primarily came from north- west direction when accepting recharge. A small amount supply source of geothermal water in Xi＇an City is from Qinling Mountain and the principal supply source comes from the west direction, but geothermal water of Chang＇an District mainly accepts supply from Qinling Mountain. Based on geothermal environ- ment is open or not, the degree of water-rock interaction, and the origin of geothermal water, geothermal water of the study area can be divided into four types： A, geothermal water of Gushi depression, perfect closed thermal environment and significant water-rock interaction, belonged to residual sedimentary wa- ter origin; B, geothermal water of Xianyang City, good closed environment and relatively significant water-rock interaction, belonged to residual sedimentary water origin mixed with fossil leaching water; C, geothermal water of Xi＇an City, half closed environment and some water-rock interaction, belonged to fossil leaching water origin; D, geothermal water of Chang＇an District, open environment and mixed with modern precipitation, belonged to fossil leaching water origin.展开更多
Disease identification for fruits and leaves in the field of agriculture is important for estimating production,crop yield,and earnings for farmers.In the specific case of pomegranates,this is challenging because of t...Disease identification for fruits and leaves in the field of agriculture is important for estimating production,crop yield,and earnings for farmers.In the specific case of pomegranates,this is challenging because of the wide range of possible diseases and their effects on the plant and the crop.This study presents an adaptive histogram-based method for solving this problem.Our method describe is domain independent in the sense that it can be easily and efficiently adapted to other similar smart agriculture tasks.The approach explores colour spaces,namely,Red,Green,and Blue along with Grey.The histograms of colour spaces and grey space are analysed based on the notion that as the disease changes,the colour also changes.The proximity between the histograms of grey images with individual colour spaces is estimated to find the closeness of images.Since the grey image is the average of colour spaces(R,G,and B),it can be considered a reference image.For estimating the distance between grey and colour spaces,the proposed approach uses a Chi-Square distance measure.Further,the method uses an Artificial Neural Network for classification.The effectiveness of our approach is demonstrated by testing on a dataset of fruit and leaf images affected by different diseases.The results show that the method outperforms existing techniques in terms of average classification rate.展开更多
Honey is a product of the elaboration of flower nectar by bees. The general features and elemental composition of honey depend on its botanical origin. In this study, five color parameters （L＊： lightness, a＊： red...Honey is a product of the elaboration of flower nectar by bees. The general features and elemental composition of honey depend on its botanical origin. In this study, five color parameters （L＊： lightness, a＊： red color, b＊： yellow color, C＊ab and hab） and five elements （Na, K, Mg, Ca and Zn） were determined and related with 91 Thai honey samples. The origins of four botanic types of （1） longan flower （Dimocarpus sp.）, （2） lynchee flower （Litchi sp.）, （3） sunflower （Helianthus sp.） and （4） wild flower （Eupatorium sp.） using principle component analysis （PCA）. The results showed that five color parameters and five metal contents related with the Thai botanic origins of the honeys using principle component analysis （PCA）. Six major indicators of PC i （variance is 44.33%） from three color parameters are L＊（-0.926）, a＊（0.927） and hue or hab （0.824） and from three metal contents are K（0.833）, Ca（0.816） and Mg（0.595）. Two minor indicators of PC2 （variance is 21.58%） from color parameters are b＊（-0.934） and Chroma or C＊ab （-0.834）. Two indicators of PC3 （%variance is 12.47%） from contents of Na （-0.722） and Zn （0.704）. Thai Lynchee （C） flower honeys classified using both six parameters in PC 1 and two color parameters in PC2. Thai longan flower （G） honeys classified using the contents of Zn and Na in PC3 parameters. Thai sunflower （S） honeys classified using two color parameters in PC2. Thai wild flower （W） honeys classified using the metal contents of K in PC 1 parameter, Zn and Na in PC3 parameters.展开更多
Automated and accurate movie genre classification is crucial for content organization,recommendation systems,and audience targeting in the film industry.Although most existing approaches focus on audiovisual features ...Automated and accurate movie genre classification is crucial for content organization,recommendation systems,and audience targeting in the film industry.Although most existing approaches focus on audiovisual features such as trailers and posters,the text-based classification remains underexplored despite its accessibility and semantic richness.This paper introduces the Genre Attention Model(GAM),a deep learning architecture that integrates transformer models with a hierarchical attention mechanism to extract and leverage contextual information from movie plots formulti-label genre classification.In order to assess its effectiveness,we assessmultiple transformer-based models,including Bidirectional Encoder Representations fromTransformers(BERT),ALite BERT(ALBERT),Distilled BERT(DistilBERT),Robustly Optimized BERT Pretraining Approach(RoBERTa),Efficiently Learning an Encoder that Classifies Token Replacements Accurately(ELECTRA),eXtreme Learning Network(XLNet)and Decodingenhanced BERT with Disentangled Attention(DeBERTa).Experimental results demonstrate the superior performance of DeBERTa-based GAM,which employs a two-tier hierarchical attention mechanism:word-level attention highlights key terms,while sentence-level attention captures critical narrative segments,ensuring a refined and interpretable representation of movie plots.Evaluated on three benchmark datasets Trailers12K,Large Movie Trailer Dataset-9(LMTD-9),and MovieLens37K.GAM achieves micro-average precision scores of 83.63%,83.32%,and 83.34%,respectively,surpassing state-of-the-artmodels.Additionally,GAMis computationally efficient,requiring just 6.10Giga Floating Point Operations Per Second(GFLOPS),making it a scalable and cost-effective solution.These results highlight the growing potential of text-based deep learning models in genre classification and GAM’s effectiveness in improving predictive accuracy while maintaining computational efficiency.With its robust performance,GAM offers a versatile and scalable framework for content recommendation,film indexing,and media analytics,providing an interpretable alternative to traditional audiovisual-based classification techniques.展开更多
In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering...In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering correction(MSC)-maximum-minimum normalization(MN)was identified as the optimal preprocessing technique.The competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA),and their combined methods were employed to extract feature wavelengths.Classification models based on back propagation(BP),support vector machine(SVM),random forest(RF),and partial least squares(PLS)were established using full-band data and feature wavelengths.Among all models,the(CARS-SPA)-BP model achieved the highest accuracy rate of 98.44%.This study offers novel insights and methodologies for the rapid and accurate identification of corn seeds as well as other crop seeds.展开更多
Accurate identification of natural gas origin is fundamental to the theoretical research on natural gas geosciences and the exploration deployment and resource potential assessment of oil and gas.Since the 1970s,Acade...Accurate identification of natural gas origin is fundamental to the theoretical research on natural gas geosciences and the exploration deployment and resource potential assessment of oil and gas.Since the 1970s,Academician Dai Jinxing has developed a comprehensive system for natural gas origin determination,grounded in geochemical theory and practice,and based on the integrated analysis of stable isotopic compositions,molecular composition,light hydrocarbon fingerprints,and geological context.This paper systematically reviews the core framework established by him and his team according to related references and application results,focusing on the conceptual design and technical pathways of key diagnostic diagrams such asδ^(13)C_(1)-C_(1)/(C_(2)+C_(3)),δ^(13)C_(1)-δ^(13)C_(2)-δ^(13)C_(3),δ^(13)CCO_(2)versus CO_(2)content,and the C7light hydrocarbon ternary plot.We evaluate the applicability and innovation of these tools in distinguishing between oil-type gas,coal-derived gas,microbial gas,and abiogenic gas,as well as in identifying mixed-source gases and multi-stage charging systems.The findings suggest that this identification system has significantly advanced natural gas geochemical interpretation in China,shifting from single-indicator analyses to multi-parameter integration and from qualitative assessments to systematic graphical identification,and has also exerted considerable influence on international research in natural gas geochemistry.The structured overview of the development trajectory of natural gas origin discrimination methodologies provides a technical support for natural gas geological theory and practice and offers a scientific foundation for the academic evaluation and application of related achievements.展开更多
Objective To provide a theoretical basis for the adjustment of the registration classification of China’s biological products,and to establish a continuously improved registration classification system.Methods Based ...Objective To provide a theoretical basis for the adjustment of the registration classification of China’s biological products,and to establish a continuously improved registration classification system.Methods Based on literature research,the specific classification methods,classification principles and considerations of biological registration in China,the United States and the European Union were studied to form a complete comparative analysis.Results and Conclusion It is recommended that the division between therapeutic and preventive use should be removed from the registration classification of biologics.The therapeutic,preventive and diagnostic use of the product should be limited as part of the product specification,and the registration should be classified according to the development of biotechnology,innovation,modification and bio-similar drugs.In addition,the supervision of registration of advanced therapeutic products should be different from that of traditional biologics.展开更多
In the context of the rapid development of digital education,the security of educational data has become an increasing concern.This paper explores strategies for the classification and grading of educational data,and ...In the context of the rapid development of digital education,the security of educational data has become an increasing concern.This paper explores strategies for the classification and grading of educational data,and constructs a higher educational data security management and control model centered on the integration of medical and educational data.By implementing a multi-dimensional strategy of dynamic classification,real-time authorization,and secure execution through educational data security levels,dynamic access control is applied to effectively enhance the security and controllability of educational data,providing a secure foundation for data sharing and openness.展开更多
Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or...Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.展开更多
We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hie...We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.展开更多
Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networ...Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.展开更多
Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services...Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services is influenced by species diversity,tree health,and the distribution and the composition of trees.Traditionally,data on urban trees has been collected through field surveys and manual interpretation of remote sensing images.In this study,we evaluated the effectiveness of multispectral airborne laser scanning(ALS)data in classifying 24 common urban roadside tree species in Espoo,Finland.Tree crown structure information,intensity features,and spectral data were used for classification.Eight different machine learning algorithms were tested,with the extra trees(ET)algorithm performing the best,achieving an overall accuracy of 71.7%using multispectral LiDAR data.This result highlights that integrating structural and spectral information within a single framework can improve the classification accuracy.Future research will focus on identifying the most important features for species classification and developing algorithms with greater efficiency and accuracy.展开更多
If the singularity of the cosmic Big Bang is taken as the origin of the reference coordinate system,the surrounding vacuum in the initial moments of it would exhibit radially-outward right-handed spiral motion at ligh...If the singularity of the cosmic Big Bang is taken as the origin of the reference coordinate system,the surrounding vacuum in the initial moments of it would exhibit radially-outward right-handed spiral motion at light speed.Based on this spatial motion hypothesis,we derive a unified field equation and a set of Maxwell’s equations for vacuum SWs(Scalar Waves)generating a huge spiral force field that drives the energy to spiral inwardly and distort,leading to the formation of mass.Furthermore,they also uncover that mass is fundamentally an ultimate expression of energy,manifesting as the result of spiral motion of space at light speed.And then,we indirectly validate the theory that coherent light waves’collision generate SWs and subsequently mass through the experiment verifying the Breit-Wheeler process.The establishment of our theory offers a new analytical tool for the exploration of mass origin,the cosmic Big Bang,unified field theories.展开更多
The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textile...The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles.By fusing band combination optimization with deep learning,this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line.By applying hyperspectral imaging and a one-dimensional deep learning algorithm,we detect and classify impurities in seed cotton after harvest.The main categories detected include pure cotton,conveyor belt,film covering seed cotton,and film adhered to the conveyor belt.The proposed method achieves an impurity detection rate of 99.698%.To further ensure the feasibility and practical application potential of this strategy,we compare our results against existing mainstream methods.In addition,the model shows excellent recognition performance on pseudo-color images of real samples.With a processing time of 11.764μs per pixel from experimental data,it shows a much improved speed requirement while maintaining the accuracy of real production lines.This strategy provides an accurate and efficient method for removing impurities during cotton processing.展开更多
Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronar...Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image classification.Image denoising is done by a U-Net architecture that ensures effective image denoising.Attenuation correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of classification.Finally,a novel multi-scale diluted convolution(MSDC)network is proposed.It merges the features extracted in different scales and makes the model learn the features more efficiently.Three scales of filters with size 3×3 are used to extract features.All three steps are compared with state-of-the-art methods.The proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of 39.7.The proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.展开更多
文摘The goal of this study was to use Fourier transform mid-infrared （FTIR） spectroscopy for discrimination of samples of pods and seeds of carob from three Moroccan regions. The origin of samples Pods and seeds of carob could be distinguished from their IR spectra and this measurement was used for discriminate analysis. A multivariate analysis procedure based on the combined use of Hierarchical Cluster Aanalysis （HCA） and Partial Least Squares-Discriminant Analysis （PLS-DA） was tested and provided good classification results. Three distinctive clusters were recognised, related to the three Moroccan regions. Afterwards, PLS-DA was used for the discrimination and classification of the origin of the various Pods and seeds of carob samples. The results demonstrated that the combined use of FTIR and chemometric analysis （cluster analysis and discrimination by PLS- DA） can be used to rapidly and simply determine the origin of carob pulpe samples.
基金Supported by the Natural Science Foundation of Henan Provincial Department of Science and Technology(222300420508)Henan Provincial Key Science and Technology Research Project(202102310478)+1 种基金the Ph D Research Fund of Pingdingshan University(PXY-BSQD-2012009)Training Program for Young Backbone Teachers in Higher Education Institutions in Henan Province(2021GGJS147)。
文摘China is not only one of the origin centers of Pyrus L.,but also the earliest birthplace of Pyrus L.in the world.This paper reviews the evolution of Pyrus L.from the aspects of leaf edge morphology,inflorescence and fruit type,and summarizes the research progress of classification and species distribution of Pyrus L.,which is of great significance for the protection,evaluation and utilization of germplasm resources.
基金financially supported by the National Natural Science Foundation of China(No.41172211)
文摘Combined with tectonic evolution, a multi-isotopic method （δD, δ^18O, ^87Sr/^86Sr and ^14C） and hydrochemistry data have been used to study the origin and classification of geothermal water in the Guanzhong Basin. The study shows that geothermal water of Xianli terrace primarily came from north- west direction when accepting recharge. A small amount supply source of geothermal water in Xi＇an City is from Qinling Mountain and the principal supply source comes from the west direction, but geothermal water of Chang＇an District mainly accepts supply from Qinling Mountain. Based on geothermal environ- ment is open or not, the degree of water-rock interaction, and the origin of geothermal water, geothermal water of the study area can be divided into four types： A, geothermal water of Gushi depression, perfect closed thermal environment and significant water-rock interaction, belonged to residual sedimentary wa- ter origin; B, geothermal water of Xianyang City, good closed environment and relatively significant water-rock interaction, belonged to residual sedimentary water origin mixed with fossil leaching water; C, geothermal water of Xi＇an City, half closed environment and some water-rock interaction, belonged to fossil leaching water origin; D, geothermal water of Chang＇an District, open environment and mixed with modern precipitation, belonged to fossil leaching water origin.
文摘Disease identification for fruits and leaves in the field of agriculture is important for estimating production,crop yield,and earnings for farmers.In the specific case of pomegranates,this is challenging because of the wide range of possible diseases and their effects on the plant and the crop.This study presents an adaptive histogram-based method for solving this problem.Our method describe is domain independent in the sense that it can be easily and efficiently adapted to other similar smart agriculture tasks.The approach explores colour spaces,namely,Red,Green,and Blue along with Grey.The histograms of colour spaces and grey space are analysed based on the notion that as the disease changes,the colour also changes.The proximity between the histograms of grey images with individual colour spaces is estimated to find the closeness of images.Since the grey image is the average of colour spaces(R,G,and B),it can be considered a reference image.For estimating the distance between grey and colour spaces,the proposed approach uses a Chi-Square distance measure.Further,the method uses an Artificial Neural Network for classification.The effectiveness of our approach is demonstrated by testing on a dataset of fruit and leaf images affected by different diseases.The results show that the method outperforms existing techniques in terms of average classification rate.
文摘Honey is a product of the elaboration of flower nectar by bees. The general features and elemental composition of honey depend on its botanical origin. In this study, five color parameters （L＊： lightness, a＊： red color, b＊： yellow color, C＊ab and hab） and five elements （Na, K, Mg, Ca and Zn） were determined and related with 91 Thai honey samples. The origins of four botanic types of （1） longan flower （Dimocarpus sp.）, （2） lynchee flower （Litchi sp.）, （3） sunflower （Helianthus sp.） and （4） wild flower （Eupatorium sp.） using principle component analysis （PCA）. The results showed that five color parameters and five metal contents related with the Thai botanic origins of the honeys using principle component analysis （PCA）. Six major indicators of PC i （variance is 44.33%） from three color parameters are L＊（-0.926）, a＊（0.927） and hue or hab （0.824） and from three metal contents are K（0.833）, Ca（0.816） and Mg（0.595）. Two minor indicators of PC2 （variance is 21.58%） from color parameters are b＊（-0.934） and Chroma or C＊ab （-0.834）. Two indicators of PC3 （%variance is 12.47%） from contents of Na （-0.722） and Zn （0.704）. Thai Lynchee （C） flower honeys classified using both six parameters in PC 1 and two color parameters in PC2. Thai longan flower （G） honeys classified using the contents of Zn and Na in PC3 parameters. Thai sunflower （S） honeys classified using two color parameters in PC2. Thai wild flower （W） honeys classified using the metal contents of K in PC 1 parameter, Zn and Na in PC3 parameters.
基金would like to thank the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025).
文摘Automated and accurate movie genre classification is crucial for content organization,recommendation systems,and audience targeting in the film industry.Although most existing approaches focus on audiovisual features such as trailers and posters,the text-based classification remains underexplored despite its accessibility and semantic richness.This paper introduces the Genre Attention Model(GAM),a deep learning architecture that integrates transformer models with a hierarchical attention mechanism to extract and leverage contextual information from movie plots formulti-label genre classification.In order to assess its effectiveness,we assessmultiple transformer-based models,including Bidirectional Encoder Representations fromTransformers(BERT),ALite BERT(ALBERT),Distilled BERT(DistilBERT),Robustly Optimized BERT Pretraining Approach(RoBERTa),Efficiently Learning an Encoder that Classifies Token Replacements Accurately(ELECTRA),eXtreme Learning Network(XLNet)and Decodingenhanced BERT with Disentangled Attention(DeBERTa).Experimental results demonstrate the superior performance of DeBERTa-based GAM,which employs a two-tier hierarchical attention mechanism:word-level attention highlights key terms,while sentence-level attention captures critical narrative segments,ensuring a refined and interpretable representation of movie plots.Evaluated on three benchmark datasets Trailers12K,Large Movie Trailer Dataset-9(LMTD-9),and MovieLens37K.GAM achieves micro-average precision scores of 83.63%,83.32%,and 83.34%,respectively,surpassing state-of-the-artmodels.Additionally,GAMis computationally efficient,requiring just 6.10Giga Floating Point Operations Per Second(GFLOPS),making it a scalable and cost-effective solution.These results highlight the growing potential of text-based deep learning models in genre classification and GAM’s effectiveness in improving predictive accuracy while maintaining computational efficiency.With its robust performance,GAM offers a versatile and scalable framework for content recommendation,film indexing,and media analytics,providing an interpretable alternative to traditional audiovisual-based classification techniques.
基金supported by the Science and Technology Development Plan Project of Jilin Provincial Department of Science and Technology (No.20220203112S)the Jilin Provincial Department of Education Science and Technology Research Project (No.JJKH20210039KJ)。
文摘In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering correction(MSC)-maximum-minimum normalization(MN)was identified as the optimal preprocessing technique.The competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA),and their combined methods were employed to extract feature wavelengths.Classification models based on back propagation(BP),support vector machine(SVM),random forest(RF),and partial least squares(PLS)were established using full-band data and feature wavelengths.Among all models,the(CARS-SPA)-BP model achieved the highest accuracy rate of 98.44%.This study offers novel insights and methodologies for the rapid and accurate identification of corn seeds as well as other crop seeds.
基金Supported by the“14th Five-Year Plan”Prospective and Basic Research Project of CNP)(2021DJ0502)Open Project of Key Laboratory of Shale Gas Resource Exploration(Chongqing Institute of Geology and Mineral Resources),Ministry of Natural Resources(KLSGE-2023)National Natural Science Foundation of China(42172149,U2244209)。
文摘Accurate identification of natural gas origin is fundamental to the theoretical research on natural gas geosciences and the exploration deployment and resource potential assessment of oil and gas.Since the 1970s,Academician Dai Jinxing has developed a comprehensive system for natural gas origin determination,grounded in geochemical theory and practice,and based on the integrated analysis of stable isotopic compositions,molecular composition,light hydrocarbon fingerprints,and geological context.This paper systematically reviews the core framework established by him and his team according to related references and application results,focusing on the conceptual design and technical pathways of key diagnostic diagrams such asδ^(13)C_(1)-C_(1)/(C_(2)+C_(3)),δ^(13)C_(1)-δ^(13)C_(2)-δ^(13)C_(3),δ^(13)CCO_(2)versus CO_(2)content,and the C7light hydrocarbon ternary plot.We evaluate the applicability and innovation of these tools in distinguishing between oil-type gas,coal-derived gas,microbial gas,and abiogenic gas,as well as in identifying mixed-source gases and multi-stage charging systems.The findings suggest that this identification system has significantly advanced natural gas geochemical interpretation in China,shifting from single-indicator analyses to multi-parameter integration and from qualitative assessments to systematic graphical identification,and has also exerted considerable influence on international research in natural gas geochemistry.The structured overview of the development trajectory of natural gas origin discrimination methodologies provides a technical support for natural gas geological theory and practice and offers a scientific foundation for the academic evaluation and application of related achievements.
文摘Objective To provide a theoretical basis for the adjustment of the registration classification of China’s biological products,and to establish a continuously improved registration classification system.Methods Based on literature research,the specific classification methods,classification principles and considerations of biological registration in China,the United States and the European Union were studied to form a complete comparative analysis.Results and Conclusion It is recommended that the division between therapeutic and preventive use should be removed from the registration classification of biologics.The therapeutic,preventive and diagnostic use of the product should be limited as part of the product specification,and the registration should be classified according to the development of biotechnology,innovation,modification and bio-similar drugs.In addition,the supervision of registration of advanced therapeutic products should be different from that of traditional biologics.
基金supported by:the 2023 Basic Public Welfare Research Project of the Wenzhou Science and Technology Bureau“Research on Multi-Source Data Classification and Grading Standards and Intelligent Algorithms for Higher Education Institutions”(Project No.G2023094)Major Humanities and Social Sciences Research Projects in Zhejiang higher education institutions(Grant/Award Number:2024QN061)2023 Basic Public Welfare Research Project of Wenzhou(No.:S2023014).
文摘In the context of the rapid development of digital education,the security of educational data has become an increasing concern.This paper explores strategies for the classification and grading of educational data,and constructs a higher educational data security management and control model centered on the integration of medical and educational data.By implementing a multi-dimensional strategy of dynamic classification,real-time authorization,and secure execution through educational data security levels,dynamic access control is applied to effectively enhance the security and controllability of educational data,providing a secure foundation for data sharing and openness.
基金funded by Scientific Research Deanship at University of Hail-Saudi Arabia through Project Number RG-23092.
文摘Cyberbullying on social media poses significant psychological risks,yet most detection systems over-simplify the task by focusing on binary classification,ignoring nuanced categories like passive-aggressive remarks or indirect slurs.To address this gap,we propose a hybrid framework combining Term Frequency-Inverse Document Frequency(TF-IDF),word-to-vector(Word2Vec),and Bidirectional Encoder Representations from Transformers(BERT)based models for multi-class cyberbullying detection.Our approach integrates TF-IDF for lexical specificity and Word2Vec for semantic relationships,fused with BERT’s contextual embeddings to capture syntactic and semantic complexities.We evaluate the framework on a publicly available dataset of 47,000 annotated social media posts across five cyberbullying categories:age,ethnicity,gender,religion,and indirect aggression.Among BERT variants tested,BERT Base Un-Cased achieved the highest performance with 93%accuracy(standard deviation across±1%5-fold cross-validation)and an average AUC of 0.96,outperforming standalone TF-IDF(78%)and Word2Vec(82%)models.Notably,it achieved near-perfect AUC scores(0.99)for age and ethnicity-based bullying.A comparative analysis with state-of-the-art benchmarks,including Generative Pre-trained Transformer 2(GPT-2)and Text-to-Text Transfer Transformer(T5)models highlights BERT’s superiority in handling ambiguous language.This work advances cyberbullying detection by demonstrating how hybrid feature extraction and transformer models improve multi-class classification,offering a scalable solution for moderating nuanced harmful content.
基金supported by the National Natural Science Foundation of China (Nos.61806107 and 61702135)。
文摘We propose a hierarchical multi-scale attention mechanism-based model in response to the low accuracy and inefficient manual classification of existing oceanic biological image classification methods. Firstly, the hierarchical efficient multi-scale attention(H-EMA) module is designed for lightweight feature extraction, achieving outstanding performance at a relatively low cost. Secondly, an improved EfficientNetV2 block is used to integrate information from different scales better and enhance inter-layer message passing. Furthermore, introducing the convolutional block attention module(CBAM) enhances the model's perception of critical features, optimizing its generalization ability. Lastly, Focal Loss is introduced to adjust the weights of complex samples to address the issue of imbalanced categories in the dataset, further improving the model's performance. The model achieved 96.11% accuracy on the intertidal marine organism dataset of Nanji Islands and 84.78% accuracy on the CIFAR-100 dataset, demonstrating its strong generalization ability to meet the demands of oceanic biological image classification.
基金the Deanship of Graduate Studies and Scientific Research at Najran University,Saudi Arabia,for their financial support through the Easy Track Research program,grant code(NU/EFP/MRC/13).
文摘Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.
文摘Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services is influenced by species diversity,tree health,and the distribution and the composition of trees.Traditionally,data on urban trees has been collected through field surveys and manual interpretation of remote sensing images.In this study,we evaluated the effectiveness of multispectral airborne laser scanning(ALS)data in classifying 24 common urban roadside tree species in Espoo,Finland.Tree crown structure information,intensity features,and spectral data were used for classification.Eight different machine learning algorithms were tested,with the extra trees(ET)algorithm performing the best,achieving an overall accuracy of 71.7%using multispectral LiDAR data.This result highlights that integrating structural and spectral information within a single framework can improve the classification accuracy.Future research will focus on identifying the most important features for species classification and developing algorithms with greater efficiency and accuracy.
文摘If the singularity of the cosmic Big Bang is taken as the origin of the reference coordinate system,the surrounding vacuum in the initial moments of it would exhibit radially-outward right-handed spiral motion at light speed.Based on this spatial motion hypothesis,we derive a unified field equation and a set of Maxwell’s equations for vacuum SWs(Scalar Waves)generating a huge spiral force field that drives the energy to spiral inwardly and distort,leading to the formation of mass.Furthermore,they also uncover that mass is fundamentally an ultimate expression of energy,manifesting as the result of spiral motion of space at light speed.And then,we indirectly validate the theory that coherent light waves’collision generate SWs and subsequently mass through the experiment verifying the Breit-Wheeler process.The establishment of our theory offers a new analytical tool for the exploration of mass origin,the cosmic Big Bang,unified field theories.
基金supported in part by the Six Talent Peaks Project in Jiangsu Province under Grant 013040315in part by the China Textile Industry Federation Science and Technology Guidance Project under Grant 2017107+1 种基金in part by the National Natural Science Foundation of China under Grant 31570714in part by the China Scholarship Council under Grant 202108320290。
文摘The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles.By fusing band combination optimization with deep learning,this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line.By applying hyperspectral imaging and a one-dimensional deep learning algorithm,we detect and classify impurities in seed cotton after harvest.The main categories detected include pure cotton,conveyor belt,film covering seed cotton,and film adhered to the conveyor belt.The proposed method achieves an impurity detection rate of 99.698%.To further ensure the feasibility and practical application potential of this strategy,we compare our results against existing mainstream methods.In addition,the model shows excellent recognition performance on pseudo-color images of real samples.With a processing time of 11.764μs per pixel from experimental data,it shows a much improved speed requirement while maintaining the accuracy of real production lines.This strategy provides an accurate and efficient method for removing impurities during cotton processing.
基金the Research Grant of Kwangwoon University in 2024.
文摘Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image classification.Image denoising is done by a U-Net architecture that ensures effective image denoising.Attenuation correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of classification.Finally,a novel multi-scale diluted convolution(MSDC)network is proposed.It merges the features extracted in different scales and makes the model learn the features more efficiently.Three scales of filters with size 3×3 are used to extract features.All three steps are compared with state-of-the-art methods.The proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of 39.7.The proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.
