Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noti...Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.展开更多
Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already fe...Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already few.Even established nations would not be in a perfect position to manage this epidemic correctly,leaving emerging countries and countries that have not yet begun to grow to address the problem.These problems can be solved by using machine learning models in a realistic way,such as by using computer-aided images during medical examinations.These models help predict the effects of the disease outbreak and help detect the effects in the coming days.In this paper,Multi-Features Decease Analysis(MFDA)is used with different ensemble classifiers to diagnose the disease’s impact with the help of Computed Tomography(CT)scan images.There are various features associated with chest CT images,which help know the possibility of an individual being affected and how COVID-19 will affect the persons suffering from pneumonia.The current study attempts to increase the precision of the diagnosis model by evaluating various feature sets and choosing the best combination for better results.The model’s performance is assessed using Receiver Operating Characteristic(ROC)curve,the Root Mean Square Error(RMSE),and the Confusion Matrix.It is observed from the resultant outcome that the performance of the proposed model has exhibited better efficient.展开更多
In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The e...In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.展开更多
This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data a...This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data and historical academic performance)with dynamic behavioral patterns(e.g.,real-time interactions and evolving interests over time).The research employs Term Frequency-Inverse Document Frequency(TF-IDF)for semantic feature extraction,integrates the Analytic Hierarchy Process(AHP)for feature weighting,and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’interests.Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’behaviors and provides context-aware learning resource recommendations.The study introduces a novel paradigm for learner modeling in educational technology,combining methodological innovation with a scalable technical architecture,thereby laying a foundation for the development of adaptive learning systems.展开更多
The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland im...The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland image segmentation and extraction.An EnFCM remote sensing forest land extraction method based on PCA multi-feature fusion was proposed.Firstly,histogram equalization was applied to improve the image contrast.Secondly,the texture and edge features of the image were extracted,and a multi-feature fused pixel image was generated using the PCA technique.Moreover,the fused feature was used as a feature constraint to measure the difference of pixels instead of a single grey-scale feature.Finally,an improved feature distance metric calculated the similarity between the pixel points and the cluster center to complete the cluster segmentation.The experimental results showed that the error was between 1.5%and 4.0%compared with the forested area counted by experts’hand-drawing,which could obtain a high accuracy segmentation and extraction result.展开更多
Closed circuit television(CCTV)systems are widely used to inspect sewer pipe conditions.During the diagnosis process,the manual diagnosis of defects is time consuming,labor intensive and error prone.To assist inspecto...Closed circuit television(CCTV)systems are widely used to inspect sewer pipe conditions.During the diagnosis process,the manual diagnosis of defects is time consuming,labor intensive and error prone.To assist inspectors in diagnosing sewer pipe defects on CCTV inspection images,this paper presents an image recognition algorithm that applies features extraction and machine learning approaches.An algorithm of image recognition techniques,including Hu invariant moment,texture features,lateral Fourier transform and Daubechies(DBn)wavelet transform,was used to describe the features of defects,and support vector machines were used to classify sewer pipe defects.According to the inspection results,seven defects were defined;the diagnostic system was applied to a sewer pipe system in a southern city of China,and 28,760 m of sewer pipes were inspected.The results revealed that the classification accuracies of the different defects ranged from 51.6% to 99.3%.The overall accuracy reached 84.1%.The diagnosing accuracy depended on the number of the training samples,and four fitting curves were applied to fit the data.According to this paper,the logarithmic fitting curve presents the highest coefficient of determination of 0.882,and more than 200 images need to be used for training samples to guarantee the accuracy higher than 85%.展开更多
In this paper,a fast and effective method based on multiple image features and a weighted K-means clustering algorithm is proposed to achieve the automatic grading of apples.The method provides a novel way of using fo...In this paper,a fast and effective method based on multiple image features and a weighted K-means clustering algorithm is proposed to achieve the automatic grading of apples.The method provides a novel way of using four images(top,bottom and two sides)and average gray values for each apple to distinguish between the apple defects,stem and calyx.Furthermore,weighted features(MCSAD(maximum cross-sectional average diameter),circularity,PRA(proportion of red area)and defect regions)were carefully selected according to the requirements of the national apple grading standard,which improves the practicality of the proposed method.Finally,qualitative and quantitative evaluation results demonstrate that the total accuracy of the proposed multi-feature grading method is greater than 96%,which provides encouragement for the additional research and implementation of multifeature automatic grading for the fruit industry.展开更多
In recent years,in order to achieve the goal of“carbon peaking and carbon neutralization”,many countries have focused on the development of clean energy,and the prediction of photovoltaic power generation has become...In recent years,in order to achieve the goal of“carbon peaking and carbon neutralization”,many countries have focused on the development of clean energy,and the prediction of photovoltaic power generation has become a hot research topic.However,many traditional methods only use meteorological factors such as temperature and irradiance as the features of photovoltaic power generation,and they rarely consider the multi-features fusion methods for power prediction.This paper first preprocesses abnormal data points and missing values in the data from 18 power stations in Northwest China,and then carries out correlation analysis to screen out 8 meteorological features as the most relevant to power generation.Next,the historical generating power and 8 meteorological features are fused in different ways to construct three types of experimental datasets.Finally,traditional time series prediction methods,such as Recurrent Neural Network(RNN),Convolution Neural Network(CNN)combined with eXtreme Gradient Boosting(XGBoost),are applied to study the impact of different feature fusion methods on power prediction.The results show that the prediction accuracy of Long Short-Term Memory(LSTM),stacked Long Short-Term Memory(stacked LSTM),Bi-directional LSTM(Bi-LSTM),Temporal Convolutional Network(TCN),and XGBoost algorithms can be greatly improved by the method of integrating historical generation power and meteorological features.Therefore,the feature fusion based photovoltaic power prediction method proposed in this paper is of great significance to the development of the photovoltaic power generation industry.展开更多
Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity...Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.展开更多
Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend o...Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.展开更多
In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,th...In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.展开更多
This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chin...This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.展开更多
The compressive strength of the pellets is a key indicator that determines the production efficiency in straight grate.It usually relies on manual sampling and testing,which is cumbersome and inefficient.To address th...The compressive strength of the pellets is a key indicator that determines the production efficiency in straight grate.It usually relies on manual sampling and testing,which is cumbersome and inefficient.To address this,a time series prediction model for pellet compressive strength was developed,combining a gradient boosting decision tree with a temporal convolutional network(GBDT-TCN).Firstly,the key physical characteristics of the pellet production process were established through the feature construction method,and then the multicollinear features were eliminated based on the Spearman correlation coefficient.The final selection of feature parameters,amounting to 9,was determined using recursive feature elimination(RFE)method.Finally,the GBDT algorithm was used to establish the nonlinear relationship between these features and the compressive strength.The GBDT prediction results and process data were constructed into a time series dataset,which was input into the TCN unit cascade model.The time series information was captured through the distribution coefficient of the loss function in the time series.Results illustrate that the GBDT-TCN method proposed performs well in the task of predicting the compressive strength of pellets.Compared with the prediction model using only GBDT,the accuracy within±100 N is increased from 83.33%to 90.00%.展开更多
Since the problems of branch loss and fracture in retinal blood vessel segmentation algorithms,an image segmentation method is proposed based on improved pulse coupled neural network(PCNN)and gray wolf optimization al...Since the problems of branch loss and fracture in retinal blood vessel segmentation algorithms,an image segmentation method is proposed based on improved pulse coupled neural network(PCNN)and gray wolf optimization algorithm(GWO).Simplifying the neuron input domain and neuron connection domain of the PCNN network,increasing the gradient information factor in the internal activity items,reducing the model parameters,enhancing the pulse issuing ability,and the optimal parameters of the network are automatically obtained based on multiple feature evaluation criteria and the GWO algorithm.The test in the public data set drive shows that the sensitivity,accuracy,precision,and specificity of the algorithm are 0.799549,0.962789,0.889163,and 0.986552,respectively.The accuracy and specificity are better than the classical segmentation algorithm.It solved the influence of low illumination,optic disc highlight,and foveal shadow on vascular segmentation,and showed excellent performance of vessel connectivity and terminal sensitivity.展开更多
In space probes,anomaly detection of sequence data collected by various sensors is essential to help detect potential faults promptly,improve the reliability of equipment operation,and ensure the smooth operation of t...In space probes,anomaly detection of sequence data collected by various sensors is essential to help detect potential faults promptly,improve the reliability of equipment operation,and ensure the smooth operation of the mission.However,sensors'signals often contain a superposition of various frequencies,changing fluctuations,and correlations between features.This complexity of data attributes makes building effective models challenging.This paper proposes a TimeEvolving Multi-Period Observational(TEMPO)anomaly detection method for space probes.First,fusing wavelet analysis and natural periods improves the ability to capture multi-period features in data.Then,the feature extraction framework proposed enhances the effectiveness of anomaly detection by comprehensively extracting the complex features of data through the multi-module synergy of temporal and channel.The results demonstrate that the proposed method enhances anomaly detection accuracy and its effectiveness is confirmed.Additionally,the ablation experiment results further validate the efficacy of each module.An evaluation of the algorithm's computational complexity confirms its suitability for real-time processing.展开更多
Counterfeit agricultural products pose a significant challenge to global food security and economic stability, necessitating advanced detection mechanisms to ensure authenticity and quality. To address this pressing i...Counterfeit agricultural products pose a significant challenge to global food security and economic stability, necessitating advanced detection mechanisms to ensure authenticity and quality. To address this pressing issue, we introduce iGFruit, an innovative model designed to enhance the detection of counterfeit agricultural products by integrating multimodal data processing. Our approach utilizes both image and text data for comprehensive feature extraction, employing advanced backbone models such as Vision Transformer (ViT), Normalizer-Free Network (NFNet), and Bidirectional Encoder Representations from Transformers (BERT). These extracted features are fused and processed using a Graph Attention Network (GAT) to capture intricate relationships within the multimodal data. The resulting fused representation is subsequently classified to detect counterfeit products with high precision. We validate the effectiveness of iGFruit through extensive experiments on two datasets: the publicly available MIT-States dataset and the proprietary TLU-States dataset, achieving state-of-the-art performance on both benchmarks. Specifically, iGFruit demonstrates an improvement of over 3% in average accuracy compared to baseline models, all while maintaining computational efficiency during inference. This work underscores the necessity and innovativeness of integrating graph-based feature learning to tackle the critical issue of counterfeit agricultural product detection.展开更多
Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of int...Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.展开更多
The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to ide...The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to identify flow regime in two-phase flow was presented. Firstly, gas-liquid two-phase flow images including bub- bly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques. To improve the performance of a multiple classifier system, the rough sets theory was used for reducing the inessential factors. Furthermore, the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples, and the flow regime intelligent identification was realized. The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow, and achieved higher identification ability than that of single characteristic. The overall identification accuracy was 100%, and an estimate of the image processing time was 8 ms for online flow regime identification.展开更多
Massive open online courses(MOOC)have recently gained worldwide attention in the field of education.The manner of MOOC provides a new option for learning various kinds of knowledge.A mass of data miming algorithms hav...Massive open online courses(MOOC)have recently gained worldwide attention in the field of education.The manner of MOOC provides a new option for learning various kinds of knowledge.A mass of data miming algorithms have been proposed to analyze the learner’s characteristics and classify the learners into different groups.However,most current algorithms mainly focus on the final grade of the learners,which may result in an improper classification.To overcome the shortages of the existing algorithms,a novel multi-feature weighting based K-means(MFWK-means)algorithm is proposed in this paper.Correlations between the widely used feature grade and other features are first investigated,and then the learners are classified based on their grades and weighted features with the proposed MFWK-means algorithm.Experimental results with the Canvas Network Person-Course(CNPC)dataset demonstrate the effectiveness of our method.Moreover,a comparison between the new MFWK-means and the traditional K-means clustering algorithm is implemented to show the superiority of the proposed method.展开更多
As a new type of Denial of Service(DoS)attacks,the Low-rate Denial of Service(LDoS)attacks make the traditional method of detecting Distributed Denial of Service Attack(DDoS)attacks useless due to the characteristics ...As a new type of Denial of Service(DoS)attacks,the Low-rate Denial of Service(LDoS)attacks make the traditional method of detecting Distributed Denial of Service Attack(DDoS)attacks useless due to the characteristics of a low average rate and concealment.With features extracted from the network traffic,a new detection approach based on multi-feature fusion is proposed to solve the problem in this paper.An attack feature set containing the Acknowledge character(ACK)sequence number,the packet size,and the queue length is used to classify normal and LDoS attack traffics.Each feature is digitalized and preprocessed to fit the input of the K-Nearest Neighbor(KNN)classifier separately,and to obtain the decision contour matrix.Then a posteriori probability in the matrix is fused,and the fusion decision index D is used as the basis of detecting the LDoS attacks.Experiments proved that the detection rate of the multi-feature fusion algorithm is higher than those of the single-based detection method and other algorithms.展开更多
基金The paper is supported by the Research Foundation for OutstandingYoung Teachers , China University of Geosciences ( Wuhan) ( No .CUGQNL0616) Research Foundationfor State Key Laboratory of Geo-logical Processes and Mineral Resources ( No . MGMR2002-02)Hubei Provincial Depart ment of Education (B) .
文摘Urban land provides a suitable location for various economic activities which affect the development of surrounding areas. With rapid industrialization and urbanization, the contradictions in land-use become more noticeable. Urban administrators and decision-makers seek modern methods and technology to provide information support for urban growth. Recently, with the fast development of high-resolution sensor technology, more relevant data can be obtained, which is an advantage in studying the sustainable development of urban land-use. However, these data are only information sources and are a mixture of ＂information＂ and ＂noise＂. Processing, analysis and information extraction from remote sensing data is necessary to provide useful information. This paper extracts urban land-use information from a high-resolution image by using the multi-feature information of the image objects, and adopts an object-oriented image analysis approach and multi-scale image segmentation technology. A classification and extraction model is set up based on the multi-features of the image objects, in order to contribute to information for reasonable planning and effective management. This new image analysis approach offers a satisfactory solution for extracting information quickly and efficiently.
基金This work was supported by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia(Project no.GRANT 324).
文摘Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already few.Even established nations would not be in a perfect position to manage this epidemic correctly,leaving emerging countries and countries that have not yet begun to grow to address the problem.These problems can be solved by using machine learning models in a realistic way,such as by using computer-aided images during medical examinations.These models help predict the effects of the disease outbreak and help detect the effects in the coming days.In this paper,Multi-Features Decease Analysis(MFDA)is used with different ensemble classifiers to diagnose the disease’s impact with the help of Computed Tomography(CT)scan images.There are various features associated with chest CT images,which help know the possibility of an individual being affected and how COVID-19 will affect the persons suffering from pneumonia.The current study attempts to increase the precision of the diagnosis model by evaluating various feature sets and choosing the best combination for better results.The model’s performance is assessed using Receiver Operating Characteristic(ROC)curve,the Root Mean Square Error(RMSE),and the Confusion Matrix.It is observed from the resultant outcome that the performance of the proposed model has exhibited better efficient.
基金supported by the National Natural Science Foundation of China(Nos.12072027,62103052,61603346 and 62103379)the Henan Key Laboratory of General Aviation Technology,China(No.ZHKF-230201)+3 种基金the Funding for the Open Research Project of the Rotor Aerodynamics Key Laboratory,China(No.RAL20200101)the Key Research and Development Program of Henan Province,China(Nos.241111222000 and 241111222900)the Key Science and Technology Program of Henan Province,China(No.232102220067)the Scholarship Funding from the China Scholarship Council(No.202206030079).
文摘In global navigation satellite system denial environment,cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle(UAV)systems.The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms,such as UAV-view and satellite-view images.However,images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform,view,and timing.The existing methods predominantly extract features by segmenting feature maps,which overlook the holistic semantic distribution and structural information of objects,resulting in loss of image information.To address these challenges,dilated neighborhood attention Transformer is employed as the feature extraction backbone,and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation(MMHCA)is proposed.In the proposed MMHCA method,the multiscale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels,establishing feature associations of contextual information with global and local information in the image.Subsequently,the multi-feature representations method is utilized to obtain rich discriminative feature information,bolstering the robustness of model in scenarios characterized by positional shifts,varying distances,and scale ambiguities.Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques.showing outstanding results in UAV localization and navigation.
基金This work is supported by the Ministry of Education of Humanities and Social Science projects in China(No.20YJCZH124)Guangdong Province Education and Teaching Reform Project No.640:Research on the Teaching Practice and Application of Online Peer Assessment Methods in the Context of Artificial Intelligence.
文摘This study proposes a learner profile framework based on multi-feature fusion,aiming to enhance the precision of personalized learning recommendations by integrating learners’static attributes(e.g.,demographic data and historical academic performance)with dynamic behavioral patterns(e.g.,real-time interactions and evolving interests over time).The research employs Term Frequency-Inverse Document Frequency(TF-IDF)for semantic feature extraction,integrates the Analytic Hierarchy Process(AHP)for feature weighting,and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’interests.Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’behaviors and provides context-aware learning resource recommendations.The study introduces a novel paradigm for learner modeling in educational technology,combining methodological innovation with a scalable technical architecture,thereby laying a foundation for the development of adaptive learning systems.
基金supported by National Natural Science Foundation of China(No.61761027)Gansu Young Doctor’s Fund for Higher Education Institutions(No.2021QB-053)。
文摘The traditional EnFCM(Enhanced fuzzy C-means)algorithm only considers the grey-scale features in image segmentation,resulting in less than satisfactory results when the algorithm is used for remote sensing woodland image segmentation and extraction.An EnFCM remote sensing forest land extraction method based on PCA multi-feature fusion was proposed.Firstly,histogram equalization was applied to improve the image contrast.Secondly,the texture and edge features of the image were extracted,and a multi-feature fused pixel image was generated using the PCA technique.Moreover,the fused feature was used as a feature constraint to measure the difference of pixels instead of a single grey-scale feature.Finally,an improved feature distance metric calculated the similarity between the pixel points and the cluster center to complete the cluster segmentation.The experimental results showed that the error was between 1.5%and 4.0%compared with the forested area counted by experts’hand-drawing,which could obtain a high accuracy segmentation and extraction result.
文摘Closed circuit television(CCTV)systems are widely used to inspect sewer pipe conditions.During the diagnosis process,the manual diagnosis of defects is time consuming,labor intensive and error prone.To assist inspectors in diagnosing sewer pipe defects on CCTV inspection images,this paper presents an image recognition algorithm that applies features extraction and machine learning approaches.An algorithm of image recognition techniques,including Hu invariant moment,texture features,lateral Fourier transform and Daubechies(DBn)wavelet transform,was used to describe the features of defects,and support vector machines were used to classify sewer pipe defects.According to the inspection results,seven defects were defined;the diagnostic system was applied to a sewer pipe system in a southern city of China,and 28,760 m of sewer pipes were inspected.The results revealed that the classification accuracies of the different defects ranged from 51.6% to 99.3%.The overall accuracy reached 84.1%.The diagnosing accuracy depended on the number of the training samples,and four fitting curves were applied to fit the data.According to this paper,the logarithmic fitting curve presents the highest coefficient of determination of 0.882,and more than 200 images need to be used for training samples to guarantee the accuracy higher than 85%.
基金This research was mainly supported by the Collaborative Innovation Center of Henan Grain Crops,Zhengzhou and by the National Key research and development programof China(No.2017YFD0301105)Key science and Technology Program of Henan Province(No.192102110196).
文摘In this paper,a fast and effective method based on multiple image features and a weighted K-means clustering algorithm is proposed to achieve the automatic grading of apples.The method provides a novel way of using four images(top,bottom and two sides)and average gray values for each apple to distinguish between the apple defects,stem and calyx.Furthermore,weighted features(MCSAD(maximum cross-sectional average diameter),circularity,PRA(proportion of red area)and defect regions)were carefully selected according to the requirements of the national apple grading standard,which improves the practicality of the proposed method.Finally,qualitative and quantitative evaluation results demonstrate that the total accuracy of the proposed multi-feature grading method is greater than 96%,which provides encouragement for the additional research and implementation of multifeature automatic grading for the fruit industry.
基金supported by the State Grid Gansu Electric Power Research Institute(Nos.SGGSKY00WYJS2100164 and 52272220002W).
文摘In recent years,in order to achieve the goal of“carbon peaking and carbon neutralization”,many countries have focused on the development of clean energy,and the prediction of photovoltaic power generation has become a hot research topic.However,many traditional methods only use meteorological factors such as temperature and irradiance as the features of photovoltaic power generation,and they rarely consider the multi-features fusion methods for power prediction.This paper first preprocesses abnormal data points and missing values in the data from 18 power stations in Northwest China,and then carries out correlation analysis to screen out 8 meteorological features as the most relevant to power generation.Next,the historical generating power and 8 meteorological features are fused in different ways to construct three types of experimental datasets.Finally,traditional time series prediction methods,such as Recurrent Neural Network(RNN),Convolution Neural Network(CNN)combined with eXtreme Gradient Boosting(XGBoost),are applied to study the impact of different feature fusion methods on power prediction.The results show that the prediction accuracy of Long Short-Term Memory(LSTM),stacked Long Short-Term Memory(stacked LSTM),Bi-directional LSTM(Bi-LSTM),Temporal Convolutional Network(TCN),and XGBoost algorithms can be greatly improved by the method of integrating historical generation power and meteorological features.Therefore,the feature fusion based photovoltaic power prediction method proposed in this paper is of great significance to the development of the photovoltaic power generation industry.
基金This study was supported by the National Natural Science Foundation of China(61911540482 and 61702324).
文摘Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.
基金funded by the Science and Technology Project of China Southern Power Grid(YNKJXM20210175)the National Natural Science Foundation of China(52177070).
文摘Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.
基金supported by the National Natural Science Foundation of China(62073036,62076031)Beijing Natural Science Foundation(4242049).
文摘In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.
文摘This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.
基金supported by the National Key Research and Development Program of China(No.2023YFC3707002).
文摘The compressive strength of the pellets is a key indicator that determines the production efficiency in straight grate.It usually relies on manual sampling and testing,which is cumbersome and inefficient.To address this,a time series prediction model for pellet compressive strength was developed,combining a gradient boosting decision tree with a temporal convolutional network(GBDT-TCN).Firstly,the key physical characteristics of the pellet production process were established through the feature construction method,and then the multicollinear features were eliminated based on the Spearman correlation coefficient.The final selection of feature parameters,amounting to 9,was determined using recursive feature elimination(RFE)method.Finally,the GBDT algorithm was used to establish the nonlinear relationship between these features and the compressive strength.The GBDT prediction results and process data were constructed into a time series dataset,which was input into the TCN unit cascade model.The time series information was captured through the distribution coefficient of the loss function in the time series.Results illustrate that the GBDT-TCN method proposed performs well in the task of predicting the compressive strength of pellets.Compared with the prediction model using only GBDT,the accuracy within±100 N is increased from 83.33%to 90.00%.
基金The 2019 Guangdong Province General College Youth Innovation Talent Project(2019GKQNCX009)。
文摘Since the problems of branch loss and fracture in retinal blood vessel segmentation algorithms,an image segmentation method is proposed based on improved pulse coupled neural network(PCNN)and gray wolf optimization algorithm(GWO).Simplifying the neuron input domain and neuron connection domain of the PCNN network,increasing the gradient information factor in the internal activity items,reducing the model parameters,enhancing the pulse issuing ability,and the optimal parameters of the network are automatically obtained based on multiple feature evaluation criteria and the GWO algorithm.The test in the public data set drive shows that the sensitivity,accuracy,precision,and specificity of the algorithm are 0.799549,0.962789,0.889163,and 0.986552,respectively.The accuracy and specificity are better than the classical segmentation algorithm.It solved the influence of low illumination,optic disc highlight,and foveal shadow on vascular segmentation,and showed excellent performance of vessel connectivity and terminal sensitivity.
基金supported by the National Natural Science Foundation of China(Nos.92467108,62141604,62032016,92467206)Beijing Nova Program,China No.(20220484106,20230484451)。
文摘In space probes,anomaly detection of sequence data collected by various sensors is essential to help detect potential faults promptly,improve the reliability of equipment operation,and ensure the smooth operation of the mission.However,sensors'signals often contain a superposition of various frequencies,changing fluctuations,and correlations between features.This complexity of data attributes makes building effective models challenging.This paper proposes a TimeEvolving Multi-Period Observational(TEMPO)anomaly detection method for space probes.First,fusing wavelet analysis and natural periods improves the ability to capture multi-period features in data.Then,the feature extraction framework proposed enhances the effectiveness of anomaly detection by comprehensively extracting the complex features of data through the multi-module synergy of temporal and channel.The results demonstrate that the proposed method enhances anomaly detection accuracy and its effectiveness is confirmed.Additionally,the ablation experiment results further validate the efficacy of each module.An evaluation of the algorithm's computational complexity confirms its suitability for real-time processing.
文摘Counterfeit agricultural products pose a significant challenge to global food security and economic stability, necessitating advanced detection mechanisms to ensure authenticity and quality. To address this pressing issue, we introduce iGFruit, an innovative model designed to enhance the detection of counterfeit agricultural products by integrating multimodal data processing. Our approach utilizes both image and text data for comprehensive feature extraction, employing advanced backbone models such as Vision Transformer (ViT), Normalizer-Free Network (NFNet), and Bidirectional Encoder Representations from Transformers (BERT). These extracted features are fused and processed using a Graph Attention Network (GAT) to capture intricate relationships within the multimodal data. The resulting fused representation is subsequently classified to detect counterfeit products with high precision. We validate the effectiveness of iGFruit through extensive experiments on two datasets: the publicly available MIT-States dataset and the proprietary TLU-States dataset, achieving state-of-the-art performance on both benchmarks. Specifically, iGFruit demonstrates an improvement of over 3% in average accuracy compared to baseline models, all while maintaining computational efficiency during inference. This work underscores the necessity and innovativeness of integrating graph-based feature learning to tackle the critical issue of counterfeit agricultural product detection.
基金This work was supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401+1 种基金in part,by the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant Numbers SJCX21_0363in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.
基金Supported by the National Natural Science Foundation of China （50706006） and the Science and Technology Development Program of Jilin Province （20040513）.
文摘The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to identify flow regime in two-phase flow was presented. Firstly, gas-liquid two-phase flow images including bub- bly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques. To improve the performance of a multiple classifier system, the rough sets theory was used for reducing the inessential factors. Furthermore, the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples, and the flow regime intelligent identification was realized. The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow, and achieved higher identification ability than that of single characteristic. The overall identification accuracy was 100%, and an estimate of the image processing time was 8 ms for online flow regime identification.
文摘Massive open online courses(MOOC)have recently gained worldwide attention in the field of education.The manner of MOOC provides a new option for learning various kinds of knowledge.A mass of data miming algorithms have been proposed to analyze the learner’s characteristics and classify the learners into different groups.However,most current algorithms mainly focus on the final grade of the learners,which may result in an improper classification.To overcome the shortages of the existing algorithms,a novel multi-feature weighting based K-means(MFWK-means)algorithm is proposed in this paper.Correlations between the widely used feature grade and other features are first investigated,and then the learners are classified based on their grades and weighted features with the proposed MFWK-means algorithm.Experimental results with the Canvas Network Person-Course(CNPC)dataset demonstrate the effectiveness of our method.Moreover,a comparison between the new MFWK-means and the traditional K-means clustering algorithm is implemented to show the superiority of the proposed method.
基金the National Natural Science Foundation of China-Civil Aviation joint fund(U1933108)the Fundamental Research Funds for the Central Universities of China(3122019051).
文摘As a new type of Denial of Service(DoS)attacks,the Low-rate Denial of Service(LDoS)attacks make the traditional method of detecting Distributed Denial of Service Attack(DDoS)attacks useless due to the characteristics of a low average rate and concealment.With features extracted from the network traffic,a new detection approach based on multi-feature fusion is proposed to solve the problem in this paper.An attack feature set containing the Acknowledge character(ACK)sequence number,the packet size,and the queue length is used to classify normal and LDoS attack traffics.Each feature is digitalized and preprocessed to fit the input of the K-Nearest Neighbor(KNN)classifier separately,and to obtain the decision contour matrix.Then a posteriori probability in the matrix is fused,and the fusion decision index D is used as the basis of detecting the LDoS attacks.Experiments proved that the detection rate of the multi-feature fusion algorithm is higher than those of the single-based detection method and other algorithms.
