Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimoda...Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.展开更多
Purpose-As intelligent technology advances,practical applications often involve data with multiple labels.Therefore,multi-label feature selection methods have attracted much attention to extract valuable information.H...Purpose-As intelligent technology advances,practical applications often involve data with multiple labels.Therefore,multi-label feature selection methods have attracted much attention to extract valuable information.However,current methods tend to lack interpretability when evaluating the relationship between different types of variables without considering the potential causal relationship.Design/methodology/approach-To address the above problems,we propose an ensemble causal feature selection method based on mutual information and group fusion strategy(CMIFS)for multi-label data.First,the causal relationship between labels and features is analyzed by local causal structure learning,respectively,to obtain a causal feature set.Second,we eliminate false positive features from the obtained feature set using mutual information to improve the feature subset reliability.Eventually,we employ a group fusion strategy to fuse the obtained feature subsets from multiple data sub-space to enhance the stability of the results.Findings-Experimental comparisons are performed on six datasets to validate that our proposal can enhance the interpretation and robustness of the model compared with other methods in different metrics.Furthermore,the statistical analyses further validate the effectiveness of our approach.Originality/value-The present study makes a noteworthy contribution to proposing a causal feature selection approach based on mutual information to obtain an approximate optimal feature subset for multilabel data.Additionally,our proposal adopts the group fusion strategy to guarantee the robustness of the obtained feature subset.展开更多
Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images.However,existing method...Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images.However,existing methods often fail to distinguish salient objects from background regions,leading to detail suppression in salient regions due to global fusion strategies.This study presents a mask-guided latent low-rank representation fusion method to address this issue.First,the GrabCut algorithm is employed to extract a saliency mask,distinguishing salient regions from background regions.Then,latent low-rank representation(LatLRR)is applied to extract deep image features,enhancing key information extraction.In the fusion stage,a weighted fusion strategy strengthens infrared thermal information and visible texture details in salient regions,while an average fusion strategy improves background smoothness and stability.Experimental results on the TNO dataset demonstrate that the proposed method achieves superior performance in SPI,MI,Qabf,PSNR,and EN metrics,effectively preserving salient target details while maintaining balanced background information.Compared to state-of-the-art fusion methods,our approach achieves more stable and visually consistent fusion results.The fusion code is available on GitHub at:https://github.com/joyzhen1/Image(accessed on 15 January 2025).展开更多
Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit informati...Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit information,a Semi-supervised New Intent Discovery for Elastic Neighborhood Syntactic Elimination and Fusion model(SNID-ENSEF)is proposed.Syntactic elimination contrast learning leverages verb-dominant syntactic features,systematically replacing specific words to enhance data diversity.The radius of the positive sample neighborhood is elastically adjusted to eliminate invalid samples and improve training efficiency.A neighborhood sample fusion strategy,based on sample distribution patterns,dynamically adjusts neighborhood size and fuses sample vectors to reduce noise and improve implicit information utilization and discovery accuracy.Experimental results show that SNID-ENSEF achieves average improvements of 0.88%,1.27%,and 1.30%in Normalized Mutual Information(NMI),Accuracy(ACC),and Adjusted Rand Index(ARI),respectively,outperforming PTJN,DPN,MTP-CLNN,and DWG models on the Banking77,StackOverflow,and Clinc150 datasets.The code is available at https://github.com/qsdesz/SNID-ENSEF,accessed on 16 January 2025.展开更多
Image fusion has been developing into an important area of research. In remote sensing, the use of the same image sensor in different working modes, or different image sensors, can provide reinforcing or complementary...Image fusion has been developing into an important area of research. In remote sensing, the use of the same image sensor in different working modes, or different image sensors, can provide reinforcing or complementary information. Therefore, it is highly valuable to fuse outputs from multiple sensors (or the same sensor in different working modes) to improve the overall performance of the remote images, which are very useful for human visual perception and image processing task. Accordingly, in this paper, we first provide a comprehensive survey of the state of the art of multi-sensor image fusion methods in terms of three aspects: pixel-level fusion, feature-level fusion and decision-level fusion. An overview of existing fusion strategies is then introduced, after which the existing fusion quality measures are summarized. Finally, this review analyzes the development trends in fusion algorithms that may attract researchers to further explore the research in this field.展开更多
Real-time pedestrian detection is an important task for unmanned driving systems and video surveillance.The existing pedestrian detection methods often work at low speed and also fail to detect smaller and densely dis...Real-time pedestrian detection is an important task for unmanned driving systems and video surveillance.The existing pedestrian detection methods often work at low speed and also fail to detect smaller and densely distributed pedestrians by losing some of their detection accuracy in such cases.Therefore,the proposed algorithm YOLOv2(“YOU ONLY LOOK ONCE Version 2”)-based pedestrian detection(referred to as YOLOv2PD)would be more suitable for detecting smaller and densely distributed pedestrians in real-time complex road scenes.The proposed YOLOv2PD algorithm adopts a Multi-layer Feature Fusion(MLFF)strategy,which helps to improve the model’s feature extraction ability.In addition,one repeated convolution layer is removed from the final layer,which in turn reduces the computational complexity without losing any detection accuracy.The proposed algorithm applies the K-means clustering method on the Pascal Voc-2007+2012 pedestrian dataset before training to find the optimal anchor boxes.Both the proposed network structure and the loss function are improved to make the model more accurate and faster while detecting smaller pedestrians.Experimental results show that,at 544×544 image resolution,the proposed model achieves 80.7%average precision(AP),which is 2.1%higher than the YOLOv2 Model on the Pascal Voc-2007+2012 pedestrian dataset.Besides,based on the experimental results,the proposed model YOLOv2PD achieves a good trade-off balance between detection accuracy and real-time speed when evaluated on INRIA and Caltech test pedestrian datasets and achieves state-of-the-art detection results.展开更多
A novel approach （HGO-EAC） for hybrid genetic op-timization （GO） with elite ant colony （EAC） is proposed for the automatic modulation recognition of communication signals,through which we improve the basic ant c...A novel approach （HGO-EAC） for hybrid genetic op-timization （GO） with elite ant colony （EAC） is proposed for the automatic modulation recognition of communication signals,through which we improve the basic ant colony algorithms by referencing elite strategy and present a new fusion strategy for genetic optimization and elite ant colony. This approach is used to train the neural networks as the classifier for modulation. Simula-tion results indicate good performance on an additive white Gaus-sian noise （AWGN） channel,with recognition rate reaching to 70% especially for CW even at signal-to-noise ratios as low as 5 dB. This approach can achieve a high recognition rate for the typical modulations such as CW,4ASK,4FSK,BPSK,and QAM16. Test result shows that it has better performance than BP algorithm and basic ant colony algorithms by achieving faster training and stronger robustness.展开更多
Kindergarten is an important place to provide children with enlightenment education. Children's cognition in early childhood has not been fully formed. Therefore, early childhood is the key stage to cultivate chil...Kindergarten is an important place to provide children with enlightenment education. Children's cognition in early childhood has not been fully formed. Therefore, early childhood is the key stage to cultivate children's good moral quality and form good behavior habits. Game teaching method is an important teaching method in early childhood. The game teaching method can fully meet children's cognitive needs. The scientific and rational use of the game teaching method in kindergarten teaching can help children develop healthily physically and mentally, improve children's interest in learning, and mobilize children's initiative to participate in the collective.展开更多
To scientifically and objectively monitor the fermentation quality of black tea,a computer vision system(CVS)and electronic nose(e-nose)were employed to analyze the black tea image and odor eigenvalues of Yinghong No....To scientifically and objectively monitor the fermentation quality of black tea,a computer vision system(CVS)and electronic nose(e-nose)were employed to analyze the black tea image and odor eigenvalues of Yinghong No.9 black tea.First,the variation trends of tea polyphenols,volatile substances,image eigenvalues and odor eigenvalues with the extension of fermentation time were analyzed,and the fermentation process was categorized into three stages for classification.Second,principal component analysis(PCA)was employed on the image and odor eigenvalues obtained by CVS and e-nose.Partial least squares discriminant analysis(PLS-DA)was performed on 117 volatile components,and 51 differential volatiles were screened out based on variable importance in projection(VIP≥1)and one-way analysis of variance(P<0.05),including geraniol,linalool,nerolidol,and α-ionone.Then,image features and odor features are fused by using a data fusion strategy.Finally,the image,smell and fusion information were combined with random forest(RF),K-nearest neighbor(KNN)and support vector machine(SVM)to establish the classification models of different fermentation stages and to compare them.The results show that the feature-level fusion strategy integrating the SVM was the most efficient approach,with classification accuracy rates of 100%for the training sets and 95.6%for the testing sets.The performance of Support Vector Regression(SVR)prediction models for tea polyphenol content based on feature-level fusion data outperformed data-level models(Rc,RMSEC,Rp and RMSEP of 0.96,0.48 mg/g,0.94,0.6 mg/g).展开更多
In general,physicians make a preliminary diagnosis based on patients’admission narratives and admission conditions,largely depending on their experiences and professional knowledge.An automatic and accurate tentative...In general,physicians make a preliminary diagnosis based on patients’admission narratives and admission conditions,largely depending on their experiences and professional knowledge.An automatic and accurate tentative diagnosis based on clinical narratives would be of great importance to physicians,particularly in the shortage of medical resources.Despite its great value,little work has been conducted on this diagnosis method.Thus,in this study,we propose a fusion model that integrates the semantic and symptom features contained in the clinical text.The semantic features of the input text are initially captured by an attention-based Bidirectional Long Short-Term Memory(BiLSTM)network.The symptom concepts,recognized from the input text,are then vectorized by using the term frequency-inverse document frequency method based on the relations between symptoms and diseases.Finally,two fusion strategies are utilized to recommend the most potential candidate for the international classification of diseases code.Model training and evaluation are performed on a public clinical dataset.The results show that both fusion strategies achieved a promising performance,in which the best performance obtained a top-3 accuracy of 0.7412.展开更多
In order to improve the accuracy of hail forecasting for mountainous and plateau areas in China,this study presents a novel fusion forecast model based on machine learning techniques.Specifically,known mechanisms of h...In order to improve the accuracy of hail forecasting for mountainous and plateau areas in China,this study presents a novel fusion forecast model based on machine learning techniques.Specifically,known mechanisms of hail formation and two newly proposed elevation features calculated from radar data,sounding data,automatic station data,and terrain data,are firstly combined,from which a hail/short-duration heavy rainfall(SDHR)classification model based on the random forest(RF)algorithm is built up.Then,we construct a hail/SDHR probability identification(PI)model based on the Bayesian minimum error decision and principal component analysis methods.Finally,an"and"fusion strategy for coupling the RF and PI models is proposed.In addition to the mechanism features,the new elevation features improve the models’performance significantly.Experimental results show that the fusion strategy is particularly notable for reducing the number of false alarms on the premise of ensuring the hit rate.A comparison with two classical hail indexes shows that our proposed algorithm has a higher forecasting accuracy for hail in mountainous and plateau areas.All 19 hail cases used for testing could be identified,and our algorithm is able to provide an early warning for 89.5%(17 cases)of hail cases,among which 52.6%(10 cases)receive an early warning of more than 42 minutes in advance.The PI model sheds new light on using Bayesian classification approaches for highdimensional solutions.展开更多
The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition.In this study,a new method is proposed based on ensemble deep transfer lear...The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition.In this study,a new method is proposed based on ensemble deep transfer learning and multisensor signals to enhance the fault diagnosis adaptability and reliability of bevel gear under various operation conditions.First,a novel stacked autoencoder(NSAE)is constructed using a denoising autoencoder,batch normalization,and the Swish activation function.Second,a series of source-domain NSAEs with multisensor vibration signals is pretrained.Third,the good model parameters provided by the source-domain NSAEs are transferred to initialize the corresponding target-domain NSAEs.Finally,a modified voting fusion strategy is designed to obtain a comprehensive result.The multisensor signals collected under the different operation conditions of bevel gear are used to verify the proposed method.The comparison results show that the proposed method can diagnose different faults in an accurate and stable manner using only one target-domain sample,thereby outperforming the existing methods.展开更多
Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel...Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel tabu search algorithm(GPTS)for HW/SW partitioning.A single GPU kernel of compacting neighborhood is proposed to reduce the amount of GPU global memory accesses theoretically.A kernel fusion strategy is further proposed to reduce the amount of GPU global memory accesses of GPTS.To further minimize the transfer overhead of GPTS between CPU and GPU,an optimized transfer strategy for GPU-based tabu evaluation is proposed,which considers that all the candidates do not satisfy the given constraint.Experiments show that GPTS outperforms state-of-the-art work of tabu search and is competitive with other methods for HW/SW partitioning.The proposed parallelization is significant when considering the ordinary GPU platform.展开更多
基金funded by the National Natural Science Foundation of China (Grant No.61872126,No.62273290)supported by the Key project of Natural Science Foundation of Shandong Province (Grant No.ZR2020KF019).
文摘Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.
基金supported by the Nature Science Foundation of China(Grant No.62376114)the Nature Science Foundation of Fujian Province(Grant No.2021J011004,No.2021J011002)+1 种基金the Ministry of Education Industry-University-Research Innovation Program(Grant No.2021LDA09003)the Department of Education Foundation of Fujian Province(No.JAT210266)。
文摘Purpose-As intelligent technology advances,practical applications often involve data with multiple labels.Therefore,multi-label feature selection methods have attracted much attention to extract valuable information.However,current methods tend to lack interpretability when evaluating the relationship between different types of variables without considering the potential causal relationship.Design/methodology/approach-To address the above problems,we propose an ensemble causal feature selection method based on mutual information and group fusion strategy(CMIFS)for multi-label data.First,the causal relationship between labels and features is analyzed by local causal structure learning,respectively,to obtain a causal feature set.Second,we eliminate false positive features from the obtained feature set using mutual information to improve the feature subset reliability.Eventually,we employ a group fusion strategy to fuse the obtained feature subsets from multiple data sub-space to enhance the stability of the results.Findings-Experimental comparisons are performed on six datasets to validate that our proposal can enhance the interpretation and robustness of the model compared with other methods in different metrics.Furthermore,the statistical analyses further validate the effectiveness of our approach.Originality/value-The present study makes a noteworthy contribution to proposing a causal feature selection approach based on mutual information to obtain an approximate optimal feature subset for multilabel data.Additionally,our proposal adopts the group fusion strategy to guarantee the robustness of the obtained feature subset.
基金supported by Universiti Teknologi MARA through UiTM MyRA Research Grant,600-RMC 5/3/GPM(053/2022).
文摘Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images.However,existing methods often fail to distinguish salient objects from background regions,leading to detail suppression in salient regions due to global fusion strategies.This study presents a mask-guided latent low-rank representation fusion method to address this issue.First,the GrabCut algorithm is employed to extract a saliency mask,distinguishing salient regions from background regions.Then,latent low-rank representation(LatLRR)is applied to extract deep image features,enhancing key information extraction.In the fusion stage,a weighted fusion strategy strengthens infrared thermal information and visible texture details in salient regions,while an average fusion strategy improves background smoothness and stability.Experimental results on the TNO dataset demonstrate that the proposed method achieves superior performance in SPI,MI,Qabf,PSNR,and EN metrics,effectively preserving salient target details while maintaining balanced background information.Compared to state-of-the-art fusion methods,our approach achieves more stable and visually consistent fusion results.The fusion code is available on GitHub at:https://github.com/joyzhen1/Image(accessed on 15 January 2025).
基金supported by Research Projects of the Nature Science Foundation of Hebei Province(F2021402005).
文摘Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit information,a Semi-supervised New Intent Discovery for Elastic Neighborhood Syntactic Elimination and Fusion model(SNID-ENSEF)is proposed.Syntactic elimination contrast learning leverages verb-dominant syntactic features,systematically replacing specific words to enhance data diversity.The radius of the positive sample neighborhood is elastically adjusted to eliminate invalid samples and improve training efficiency.A neighborhood sample fusion strategy,based on sample distribution patterns,dynamically adjusts neighborhood size and fuses sample vectors to reduce noise and improve implicit information utilization and discovery accuracy.Experimental results show that SNID-ENSEF achieves average improvements of 0.88%,1.27%,and 1.30%in Normalized Mutual Information(NMI),Accuracy(ACC),and Adjusted Rand Index(ARI),respectively,outperforming PTJN,DPN,MTP-CLNN,and DWG models on the Banking77,StackOverflow,and Clinc150 datasets.The code is available at https://github.com/qsdesz/SNID-ENSEF,accessed on 16 January 2025.
文摘Image fusion has been developing into an important area of research. In remote sensing, the use of the same image sensor in different working modes, or different image sensors, can provide reinforcing or complementary information. Therefore, it is highly valuable to fuse outputs from multiple sensors (or the same sensor in different working modes) to improve the overall performance of the remote images, which are very useful for human visual perception and image processing task. Accordingly, in this paper, we first provide a comprehensive survey of the state of the art of multi-sensor image fusion methods in terms of three aspects: pixel-level fusion, feature-level fusion and decision-level fusion. An overview of existing fusion strategies is then introduced, after which the existing fusion quality measures are summarized. Finally, this review analyzes the development trends in fusion algorithms that may attract researchers to further explore the research in this field.
基金The authors are grateful to the Deanship of Scientific Research,King Saud University,Riyadh,Saudi Arabia,for funding this work through the Vice Deanship of Scientific Research Chairs:Research Chair of Pervasive and Mobile Computing.
文摘Real-time pedestrian detection is an important task for unmanned driving systems and video surveillance.The existing pedestrian detection methods often work at low speed and also fail to detect smaller and densely distributed pedestrians by losing some of their detection accuracy in such cases.Therefore,the proposed algorithm YOLOv2(“YOU ONLY LOOK ONCE Version 2”)-based pedestrian detection(referred to as YOLOv2PD)would be more suitable for detecting smaller and densely distributed pedestrians in real-time complex road scenes.The proposed YOLOv2PD algorithm adopts a Multi-layer Feature Fusion(MLFF)strategy,which helps to improve the model’s feature extraction ability.In addition,one repeated convolution layer is removed from the final layer,which in turn reduces the computational complexity without losing any detection accuracy.The proposed algorithm applies the K-means clustering method on the Pascal Voc-2007+2012 pedestrian dataset before training to find the optimal anchor boxes.Both the proposed network structure and the loss function are improved to make the model more accurate and faster while detecting smaller pedestrians.Experimental results show that,at 544×544 image resolution,the proposed model achieves 80.7%average precision(AP),which is 2.1%higher than the YOLOv2 Model on the Pascal Voc-2007+2012 pedestrian dataset.Besides,based on the experimental results,the proposed model YOLOv2PD achieves a good trade-off balance between detection accuracy and real-time speed when evaluated on INRIA and Caltech test pedestrian datasets and achieves state-of-the-art detection results.
基金Supported by the National Natural Science Foundation of China (41001195)
文摘A novel approach （HGO-EAC） for hybrid genetic op-timization （GO） with elite ant colony （EAC） is proposed for the automatic modulation recognition of communication signals,through which we improve the basic ant colony algorithms by referencing elite strategy and present a new fusion strategy for genetic optimization and elite ant colony. This approach is used to train the neural networks as the classifier for modulation. Simula-tion results indicate good performance on an additive white Gaus-sian noise （AWGN） channel,with recognition rate reaching to 70% especially for CW even at signal-to-noise ratios as low as 5 dB. This approach can achieve a high recognition rate for the typical modulations such as CW,4ASK,4FSK,BPSK,and QAM16. Test result shows that it has better performance than BP algorithm and basic ant colony algorithms by achieving faster training and stronger robustness.
文摘Kindergarten is an important place to provide children with enlightenment education. Children's cognition in early childhood has not been fully formed. Therefore, early childhood is the key stage to cultivate children's good moral quality and form good behavior habits. Game teaching method is an important teaching method in early childhood. The game teaching method can fully meet children's cognitive needs. The scientific and rational use of the game teaching method in kindergarten teaching can help children develop healthily physically and mentally, improve children's interest in learning, and mobilize children's initiative to participate in the collective.
基金The authors gratefully acknowledge financial support from the Open Project of Guangdong Provincial Key Laboratory of Tea Plant Resources Innovation and Utilization(2020KF02)Guangzhou Science and Technology Program Project(202002020079)+1 种基金Guangdong Provincial Special Fund for Modern Agriculture Industry Technology Innovation Teams(2022KJ120)Qingyuan Science and Technology Program Project(2022KJJH065).
文摘To scientifically and objectively monitor the fermentation quality of black tea,a computer vision system(CVS)and electronic nose(e-nose)were employed to analyze the black tea image and odor eigenvalues of Yinghong No.9 black tea.First,the variation trends of tea polyphenols,volatile substances,image eigenvalues and odor eigenvalues with the extension of fermentation time were analyzed,and the fermentation process was categorized into three stages for classification.Second,principal component analysis(PCA)was employed on the image and odor eigenvalues obtained by CVS and e-nose.Partial least squares discriminant analysis(PLS-DA)was performed on 117 volatile components,and 51 differential volatiles were screened out based on variable importance in projection(VIP≥1)and one-way analysis of variance(P<0.05),including geraniol,linalool,nerolidol,and α-ionone.Then,image features and odor features are fused by using a data fusion strategy.Finally,the image,smell and fusion information were combined with random forest(RF),K-nearest neighbor(KNN)and support vector machine(SVM)to establish the classification models of different fermentation stages and to compare them.The results show that the feature-level fusion strategy integrating the SVM was the most efficient approach,with classification accuracy rates of 100%for the training sets and 95.6%for the testing sets.The performance of Support Vector Regression(SVR)prediction models for tea polyphenol content based on feature-level fusion data outperformed data-level models(Rc,RMSEC,Rp and RMSEP of 0.96,0.48 mg/g,0.94,0.6 mg/g).
基金We thank the anonymous reviewers for their helpful comments.This work was supported in part by the Science and Technology Major Project of Changsha(No.kh2202004)the National Natural Science Foundation of China(No.62006251)。
文摘In general,physicians make a preliminary diagnosis based on patients’admission narratives and admission conditions,largely depending on their experiences and professional knowledge.An automatic and accurate tentative diagnosis based on clinical narratives would be of great importance to physicians,particularly in the shortage of medical resources.Despite its great value,little work has been conducted on this diagnosis method.Thus,in this study,we propose a fusion model that integrates the semantic and symptom features contained in the clinical text.The semantic features of the input text are initially captured by an attention-based Bidirectional Long Short-Term Memory(BiLSTM)network.The symptom concepts,recognized from the input text,are then vectorized by using the term frequency-inverse document frequency method based on the relations between symptoms and diseases.Finally,two fusion strategies are utilized to recommend the most potential candidate for the international classification of diseases code.Model training and evaluation are performed on a public clinical dataset.The results show that both fusion strategies achieved a promising performance,in which the best performance obtained a top-3 accuracy of 0.7412.
基金Supported by the Natural Science Foundation of TianjinChina(14JCYBJC21800)。
文摘In order to improve the accuracy of hail forecasting for mountainous and plateau areas in China,this study presents a novel fusion forecast model based on machine learning techniques.Specifically,known mechanisms of hail formation and two newly proposed elevation features calculated from radar data,sounding data,automatic station data,and terrain data,are firstly combined,from which a hail/short-duration heavy rainfall(SDHR)classification model based on the random forest(RF)algorithm is built up.Then,we construct a hail/SDHR probability identification(PI)model based on the Bayesian minimum error decision and principal component analysis methods.Finally,an"and"fusion strategy for coupling the RF and PI models is proposed.In addition to the mechanism features,the new elevation features improve the models’performance significantly.Experimental results show that the fusion strategy is particularly notable for reducing the number of false alarms on the premise of ensuring the hit rate.A comparison with two classical hail indexes shows that our proposed algorithm has a higher forecasting accuracy for hail in mountainous and plateau areas.All 19 hail cases used for testing could be identified,and our algorithm is able to provide an early warning for 89.5%(17 cases)of hail cases,among which 52.6%(10 cases)receive an early warning of more than 42 minutes in advance.The PI model sheds new light on using Bayesian classification approaches for highdimensional solutions.
基金the National Natural Science Foundation of China(Grant No.51905160)the Natural Science Foundation of Hunan Province(Grant No.2020JJ5072)the Fundamental Research Funds for the Central Universities(Grant No.531118010335)。
文摘The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition.In this study,a new method is proposed based on ensemble deep transfer learning and multisensor signals to enhance the fault diagnosis adaptability and reliability of bevel gear under various operation conditions.First,a novel stacked autoencoder(NSAE)is constructed using a denoising autoencoder,batch normalization,and the Swish activation function.Second,a series of source-domain NSAEs with multisensor vibration signals is pretrained.Third,the good model parameters provided by the source-domain NSAEs are transferred to initialize the corresponding target-domain NSAEs.Finally,a modified voting fusion strategy is designed to obtain a comprehensive result.The multisensor signals collected under the different operation conditions of bevel gear are used to verify the proposed method.The comparison results show that the proposed method can diagnose different faults in an accurate and stable manner using only one target-domain sample,thereby outperforming the existing methods.
基金This paper was supported by the National Natural Science Foundation of China(Grant No.61472289)National Key Research and Development Project(2016YFC0106305).We also would like to thank the anonymous reviewers for their valuable and constructive comments.
文摘Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel tabu search algorithm(GPTS)for HW/SW partitioning.A single GPU kernel of compacting neighborhood is proposed to reduce the amount of GPU global memory accesses theoretically.A kernel fusion strategy is further proposed to reduce the amount of GPU global memory accesses of GPTS.To further minimize the transfer overhead of GPTS between CPU and GPU,an optimized transfer strategy for GPU-based tabu evaluation is proposed,which considers that all the candidates do not satisfy the given constraint.Experiments show that GPTS outperforms state-of-the-art work of tabu search and is competitive with other methods for HW/SW partitioning.The proposed parallelization is significant when considering the ordinary GPU platform.
