In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggreg...In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggregation U-shaped attention network structure of MAAUNet(MultiRes aggregation attention UNet)is proposed based on MultiResUNet.Firstly,aggregate connection is introduced from the original feature aggregation at the same level.Skip connection is redesigned to aggregate features of different semantic scales at the decoder subnet,and the problem of semantic gaps is further solved that may exist between skip connections.Secondly,after the multi-scale convolution module,a convolution block attention module is added to focus and integrate features in the two attention directions of channel and space to adaptively optimize the intermediate feature map.Finally,the original convolution block is improved.The convolution channels are expanded with a series convolution structure to complement each other and extract richer spatial features.Residual connections are retained and the convolution block is turned into a multi-channel convolution block.The model is made to extract multi-scale spatial features.The experimental results show that MAAUNet has strong competitiveness in challenging datasets,and shows good segmentation performance and stability in dealing with multi-scale input and noise interference.展开更多
The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.I...The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.展开更多
In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is pro...In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.展开更多
Ambiguous expression is a common phenomenon in facial expression recognition(FER).Because of the existence of ambiguous expression,the effect of FER is severely limited.The reason maybe that the single label of the da...Ambiguous expression is a common phenomenon in facial expression recognition(FER).Because of the existence of ambiguous expression,the effect of FER is severely limited.The reason maybe that the single label of the data cannot effectively describe complex emotional intentions which are vital in FER.Label distribution learning contains more information and is a possible way to solve this problem.To apply label distribution learning on FER,a label distribution expression recognition algorithm based on asymptotic truth value is proposed.Under the premise of not incorporating extraneous quantitative information,the original information of database is fully used to complete the generation and utilization of label distribution.Firstly,in training part,single label learning is used to collect the mean value of the overall distribution of data.Then,the true value of data label is approached gradually on the granularity of data batch.Finally,the whole network model is retrained using the generated label distribution data.Experimental results show that this method can improve the accuracy of the network model obviously,and has certain competitiveness compared with the advanced algorithms.展开更多
In automated industrial inspection,it is often necessary to train models on anomaly-free images and perform anomaly detection on products,which is also an important and challenging task in computer vision.The student-...In automated industrial inspection,it is often necessary to train models on anomaly-free images and perform anomaly detection on products,which is also an important and challenging task in computer vision.The student-teacher network trains students to regress the output of the teacher,and uses the difference between the output of the student network and the pre-trained teacher network to locate anomalies,which has achieved advanced results in the field of abnormal segmentation.However,it is slow to predict a picture,and no anomaly detection is performed.A multi-student teacher network is proposed,which uses multiple student networks to jointly regress the output of the teacher network,and the minimum square difference between the output of students and teachers in each dimension is selected as the difference value.The information in the middle layer of the network is used to represent each area of the image and calculate the anomaly distance for anomaly segmentation,and the maximum abnormal score is used to represent the abnormal degree of the image for abnormal detection.Experiments results on MVTec anomaly detection show that the algorithm predicts a picture in 0.17 s and can output anomaly detection results at the same time,with image AUROC reaching 91.1%and Pixel AUROC reaching 94.5%.On the wall tile dataset produced by taking pictures of real scenes,image AUROC reached 89.7%,and Pixel AUROC reached 89.1%.Compared with the original student-teacher network,the proposed method can quickly complete anomaly segmentation and anomaly detection tasks at the same time with better accuracy,and it also has better results in real applications.展开更多
Evolutionary algorithms(EAs)have been used in high utility itemset mining(HUIM)to address the problem of discover-ing high utility itemsets(HUIs)in the exponential search space.EAs have good running and mining perform...Evolutionary algorithms(EAs)have been used in high utility itemset mining(HUIM)to address the problem of discover-ing high utility itemsets(HUIs)in the exponential search space.EAs have good running and mining performance,but they still require huge computational resource and may miss many HUIs.Due to the good combination of EA and graphics processing unit(GPU),we propose a parallel genetic algorithm(GA)based on the platform of GPU for mining HUIM(PHUI-GA).The evolution steps with improvements are performed in central processing unit(CPU)and the CPU intensive steps are sent to GPU to eva-luate with multi-threaded processors.Experiments show that the mining performance of PHUI-GA outperforms the existing EAs.When mining 90%HUIs,the PHUI-GA is up to 188 times better than the existing EAs and up to 36 times better than the CPU parallel approach.展开更多
Instance segmentation plays an important role in image processing.The Deep Snake algorithm based on contour iteration deforms an initial bounding box to an instance contour end-to-end,which can improve the performance...Instance segmentation plays an important role in image processing.The Deep Snake algorithm based on contour iteration deforms an initial bounding box to an instance contour end-to-end,which can improve the performance of instance segmentation,but has defects such as slow segmentation speed and sub-optimal initial contour.To solve these problems,a real-time instance segmentation algorithm based on contour learning was proposed.Firstly,ShuffleNet V2 was used as backbone network,and the receptive field of the model was expanded by using a 5×5 convolution kernel.Secondly,a lightweight up-sampling module,multi-stage aggregation(MSA),performs residual fusion of multi-layer features,which not only improves segmentation speed,but also extracts effective features more comprehensively.Thirdly,a contour initialization method for network learning was designed,and a global contour feature aggregation mechanism was used to return a coarse contour,which solves the problem of excessive error between manually initialized contour and real contour.Finally,the Snake deformation module was used to iteratively optimize the coarse contour to obtain the final instance contour.The experimental results showed that the proposed method improved the instance segmentation accuracy on semantic boundaries dataset(SBD),Cityscapes and Kins datasets,and the average precision reached 55.8 on the SBD;Compared with Deep Snake,the model parameters were reduced by 87.2%,calculation amount was reduced by 78.3%,and segmentation speed reached 39.8 frame·s−1 when instance segmentation was performed on an image with a size of 512×512 pixels on a 2080Ti GPU.The proposed method can reduce resource consumption,realize instance segmentation tasks quickly and accurately,and therefore is more suitable for embedded platforms with limited resources.展开更多
The K-multiple-means(KMM)retains the simple and efficient advantages of the K-means algorithm by setting multiple subclasses,and improves its effect on non-convex data sets.And aiming at the problem that it cannot be ...The K-multiple-means(KMM)retains the simple and efficient advantages of the K-means algorithm by setting multiple subclasses,and improves its effect on non-convex data sets.And aiming at the problem that it cannot be applied to the Internet on a multi-view data set,a multi-view K-multiple-means(MKMM)clustering method is proposed in this paper.The new algorithm introduces view weight parameter,reserves the design of setting multiple subclasses,makes the number of clusters as constraint and obtains clusters by solving optimization problem.The new algorithm is compared with some popular multi-view clustering algorithms.The effectiveness of the new algorithm is proved through the analysis of the experimental results.展开更多
Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-...Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.展开更多
Due to the increasing demand for microbially manufactured products in various industries,it has become important to find optimal designs for microbial cell factories by changing the direction of metabolic flow and its...Due to the increasing demand for microbially manufactured products in various industries,it has become important to find optimal designs for microbial cell factories by changing the direction of metabolic flow and its flux size by means of metabolic engineering such as knocking out competing pathways and introducing exogenous pathways to increase the yield of desired products.Recently,with the gradual cross-fertilization between computer science and bioinformatics fields,machine learning and intelligent optimization-based approaches have received much attention in Genome-scale metabolic network models(GSMMs)based on constrained optimization methods,and many high-quality related works have been published.Therefore,this paper focuses on the advances and applications of machine learning and intelligent optimization algorithms in metabolic engineering,with special emphasis on GSMMs.Specifically,the development history of GSMMs is first reviewed.Then,the analysis methods of GSMMs based on constraint optimization are presented.Next,this paper mainly reviews the development and application of machine learning and intelligent optimization algorithms in genome-scale metabolic models.In addition,the research gaps and future research potential in machine learning and intelligent optimization methods applied in GSMMs are discussed.展开更多
In pattern recognition,the task of image set classification has often been performed by representing data using symmetric positive definite(SPD)matrices,in conjunction with the metric of the resulting Riemannian manif...In pattern recognition,the task of image set classification has often been performed by representing data using symmetric positive definite(SPD)matrices,in conjunction with the metric of the resulting Riemannian manifold.In this paper,we propose a new data representation framework for image sets which we call component symmetric positive definite representation(CSPD).Firstly,we obtain sub-image sets by dividing the images in the set into square blocks of the same size,and use a traditional SPD model to describe them.Then,we use the Riemannian kernel to determine similarities of corresponding subimage sets.Finally,the CSPD matrix appears in the form of the kernel matrix for all the sub-image sets;its i,j-th entry measures the similarity between the i-th and j-th sub-image sets.The Riemannian kernel is shown to satisfy Mercer’s theorem,so the CSPD matrix is symmetric and positive definite,and also lies on a Riemannian manifold.Test on three benchmark datasets shows that CSPD is both lower-dimensional and more discriminative data descriptor than standard SPD for the task of image set classification.展开更多
High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data mining.However,most HUIM algorithms are mainly developed on a single machine,w...High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data mining.However,most HUIM algorithms are mainly developed on a single machine,which is inefficient for big data since limited memory and processing capacities are available.A parallel efficient high-utility itemset mining(P-EFIM)algorithm is proposed based on the Hadoop platform to solve this problem in this paper.In P-EFIM,the transaction-weighted utilization values are calculated and ordered for the itemsets with the MapReduce framework.Then the ordered itemsets are renumbered,and the low-utility itemsets are pruned to improve the dataset utility.In the Map phase,the P-EFIM algorithm divides the task into multiple independent subtasks.It uses the proposed S-style distribution strategy to distribute the subtasks evenly across all nodes to ensure load-balancing.Furthermore,the P-EFIM uses the EFIM algorithm to mine each subtask dataset to enhance the performance in the Reduce phase.Experiments are performed on eight datasets,and the results show that the runtime performance of P-EFIM is significantly higher than that of the PHUI-Growth,which is also HUIM algorithm based on the Hadoop framework.展开更多
基金National Natural Science Foundation of China(No.61806006)Jiangsu University Superior Discipline Construction Project。
文摘In view of the problems of multi-scale changes of segmentation targets,noise interference,rough segmentation results and slow training process faced by medical image semantic segmentation,a multi-scale residual aggregation U-shaped attention network structure of MAAUNet(MultiRes aggregation attention UNet)is proposed based on MultiResUNet.Firstly,aggregate connection is introduced from the original feature aggregation at the same level.Skip connection is redesigned to aggregate features of different semantic scales at the decoder subnet,and the problem of semantic gaps is further solved that may exist between skip connections.Secondly,after the multi-scale convolution module,a convolution block attention module is added to focus and integrate features in the two attention directions of channel and space to adaptively optimize the intermediate feature map.Finally,the original convolution block is improved.The convolution channels are expanded with a series convolution structure to complement each other and extract richer spatial features.Residual connections are retained and the convolution block is turned into a multi-channel convolution block.The model is made to extract multi-scale spatial features.The experimental results show that MAAUNet has strong competitiveness in challenging datasets,and shows good segmentation performance and stability in dealing with multi-scale input and noise interference.
基金National Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)University Superior Discipline Construction Project of Jiangsu Province。
文摘The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.
基金National Youth Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)Jiangsu University Superior Discipline Construction Project。
文摘In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.
基金National Youth Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)Project Supported by Jiangsu University Superior Discipline Construction Project。
文摘Ambiguous expression is a common phenomenon in facial expression recognition(FER).Because of the existence of ambiguous expression,the effect of FER is severely limited.The reason maybe that the single label of the data cannot effectively describe complex emotional intentions which are vital in FER.Label distribution learning contains more information and is a possible way to solve this problem.To apply label distribution learning on FER,a label distribution expression recognition algorithm based on asymptotic truth value is proposed.Under the premise of not incorporating extraneous quantitative information,the original information of database is fully used to complete the generation and utilization of label distribution.Firstly,in training part,single label learning is used to collect the mean value of the overall distribution of data.Then,the true value of data label is approached gradually on the granularity of data batch.Finally,the whole network model is retrained using the generated label distribution data.Experimental results show that this method can improve the accuracy of the network model obviously,and has certain competitiveness compared with the advanced algorithms.
基金National Natural Science Foundation of China(No.21706096)Natural Science Foundation of Jiangsu Province(No.BK20160162)。
文摘In automated industrial inspection,it is often necessary to train models on anomaly-free images and perform anomaly detection on products,which is also an important and challenging task in computer vision.The student-teacher network trains students to regress the output of the teacher,and uses the difference between the output of the student network and the pre-trained teacher network to locate anomalies,which has achieved advanced results in the field of abnormal segmentation.However,it is slow to predict a picture,and no anomaly detection is performed.A multi-student teacher network is proposed,which uses multiple student networks to jointly regress the output of the teacher network,and the minimum square difference between the output of students and teachers in each dimension is selected as the difference value.The information in the middle layer of the network is used to represent each area of the image and calculate the anomaly distance for anomaly segmentation,and the maximum abnormal score is used to represent the abnormal degree of the image for abnormal detection.Experiments results on MVTec anomaly detection show that the algorithm predicts a picture in 0.17 s and can output anomaly detection results at the same time,with image AUROC reaching 91.1%and Pixel AUROC reaching 94.5%.On the wall tile dataset produced by taking pictures of real scenes,image AUROC reached 89.7%,and Pixel AUROC reached 89.1%.Compared with the original student-teacher network,the proposed method can quickly complete anomaly segmentation and anomaly detection tasks at the same time with better accuracy,and it also has better results in real applications.
基金This work was supported by the National Natural Science Foundation of China(62073155,62002137,62106088,62206113)the High-End Foreign Expert Recruitment Plan(G2023144007L)the Fundamental Research Funds for the Central Universities(JUSRP221028).
文摘Evolutionary algorithms(EAs)have been used in high utility itemset mining(HUIM)to address the problem of discover-ing high utility itemsets(HUIs)in the exponential search space.EAs have good running and mining performance,but they still require huge computational resource and may miss many HUIs.Due to the good combination of EA and graphics processing unit(GPU),we propose a parallel genetic algorithm(GA)based on the platform of GPU for mining HUIM(PHUI-GA).The evolution steps with improvements are performed in central processing unit(CPU)and the CPU intensive steps are sent to GPU to eva-luate with multi-threaded processors.Experiments show that the mining performance of PHUI-GA outperforms the existing EAs.When mining 90%HUIs,the PHUI-GA is up to 188 times better than the existing EAs and up to 36 times better than the CPU parallel approach.
基金supported by National Key Research and Development Program(No.2022YFE0112400)National Natural Science Foundation of China(No.21706096)Natural Science Foundation of Jiangsu Province(No.BK20160162).
文摘Instance segmentation plays an important role in image processing.The Deep Snake algorithm based on contour iteration deforms an initial bounding box to an instance contour end-to-end,which can improve the performance of instance segmentation,but has defects such as slow segmentation speed and sub-optimal initial contour.To solve these problems,a real-time instance segmentation algorithm based on contour learning was proposed.Firstly,ShuffleNet V2 was used as backbone network,and the receptive field of the model was expanded by using a 5×5 convolution kernel.Secondly,a lightweight up-sampling module,multi-stage aggregation(MSA),performs residual fusion of multi-layer features,which not only improves segmentation speed,but also extracts effective features more comprehensively.Thirdly,a contour initialization method for network learning was designed,and a global contour feature aggregation mechanism was used to return a coarse contour,which solves the problem of excessive error between manually initialized contour and real contour.Finally,the Snake deformation module was used to iteratively optimize the coarse contour to obtain the final instance contour.The experimental results showed that the proposed method improved the instance segmentation accuracy on semantic boundaries dataset(SBD),Cityscapes and Kins datasets,and the average precision reached 55.8 on the SBD;Compared with Deep Snake,the model parameters were reduced by 87.2%,calculation amount was reduced by 78.3%,and segmentation speed reached 39.8 frame·s−1 when instance segmentation was performed on an image with a size of 512×512 pixels on a 2080Ti GPU.The proposed method can reduce resource consumption,realize instance segmentation tasks quickly and accurately,and therefore is more suitable for embedded platforms with limited resources.
基金National Youth Natural Science Foundationof China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)Project Supported by Jiangsu University Superior Discipline Construction Project。
文摘The K-multiple-means(KMM)retains the simple and efficient advantages of the K-means algorithm by setting multiple subclasses,and improves its effect on non-convex data sets.And aiming at the problem that it cannot be applied to the Internet on a multi-view data set,a multi-view K-multiple-means(MKMM)clustering method is proposed in this paper.The new algorithm introduces view weight parameter,reserves the design of setting multiple subclasses,makes the number of clusters as constraint and obtains clusters by solving optimization problem.The new algorithm is compared with some popular multi-view clustering algorithms.The effectiveness of the new algorithm is proved through the analysis of the experimental results.
基金supported by National Natural Science Foundation of China(Nos.U1836218,62020106012,61672265 and 61902153)the 111 Project of Ministry of Education of China(No.B12018)+1 种基金the EPSRC Programme FACER2VM(No.EP/N007743/1)the EPSRC/MURI/Dstl Project under(No.EP/R013616/1.)。
文摘Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.
基金supported by the National key research and development program of China(Grant no.2020YFA0908303).
文摘Due to the increasing demand for microbially manufactured products in various industries,it has become important to find optimal designs for microbial cell factories by changing the direction of metabolic flow and its flux size by means of metabolic engineering such as knocking out competing pathways and introducing exogenous pathways to increase the yield of desired products.Recently,with the gradual cross-fertilization between computer science and bioinformatics fields,machine learning and intelligent optimization-based approaches have received much attention in Genome-scale metabolic network models(GSMMs)based on constrained optimization methods,and many high-quality related works have been published.Therefore,this paper focuses on the advances and applications of machine learning and intelligent optimization algorithms in metabolic engineering,with special emphasis on GSMMs.Specifically,the development history of GSMMs is first reviewed.Then,the analysis methods of GSMMs based on constraint optimization are presented.Next,this paper mainly reviews the development and application of machine learning and intelligent optimization algorithms in genome-scale metabolic models.In addition,the research gaps and future research potential in machine learning and intelligent optimization methods applied in GSMMs are discussed.
文摘In pattern recognition,the task of image set classification has often been performed by representing data using symmetric positive definite(SPD)matrices,in conjunction with the metric of the resulting Riemannian manifold.In this paper,we propose a new data representation framework for image sets which we call component symmetric positive definite representation(CSPD).Firstly,we obtain sub-image sets by dividing the images in the set into square blocks of the same size,and use a traditional SPD model to describe them.Then,we use the Riemannian kernel to determine similarities of corresponding subimage sets.Finally,the CSPD matrix appears in the form of the kernel matrix for all the sub-image sets;its i,j-th entry measures the similarity between the i-th and j-th sub-image sets.The Riemannian kernel is shown to satisfy Mercer’s theorem,so the CSPD matrix is symmetric and positive definite,and also lies on a Riemannian manifold.Test on three benchmark datasets shows that CSPD is both lower-dimensional and more discriminative data descriptor than standard SPD for the task of image set classification.
文摘High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data mining.However,most HUIM algorithms are mainly developed on a single machine,which is inefficient for big data since limited memory and processing capacities are available.A parallel efficient high-utility itemset mining(P-EFIM)algorithm is proposed based on the Hadoop platform to solve this problem in this paper.In P-EFIM,the transaction-weighted utilization values are calculated and ordered for the itemsets with the MapReduce framework.Then the ordered itemsets are renumbered,and the low-utility itemsets are pruned to improve the dataset utility.In the Map phase,the P-EFIM algorithm divides the task into multiple independent subtasks.It uses the proposed S-style distribution strategy to distribute the subtasks evenly across all nodes to ensure load-balancing.Furthermore,the P-EFIM uses the EFIM algorithm to mine each subtask dataset to enhance the performance in the Reduce phase.Experiments are performed on eight datasets,and the results show that the runtime performance of P-EFIM is significantly higher than that of the PHUI-Growth,which is also HUIM algorithm based on the Hadoop framework.
