[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
With the increasing complexity of industrial processes, the high-dimensional industrial data exhibit a strong nonlinearity, bringing considerable challenges to the fault diagnosis of industrial processes. To efficient...With the increasing complexity of industrial processes, the high-dimensional industrial data exhibit a strong nonlinearity, bringing considerable challenges to the fault diagnosis of industrial processes. To efficiently extract deep meaningful features that are crucial for fault diagnosis, a sparse Gaussian feature extractor(SGFE) is designed to learn a nonlinear mapping that projects the raw data into the feature space with the fault label dimension. The feature space is described by the one-hot encoding of the fault category label as an orthogonal basis. In this way, the deep sparse Gaussian features related to fault categories can be gradually learned from the raw data by SGFE. In the feature space,the sparse Gaussian(SG) loss function is designed to constrain the distribution of features to multiple sparse multivariate Gaussian distributions. The sparse Gaussian features are linearly separable in the feature space, which is conducive to improving the accuracy of the downstream fault classification task. The feasibility and practical utility of the proposed SGFE are verified by the handwritten digits MNIST benchmark and Tennessee-Eastman(TE) benchmark process,respectively.展开更多
To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although havin...To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection （LFS） is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.展开更多
To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model wit...To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.展开更多
As a new neural network model,extreme learning machine(ELM)has a good learning rate and generalization ability.However,ELM with a single hidden layer structure often fails to achieve good results when faced with large...As a new neural network model,extreme learning machine(ELM)has a good learning rate and generalization ability.However,ELM with a single hidden layer structure often fails to achieve good results when faced with large-scale multi-featured problems.To resolve this problem,we propose a multi-layer framework for the ELM learning algorithm to improve the model’s generalization ability.Moreover,noises or abnormal points often exist in practical applications,and they result in the inability to obtain clean training data.The generalization ability of the original ELM decreases under such circumstances.To address this issue,we add model bias and variance to the loss function so that the model gains the ability to minimize model bias and model variance,thus reducing the influence of noise signals.A new robust multi-layer algorithm called ML-RELM is proposed to enhance outlier robustness in complex datasets.Simulation results show that the method has high generalization ability and strong robustness to noise.展开更多
Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust...Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream.In order to solve these problems,an effective and rapid image classification method was presented for the object recognition based on the video learning technique.The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence.After the selection of scene images,the local maximum points on comer of object around local area were found using the Harris comer detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform （SIFT） for extracting local descriptor.Finally,the extracted local descriptor was learned to the three-dimensional pyramid match kernel.Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.展开更多
When detecting deletions in complex human genomes,split-read approaches using short reads generated with next-generation sequencing still face the challenge that either false discovery rate is high,or sensitivity is l...When detecting deletions in complex human genomes,split-read approaches using short reads generated with next-generation sequencing still face the challenge that either false discovery rate is high,or sensitivity is low.To address the problem,an integrated strategy is proposed.It organically combines the fundamental theories of the three mainstream methods(read-pair approaches,split-read technologies and read-depth analysis) with modern machine learning algorithms,using the recipe of feature extraction as a bridge.Compared with the state-of-art split-read methods for deletion detection in both low and high sequence coverage,the machine-learning-aided strategy shows great ability in intelligently balancing sensitivity and false discovery rate and getting a both more sensitive and more precise call set at single-base-pair resolution.Thus,users do not need to rely on former experience to make an unnecessary trade-off beforehand and adjust parameters over and over again any more.It should be noted that modern machine learning models can play an important role in the field of structural variation prediction.展开更多
A new parallel architecture for quantified boolean formula(QBF)solving was proposed,and the prediction model based on machine learning technology was proposed for how sharing knowledge affects the solving performance ...A new parallel architecture for quantified boolean formula(QBF)solving was proposed,and the prediction model based on machine learning technology was proposed for how sharing knowledge affects the solving performance in QBF parallel solving system,and the experimental evaluation scheme was also designed.It shows that the characterization factor of clause and cube influence the solving performance markedly in our experiment.At the same time,the heuristic machine learning algorithm was applied,support vector machine was chosen to predict the performance of QBF parallel solving system based on clause sharing and cube sharing.The relative error of accuracy for prediction can be controlled in a reasonable range of 20%30%.The results show the important and complex role that knowledge sharing plays in any modern parallel solver.It shows that the parallel solver with machine learning reduces the quantity of knowledge sharing about 30%and saving computational resource but does not reduce the performance of solving system.展开更多
In order to improve the Mandarin vowel pronunciation quality assessment, a nox/el formant feature was proposed and applied to formant classification for Chinese Mandarin vowel pronunciation quality evaluation. Formant...In order to improve the Mandarin vowel pronunciation quality assessment, a nox/el formant feature was proposed and applied to formant classification for Chinese Mandarin vowel pronunciation quality evaluation. Formant candidates of each frame were plotted on the time-frequency plane to form a bitmap, and its Gabor feature was extracted to represent the formant trajectory. The feature was then classified by using GMM model and the classification posterior probability was mapped to pronunciation quality grade. The experiments of comparing the Gabor transformation based formant trajectory feature with several other kinds of traditionally used features show that with this method, a human-machine scoring correlation coefficient （CC） of 0.842 can be achieved, which is better than the result of 0.832 by traditional speech recognition techniques. At the same time, considering that the long-term information of formant classification and the short-term information of speech recognition technique are complementary to each other, it is investigated to combine their results with linear or nonlinear methods to further improve the evaluation performance. As a result, experiments on PSK show that the best CC of 0.913, which is very close to the correlation of inter-human rating of 0.94, is gotten by using neural network.展开更多
There are various heterogeneous networks for terminals to deliver a better quality of service. Signal system recognition and classification contribute a lot to the process. However, in low signal to noise ratio（SNR）...There are various heterogeneous networks for terminals to deliver a better quality of service. Signal system recognition and classification contribute a lot to the process. However, in low signal to noise ratio（SNR） circumstances or under time-varying multipath channels, the majority of the existing algorithms for signal recognition are already facing limitations. In this series, we present a robust signal recognition method based upon the original and latest updated version of the extreme learning machine（ELM） to help users to switch between networks. The ELM utilizes signal characteristics to distinguish systems. The superiority of this algorithm lies in the random choices of hidden nodes and in the fact that it determines the output weights analytically, which result in lower complexity. Theoretically, the algorithm tends to offer a good generalization performance at an extremely fast speed of learning. Moreover, we implement the GSM/WCDMA/LTE models in the Matlab environment by using the Simulink tools. The simulations reveal that the signals can be recognized successfully to achieve a 95% accuracy in a low SNR（0 dB） environment in the time-varying multipath Rayleigh fading channel.展开更多
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
基金Projects(62125306, 62133003) supported by the National Natural Science Foundation of ChinaProject(TPL2019C03) supported by the Open Fund of Science and Technology on Thermal Energy and Power Laboratory,ChinaProject supported by the Fundamental Research Funds for the Central Universities(Zhejiang University NGICS Platform),China。
文摘With the increasing complexity of industrial processes, the high-dimensional industrial data exhibit a strong nonlinearity, bringing considerable challenges to the fault diagnosis of industrial processes. To efficiently extract deep meaningful features that are crucial for fault diagnosis, a sparse Gaussian feature extractor(SGFE) is designed to learn a nonlinear mapping that projects the raw data into the feature space with the fault label dimension. The feature space is described by the one-hot encoding of the fault category label as an orthogonal basis. In this way, the deep sparse Gaussian features related to fault categories can be gradually learned from the raw data by SGFE. In the feature space,the sparse Gaussian(SG) loss function is designed to constrain the distribution of features to multiple sparse multivariate Gaussian distributions. The sparse Gaussian features are linearly separable in the feature space, which is conducive to improving the accuracy of the downstream fault classification task. The feasibility and practical utility of the proposed SGFE are verified by the handwritten digits MNIST benchmark and Tennessee-Eastman(TE) benchmark process,respectively.
文摘To avoid the curse of dimensionality, text categorization （TC） algorithms based on machine learning （ML） have to use an feature selection （FS） method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection （LFS） is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.
基金financial support from National Natural Science Foundation of China(Grant No.61601491)Natural Science Foundation of Hubei Province,China(Grant No.2018CFC865)Military Research Project of China(-Grant No.YJ2020B117)。
文摘To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.
基金Project(21878081)supported by the National Natural Science Foundation of ChinaProject(222201917006)supported by the Fundamental Research Funds for the Central Universities,China。
文摘As a new neural network model,extreme learning machine(ELM)has a good learning rate and generalization ability.However,ELM with a single hidden layer structure often fails to achieve good results when faced with large-scale multi-featured problems.To resolve this problem,we propose a multi-layer framework for the ELM learning algorithm to improve the model’s generalization ability.Moreover,noises or abnormal points often exist in practical applications,and they result in the inability to obtain clean training data.The generalization ability of the original ELM decreases under such circumstances.To address this issue,we add model bias and variance to the loss function so that the model gains the ability to minimize model bias and model variance,thus reducing the influence of noise signals.A new robust multi-layer algorithm called ML-RELM is proposed to enhance outlier robustness in complex datasets.Simulation results show that the method has high generalization ability and strong robustness to noise.
基金Supported by National Natural Science Foundation of China（61071131,61271388） Natural Science Foundation of Beijing（4122040）+1 种基金 Research Project of Tsinghua University（2012Z01011） Doctoral Fund of Ministry of Education of China（20120002110036）
文摘Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream.In order to solve these problems,an effective and rapid image classification method was presented for the object recognition based on the video learning technique.The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence.After the selection of scene images,the local maximum points on comer of object around local area were found using the Harris comer detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform （SIFT） for extracting local descriptor.Finally,the extracted local descriptor was learned to the three-dimensional pyramid match kernel.Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.
基金Project(61472026)supported by the National Natural Science Foundation of ChinaProject(2014J410081)supported by Guangzhou Scientific Research Program,China
文摘When detecting deletions in complex human genomes,split-read approaches using short reads generated with next-generation sequencing still face the challenge that either false discovery rate is high,or sensitivity is low.To address the problem,an integrated strategy is proposed.It organically combines the fundamental theories of the three mainstream methods(read-pair approaches,split-read technologies and read-depth analysis) with modern machine learning algorithms,using the recipe of feature extraction as a bridge.Compared with the state-of-art split-read methods for deletion detection in both low and high sequence coverage,the machine-learning-aided strategy shows great ability in intelligently balancing sensitivity and false discovery rate and getting a both more sensitive and more precise call set at single-base-pair resolution.Thus,users do not need to rely on former experience to make an unnecessary trade-off beforehand and adjust parameters over and over again any more.It should be noted that modern machine learning models can play an important role in the field of structural variation prediction.
基金Project(61171141)supported by the National Natural Science Foundation of China
文摘A new parallel architecture for quantified boolean formula(QBF)solving was proposed,and the prediction model based on machine learning technology was proposed for how sharing knowledge affects the solving performance in QBF parallel solving system,and the experimental evaluation scheme was also designed.It shows that the characterization factor of clause and cube influence the solving performance markedly in our experiment.At the same time,the heuristic machine learning algorithm was applied,support vector machine was chosen to predict the performance of QBF parallel solving system based on clause sharing and cube sharing.The relative error of accuracy for prediction can be controlled in a reasonable range of 20%30%.The results show the important and complex role that knowledge sharing plays in any modern parallel solver.It shows that the parallel solver with machine learning reduces the quantity of knowledge sharing about 30%and saving computational resource but does not reduce the performance of solving system.
基金Project(61062011)supported by the National Natural Science Foundation of ChinaProject(2010GXNSFA013128)supported by the Natural Science Foundation of Guangxi Province,China
文摘In order to improve the Mandarin vowel pronunciation quality assessment, a nox/el formant feature was proposed and applied to formant classification for Chinese Mandarin vowel pronunciation quality evaluation. Formant candidates of each frame were plotted on the time-frequency plane to form a bitmap, and its Gabor feature was extracted to represent the formant trajectory. The feature was then classified by using GMM model and the classification posterior probability was mapped to pronunciation quality grade. The experiments of comparing the Gabor transformation based formant trajectory feature with several other kinds of traditionally used features show that with this method, a human-machine scoring correlation coefficient （CC） of 0.842 can be achieved, which is better than the result of 0.832 by traditional speech recognition techniques. At the same time, considering that the long-term information of formant classification and the short-term information of speech recognition technique are complementary to each other, it is investigated to combine their results with linear or nonlinear methods to further improve the evaluation performance. As a result, experiments on PSK show that the best CC of 0.913, which is very close to the correlation of inter-human rating of 0.94, is gotten by using neural network.
基金supported by the National Science and Technology Major Project of the Ministry of Science and Technology of China(2014 ZX03001027)
文摘There are various heterogeneous networks for terminals to deliver a better quality of service. Signal system recognition and classification contribute a lot to the process. However, in low signal to noise ratio（SNR） circumstances or under time-varying multipath channels, the majority of the existing algorithms for signal recognition are already facing limitations. In this series, we present a robust signal recognition method based upon the original and latest updated version of the extreme learning machine（ELM） to help users to switch between networks. The ELM utilizes signal characteristics to distinguish systems. The superiority of this algorithm lies in the random choices of hidden nodes and in the fact that it determines the output weights analytically, which result in lower complexity. Theoretically, the algorithm tends to offer a good generalization performance at an extremely fast speed of learning. Moreover, we implement the GSM/WCDMA/LTE models in the Matlab environment by using the Simulink tools. The simulations reveal that the signals can be recognized successfully to achieve a 95% accuracy in a low SNR（0 dB） environment in the time-varying multipath Rayleigh fading channel.
