Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the ...Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the data during critical events.A skeleton representation of the human body has been proven to be effective for this task.The skeletons are presented in graphs form-like.However,the topology of a graph is not structured like Euclideanbased data.Therefore,a new set of methods to perform the convolution operation upon the skeleton graph is proposed.Our proposal is based on the Spatial Temporal-Graph Convolutional Network(ST-GCN)framework.In this study,we proposed an improved set of label mapping methods for the ST-GCN framework.We introduce three split techniques(full distance split,connection split,and index split)as an alternative approach for the convolution operation.The experiments presented in this study have been trained using two benchmark datasets:NTU-RGB+D and Kinetics to evaluate the performance.Our results indicate that our split techniques outperform the previous partition strategies and aremore stable during training without using the edge importance weighting additional training parameter.Therefore,our proposal can provide a more realistic solution for real-time applications centred on daily living recognition systems activities for indoor environments.展开更多
Background A crucial element of human-machine interaction,the automatic detection of emotional states from human speech has long been regarded as a challenging task for machine learning models.One vital challenge in s...Background A crucial element of human-machine interaction,the automatic detection of emotional states from human speech has long been regarded as a challenging task for machine learning models.One vital challenge in speech emotion recognition(SER)is learning robust and discriminative representations from speech.Although machine learning methods have been widely applied in SER research,the inadequate amount of available annotated data has become a bottleneck impeding the extended application of such techniques(e.g.,deep neural networks).To address this issue,we present a deep learning method that combines knowledge transfer and self-attention for SER tasks.Herein,we apply the log-Mel spectrogram with deltas and delta-deltas as inputs.Moreover,given that emotions are time dependent,we apply temporal convolutional neural networks to model the variations in emotions.We further introduce an attention transfer mechanism,which is based on a self-attention algorithm to learn long-term dependencies.The self-attention transfer network(SATN)in our proposed approach takes advantage of attention transfer to learn attention from speech recognition,followed by transferring this knowledge into SER.An evaluation built on Interactive Emotional Dyadic Motion Capture(IEMOCAP)dataset demonstrates the effectiveness of the proposed model.展开更多
One of the major challenges that membrane manufacturers, commercial enterprises and the scientific community in the field of membrane-based filtration or reverse osmosis (RO) desalination have to deal with is system p...One of the major challenges that membrane manufacturers, commercial enterprises and the scientific community in the field of membrane-based filtration or reverse osmosis (RO) desalination have to deal with is system performance retardation due to membrane fouling. In this respect, the prediction of fouling or system performance in membrane-based systems is the key to determining the mid and long-term plant operating conditions and costs. Despite major research efforts in the field, effective methods for the estimation of fouling in RO desalination plants are still in infancy, for example, most of the existing methods, neither consider the characteristics of the membranes such as the spacer geometry, nor the efficiency and the day to day chemical cleanings. Furthermore, most studies focus on predicting a single fouling indicator, e.g., flux decline. Faced with the limits of mathematical or numerical approach, in this paper, machine learning methods based on Multivariate Temporal Convolutional Neural networks (MTCN), which take into account the membrane characteristics, feed water quality, RO operation data and management practice such as Cleaning In Place (CIP) will be considered to predict membrane fouling using measurable multiple indicators. The temporal convolution model offers one the capability to explore the temporal dependencies among a remarkably long historical period and has potential use for operational diagnostics, early warning and system optimal control. Data collected from a Desalination RO plant will <span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">be</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> used to demonstrate the capabilities of the prediction system. The method achieves remarkable predictive accuracy (root mean square error) of 0.023, 0.012 and 0.007 for the relative differential pressure and permeate</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">s</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> Total Dissolved solids (TDS) and the feed pressure, respectively.</span></span></span></span>展开更多
There is recent interest in using model hubs–a collection of pre-trained models–in computer vision tasks.To employ a model hub,we first select a source model and then adapt the model for the target to compensate for...There is recent interest in using model hubs–a collection of pre-trained models–in computer vision tasks.To employ a model hub,we first select a source model and then adapt the model for the target to compensate for differences.There still needs to be more research on model selection and adaption for renewable power forecasts.In particular,none of the related work examines different model selection and adaptation strategies for neural network architectures.Also,none of the current studies investigates the influence of available training samples and considers seasonality in the evaluation.We close these gaps by conducting the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast,adopting recent developments from the field of computer vision on 667 wind and photovoltaic parks from six datasets.We simulate different amounts of training samples for each season to calculate informative forecast errors.We examine the marginal likelihood and forecast error for model selection for those amounts.Furthermore,we study four adaption strategies.As an extension of the current state of the art,we utilize a Bayesian linear regression for forecasting the response based on features extracted from a neural network.This approach outperforms the baseline with only seven days of training data and shows that fine-tuning is not beneficial with less than three months of data.We further show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach such that we have a similar mean error with only 30 days of training data which is otherwise only possible with an entire year of training data.We achieve a mean error of 9.8 and 14 percent for the most realistic dataset for PV and wind with only seven days of training data.展开更多
文摘Action recognition has been recognized as an activity in which individuals’behaviour can be observed.Assembling profiles of regular activities such as activities of daily living can support identifying trends in the data during critical events.A skeleton representation of the human body has been proven to be effective for this task.The skeletons are presented in graphs form-like.However,the topology of a graph is not structured like Euclideanbased data.Therefore,a new set of methods to perform the convolution operation upon the skeleton graph is proposed.Our proposal is based on the Spatial Temporal-Graph Convolutional Network(ST-GCN)framework.In this study,we proposed an improved set of label mapping methods for the ST-GCN framework.We introduce three split techniques(full distance split,connection split,and index split)as an alternative approach for the convolution operation.The experiments presented in this study have been trained using two benchmark datasets:NTU-RGB+D and Kinetics to evaluate the performance.Our results indicate that our split techniques outperform the previous partition strategies and aremore stable during training without using the edge importance weighting additional training parameter.Therefore,our proposal can provide a more realistic solution for real-time applications centred on daily living recognition systems activities for indoor environments.
基金the National Natural Science Foundation of China(62071330)the National Science Fund for Distinguished Young Scholars(61425017)+3 种基金the Key Program of the National Natural Science Foundation(61831022)the Key Program of the Natural Science Foundation of Tianjin(18JCZDJC36300)the Open Projects Program of the National Laboratory of Pattern Recognition and the Senior Visiting Scholar Program of Tianjin Normal Universitythe Innovative Medicines Initiative 2 Joint Undertaking(115902),which receives support from the European Union's Horizon 2020 research and innovation program and EFPIA.
文摘Background A crucial element of human-machine interaction,the automatic detection of emotional states from human speech has long been regarded as a challenging task for machine learning models.One vital challenge in speech emotion recognition(SER)is learning robust and discriminative representations from speech.Although machine learning methods have been widely applied in SER research,the inadequate amount of available annotated data has become a bottleneck impeding the extended application of such techniques(e.g.,deep neural networks).To address this issue,we present a deep learning method that combines knowledge transfer and self-attention for SER tasks.Herein,we apply the log-Mel spectrogram with deltas and delta-deltas as inputs.Moreover,given that emotions are time dependent,we apply temporal convolutional neural networks to model the variations in emotions.We further introduce an attention transfer mechanism,which is based on a self-attention algorithm to learn long-term dependencies.The self-attention transfer network(SATN)in our proposed approach takes advantage of attention transfer to learn attention from speech recognition,followed by transferring this knowledge into SER.An evaluation built on Interactive Emotional Dyadic Motion Capture(IEMOCAP)dataset demonstrates the effectiveness of the proposed model.
文摘One of the major challenges that membrane manufacturers, commercial enterprises and the scientific community in the field of membrane-based filtration or reverse osmosis (RO) desalination have to deal with is system performance retardation due to membrane fouling. In this respect, the prediction of fouling or system performance in membrane-based systems is the key to determining the mid and long-term plant operating conditions and costs. Despite major research efforts in the field, effective methods for the estimation of fouling in RO desalination plants are still in infancy, for example, most of the existing methods, neither consider the characteristics of the membranes such as the spacer geometry, nor the efficiency and the day to day chemical cleanings. Furthermore, most studies focus on predicting a single fouling indicator, e.g., flux decline. Faced with the limits of mathematical or numerical approach, in this paper, machine learning methods based on Multivariate Temporal Convolutional Neural networks (MTCN), which take into account the membrane characteristics, feed water quality, RO operation data and management practice such as Cleaning In Place (CIP) will be considered to predict membrane fouling using measurable multiple indicators. The temporal convolution model offers one the capability to explore the temporal dependencies among a remarkably long historical period and has potential use for operational diagnostics, early warning and system optimal control. Data collected from a Desalination RO plant will <span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">be</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> used to demonstrate the capabilities of the prediction system. The method achieves remarkable predictive accuracy (root mean square error) of 0.023, 0.012 and 0.007 for the relative differential pressure and permeate</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">s</span></span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;"> Total Dissolved solids (TDS) and the feed pressure, respectively.</span></span></span></span>
基金This work results from the project TRANSFER(01IS20020B)funded by BMBF(German Federal Ministry of Education and Research).
文摘There is recent interest in using model hubs–a collection of pre-trained models–in computer vision tasks.To employ a model hub,we first select a source model and then adapt the model for the target to compensate for differences.There still needs to be more research on model selection and adaption for renewable power forecasts.In particular,none of the related work examines different model selection and adaptation strategies for neural network architectures.Also,none of the current studies investigates the influence of available training samples and considers seasonality in the evaluation.We close these gaps by conducting the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast,adopting recent developments from the field of computer vision on 667 wind and photovoltaic parks from six datasets.We simulate different amounts of training samples for each season to calculate informative forecast errors.We examine the marginal likelihood and forecast error for model selection for those amounts.Furthermore,we study four adaption strategies.As an extension of the current state of the art,we utilize a Bayesian linear regression for forecasting the response based on features extracted from a neural network.This approach outperforms the baseline with only seven days of training data and shows that fine-tuning is not beneficial with less than three months of data.We further show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach such that we have a similar mean error with only 30 days of training data which is otherwise only possible with an entire year of training data.We achieve a mean error of 9.8 and 14 percent for the most realistic dataset for PV and wind with only seven days of training data.
