A new type of power supply which was called oxy-fuel combustion power plant was introduced to reduce greenhouse gasses emission. In this paper the volatile emission characteristic of pulverized coal is studied under a...A new type of power supply which was called oxy-fuel combustion power plant was introduced to reduce greenhouse gasses emission. In this paper the volatile emission characteristic of pulverized coal is studied under air atmosphere and oxy-fuel atmosphere. Combustion experiments of Datong bituminous coal were carried out in a wire mesh reactor at heating rates of 1 K/s, 10 K/s and 1000 K/s respectively under air and O2/CO2 atmosphere conditions in order to investigate the volatile emission characteristic. The concentrations of volatile (mainly CO and CH4) emission were on-line measured by infrared gas analyzer. It was indicated that the concentrations of CO and CH4 in O2/CO2 atmosphere were higher than those in air. The direct oxidation of carbon and gasification reaction between carbon and CO2 are the main causes of the increased amount of CO. The higher concentration of CO2 also results in the increased amount of CH4 in O2/CO2 conditions.展开更多
Brain-computer interfaces(BCIs)represent an emerging technology that facilitates direct communication between the brain and external devices.In recent years,numerous review articles have explored various aspects of BC...Brain-computer interfaces(BCIs)represent an emerging technology that facilitates direct communication between the brain and external devices.In recent years,numerous review articles have explored various aspects of BCIs,including their fundamental principles,technical advancements,and applications in specific domains.However,these reviews often focus on signal processing,hardware development,or limited applications such as motor rehabilitation or communication.This paper aims to offer a comprehensive review of recent electroencephalogram(EEG)-based BCI applications in the medical field across 8 critical areas,encompassing rehabilitation,daily communication,epilepsy,cerebral resuscitation,sleep,neurodegenerative diseases,anesthesiology,and emotion recognition.Moreover,the current challenges and future trends of BCIs were also discussed,including personal privacy and ethical concerns,network security vulnerabilities,safety issues,and biocompatibility.展开更多
Inferior crude oil and fuel oil upgrading lead to escalating increase of hydrogen consumption in refineries.It is imperative to reduce the hydrogen consumption for energy-saving operations of refineries.An integration...Inferior crude oil and fuel oil upgrading lead to escalating increase of hydrogen consumption in refineries.It is imperative to reduce the hydrogen consumption for energy-saving operations of refineries.An integration strategy of hydrogen network and an operational optimization model of hydrotreating(HDT)units are proposed based on the characteristics of reaction kinetics of HDT units.By solving the proposed model,the operating conditions of HDT units are optimized,and the parameters of hydrogen sinks are determined by coupling hydrodesulfurization(HDS),hydrodenitrification(HDN)and aromatic hydrogenation(HDA)kinetics.An example case of a refinery with annual processing capacity of eight million tons is adopted to demonstrate the feasibility of the proposed optimization strategies and the model.Results show that HDS,HDN and HDA reactions are the major source of hydrogen consumption in the refinery.The total hydrogen consumption can be reduced by 18.9%by applying conventional hydrogen network optimization model.When the hydrogen network is optimized after the operational optimization of HDT units is performed,the hydrogen consumption is reduced by28.2%.When the benefit of the fuel gas recovery is further considered,the total annual cost of hydrogen network can be reduced by 3.21×10~7CNY·a^(-1),decreased by 11.9%.Therefore,the operational optimization of the HDT units in refineries should be imposed to determine the parameters of hydrogen sinks base on the characteristics of reaction kinetics of the hydrogenation processes before the optimization of the hydrogen network is performed through the source-sink matching methods.展开更多
Recently,many online Karaoke(KTV)platforms have been released,where music lovers sing songs on these platforms.In the meantime,the system automatically evaluates user proficiency according to their singing behavior.Re...Recently,many online Karaoke(KTV)platforms have been released,where music lovers sing songs on these platforms.In the meantime,the system automatically evaluates user proficiency according to their singing behavior.Recommending approximate songs to users can initialize singers5 participation and improve users,loyalty to these platforms.However,this is not an easy task due to the unique characteristics of these platforms.First,since users may be not achieving high scores evaluated by the system on their favorite songs,how to balance user preferences with user proficiency on singing for song recommendation is still open.Second,the sparsity of the user-song interaction behavior may greatly impact the recommendation task.To solve the above two challenges,in this paper,we propose an informationfused song recommendation model by considering the unique characteristics of the singing data.Specifically,we first devise a pseudo-rating matrix by combing users’singing behavior and the system evaluations,thus users'preferences and proficiency are leveraged.Then we mitigate the data sparsity problem by fusing users*and songs'rich information in the matrix factorization process of the pseudo-rating matrix.Finally,extensive experimental results on a real-world dataset show the effectiveness of our proposed model.展开更多
Automatic generation of Chinese classical poetry is still a challenging problem in artificial intelligence.Re-cently,Encoder-Decoder models have provided a few viable methods for poetry generation.However,by reviewing...Automatic generation of Chinese classical poetry is still a challenging problem in artificial intelligence.Re-cently,Encoder-Decoder models have provided a few viable methods for poetry generation.However,by reviewing the pri-or methods,two major issues still need to be settled:1)most of them are one-stage generation methods without further polishing;2)they rarely take into consideration the restrictions of poetry,such as tone and rhyme.Intuitively,some an-cient Chinese poets tended first to write a coarse poem underlying aesthetics and then deliberated its semantics;while oth-ers first create a semantic poem and then refine its aesthetics.On this basis,in order to better imitate the human creation procedure of poems,we propose a two-stage method(i.e.,restricted polishing generation method)of which each stage fo-cuses on the different aspects of poems(i.e.,semantics and aesthetics),which can produce a higher quality of generated poems.In this way,the two-stage method develops into two symmetrical generation methods,the aesthetics-to-semantics method and the semantics-to-aesthetics method.In particular,we design a sampling method and a gate to formulate the tone and rhyme restrictions,which can further improve the rhythm of the generated poems.Experimental results demon-strate the superiority of our proposed two-stage method in both automatic evaluation metrics and human evaluation met-rics compared with baselines,especially in yielding consistent improvements in tone and rhyme.展开更多
Hand gesture recognition(HGR)plays a vital role in human-computer interaction.The integration of high-density surface electromyography(HD-sEMG)and deep neural networks(DNNs)has significantly improved the robustness an...Hand gesture recognition(HGR)plays a vital role in human-computer interaction.The integration of high-density surface electromyography(HD-sEMG)and deep neural networks(DNNs)has significantly improved the robustness and accuracy of HGR systems.These methods are typically effective for a fixed set of trained gestures.However,the need for new gesture classes over time poses a challenge.Introducing new classes to DNNs can lead to a substantial decrease in accuracy for previously learned tasks,a phenomenon known as“catastrophic forgetting,”especially when the training data for earlier tasks is not retained and retrained.This issue is exacerbated in embedded devices with limited storage,which struggle to store the large-scale data of HD-sEMG.Classincremental learning(CIL)is an effective method to reduce catastrophic forgetting.However,existing CIL methods for HGR rarely focus on reducing memory load.To address this,we propose a memory-friendly CIL method for HGR using HD-sEMG.Our approach includes a lightweight convolutional neural network,named SeparaNet,for feature representation learning,coupled with a nearest-mean-of-exemplars classifier for classifi-cation.We introduce a priority exemplar selection algorithm inspired by the herding effect to maintain a manageable set of exemplars during training.Furthermore,a task-equal-weight exemplar sampling strategy is proposed to effectively reduce memory load while preserving high recognition performance.Experimental results on two datasets demonstrate that our method significantly reduces the number of retained exemplars to only a quarter of that required by other CIL methods,accounting for less than 5%of the total samples,while still achieving comparable average accuracy.展开更多
Educational Cognitive Diagnosis(CD)aims to provide students’mastery levels on different concepts.One common observation is that students often conduct many exercises but engage with a small subset of concepts,leading...Educational Cognitive Diagnosis(CD)aims to provide students’mastery levels on different concepts.One common observation is that students often conduct many exercises but engage with a small subset of concepts,leading to a sparsity barrier.Current CD models mostly adopt mastery levels on all concepts as student modeling,overlooking the sparsity barrier.If a student does not interact with all concepts,we can not ensure that each dimension of mastery levels on concepts can be well-trained.In this paper,we propose a novel Enhancing Student Representations in Cognitive Diagnosis(ESR-CD),which combines application abilities and comprehension degrees for mastery levels on concepts.To model application ability,we propose a sparsity-based mask module that solely depends on the dense student-concept entries.Simultaneously,to further enhance comprehension degrees,we propose two layers:a matrix factorization layer and a relation refinement layer.Extensive experiments on two realworld datasets demonstrate the effectiveness of ESR-CD.展开更多
Student cognitive modeling is a fundamental task in the intelligence education field.It serves as the basis for various downstream applications,such as student profiling,personalized educational content recommendation...Student cognitive modeling is a fundamental task in the intelligence education field.It serves as the basis for various downstream applications,such as student profiling,personalized educational content recommendation,and adaptive testing.Cognitive Diagnosis(CD)and Knowledge Tracing(KT)are two mainstream categories for student cognitive modeling,which measure the cognitive ability from a limited time(e.g.,an exam)and the learning ability dynamics over a long period(e.g.,learning records from a year),respectively.Recent efforts have been dedicated to the development of open-source code libraries for student cognitive modeling.However,existing libraries often focus on a particular category and overlook the relationships between them.Additionally,these libraries lack sufficient modularization,which hinders reusability.To address these limitations,we have developed a unified PyTorch-based library EduStudio,which unifies CD and KT for student cognitive modeling.The design philosophy of EduStudio is from two folds.From a horizontal perspective,EduStudio employs the modularization that separates the main step pipeline of each algorithm.From a vertical perspective,we use templates with the inheritance style to implement each module.We also provide eco-services of EduStudio,such as the repository that collects resources about student cognitive modeling and the leaderboard that demonstrates comparison among models.Our open-source project is available at the website of edustudio.ai.展开更多
Recent years have witnessed the prevalence of recommender systems in various fields, which provide a personalized recommendation list for each user based on various kinds of information. For quite a long time, most re...Recent years have witnessed the prevalence of recommender systems in various fields, which provide a personalized recommendation list for each user based on various kinds of information. For quite a long time, most researchers have been pursing recommendation performances with predefined metrics, e.g., accuracy. However, in real-world applications, users select items from a huge item list by considering their internal personalized demand and external constraints. Thus, we argue that explicitly modeling the complex relations among items under domain-specific applications is an indispensable part for enhancing the recommendations. Actually, in this area, researchers have done some work to understand the item relations gradually from ＂implicit＂ to ＂explicit＂ views when recommending. To this end, in this paper, we conduct a survey of these recent advances on recommender systems from the perspective of the explicit item relation understanding. We organize these relevant studies from three types of item relations, i.e., combination-effect relations, sequence-dependence relations, and external-constraint relations. Specifically, the combination-effect relation and the sequence-dependence relation based work models the intra-group intrinsic relations of items from the user demand perspective, and the external-constraint relation emphasizes the external requirements for items. After that, we also propose our opinions on the open issues along the line of understanding item relations and suggest some future research directions in recommendation area.展开更多
Brain-computer interface(BCI)based on Steady-State Visual Evoked Potentials(SSVEP)provides an effective method for human-computer communication.In practical application scenarios,SSVEP-BCI systems are easily interfere...Brain-computer interface(BCI)based on Steady-State Visual Evoked Potentials(SSVEP)provides an effective method for human-computer communication.In practical application scenarios,SSVEP-BCI systems are easily interfered by physiological noises such as electromyography(EMG)and electrooculography(EOG).The performance of traditional SSVEP recognition methods will degrade in such a noisy environment,which limits their real-world applications.To alleviate the interference of noise,existing works either require additional reference electrodes or are designed for removing background noise such as trend terms rather than physiological noises.In this study,we utilize adversarial training(AT)and neural networks(NNs)to construct a robust recognition method for SSVEP contaminated by physiological noise.During model training,we generate adversarial noises which are most harmful to the current model according to gradients and enforce the model to overcome them.In this way,we strengthen the robustness of the model to potential noises,such as physiological noises.In this study,we recorded a real-world speaking SSVEP dataset and simulated various noisy datasets to conducted comparison experiments on two benchmark models named EEGNet and DeepConvNet.The experimental results demonstrated that AT strategies can help the neural networks get better performance on SSVEP data contaminated by EMG and EOG.We also verified that introducing AT can slightly improve the performance of models under a cross-subject scenario.Our method can be integrated into existing deep learning methods efficiently and will contribute to the real-world applications of SSVEP.展开更多
文摘A new type of power supply which was called oxy-fuel combustion power plant was introduced to reduce greenhouse gasses emission. In this paper the volatile emission characteristic of pulverized coal is studied under air atmosphere and oxy-fuel atmosphere. Combustion experiments of Datong bituminous coal were carried out in a wire mesh reactor at heating rates of 1 K/s, 10 K/s and 1000 K/s respectively under air and O2/CO2 atmosphere conditions in order to investigate the volatile emission characteristic. The concentrations of volatile (mainly CO and CH4) emission were on-line measured by infrared gas analyzer. It was indicated that the concentrations of CO and CH4 in O2/CO2 atmosphere were higher than those in air. The direct oxidation of carbon and gasification reaction between carbon and CO2 are the main causes of the increased amount of CO. The higher concentration of CO2 also results in the increased amount of CH4 in O2/CO2 conditions.
基金supported by the National Key R&D Program of China(2021YFF1200602)the National Science Fund for Excellent Overseas Scholars(0401260011)+3 种基金the National Defense Science and Technology Innovation Fund of Chinese Academy of Sciences(c02022088)the Tianjin Science and Technology Program(20JCZDJC00810)the National Natural Science Foundation of China(82202798)the Shanghai Sailing Program(22YF1404200).
文摘Brain-computer interfaces(BCIs)represent an emerging technology that facilitates direct communication between the brain and external devices.In recent years,numerous review articles have explored various aspects of BCIs,including their fundamental principles,technical advancements,and applications in specific domains.However,these reviews often focus on signal processing,hardware development,or limited applications such as motor rehabilitation or communication.This paper aims to offer a comprehensive review of recent electroencephalogram(EEG)-based BCI applications in the medical field across 8 critical areas,encompassing rehabilitation,daily communication,epilepsy,cerebral resuscitation,sleep,neurodegenerative diseases,anesthesiology,and emotion recognition.Moreover,the current challenges and future trends of BCIs were also discussed,including personal privacy and ethical concerns,network security vulnerabilities,safety issues,and biocompatibility.
基金Supported by the National Natural Science Foundation of China(21376188,21676211)the Key Project of Industrial Science and Technology of Shaanxi Province(2015GY095)
文摘Inferior crude oil and fuel oil upgrading lead to escalating increase of hydrogen consumption in refineries.It is imperative to reduce the hydrogen consumption for energy-saving operations of refineries.An integration strategy of hydrogen network and an operational optimization model of hydrotreating(HDT)units are proposed based on the characteristics of reaction kinetics of HDT units.By solving the proposed model,the operating conditions of HDT units are optimized,and the parameters of hydrogen sinks are determined by coupling hydrodesulfurization(HDS),hydrodenitrification(HDN)and aromatic hydrogenation(HDA)kinetics.An example case of a refinery with annual processing capacity of eight million tons is adopted to demonstrate the feasibility of the proposed optimization strategies and the model.Results show that HDS,HDN and HDA reactions are the major source of hydrogen consumption in the refinery.The total hydrogen consumption can be reduced by 18.9%by applying conventional hydrogen network optimization model.When the hydrogen network is optimized after the operational optimization of HDT units is performed,the hydrogen consumption is reduced by28.2%.When the benefit of the fuel gas recovery is further considered,the total annual cost of hydrogen network can be reduced by 3.21×10~7CNY·a^(-1),decreased by 11.9%.Therefore,the operational optimization of the HDT units in refineries should be imposed to determine the parameters of hydrogen sinks base on the characteristics of reaction kinetics of the hydrogenation processes before the optimization of the hydrogen network is performed through the source-sink matching methods.
基金grants from the National Key Research and Development Program of China(2016YFB1000904)the National Natural Science Foundation of China(Grant Nos.61325010 and U 1605251)+3 种基金the Fundamental Research Funds for the Central Universities of China(WK2350000001)Le Wu gratefully acknowledges the support of the Open Project Program of the National Laboratory of Pattern Recognition(201700017)the Fundamental Research Funds for the Central Universities(JZ2016HGBZ0749)Yong Ge acknowledges the support of the National Natural Science Foundation of China(NSFC,Grant Nos.61602234 and 61572032).
文摘Recently,many online Karaoke(KTV)platforms have been released,where music lovers sing songs on these platforms.In the meantime,the system automatically evaluates user proficiency according to their singing behavior.Recommending approximate songs to users can initialize singers5 participation and improve users,loyalty to these platforms.However,this is not an easy task due to the unique characteristics of these platforms.First,since users may be not achieving high scores evaluated by the system on their favorite songs,how to balance user preferences with user proficiency on singing for song recommendation is still open.Second,the sparsity of the user-song interaction behavior may greatly impact the recommendation task.To solve the above two challenges,in this paper,we propose an informationfused song recommendation model by considering the unique characteristics of the singing data.Specifically,we first devise a pseudo-rating matrix by combing users’singing behavior and the system evaluations,thus users'preferences and proficiency are leveraged.Then we mitigate the data sparsity problem by fusing users*and songs'rich information in the matrix factorization process of the pseudo-rating matrix.Finally,extensive experimental results on a real-world dataset show the effectiveness of our proposed model.
基金supported by the National Natural Science Foundation of China under Grant Nos.61922073 and 72101176.
文摘Automatic generation of Chinese classical poetry is still a challenging problem in artificial intelligence.Re-cently,Encoder-Decoder models have provided a few viable methods for poetry generation.However,by reviewing the pri-or methods,two major issues still need to be settled:1)most of them are one-stage generation methods without further polishing;2)they rarely take into consideration the restrictions of poetry,such as tone and rhyme.Intuitively,some an-cient Chinese poets tended first to write a coarse poem underlying aesthetics and then deliberated its semantics;while oth-ers first create a semantic poem and then refine its aesthetics.On this basis,in order to better imitate the human creation procedure of poems,we propose a two-stage method(i.e.,restricted polishing generation method)of which each stage fo-cuses on the different aspects of poems(i.e.,semantics and aesthetics),which can produce a higher quality of generated poems.In this way,the two-stage method develops into two symmetrical generation methods,the aesthetics-to-semantics method and the semantics-to-aesthetics method.In particular,we design a sampling method and a gate to formulate the tone and rhyme restrictions,which can further improve the rhythm of the generated poems.Experimental results demon-strate the superiority of our proposed two-stage method in both automatic evaluation metrics and human evaluation met-rics compared with baselines,especially in yielding consistent improvements in tone and rhyme.
基金supported in part by the National Key Research and Development Program of China under Grant 2021YFF1200600in part by the National Natural Science Foundation of China under Grant 62301523.
文摘Hand gesture recognition(HGR)plays a vital role in human-computer interaction.The integration of high-density surface electromyography(HD-sEMG)and deep neural networks(DNNs)has significantly improved the robustness and accuracy of HGR systems.These methods are typically effective for a fixed set of trained gestures.However,the need for new gesture classes over time poses a challenge.Introducing new classes to DNNs can lead to a substantial decrease in accuracy for previously learned tasks,a phenomenon known as“catastrophic forgetting,”especially when the training data for earlier tasks is not retained and retrained.This issue is exacerbated in embedded devices with limited storage,which struggle to store the large-scale data of HD-sEMG.Classincremental learning(CIL)is an effective method to reduce catastrophic forgetting.However,existing CIL methods for HGR rarely focus on reducing memory load.To address this,we propose a memory-friendly CIL method for HGR using HD-sEMG.Our approach includes a lightweight convolutional neural network,named SeparaNet,for feature representation learning,coupled with a nearest-mean-of-exemplars classifier for classifi-cation.We introduce a priority exemplar selection algorithm inspired by the herding effect to maintain a manageable set of exemplars during training.Furthermore,a task-equal-weight exemplar sampling strategy is proposed to effectively reduce memory load while preserving high recognition performance.Experimental results on two datasets demonstrate that our method significantly reduces the number of retained exemplars to only a quarter of that required by other CIL methods,accounting for less than 5%of the total samples,while still achieving comparable average accuracy.
基金supported in part by grants from the National Science and Technology Major Project(2021ZD0111802)the New Cornerstone Science Foundation through the XPLORER PRIZE,the National Natural Science Foundation of China(Grant Nos.72188101,62376086)the Joint Funds of the National Natural Science Foundation of China(U22A2094).
文摘Educational Cognitive Diagnosis(CD)aims to provide students’mastery levels on different concepts.One common observation is that students often conduct many exercises but engage with a small subset of concepts,leading to a sparsity barrier.Current CD models mostly adopt mastery levels on all concepts as student modeling,overlooking the sparsity barrier.If a student does not interact with all concepts,we can not ensure that each dimension of mastery levels on concepts can be well-trained.In this paper,we propose a novel Enhancing Student Representations in Cognitive Diagnosis(ESR-CD),which combines application abilities and comprehension degrees for mastery levels on concepts.To model application ability,we propose a sparsity-based mask module that solely depends on the dense student-concept entries.Simultaneously,to further enhance comprehension degrees,we propose two layers:a matrix factorization layer and a relation refinement layer.Extensive experiments on two realworld datasets demonstrate the effectiveness of ESR-CD.
基金supported in part by grants from the National Science and Technology Major Project,China(Grant No.2021ZD0111802)the National Natural Science Foundation of China(Grant Nos.72188101,62406096,and 62376086)the Fundamental Research Funds for the Central Universities,China(Grant No.JZ2024HGQB0093).
文摘Student cognitive modeling is a fundamental task in the intelligence education field.It serves as the basis for various downstream applications,such as student profiling,personalized educational content recommendation,and adaptive testing.Cognitive Diagnosis(CD)and Knowledge Tracing(KT)are two mainstream categories for student cognitive modeling,which measure the cognitive ability from a limited time(e.g.,an exam)and the learning ability dynamics over a long period(e.g.,learning records from a year),respectively.Recent efforts have been dedicated to the development of open-source code libraries for student cognitive modeling.However,existing libraries often focus on a particular category and overlook the relationships between them.Additionally,these libraries lack sufficient modularization,which hinders reusability.To address these limitations,we have developed a unified PyTorch-based library EduStudio,which unifies CD and KT for student cognitive modeling.The design philosophy of EduStudio is from two folds.From a horizontal perspective,EduStudio employs the modularization that separates the main step pipeline of each algorithm.From a vertical perspective,we use templates with the inheritance style to implement each module.We also provide eco-services of EduStudio,such as the repository that collects resources about student cognitive modeling and the leaderboard that demonstrates comparison among models.Our open-source project is available at the website of edustudio.ai.
基金This research was partially supported by the National Natural Science Foundation of China under Grant Nos. U1605251, 61672483 and 61602147, and the Fundamental Research Funds for the Central Universities of China under Grant No. JZ2016HGBZ0749. Qi Liu gratefully acknowledges the support of the Young Elite Scientist Sponsorship Program of China Association for Science and Technology （CAST） and the Youth Innovation Promotion Association of Chinese Academy of Sciences （CAS） under Grant No. 2014299.
文摘Recent years have witnessed the prevalence of recommender systems in various fields, which provide a personalized recommendation list for each user based on various kinds of information. For quite a long time, most researchers have been pursing recommendation performances with predefined metrics, e.g., accuracy. However, in real-world applications, users select items from a huge item list by considering their internal personalized demand and external constraints. Thus, we argue that explicitly modeling the complex relations among items under domain-specific applications is an indispensable part for enhancing the recommendations. Actually, in this area, researchers have done some work to understand the item relations gradually from ＂implicit＂ to ＂explicit＂ views when recommending. To this end, in this paper, we conduct a survey of these recent advances on recommender systems from the perspective of the explicit item relation understanding. We organize these relevant studies from three types of item relations, i.e., combination-effect relations, sequence-dependence relations, and external-constraint relations. Specifically, the combination-effect relation and the sequence-dependence relation based work models the intra-group intrinsic relations of items from the user demand perspective, and the external-constraint relation emphasizes the external requirements for items. After that, we also propose our opinions on the open issues along the line of understanding item relations and suggest some future research directions in recommendation area.
基金This work was supported in part by the National Natural Science Foundation of China under Grant 61922075,Grant 32271431,and Grant 82272070in part by the Fundamental Research Funds for the Central Universities under Grant KY2100000123+1 种基金in part by the China Postdoctoral Science Foundation under Grant 2022M723055in part by the University Synergy Innovation Program of Anhui Province under Grant GXXT-2019-025.
文摘Brain-computer interface(BCI)based on Steady-State Visual Evoked Potentials(SSVEP)provides an effective method for human-computer communication.In practical application scenarios,SSVEP-BCI systems are easily interfered by physiological noises such as electromyography(EMG)and electrooculography(EOG).The performance of traditional SSVEP recognition methods will degrade in such a noisy environment,which limits their real-world applications.To alleviate the interference of noise,existing works either require additional reference electrodes or are designed for removing background noise such as trend terms rather than physiological noises.In this study,we utilize adversarial training(AT)and neural networks(NNs)to construct a robust recognition method for SSVEP contaminated by physiological noise.During model training,we generate adversarial noises which are most harmful to the current model according to gradients and enforce the model to overcome them.In this way,we strengthen the robustness of the model to potential noises,such as physiological noises.In this study,we recorded a real-world speaking SSVEP dataset and simulated various noisy datasets to conducted comparison experiments on two benchmark models named EEGNet and DeepConvNet.The experimental results demonstrated that AT strategies can help the neural networks get better performance on SSVEP data contaminated by EMG and EOG.We also verified that introducing AT can slightly improve the performance of models under a cross-subject scenario.Our method can be integrated into existing deep learning methods efficiently and will contribute to the real-world applications of SSVEP.
