Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-iti...Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-ities where operational records are scarce.This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such“cold-start”forecasting problems.It primarily covers three interrelated domains—solar photovoltaic(PV),wind power,and electrical load forecasting—where data scarcity and operational variability are most critical,while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective.To this end,we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025,highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data.Moreover,transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new,data-sparse environments,effectively capturing hidden dependencies among geographic features,meteorological dynamics,and grid structures.Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios.In addition,large language models and explainable artificial intelligence(XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms,fostering operator trust from the earliest deployment stages.By consolidating methodological advances,unresolved challenges,and open-source resources,this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient,low-carbon electricity grids.展开更多
Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),...Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),comprising an initialization followed by subsequent learning,selects a small subset of informative data points for labeling.Recent advancements in pretrained models by supervised or self-supervised learning tailored to chest radiograph have shown broad applicability to diverse downstream tasks.However,their potential in cold-start AL remains unexplored.Methods:To validate the efficacy of domain-specific pretraining,we compared two foundation models:supervised TXRV and self-supervised REMEDIS with their general domain counterparts pretrained on ImageNet.Model performance was evaluated at both initialization and subsequent learning stages on two diagnostic tasks:psychiatric pneumonia and COVID-19.For initialization,we assessed their integration with three strategies:diversity,uncertainty,and hybrid sampling.For subsequent learning,we focused on uncertainty sampling powered by different pretrained models.We also conducted statistical tests to compare the foundation models with ImageNet counterparts,investigate the relationship between initialization and subsequent learning,examine the performance of one-shot initialization against the full AL process,and investigate the influence of class balance in initialization samples on initialization and subsequent learning.Results:First,domain-specific foundation models failed to outperform ImageNet counterparts in six out of eight experiments on informative sample selection.Both domain-specific and general pretrained models were unable to generate representations that could substitute for the original images as model inputs in seven of the eight scenarios.However,pretrained model-based initialization surpassed random sampling,the default approach in cold-start AL.Second,initialization performance was positively correlated with subsequent learning performance,highlighting the importance of initialization strategies.Third,one-shot initialization performed comparably to the full AL process,demonstrating the potential of reducing experts'repeated waiting during AL iterations.Last,a U-shaped correlation was observed between the class balance of initialization samples and model performance,suggesting that the class balance is more strongly associated with performance at middle budget levels than at low or high budgets.Conclusions:In this study,we highlighted the limitations of medical pretraining compared to general pretraining in the context of cold-start AL.We also identified promising outcomes related to cold-start AL,including initialization based on pretrained models,the positive influence of initialization on subsequent learning,the potential for one-shot initialization,and the influence of class balance on middle-budget AL.Researchers are encouraged to improve medical pretraining for versatile DL foundations and explore novel AL methods.展开更多
The Co_(3)O_(4)nanoparticles,dominated by a catalytically active(110)lattice plane,were synthesized as a low-temperature NO_(x) adsorbent to control the cold start emissions from vehicles.These nanoparticles boast a s...The Co_(3)O_(4)nanoparticles,dominated by a catalytically active(110)lattice plane,were synthesized as a low-temperature NO_(x) adsorbent to control the cold start emissions from vehicles.These nanoparticles boast a substantial quantity of active chemisorbed oxygen and lattice oxygen,which exhibited a NO_(x) uptake capacity commensurate with Pd/SSZ-13 at 100℃.The primary NO_(x) release temperature falls within a temperature range of 200-350℃,making it perfectly suitable for diesel engines.The characterization results demonstrate that chemisorbed oxygen facilitate nitro/nitrites intermediates formation,contributing to the NO_(x) storage at 100℃,while the nitrites begin to decompose within the 150-200℃range.Fortunately,lattice oxygen likely becomes involved in the activation of nitrites into more stable nitrate within this particular temperature range.The concurrent processes of nitrites decomposition and its conversion to nitrates results in a minimal NO_(x) release between the temperatures of 150-200℃.The nitrate formed via lattice oxygen mainly induces the NO_(x) to be released as NO_(2) within a temperature range of 200-350℃,which is advantageous in enhancing the NO_(x) activity of downstream NH_(3)-SCR catalysts,by boosting the fast SCR reaction pathway.Thanks to its low cost,considerable NO_(x) absorption capacity,and optimal release temperature,Co_(3)O_(4)demonstrates potential as an effective material for passive NO_(x) adsorber applications.展开更多
Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in futu...Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future networks.Despite the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connectedgraph. However, the complexity of the real world makes the complex networksabstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start linkprediction is favored as one of the most valuable subproblems of traditional linkprediction. However, due to the loss of many links in the observation network, thetopological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topologicalinformation from observed network becomes the key point to solve the problemof cold-start link prediction. In this paper, we propose a framework for solving thecold-start link prediction problem, a joint-weighted symmetric nonnegative matrixfactorization model fusing graph regularization information, based on low-rankapproximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designedgraph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain eachother. Finally, a unified framework for implementing cold-start link prediction isconstructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validationon five real networks with attributes shows that the proposed model has very goodpredictive performance when predicting missing edges of isolated nodes.展开更多
In order to give accurate recommendations for cold-start user, researchers use social network to find similar users. These efforts assume that cold-start user’s social relationships are static. However social relatio...In order to give accurate recommendations for cold-start user, researchers use social network to find similar users. These efforts assume that cold-start user’s social relationships are static. However social relationships of cold-start user may change as time pass by. In order to give accurate and timely in manner recommendations for cold-start user, it is need to update social relationship continuously. In this paper, we proposed an incremental graph pattern matching based dynamic cold-start recommendation method (IGPMDCR), which updates similar users for cold-start user based on topology of social network, and gives recommendations based on the latest similar users’ records. The experimental results show that, IGPMDCR could give accurate and timely in manner recommendations for cold-start user.展开更多
In order to improve the cold start performance of heavy duty diesel engine, electronically controlling the preheating of intake air by flame was researched. According to simulation and thermodynamic analysis about th...In order to improve the cold start performance of heavy duty diesel engine, electronically controlling the preheating of intake air by flame was researched. According to simulation and thermodynamic analysis about the partial working processes of the diesel engine, the amount of heat energy, enough to make the fuel self ignite at the end of compression process at different temperatures of coolant and intake air, was calculated. Several HY20 preheating plugs were used to heat up the intake air. Meanwhile, an electronic control system based on 8 bit micro controller unit (MCS 8031) was designed to automatically control the process of heating intake air. According to the various temperatures of coolant and ambient air, one plug or two plugs can automatically be selected to heat intake air. The demo experiment validated that the total system could operate successfully and achieve the scheduled function.展开更多
In the rolling production of steel,predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categorie...In the rolling production of steel,predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories.This scenario poses a significant hurdle for machine learning models,leading to what is commonly known as the“cold-start problem”.To address this issue,we propose a knowledge graph attention neural network for steel manufacturing(SteelKGAT).By leveraging expert knowledge and a multi-head attention mechanism,SteelKGAT aims to enhance prediction accuracy.Our experimental results demonstrate that the SteelKGAT model outperforms existing methods when generalizing to previously unseen products.Only the SteelKGAT model accurately captures the feature trend,thereby offering correct guidance in product tuning,which is of practical significance for new product development(NPD).Additionally,we employ the Integrated Gradients(IG)method to shed light on the model's predictions,revealing the relative importance of each feature within the knowledge graph.Notably,this work represents the first application of knowledge graph attention neural networks to address the cold-start problem in steel rolling production.By combining domain expertise and interpretable predictions,our knowledge-informed SteelKGAT model provides accurate insights into the mechanical properties of products even in cold-start scenarios.展开更多
The problem of recommending new items to users(often referred to as item cold-start recommendation)remains a challenge due to the absence of users’past preferences for these items.Item features from side information ...The problem of recommending new items to users(often referred to as item cold-start recommendation)remains a challenge due to the absence of users’past preferences for these items.Item features from side information are typically leveraged to tackle the problem.Existing methods formulate regression methods,taking item features as input and user ratings as output.These methods are confronted with the issue of overfitting when item features are high-dimensional,which greatly impedes the recommendation experience.Availing of high-dimensional item features,in this work,we opt for feature selection to solve the problem of recommending top-N new items.Existing feature selection methods find a common set of features for all users,which fails to differentiate users1 preferences over item features.To personalize feature selection,we propose to select item features discriminately for different users.We study the personalization of feature selection at the level of the user or user group.We fulfill the task by proposing two embedded feature selection models.The process of personalized feature selection filters out the dimensions that are irrelevant to recommendations or unappealing to users.Experimental results on real-life datasets with high-dimensional side information reveal that the proposed method is effective in singling out features that are crucial to top-N recommendation and hence improving performance.展开更多
The Self-adaptive control of the temperature can achieve the start of fuel cell at different operating temperatures, which is very important for the successful cold-start of the air-cooled PEMFC. The temperature distr...The Self-adaptive control of the temperature can achieve the start of fuel cell at different operating temperatures, which is very important for the successful cold-start of the air-cooled PEMFC. The temperature distribution characteristics during the cold-start process were analyzed based on adaptive temperature recognition control in this paper. Preheating model and cold-start model were established and the optimal balance between the hot air flow rate and the temperature required to promote a uniform temperature distribution in the stack was explored in the preheating stage. Finally, the non-equilibrium mass transfer, as well as the temperature rise in the catalyst layer and gas diffusion layer with different current densities, were analyzed in the start-up stage. The results indicate that the air-cooled PEMFC stack can be successfully started up at -40 ◦C within 10 min by means of external gas heating. The current density and air velocity have significant impacts on the temperature of aircooled PEMFC stack. Dynamic analysis of air-cooled PEMFCs and real-time monitoring are suitable for machine learning and self-adaptive control to set the operation parameters to achieve successful cold start. Optimize the matching of load current and cathode inlet speed to achieve thermal management in low temperature environment.展开更多
文摘Predicting the behavior of renewable energy systems requires models capable of generating accurate forecasts from limited historical data,a challenge that becomes especially pronounced when commissioning new facil-ities where operational records are scarce.This review aims to synthesize recent progress in data-efficient deep learning approaches for addressing such“cold-start”forecasting problems.It primarily covers three interrelated domains—solar photovoltaic(PV),wind power,and electrical load forecasting—where data scarcity and operational variability are most critical,while also including representative studies on hydropower and carbon emission prediction to provide a broader systems perspective.To this end,we examined trends from over 150 predominantly peer-reviewed studies published between 2019 and mid-2025,highlighting advances in zero-shot and few-shot meta-learning frameworks that enable rapid model adaptation with minimal labeled data.Moreover,transfer learning approaches combined with spatiotemporal graph neural networks have been employed to transfer knowledge from existing energy assets to new,data-sparse environments,effectively capturing hidden dependencies among geographic features,meteorological dynamics,and grid structures.Synthetic data generation has further proven valuable for expanding training samples and mitigating overfitting in cold-start scenarios.In addition,large language models and explainable artificial intelligence(XAI)—notably conversational XAI systems—have been used to interpret and communicate complex model behaviors in accessible terms,fostering operator trust from the earliest deployment stages.By consolidating methodological advances,unresolved challenges,and open-source resources,this review provides a coherent overview of deep learning strategies that can shorten the data-sparse ramp-up period of new energy infrastructures and accelerate the transition toward resilient,low-carbon electricity grids.
文摘Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),comprising an initialization followed by subsequent learning,selects a small subset of informative data points for labeling.Recent advancements in pretrained models by supervised or self-supervised learning tailored to chest radiograph have shown broad applicability to diverse downstream tasks.However,their potential in cold-start AL remains unexplored.Methods:To validate the efficacy of domain-specific pretraining,we compared two foundation models:supervised TXRV and self-supervised REMEDIS with their general domain counterparts pretrained on ImageNet.Model performance was evaluated at both initialization and subsequent learning stages on two diagnostic tasks:psychiatric pneumonia and COVID-19.For initialization,we assessed their integration with three strategies:diversity,uncertainty,and hybrid sampling.For subsequent learning,we focused on uncertainty sampling powered by different pretrained models.We also conducted statistical tests to compare the foundation models with ImageNet counterparts,investigate the relationship between initialization and subsequent learning,examine the performance of one-shot initialization against the full AL process,and investigate the influence of class balance in initialization samples on initialization and subsequent learning.Results:First,domain-specific foundation models failed to outperform ImageNet counterparts in six out of eight experiments on informative sample selection.Both domain-specific and general pretrained models were unable to generate representations that could substitute for the original images as model inputs in seven of the eight scenarios.However,pretrained model-based initialization surpassed random sampling,the default approach in cold-start AL.Second,initialization performance was positively correlated with subsequent learning performance,highlighting the importance of initialization strategies.Third,one-shot initialization performed comparably to the full AL process,demonstrating the potential of reducing experts'repeated waiting during AL iterations.Last,a U-shaped correlation was observed between the class balance of initialization samples and model performance,suggesting that the class balance is more strongly associated with performance at middle budget levels than at low or high budgets.Conclusions:In this study,we highlighted the limitations of medical pretraining compared to general pretraining in the context of cold-start AL.We also identified promising outcomes related to cold-start AL,including initialization based on pretrained models,the positive influence of initialization on subsequent learning,the potential for one-shot initialization,and the influence of class balance on middle-budget AL.Researchers are encouraged to improve medical pretraining for versatile DL foundations and explore novel AL methods.
基金supported by the National Natural Science Foundation of China(22006044,22006043)External Cooperation Program of Science and Technology Planning of Fujian Province(2023I0018)+2 种基金the Fujian Province Science and Technology Program Funds(2020H6013)the National Engineering Laboratory for Mobile Source Emission Control Technology(NELMS2020A03)the Scientific Research Funds of Huaqiao University(605-50Y200270001)。
文摘The Co_(3)O_(4)nanoparticles,dominated by a catalytically active(110)lattice plane,were synthesized as a low-temperature NO_(x) adsorbent to control the cold start emissions from vehicles.These nanoparticles boast a substantial quantity of active chemisorbed oxygen and lattice oxygen,which exhibited a NO_(x) uptake capacity commensurate with Pd/SSZ-13 at 100℃.The primary NO_(x) release temperature falls within a temperature range of 200-350℃,making it perfectly suitable for diesel engines.The characterization results demonstrate that chemisorbed oxygen facilitate nitro/nitrites intermediates formation,contributing to the NO_(x) storage at 100℃,while the nitrites begin to decompose within the 150-200℃range.Fortunately,lattice oxygen likely becomes involved in the activation of nitrites into more stable nitrate within this particular temperature range.The concurrent processes of nitrites decomposition and its conversion to nitrates results in a minimal NO_(x) release between the temperatures of 150-200℃.The nitrate formed via lattice oxygen mainly induces the NO_(x) to be released as NO_(2) within a temperature range of 200-350℃,which is advantageous in enhancing the NO_(x) activity of downstream NH_(3)-SCR catalysts,by boosting the fast SCR reaction pathway.Thanks to its low cost,considerable NO_(x) absorption capacity,and optimal release temperature,Co_(3)O_(4)demonstrates potential as an effective material for passive NO_(x) adsorber applications.
基金supported by the Teaching Reform Research Project of Qinghai Minzu University,China(2021-JYYB-009)the“Chunhui Plan”Cooperative Scientific Research Project of the Ministry of Education of China(2018).
文摘Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future networks.Despite the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connectedgraph. However, the complexity of the real world makes the complex networksabstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start linkprediction is favored as one of the most valuable subproblems of traditional linkprediction. However, due to the loss of many links in the observation network, thetopological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topologicalinformation from observed network becomes the key point to solve the problemof cold-start link prediction. In this paper, we propose a framework for solving thecold-start link prediction problem, a joint-weighted symmetric nonnegative matrixfactorization model fusing graph regularization information, based on low-rankapproximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designedgraph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain eachother. Finally, a unified framework for implementing cold-start link prediction isconstructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validationon five real networks with attributes shows that the proposed model has very goodpredictive performance when predicting missing edges of isolated nodes.
文摘In order to give accurate recommendations for cold-start user, researchers use social network to find similar users. These efforts assume that cold-start user’s social relationships are static. However social relationships of cold-start user may change as time pass by. In order to give accurate and timely in manner recommendations for cold-start user, it is need to update social relationship continuously. In this paper, we proposed an incremental graph pattern matching based dynamic cold-start recommendation method (IGPMDCR), which updates similar users for cold-start user based on topology of social network, and gives recommendations based on the latest similar users’ records. The experimental results show that, IGPMDCR could give accurate and timely in manner recommendations for cold-start user.
文摘In order to improve the cold start performance of heavy duty diesel engine, electronically controlling the preheating of intake air by flame was researched. According to simulation and thermodynamic analysis about the partial working processes of the diesel engine, the amount of heat energy, enough to make the fuel self ignite at the end of compression process at different temperatures of coolant and intake air, was calculated. Several HY20 preheating plugs were used to heat up the intake air. Meanwhile, an electronic control system based on 8 bit micro controller unit (MCS 8031) was designed to automatically control the process of heating intake air. According to the various temperatures of coolant and ambient air, one plug or two plugs can automatically be selected to heat intake air. The demo experiment validated that the total system could operate successfully and achieve the scheduled function.
基金supported by the National Key R&D Program(No.2021YFB3702404)National Natural Science Foundation of China(Nos.52311530082 and U22A20106)support provided by“Xingliao Talent Plan”project(Grant No.XLYC2203027)is gratefully acknowledged.
文摘In the rolling production of steel,predicting the performance of new products is challenging due to the low variety of data distributions resulting from standardized manufacturing processes and fixed product categories.This scenario poses a significant hurdle for machine learning models,leading to what is commonly known as the“cold-start problem”.To address this issue,we propose a knowledge graph attention neural network for steel manufacturing(SteelKGAT).By leveraging expert knowledge and a multi-head attention mechanism,SteelKGAT aims to enhance prediction accuracy.Our experimental results demonstrate that the SteelKGAT model outperforms existing methods when generalizing to previously unseen products.Only the SteelKGAT model accurately captures the feature trend,thereby offering correct guidance in product tuning,which is of practical significance for new product development(NPD).Additionally,we employ the Integrated Gradients(IG)method to shed light on the model's predictions,revealing the relative importance of each feature within the knowledge graph.Notably,this work represents the first application of knowledge graph attention neural networks to address the cold-start problem in steel rolling production.By combining domain expertise and interpretable predictions,our knowledge-informed SteelKGAT model provides accurate insights into the mechanical properties of products even in cold-start scenarios.
基金supported by the National Natural Science Foundation of China under Grant Nos.61872446,61902417,71690233,and 71971212the Natural Science Foundation of Hunan Province of China under Grant No.2019JJ20024.
文摘The problem of recommending new items to users(often referred to as item cold-start recommendation)remains a challenge due to the absence of users’past preferences for these items.Item features from side information are typically leveraged to tackle the problem.Existing methods formulate regression methods,taking item features as input and user ratings as output.These methods are confronted with the issue of overfitting when item features are high-dimensional,which greatly impedes the recommendation experience.Availing of high-dimensional item features,in this work,we opt for feature selection to solve the problem of recommending top-N new items.Existing feature selection methods find a common set of features for all users,which fails to differentiate users1 preferences over item features.To personalize feature selection,we propose to select item features discriminately for different users.We study the personalization of feature selection at the level of the user or user group.We fulfill the task by proposing two embedded feature selection models.The process of personalized feature selection filters out the dimensions that are irrelevant to recommendations or unappealing to users.Experimental results on real-life datasets with high-dimensional side information reveal that the proposed method is effective in singling out features that are crucial to top-N recommendation and hence improving performance.
基金supported by the National Key Research and Development Program of China(No.2020YFB1506300)the National Natural Science Foundation of China(No.51806071)+1 种基金the Natural Science Foundation of Hubei Province(No.2020CFA040)Wuhan Applied Foundational Frontier Project(No.2020010601012205).
文摘The Self-adaptive control of the temperature can achieve the start of fuel cell at different operating temperatures, which is very important for the successful cold-start of the air-cooled PEMFC. The temperature distribution characteristics during the cold-start process were analyzed based on adaptive temperature recognition control in this paper. Preheating model and cold-start model were established and the optimal balance between the hot air flow rate and the temperature required to promote a uniform temperature distribution in the stack was explored in the preheating stage. Finally, the non-equilibrium mass transfer, as well as the temperature rise in the catalyst layer and gas diffusion layer with different current densities, were analyzed in the start-up stage. The results indicate that the air-cooled PEMFC stack can be successfully started up at -40 ◦C within 10 min by means of external gas heating. The current density and air velocity have significant impacts on the temperature of aircooled PEMFC stack. Dynamic analysis of air-cooled PEMFCs and real-time monitoring are suitable for machine learning and self-adaptive control to set the operation parameters to achieve successful cold start. Optimize the matching of load current and cathode inlet speed to achieve thermal management in low temperature environment.
