In the realm of all-electric aircraft research,the integration of cathode-open proton exchange membrane fuel cells(PEMFC)with lithiumbatteries as a hybrid power source for small to medium-sized unmanned aerial vehicle...In the realm of all-electric aircraft research,the integration of cathode-open proton exchange membrane fuel cells(PEMFC)with lithiumbatteries as a hybrid power source for small to medium-sized unmanned aerial vehicles(UAVs)has garnered significant attention.The PEMFC,serving as the primary energy supply,markedly extends the UAV’s operational endurance.However,due to payload limitations and spatial constraints in the airframe layout of UAVs,the stack requires customized adaptation.Moreover,the implementation of auxiliary systems to facilitate cold starts of the PEMFC under low-temperature conditions is not feasible.Relying solely on thermal insulation measures also proves inadequate to address the challenges posed by complex low-temperature startup scenarios.To overcomethis,our study leverages the UAV’s lithium battery to heat the cathode inlet airflow,aiding the cathode-open PEMFC cold start process.To validate the feasibility of the proposed air-assisted heating strategy during the conceptual design phase,this study develops a transient,non-isothermal 3Dcathode-open PEMF Cunitmodel incorporating cathode air-assisted heating and gas-ice phase change.The model’s accuracy was verified against experimental cold-start data from a stack composed of identical single cells.This computational framework enables quantitative analysis of temperature fields and ice fraction distributions across domains under varying air-assisted heating powers during cold starts.Building upon this model,the study further investigates the improvement in cold start performance by heating the cathode intake air with varying power levels.The results demonstrate that the fuel cell achieves self-startup at temperatures as low as−13℃ under a constant current density of 100mA/cm^(2) without air-assisted heating.At an ambient temperature of−20℃,a successful start-up can be achieved with a heating power of 0.45 W/cm^(2).The temperature variation overtime during the cold start process can be represented by a sum of two exponential functions.The air-assisted heating scheme proposed in this study has significantly improved the cold start performance of fuel cells in low-temperature environments.Additionally,it provides critical reference data and validation support for component selection and feasibility assessment of hybrid power systems.展开更多
The exponential growth of over-the-top(OTT)entertainment has fueled a surge in content consumption across diverse formats,especially in regional Indian languages.With the Indian film industry producing over 1500 films...The exponential growth of over-the-top(OTT)entertainment has fueled a surge in content consumption across diverse formats,especially in regional Indian languages.With the Indian film industry producing over 1500 films annually in more than 20 languages,personalized recommendations are essential to highlight relevant content.To overcome the limitations of traditional recommender systems-such as static latent vectors,poor handling of cold-start scenarios,and the absence of uncertainty modeling-we propose a deep Collaborative Neural Generative Embedding(C-NGE)model.C-NGE dynamically learns user and item representations by integrating rating information and metadata features in a unified neural framework.It uses metadata as sampled noise and applies the reparameterization trick to capture latent patterns better and support predictions for new users or items without retraining.We evaluate CNGE on the Indian Regional Movies(IRM)dataset,along with MovieLens 100 K and 1 M.Results show that our model consistently outperforms several existing methods,and its extensibility allows for incorporating additional signals like user reviews and multimodal data to enhance recommendation quality.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
As a major function of smart transportation in smart cities,vehicle model recognition plays an important role in intelligent transportation.Due to the difference among different vehicle models recognition datasets,the...As a major function of smart transportation in smart cities,vehicle model recognition plays an important role in intelligent transportation.Due to the difference among different vehicle models recognition datasets,the accuracy of network model training in one scene will be greatly reduced in another one.However,if you don’t have a lot of vehicle model datasets for the current scene,you cannot properly train a model.To address this problem,we study the problem of cold start of vehicle model recognition under cross-scenario.Under the condition of small amount of datasets,combined with the method of transfer learning,load the DAN(Deep Adaptation Networks)and JAN(Joint Adaptation Networks)domain adaptation modules into the convolutional neural network AlexNet and ResNet,and get four models:AlexNet-JAN,AlexNet-DAN,ResNet-JAN,and ResNet-DAN which can achieve a higher accuracy at the beginning.Through experiments,transfer the vehicle model recognition from the network image dataset(source domain)to the surveillance-nature dataset(target domain),both Top-1 and Top-5 accuracy have been improved by at least 20%.展开更多
Recommender system (RS) has become a very important factor in many eCommerce sites. In our daily life, we rely on the recommendation from other persons either by word of mouth, recommendation letters, movie, item and ...Recommender system (RS) has become a very important factor in many eCommerce sites. In our daily life, we rely on the recommendation from other persons either by word of mouth, recommendation letters, movie, item and book reviews printed in newspapers, etc. The typical Recommender Systems are software tools and techniques that provide support to people by identifying interesting products and services in online store. It also provides a recommendation for certain users who search for the recommendations. The most important open challenge in Collaborative filtering recommender system is the cold start problem. If the adequate or sufficient information is not available for a new item or users, the recommender system runs into the cold start problem. To increase the usefulness of collaborative recommender systems, it could be desirable to eliminate the challenge such as cold start problem. Revealing the community structures is crucial to understand and more important with the increasing popularity of online social networks. The community detection is a key issue in social network analysis in which nodes of the communities are tightly connected each other and loosely connected between other communities. Many algorithms like Givan-Newman algorithm, modularity maximization, leading eigenvector, walk trap, etc., are used to detect the communities in the networks. To test the community division is meaningful we define a quality function called modularity. Modularity is that the links within a community are higher than the expected links in those communities. In this paper, we try to give a solution to the cold-start problem based on community detection algorithm that extracts the community from the social networks and identifies the similar users on that network. Hence, within the proposed work several intrinsic details are taken as a rule of thumb to boost the results higher. Moreover, the simulation experiment was taken to solve the cold start problem.展开更多
This paper integrated a two-dimensional axisymmetrical transient model applicable to cold-start emission applications. The model can be used to simulate and explain effects of the flow and temperature distribution on ...This paper integrated a two-dimensional axisymmetrical transient model applicable to cold-start emission applications. The model can be used to simulate and explain effects of the flow and temperature distribution on performance of a converter. The evolutions of distribution of the temperature and concentration in the monolith during the cold-start period and the effects of flow distribution in the monolith on the cold-start performance are simulated in terms of the integrated model. The investigation indicates that the axial and radial gradients of temperature of the solid become steeper as the inlet gas temperature ramp increases; this furthermore results in the movement of reaction region in the monolith, and the flow distribution in the monolith affects the radial distribution of temperature of the solid;the radial gradients of temperature of the solid become greater as the flow uniformity index decreases, whereas the light-off time doesn't always increase as the flow uniformity index decreases. The analyses on the distribution of temperature and concentration in the monolith show that the catalytic reaction zone concentrates in central area near the front face. The predicted curves of the velocity distribution have a good agreement with the experimental data.展开更多
Passive NO_(x) adsorbers(PNAs)were proposed to address the NO_(x) emissions during the cold start phase.Here we show a novel Ce-based BEA zeolite,as a noble-metal-free passive NO_(x)adsorber.The NO_(x) adsorption capa...Passive NO_(x) adsorbers(PNAs)were proposed to address the NO_(x) emissions during the cold start phase.Here we show a novel Ce-based BEA zeolite,as a noble-metal-free passive NO_(x)adsorber.The NO_(x) adsorption capacity of Ce/BEA reaches 36μmol/g in the feed gas close to realistic exhaust conditions,and the NO_(x) desorption temperature,which is around 290℃,is ideal for diesel exhaust after-treatment systems.Ce/BEA also behaves notable stability of high temperature CO exposure conditions.Multiple characterizations were performed to explore the NO_(x) adsorption chemistry of Ce/BEA.The Ce(Ⅳ)species in the BEA zeolite serves as the active center for NO_(x) adsorption.The bidentate nitrate species is responsible for the observed NO_(x) storage capacity,and the active oxygen around Ce(Ⅳ)plays a critical role in its formation.Considering the significantly better cost efficiency of Ce compared to Pd,Ce/BEA presents an enormous potential for the PNA applications and provides a novel formulation for the noblemetal choice of PNA materials.展开更多
Based on the introduction of the basic combustion concept of gasoline direct injection(GDI)engine and its operation under different operating conditions,HC emission mechanisms of the GDI en-gine are analyzed.And HC em...Based on the introduction of the basic combustion concept of gasoline direct injection(GDI)engine and its operation under different operating conditions,HC emission mechanisms of the GDI en-gine are analyzed.And HC emission characteristics of the GDI engine are compared with the PFI en-gine via a comparison test based on the FTP-75 driving cycle.It can be concluded that the GDI engineis facing a big challenge in meeting the future's HC emission standard.Reasons for the higher HC e-missions of the GDI engine are discussed and the ways for HC emission control are given.展开更多
When an aircraft moves under a low carrier-to-noise ratio （CNR） or at a high speed, increasing the sensitivity of global navigation satellite system （GNSS） receiver is a goal quite hard to achieve. A novel acquisi...When an aircraft moves under a low carrier-to-noise ratio （CNR） or at a high speed, increasing the sensitivity of global navigation satellite system （GNSS） receiver is a goal quite hard to achieve. A novel acquisition scheme assisted with micro-electro-mechanical-sensor （MEMS） inertial navigation system （INS） is presented to estimate the Doppler caused by user dynamics relative to each satellite ahead of time. Based on tightly coupled GNSS/INS estimation algorithm, MEMS INS Doppler error that can be achieved is first described. Then, by analyzing the mean acquisition time and signal detection probability, the MEMS INS-assisted acquisition capabilities in cold, warm and hot starts are quantitatively determined and compared with the standard GNSS acquisition capability. The simulations and comparisons have shown that： the acquisition time in cold start can be shortened by at least 23 s, the time in warm start can be shortened to i s and the acquisition capability is improved 95%, and the reaequisition time in hot start can be shortened by around 0.090 s and the capability can be enhanced 40%. The results demonstrate the validity of the novel method.展开更多
The number of mobile application services is showing an explosive growth trend,which makes it difficult for users to determine which ones are of interest.Especially,the new mobile application services are emerge conti...The number of mobile application services is showing an explosive growth trend,which makes it difficult for users to determine which ones are of interest.Especially,the new mobile application services are emerge continuously,most of them have not be rated when they need to be recommended to users.This is the typical problem of cold start in the field of collaborative filtering recommendation.This problem may makes it difficult for users to locate and acquire the services that they actually want,and the accuracy and novelty of service recommendations are also difficult to satisfy users.To solve this problem,a hybrid recommendation method for mobile application services based on content feature extraction is proposed in this paper.First,the proposed method in this paper extracts service content features through Natural Language Processing technologies such as word segmentation,part-of-speech tagging,and dependency parsing.It improves the accuracy of describing service attributes and the rationality of the method of calculating service similarity.Then,a language representation model called Bidirectional Encoder Representation from Transformers(BERT)is used to vectorize the content feature text,and an improved weighted word mover’s distance algorithm based on Term Frequency-Inverse Document Frequency(TFIDF-WMD)is used to calculate the similarity of mobile application services.Finally,the recommendation process is completed by combining the item-based collaborative filtering recommendation algorithm.The experimental results show that by using the proposed hybrid recommendation method presented in this paper,the cold start problem is alleviated to a certain extent,and the accuracy of the recommendation result has been significantly improved.展开更多
A catalyst comprised novel high surface area alumina support was prepared to control emission of automobiles. The results showed that prepared catalyst could satisfy the requirements of a high performance close couple...A catalyst comprised novel high surface area alumina support was prepared to control emission of automobiles. The results showed that prepared catalyst could satisfy the requirements of a high performance close coupled catalyst for its good catalytic activity at low temperature and good stability at high temperature.展开更多
Due to the technology limitation and inferior deNO_(x) efficiency of urea selective catalytic reduction (SCR) catalysts at low temperatures, passive NO_(x) adsorber (PNA) for decrease of NO_(x), CO and hydrocarbons (H...Due to the technology limitation and inferior deNO_(x) efficiency of urea selective catalytic reduction (SCR) catalysts at low temperatures, passive NO_(x) adsorber (PNA) for decrease of NO_(x), CO and hydrocarbons (HCs) during “cold start” of vehicles was proposed to meet the further tighten NO_(x) emission regulations in future. Among them, Pd modified zeolite PNA materials have received more attention because of their excellent NO_(x) storage capacity, anti-poisoning and hydrothermal stability and since Pd/zeolite PNA was proposed, a variety of advanced characterization methods have been applied to investigate its adsorption behavior and structure-performance relationship. The comprehension of the active sites and adsorption chemistry of Pd/zeolite PNA was also significantly improved. However, there are few reviews that systematically summarize the recent progress and application challenges in atomic-level understanding of this material. In this review, we summarized the latest research progress of Pd/zeolite PNA, including active adsorption sites, adsorption mechanism, material physicochemical properties, preparation methods, storage and release performance and structure-performance relationships. In addition, the deactivation challenges faced by Pd/zeolite PNA in practical applications, such as chemical poisoning, high temperature hydrothermal aging deactivation, etc., were also discussed at the micro-level, and some possible effective countermeasures are given. Besides, some possible improvements and research hotspots were put forward, which could be helpful for designing and constructing more efficient PNA materials for meeting the ultra-low NO_(x) emission regulation in the future.展开更多
Water transport is of paramount importance to the cold start of proton exchange membrane fuel cells(PEMFCs).Analysis of water transport in cathode catalyst layer(CCL)during cold start reveals the distinct characterist...Water transport is of paramount importance to the cold start of proton exchange membrane fuel cells(PEMFCs).Analysis of water transport in cathode catalyst layer(CCL)during cold start reveals the distinct characteristics from the normal temperature operation.This work studies the effect of CCL mesoscopic pore-morphology on PEMFC cold start.The CCL mesoscale morphology is characterized by two tortuosity factors of the ionomer network and pore structure,respectively.The simulation results demonstrate that the mesoscale morphology of CCL has a significant influence on the performance of PEMFC cold start.It was found that cold-starting of a cell with a CCL of less tortuous mesoscale morphology can succeed,whereas starting up a cell with a CCL of more tortuous mesoscale morphology may fail.The CCL of less tortuous pore structure reduces the water back diffusion resistance from the CCL to proton exchange membrane(PEM),thus enhancing the water storage in PEM,while reducing the tortuosity in ionomer network of CCL is found to enhance the water transport in and the water removal from CCL.For the sake of better cold start performance,novel preparation methods,which can create catalyst layers of larger size primary pores and less tortuous pore structure and ionomer network,are desirable.展开更多
To enhance the fuel economy of a vehicle powered by a gasoline engine under road conditions,an energy flow test of a vehicle was performed experimentally under the New European Driving Cycle of cold start.The energy d...To enhance the fuel economy of a vehicle powered by a gasoline engine under road conditions,an energy flow test of a vehicle was performed experimentally under the New European Driving Cycle of cold start.The energy distributions and related influencing factors were analyzed using the test data.Results show that the effective power and thermal efficiency are mainly affected by the engine load except in the early stage of the New European Driving Cycle.Because of the retarded CA50 and longer CA10-90,the effective thermal efficiency is lower in the early phase of driving conditions.Initially,the heat transfer loss mainly comprises the loss of the heating,ventilation,and air conditioning system.The radiator then plays the major role,with its percentage affected by the engine load and decreasing under the extra-urban driving cycle.The exhaust gas loss is decided by the temperature and flow rate of the exhaust gas,while its percentage is mainly affected by the temperature of the exhaust gas.In the early phase of driving conditions,the retarded spark advance angle leads to a higher temperature of the exhaust gas and a greater exhaust gas loss.The pumping loss and its percentage are mainly determined by the engine speed under the urban driving cycle,and both decrease under the extra-urban driving cycle except at maximum vehicle speed.展开更多
To reduce the fuel consumption of internal combustion engines, more attention has been paid to the tribological performance of the piston ring pack during the cold start and idle operations. In this research, a numeri...To reduce the fuel consumption of internal combustion engines, more attention has been paid to the tribological performance of the piston ring pack during the cold start and idle operations. In this research, a numerical model considering the cylinder liner deformation and the piston ring conformability is developed to predict the blow-by, lubrication, friction and wear of the piston ring pack under different operating conditions. The gas flow rate, inter-ring gas pressures, minimum oil film thickness, frictional force and wear load during cold start are calculated and compared with those during warm idle operating conditions. The results show that cylinder liner deformation and piston ring conformability together obviously affect blow-by and other tribological performance. Meanwhile, it is found that friction loss is larger during cold start than during warm idle operating conditions. However, the wear process is more severe during warm idle operation than during cold start. From this research, the blow-by and tribological performance of the piston ring pack during cold start and warm idle operations are understood more deeply.展开更多
Grid-based recommendation algorithms view users and items as abstract nodes,and the information utilised by the algorithm is hidden in the selection relationships between users and items.Although these relationships c...Grid-based recommendation algorithms view users and items as abstract nodes,and the information utilised by the algorithm is hidden in the selection relationships between users and items.Although these relationships can be easily handled,much useful information is overlooked,resulting in a less accurate recommendation algorithm.The aim of this paper is to propose improvements on the standard substance diffusion algorithm,taking into account the influence of the user’s rating on the recommended item,adding a moderating factor,and optimising the initial resource allocation vector and resource transfer matrix in the recommendation algorithm.An average ranking score evaluation index is introduced to quantify user satisfaction with the recommendation results.Experiments are conducted on the MovieLens training dataset,and the experimental results show that the proposed algorithm outperforms classical collaborative filtering systems and network structure based recommendation systems in terms of recommendation accuracy and hit rate.展开更多
Purpose-English original movies played an important role in English learning and communication.In order to find the required movies for us from a large number of English original movies and reviews,this paper proposed...Purpose-English original movies played an important role in English learning and communication.In order to find the required movies for us from a large number of English original movies and reviews,this paper proposed an improved deep reinforcement learning algorithm for the recommendation of movies.In fact,although the conventional movies recommendation algorithms have solved the problem of information overload,they still have their limitations in the case of cold start-up and sparse data.Design/methodology/approach-To solve the aforementioned problems of conventional movies recommendation algorithms,this paper proposed a recommendation algorithm based on the theory of deep reinforcement learning,which uses the deep deterministic policy gradient(DDPG)algorithm to solve the cold starting and sparse data problems and uses Item2vec to transform discrete action space into a continuous one.Meanwhile,a reward function combining with cosine distance and Euclidean distance is proposed to ensure that the neural network does not converge to local optimum prematurely.Findings-In order to verify the feasibility and validity of the proposed algorithm,the state of the art and the proposed algorithm are compared in indexes of RMSE,recall rate and accuracy based on the MovieLens English original movie data set for the experiments.Experimental results have shown that the proposed algorithm is superior to the conventional algorithm in various indicators.Originality/value-Applying the proposed algorithm to recommend English original movies,DDPG policy produces better recommendation results and alleviates the impact of cold start and sparse data.展开更多
基金funded by Zhejiang Province Spearhead and Leading Goose Research and Development Key Program,grant number 2023C01239.
文摘In the realm of all-electric aircraft research,the integration of cathode-open proton exchange membrane fuel cells(PEMFC)with lithiumbatteries as a hybrid power source for small to medium-sized unmanned aerial vehicles(UAVs)has garnered significant attention.The PEMFC,serving as the primary energy supply,markedly extends the UAV’s operational endurance.However,due to payload limitations and spatial constraints in the airframe layout of UAVs,the stack requires customized adaptation.Moreover,the implementation of auxiliary systems to facilitate cold starts of the PEMFC under low-temperature conditions is not feasible.Relying solely on thermal insulation measures also proves inadequate to address the challenges posed by complex low-temperature startup scenarios.To overcomethis,our study leverages the UAV’s lithium battery to heat the cathode inlet airflow,aiding the cathode-open PEMFC cold start process.To validate the feasibility of the proposed air-assisted heating strategy during the conceptual design phase,this study develops a transient,non-isothermal 3Dcathode-open PEMF Cunitmodel incorporating cathode air-assisted heating and gas-ice phase change.The model’s accuracy was verified against experimental cold-start data from a stack composed of identical single cells.This computational framework enables quantitative analysis of temperature fields and ice fraction distributions across domains under varying air-assisted heating powers during cold starts.Building upon this model,the study further investigates the improvement in cold start performance by heating the cathode intake air with varying power levels.The results demonstrate that the fuel cell achieves self-startup at temperatures as low as−13℃ under a constant current density of 100mA/cm^(2) without air-assisted heating.At an ambient temperature of−20℃,a successful start-up can be achieved with a heating power of 0.45 W/cm^(2).The temperature variation overtime during the cold start process can be represented by a sum of two exponential functions.The air-assisted heating scheme proposed in this study has significantly improved the cold start performance of fuel cells in low-temperature environments.Additionally,it provides critical reference data and validation support for component selection and feasibility assessment of hybrid power systems.
文摘The exponential growth of over-the-top(OTT)entertainment has fueled a surge in content consumption across diverse formats,especially in regional Indian languages.With the Indian film industry producing over 1500 films annually in more than 20 languages,personalized recommendations are essential to highlight relevant content.To overcome the limitations of traditional recommender systems-such as static latent vectors,poor handling of cold-start scenarios,and the absence of uncertainty modeling-we propose a deep Collaborative Neural Generative Embedding(C-NGE)model.C-NGE dynamically learns user and item representations by integrating rating information and metadata features in a unified neural framework.It uses metadata as sampled noise and applies the reparameterization trick to capture latent patterns better and support predictions for new users or items without retraining.We evaluate CNGE on the Indian Regional Movies(IRM)dataset,along with MovieLens 100 K and 1 M.Results show that our model consistently outperforms several existing methods,and its extensibility allows for incorporating additional signals like user reviews and multimodal data to enhance recommendation quality.
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This work was supported by CETC Joint Research Program under Grant 6141B08020101,6141B08080101National Key R&D Program of China under Grant 2018ZX09201014the National Natural Science Foundation of China under Grant 61002011.
文摘As a major function of smart transportation in smart cities,vehicle model recognition plays an important role in intelligent transportation.Due to the difference among different vehicle models recognition datasets,the accuracy of network model training in one scene will be greatly reduced in another one.However,if you don’t have a lot of vehicle model datasets for the current scene,you cannot properly train a model.To address this problem,we study the problem of cold start of vehicle model recognition under cross-scenario.Under the condition of small amount of datasets,combined with the method of transfer learning,load the DAN(Deep Adaptation Networks)and JAN(Joint Adaptation Networks)domain adaptation modules into the convolutional neural network AlexNet and ResNet,and get four models:AlexNet-JAN,AlexNet-DAN,ResNet-JAN,and ResNet-DAN which can achieve a higher accuracy at the beginning.Through experiments,transfer the vehicle model recognition from the network image dataset(source domain)to the surveillance-nature dataset(target domain),both Top-1 and Top-5 accuracy have been improved by at least 20%.
文摘Recommender system (RS) has become a very important factor in many eCommerce sites. In our daily life, we rely on the recommendation from other persons either by word of mouth, recommendation letters, movie, item and book reviews printed in newspapers, etc. The typical Recommender Systems are software tools and techniques that provide support to people by identifying interesting products and services in online store. It also provides a recommendation for certain users who search for the recommendations. The most important open challenge in Collaborative filtering recommender system is the cold start problem. If the adequate or sufficient information is not available for a new item or users, the recommender system runs into the cold start problem. To increase the usefulness of collaborative recommender systems, it could be desirable to eliminate the challenge such as cold start problem. Revealing the community structures is crucial to understand and more important with the increasing popularity of online social networks. The community detection is a key issue in social network analysis in which nodes of the communities are tightly connected each other and loosely connected between other communities. Many algorithms like Givan-Newman algorithm, modularity maximization, leading eigenvector, walk trap, etc., are used to detect the communities in the networks. To test the community division is meaningful we define a quality function called modularity. Modularity is that the links within a community are higher than the expected links in those communities. In this paper, we try to give a solution to the cold-start problem based on community detection algorithm that extracts the community from the social networks and identifies the similar users on that network. Hence, within the proposed work several intrinsic details are taken as a rule of thumb to boost the results higher. Moreover, the simulation experiment was taken to solve the cold start problem.
基金PhD Discipline Foundation of Educational Department of China (No. 20010248003).
文摘This paper integrated a two-dimensional axisymmetrical transient model applicable to cold-start emission applications. The model can be used to simulate and explain effects of the flow and temperature distribution on performance of a converter. The evolutions of distribution of the temperature and concentration in the monolith during the cold-start period and the effects of flow distribution in the monolith on the cold-start performance are simulated in terms of the integrated model. The investigation indicates that the axial and radial gradients of temperature of the solid become steeper as the inlet gas temperature ramp increases; this furthermore results in the movement of reaction region in the monolith, and the flow distribution in the monolith affects the radial distribution of temperature of the solid;the radial gradients of temperature of the solid become greater as the flow uniformity index decreases, whereas the light-off time doesn't always increase as the flow uniformity index decreases. The analyses on the distribution of temperature and concentration in the monolith show that the catalytic reaction zone concentrates in central area near the front face. The predicted curves of the velocity distribution have a good agreement with the experimental data.
基金supported by the National Key R&D Program of China(2021YFB3503200)the Major Science and Technology Programs of Yunnan Province(202002AB080001-1)。
文摘Passive NO_(x) adsorbers(PNAs)were proposed to address the NO_(x) emissions during the cold start phase.Here we show a novel Ce-based BEA zeolite,as a noble-metal-free passive NO_(x)adsorber.The NO_(x) adsorption capacity of Ce/BEA reaches 36μmol/g in the feed gas close to realistic exhaust conditions,and the NO_(x) desorption temperature,which is around 290℃,is ideal for diesel exhaust after-treatment systems.Ce/BEA also behaves notable stability of high temperature CO exposure conditions.Multiple characterizations were performed to explore the NO_(x) adsorption chemistry of Ce/BEA.The Ce(Ⅳ)species in the BEA zeolite serves as the active center for NO_(x) adsorption.The bidentate nitrate species is responsible for the observed NO_(x) storage capacity,and the active oxygen around Ce(Ⅳ)plays a critical role in its formation.Considering the significantly better cost efficiency of Ce compared to Pd,Ce/BEA presents an enormous potential for the PNA applications and provides a novel formulation for the noblemetal choice of PNA materials.
文摘Based on the introduction of the basic combustion concept of gasoline direct injection(GDI)engine and its operation under different operating conditions,HC emission mechanisms of the GDI en-gine are analyzed.And HC emission characteristics of the GDI engine are compared with the PFI en-gine via a comparison test based on the FTP-75 driving cycle.It can be concluded that the GDI engineis facing a big challenge in meeting the future's HC emission standard.Reasons for the higher HC e-missions of the GDI engine are discussed and the ways for HC emission control are given.
基金the National High Technology Research and Development Program (863) of China(No.2009AA12Z322)
文摘When an aircraft moves under a low carrier-to-noise ratio （CNR） or at a high speed, increasing the sensitivity of global navigation satellite system （GNSS） receiver is a goal quite hard to achieve. A novel acquisition scheme assisted with micro-electro-mechanical-sensor （MEMS） inertial navigation system （INS） is presented to estimate the Doppler caused by user dynamics relative to each satellite ahead of time. Based on tightly coupled GNSS/INS estimation algorithm, MEMS INS Doppler error that can be achieved is first described. Then, by analyzing the mean acquisition time and signal detection probability, the MEMS INS-assisted acquisition capabilities in cold, warm and hot starts are quantitatively determined and compared with the standard GNSS acquisition capability. The simulations and comparisons have shown that： the acquisition time in cold start can be shortened by at least 23 s, the time in warm start can be shortened to i s and the acquisition capability is improved 95%, and the reaequisition time in hot start can be shortened by around 0.090 s and the capability can be enhanced 40%. The results demonstrate the validity of the novel method.
基金Project supported by the National Natural Science Foundation,China(No.62172123)the Postdoctoral Science Foundation of Heilongjiang Province,China(No.LBH-Z19067)+1 种基金the special projects for the central government to guide the development of local science and technology,China(No.ZY20B11)the Natural Science Foundation of Heilongjiang Province,China(No.QC2018081).
文摘The number of mobile application services is showing an explosive growth trend,which makes it difficult for users to determine which ones are of interest.Especially,the new mobile application services are emerge continuously,most of them have not be rated when they need to be recommended to users.This is the typical problem of cold start in the field of collaborative filtering recommendation.This problem may makes it difficult for users to locate and acquire the services that they actually want,and the accuracy and novelty of service recommendations are also difficult to satisfy users.To solve this problem,a hybrid recommendation method for mobile application services based on content feature extraction is proposed in this paper.First,the proposed method in this paper extracts service content features through Natural Language Processing technologies such as word segmentation,part-of-speech tagging,and dependency parsing.It improves the accuracy of describing service attributes and the rationality of the method of calculating service similarity.Then,a language representation model called Bidirectional Encoder Representation from Transformers(BERT)is used to vectorize the content feature text,and an improved weighted word mover’s distance algorithm based on Term Frequency-Inverse Document Frequency(TFIDF-WMD)is used to calculate the similarity of mobile application services.Finally,the recommendation process is completed by combining the item-based collaborative filtering recommendation algorithm.The experimental results show that by using the proposed hybrid recommendation method presented in this paper,the cold start problem is alleviated to a certain extent,and the accuracy of the recommendation result has been significantly improved.
基金the National Natural Science Foundation of China(No.20333030)for providing financial support for this project.
文摘A catalyst comprised novel high surface area alumina support was prepared to control emission of automobiles. The results showed that prepared catalyst could satisfy the requirements of a high performance close coupled catalyst for its good catalytic activity at low temperature and good stability at high temperature.
基金financial support from the National Natural Science Foundation of China (No. 52000084)the China Postdoctoral Science Foundation (No. 2019M662630)National Engineering Laboratory for Mobile Source Emission Control Technology (No. NELMS2018A08)。
文摘Due to the technology limitation and inferior deNO_(x) efficiency of urea selective catalytic reduction (SCR) catalysts at low temperatures, passive NO_(x) adsorber (PNA) for decrease of NO_(x), CO and hydrocarbons (HCs) during “cold start” of vehicles was proposed to meet the further tighten NO_(x) emission regulations in future. Among them, Pd modified zeolite PNA materials have received more attention because of their excellent NO_(x) storage capacity, anti-poisoning and hydrothermal stability and since Pd/zeolite PNA was proposed, a variety of advanced characterization methods have been applied to investigate its adsorption behavior and structure-performance relationship. The comprehension of the active sites and adsorption chemistry of Pd/zeolite PNA was also significantly improved. However, there are few reviews that systematically summarize the recent progress and application challenges in atomic-level understanding of this material. In this review, we summarized the latest research progress of Pd/zeolite PNA, including active adsorption sites, adsorption mechanism, material physicochemical properties, preparation methods, storage and release performance and structure-performance relationships. In addition, the deactivation challenges faced by Pd/zeolite PNA in practical applications, such as chemical poisoning, high temperature hydrothermal aging deactivation, etc., were also discussed at the micro-level, and some possible effective countermeasures are given. Besides, some possible improvements and research hotspots were put forward, which could be helpful for designing and constructing more efficient PNA materials for meeting the ultra-low NO_(x) emission regulation in the future.
文摘Water transport is of paramount importance to the cold start of proton exchange membrane fuel cells(PEMFCs).Analysis of water transport in cathode catalyst layer(CCL)during cold start reveals the distinct characteristics from the normal temperature operation.This work studies the effect of CCL mesoscopic pore-morphology on PEMFC cold start.The CCL mesoscale morphology is characterized by two tortuosity factors of the ionomer network and pore structure,respectively.The simulation results demonstrate that the mesoscale morphology of CCL has a significant influence on the performance of PEMFC cold start.It was found that cold-starting of a cell with a CCL of less tortuous mesoscale morphology can succeed,whereas starting up a cell with a CCL of more tortuous mesoscale morphology may fail.The CCL of less tortuous pore structure reduces the water back diffusion resistance from the CCL to proton exchange membrane(PEM),thus enhancing the water storage in PEM,while reducing the tortuosity in ionomer network of CCL is found to enhance the water transport in and the water removal from CCL.For the sake of better cold start performance,novel preparation methods,which can create catalyst layers of larger size primary pores and less tortuous pore structure and ionomer network,are desirable.
基金This research work is jointly sponsored by the National Natural Science Foundation of China(No.51776061)Young Elite Scientists Sponsorship Program of the China Association for Science and Technology(No.2017QNRC001)Fundamental Research Funds for the Central Universities.
文摘To enhance the fuel economy of a vehicle powered by a gasoline engine under road conditions,an energy flow test of a vehicle was performed experimentally under the New European Driving Cycle of cold start.The energy distributions and related influencing factors were analyzed using the test data.Results show that the effective power and thermal efficiency are mainly affected by the engine load except in the early stage of the New European Driving Cycle.Because of the retarded CA50 and longer CA10-90,the effective thermal efficiency is lower in the early phase of driving conditions.Initially,the heat transfer loss mainly comprises the loss of the heating,ventilation,and air conditioning system.The radiator then plays the major role,with its percentage affected by the engine load and decreasing under the extra-urban driving cycle.The exhaust gas loss is decided by the temperature and flow rate of the exhaust gas,while its percentage is mainly affected by the temperature of the exhaust gas.In the early phase of driving conditions,the retarded spark advance angle leads to a higher temperature of the exhaust gas and a greater exhaust gas loss.The pumping loss and its percentage are mainly determined by the engine speed under the urban driving cycle,and both decrease under the extra-urban driving cycle except at maximum vehicle speed.
基金supported by the National Natural Science Foundation of China(Grant No.51375300)the Research Project of State Key Laboratory of Mechanical System and Vibration(Grant No.MSVZD201401)
文摘To reduce the fuel consumption of internal combustion engines, more attention has been paid to the tribological performance of the piston ring pack during the cold start and idle operations. In this research, a numerical model considering the cylinder liner deformation and the piston ring conformability is developed to predict the blow-by, lubrication, friction and wear of the piston ring pack under different operating conditions. The gas flow rate, inter-ring gas pressures, minimum oil film thickness, frictional force and wear load during cold start are calculated and compared with those during warm idle operating conditions. The results show that cylinder liner deformation and piston ring conformability together obviously affect blow-by and other tribological performance. Meanwhile, it is found that friction loss is larger during cold start than during warm idle operating conditions. However, the wear process is more severe during warm idle operation than during cold start. From this research, the blow-by and tribological performance of the piston ring pack during cold start and warm idle operations are understood more deeply.
基金supported by the National Natural Science Foundation of China(No.62302199)China Postdoctoral Science Foundation(No.2023M731368)+2 种基金Natural Science Foundation of the Jiangsu Higher Education Institutions(No.22KJB520016)Ministry of Education in China(MOE)Youth Foundation Project of Humanities and Social Sciences(No.22YJC870007)2022 Jiangsu University Undergraduate Student English Teaching Excellence Program,and Ministry of Education’s Industry-Education Cooperation Collaborative Education Project(No.202102306005).
文摘Grid-based recommendation algorithms view users and items as abstract nodes,and the information utilised by the algorithm is hidden in the selection relationships between users and items.Although these relationships can be easily handled,much useful information is overlooked,resulting in a less accurate recommendation algorithm.The aim of this paper is to propose improvements on the standard substance diffusion algorithm,taking into account the influence of the user’s rating on the recommended item,adding a moderating factor,and optimising the initial resource allocation vector and resource transfer matrix in the recommendation algorithm.An average ranking score evaluation index is introduced to quantify user satisfaction with the recommendation results.Experiments are conducted on the MovieLens training dataset,and the experimental results show that the proposed algorithm outperforms classical collaborative filtering systems and network structure based recommendation systems in terms of recommendation accuracy and hit rate.
基金supported by the education and research project of young and middle-aged teachers in Fujian province(special research project of foreign language teaching reform in colleges and universities):No.JZ170067.
文摘Purpose-English original movies played an important role in English learning and communication.In order to find the required movies for us from a large number of English original movies and reviews,this paper proposed an improved deep reinforcement learning algorithm for the recommendation of movies.In fact,although the conventional movies recommendation algorithms have solved the problem of information overload,they still have their limitations in the case of cold start-up and sparse data.Design/methodology/approach-To solve the aforementioned problems of conventional movies recommendation algorithms,this paper proposed a recommendation algorithm based on the theory of deep reinforcement learning,which uses the deep deterministic policy gradient(DDPG)algorithm to solve the cold starting and sparse data problems and uses Item2vec to transform discrete action space into a continuous one.Meanwhile,a reward function combining with cosine distance and Euclidean distance is proposed to ensure that the neural network does not converge to local optimum prematurely.Findings-In order to verify the feasibility and validity of the proposed algorithm,the state of the art and the proposed algorithm are compared in indexes of RMSE,recall rate and accuracy based on the MovieLens English original movie data set for the experiments.Experimental results have shown that the proposed algorithm is superior to the conventional algorithm in various indicators.Originality/value-Applying the proposed algorithm to recommend English original movies,DDPG policy produces better recommendation results and alleviates the impact of cold start and sparse data.
