Recommendation systems provide users with ranked items based on individual’s preferences. Two types of preferences are commonly used to generate ranking lists: long-term preferences which are relatively stable and sh...Recommendation systems provide users with ranked items based on individual’s preferences. Two types of preferences are commonly used to generate ranking lists: long-term preferences which are relatively stable and short-term preferences which are constantly changeable. But short-term preferences have an important real-time impact on individual’s current preferences. In order to predict personalized sequential patterns, the long-term user preferences and the short-term variations in preference need to be jointly considered for both personalization and sequential transitions. In this paper, a IFNR model is proposed to leverage long-term and short-term preferences for Next-Basket recommendation. In IFNR, similarity was used to represent long-term preferences. Personalized Markov model was exploited to mine short-term preferences based on individual’s behavior sequences. Personalized Markov transition matrix is generally very sparse, and thus it integrated Interest-Forgetting attribute, social trust relation and item similarity into personalized Markov model. Experimental results are on two real data sets, and show that this approach can improve the quality of recommendations compared with the existed methods.展开更多
Rolling bearing and Squeeze Film Damper(SFD)are used in rotor support structures,and most researches on the nonlinear rotor-bearing system are focused on the simple rotor-bearing systems.This work emphasizes the compa...Rolling bearing and Squeeze Film Damper(SFD)are used in rotor support structures,and most researches on the nonlinear rotor-bearing system are focused on the simple rotor-bearing systems.This work emphasizes the comparative analysis of the influence of SFD on the nonlinear dynamic behavior of the dual-rotor system supported by rolling bearings.Firstly,a reduced dynamic model is established by combining the Finite Element(FE)method and the freeinterface method of component mode synthesis.The proposed model is verified by comparing the natural characteristics obtained from an FE model with those from the experiment.Then,the steady-state vibration responses of the system with or without SFD are solved by the numerical integration method.The influences of the ball bearing clearance,unbalance,centralizing spring stiffness and oil film clearance of SFD on the nonlinear steady-state vibration responses of the dual-rotor system are analyzed.Results show that SFD can effectively suppress the amplitude jump of the dual rotor system sustaining two rotors unbalance excitations.As the ball bearing clearance or unbalance increases,the amplitude jump phenomenon becomes more obvious,the resonance hysteresis phenomenon strengthens or weakens,the resonant peaks shift to the left or the right,respectively.SFD with unreasonable parameters will aggravate the system vibration,the smaller the oil film clearance,the better the damping performance of the SFD,the larger the centralizing spring stiffness is,the larger resonance amplitudes are.展开更多
Irregular vasculature of solid tumors has proven to be a pivotal factor restricting their response to chimeric antigen receptor-T(CAR-T)cell therapy because it is tightly associated with hypoxia and other biological b...Irregular vasculature of solid tumors has proven to be a pivotal factor restricting their response to chimeric antigen receptor-T(CAR-T)cell therapy because it is tightly associated with hypoxia and other biological barriers.Herein,an injectable hydrogel composed of poly(ethylene glycol)dimethacrylate(PEGDMA)and ferrous chloride(FeCl2)responding to endogenous hydrogen peroxides(H2O2)is developed to enable sustained intratumoral release of Chinese herbal extracts tetramethylpyrazine(TMP).TMP is selected due to its potency in activating vascular endothelial growth factor(VEGF)expression and the endothelial nitric oxide synthase/nitric oxide(eNOS/NO)axis inside vascular endothelial cells.Upon being fixed inside tumors with the PEGDMA based hydrogel,TMP can remodel tumor vasculature by simultaneously promoting angiogenesis and dilating tumor vasculature and thus attenuate tumor hypoxia in two murine xenografts bearing human triple negative breast cancer(TNBC).Resultantly,treatment with TMP fixation potentiates the tumor suppression effect of intravenously injected epidermal growth factor receptor expressing CAR-T(HER1-CAR-T)cells toward two TNBC tumor xenografts by promoting their tumor infiltration,survival,and effector function.This study highlights a concise yet effective approach to reinforce the therapeutic potency of CAR-T cells towards targeted solid tumors by simply remodeling tumor vasculature.展开更多
Point of interest(POI)recommendation is one of the most important tasks in location-based social networks(LBSN).The existing recommendation methods face two challenges:(1)the cold start problem caused by data sparsity...Point of interest(POI)recommendation is one of the most important tasks in location-based social networks(LBSN).The existing recommendation methods face two challenges:(1)the cold start problem caused by data sparsity;(2)underutilization of the abundant side information besides user-POI interaction in large-scale data.Recent research shows that a user’s social relationship can be used to solve the cold start problem to some extent.The deep neural network learns users’long term and short term preferences to improve the recommendation quality.Therefore,this paper proposes a POI recommendation model called SSANet,applying side information(S)and self-attention(SA)to provide the high-satisfaction POI recommendations for users.Specifically,first,the user-POI interaction matrix were constructed by users history data to represents the user hidden representation;second,the side information includes rating scores,access frequency,social relationship,and geographic information were used to extract users preference;third,we use self-attention mechanism to learn user long term and short term preference.The experimental results on the real LBSN datasets show that the recommendation performance of the SSANet model is better than the existing POI recommendation model.展开更多
In the context of the rapid development of location-based socialnetworks (LBSN), point of interest (POI) recommendation becomes an importantservice in LBSN. The POI recommendation service aims to recommendsome new pla...In the context of the rapid development of location-based socialnetworks (LBSN), point of interest (POI) recommendation becomes an importantservice in LBSN. The POI recommendation service aims to recommendsome new places that may be of interest to users, help users to better understandtheir cities, and improve users’ experience of the platform. Although the geographicinfluence, similarity of POIs, and user check-ins information have beenused in the existing work recommended by POI, little existing work consideredcombing the aforementioned information. In this paper, we propose to makerecommendations by combing user ratings with the above information. Wemodel four types of information under a unified POI recommendation frameworkand this model is called extended user preference model based on matrixfactorization, referred to as UPEMF. Experiments were conducted on two realworld datasets, and the results show that the proposed method improves theaccuracy of POI recommendations compared to other recent methods.展开更多
基金the National Science Foundation of China (61100048, 61602159)the Natural Science Foundation of Heilongjiang Province (F2016034)the Education Department of Heilongjiang Province (12531498).
文摘Recommendation systems provide users with ranked items based on individual’s preferences. Two types of preferences are commonly used to generate ranking lists: long-term preferences which are relatively stable and short-term preferences which are constantly changeable. But short-term preferences have an important real-time impact on individual’s current preferences. In order to predict personalized sequential patterns, the long-term user preferences and the short-term variations in preference need to be jointly considered for both personalization and sequential transitions. In this paper, a IFNR model is proposed to leverage long-term and short-term preferences for Next-Basket recommendation. In IFNR, similarity was used to represent long-term preferences. Personalized Markov model was exploited to mine short-term preferences based on individual’s behavior sequences. Personalized Markov transition matrix is generally very sparse, and thus it integrated Interest-Forgetting attribute, social trust relation and item similarity into personalized Markov model. Experimental results are on two real data sets, and show that this approach can improve the quality of recommendations compared with the existed methods.
基金supported by the National Natural Science Foundation of China(Nos.11772089,11972112)the Fundamental Research Funds for the Central Universities,China(Nos.N170308028,N2003014 and N180708009)LiaoNing Revitalization Talents Program,China(Nos.XLYC1807008)。
文摘Rolling bearing and Squeeze Film Damper(SFD)are used in rotor support structures,and most researches on the nonlinear rotor-bearing system are focused on the simple rotor-bearing systems.This work emphasizes the comparative analysis of the influence of SFD on the nonlinear dynamic behavior of the dual-rotor system supported by rolling bearings.Firstly,a reduced dynamic model is established by combining the Finite Element(FE)method and the freeinterface method of component mode synthesis.The proposed model is verified by comparing the natural characteristics obtained from an FE model with those from the experiment.Then,the steady-state vibration responses of the system with or without SFD are solved by the numerical integration method.The influences of the ball bearing clearance,unbalance,centralizing spring stiffness and oil film clearance of SFD on the nonlinear steady-state vibration responses of the dual-rotor system are analyzed.Results show that SFD can effectively suppress the amplitude jump of the dual rotor system sustaining two rotors unbalance excitations.As the ball bearing clearance or unbalance increases,the amplitude jump phenomenon becomes more obvious,the resonance hysteresis phenomenon strengthens or weakens,the resonant peaks shift to the left or the right,respectively.SFD with unreasonable parameters will aggravate the system vibration,the smaller the oil film clearance,the better the damping performance of the SFD,the larger the centralizing spring stiffness is,the larger resonance amplitudes are.
基金supports from National Natural Science Foundation of China(82103099,22077093)the National Research Programs from Ministry of Science and Technology(MOST)of China(2021YFF0701800,2022YFF0706500)+3 种基金the Basic Science(Natural Science)Research Projects in Higher Education Institutions in Jiangsu Province(22KJB310010)the Natural Science Foundation of Jiangsu Province(BK20220110)the Suzhou Key Laboratory of Nanotechnology and Biomedicine,the Collaborative Innovation Center of Suzhou Nano Science and Technologythe 111 Program from the Ministry of Education of China。
文摘Irregular vasculature of solid tumors has proven to be a pivotal factor restricting their response to chimeric antigen receptor-T(CAR-T)cell therapy because it is tightly associated with hypoxia and other biological barriers.Herein,an injectable hydrogel composed of poly(ethylene glycol)dimethacrylate(PEGDMA)and ferrous chloride(FeCl2)responding to endogenous hydrogen peroxides(H2O2)is developed to enable sustained intratumoral release of Chinese herbal extracts tetramethylpyrazine(TMP).TMP is selected due to its potency in activating vascular endothelial growth factor(VEGF)expression and the endothelial nitric oxide synthase/nitric oxide(eNOS/NO)axis inside vascular endothelial cells.Upon being fixed inside tumors with the PEGDMA based hydrogel,TMP can remodel tumor vasculature by simultaneously promoting angiogenesis and dilating tumor vasculature and thus attenuate tumor hypoxia in two murine xenografts bearing human triple negative breast cancer(TNBC).Resultantly,treatment with TMP fixation potentiates the tumor suppression effect of intravenously injected epidermal growth factor receptor expressing CAR-T(HER1-CAR-T)cells toward two TNBC tumor xenografts by promoting their tumor infiltration,survival,and effector function.This study highlights a concise yet effective approach to reinforce the therapeutic potency of CAR-T cells towards targeted solid tumors by simply remodeling tumor vasculature.
文摘Point of interest(POI)recommendation is one of the most important tasks in location-based social networks(LBSN).The existing recommendation methods face two challenges:(1)the cold start problem caused by data sparsity;(2)underutilization of the abundant side information besides user-POI interaction in large-scale data.Recent research shows that a user’s social relationship can be used to solve the cold start problem to some extent.The deep neural network learns users’long term and short term preferences to improve the recommendation quality.Therefore,this paper proposes a POI recommendation model called SSANet,applying side information(S)and self-attention(SA)to provide the high-satisfaction POI recommendations for users.Specifically,first,the user-POI interaction matrix were constructed by users history data to represents the user hidden representation;second,the side information includes rating scores,access frequency,social relationship,and geographic information were used to extract users preference;third,we use self-attention mechanism to learn user long term and short term preference.The experimental results on the real LBSN datasets show that the recommendation performance of the SSANet model is better than the existing POI recommendation model.
文摘In the context of the rapid development of location-based socialnetworks (LBSN), point of interest (POI) recommendation becomes an importantservice in LBSN. The POI recommendation service aims to recommendsome new places that may be of interest to users, help users to better understandtheir cities, and improve users’ experience of the platform. Although the geographicinfluence, similarity of POIs, and user check-ins information have beenused in the existing work recommended by POI, little existing work consideredcombing the aforementioned information. In this paper, we propose to makerecommendations by combing user ratings with the above information. Wemodel four types of information under a unified POI recommendation frameworkand this model is called extended user preference model based on matrixfactorization, referred to as UPEMF. Experiments were conducted on two realworld datasets, and the results show that the proposed method improves theaccuracy of POI recommendations compared to other recent methods.
