The emergence of on-demand service provisioning by Federated Cloud Providers(FCPs)to Cloud Users(CU)has fuelled significant innovations in cloud provisioning models.Owing to the massive traffic,massive CU resource req...The emergence of on-demand service provisioning by Federated Cloud Providers(FCPs)to Cloud Users(CU)has fuelled significant innovations in cloud provisioning models.Owing to the massive traffic,massive CU resource requests are sent to FCPs,and appropriate service recommendations are sent by FCPs.Currently,the FourthGeneration(4G)-Long Term Evolution(LTE)network faces bottlenecks that affect end-user throughput and latency.Moreover,the data is exchanged among heterogeneous stakeholders,and thus trust is a prime concern.To address these limitations,the paper proposes a Blockchain(BC)-leveraged rank-based recommender scheme,FedRec,to expedite secure and trusted Cloud Service Provisioning(CSP)to the CU through the FCP at the backdrop of base 5G communication service.The scheme operates in three phases.In the first phase,a BCintegrated request-response broker model is formulated between the CU,Cloud Brokers(BR),and the FCP,where a CU service request is forwarded through the BR to different FCPs.For service requests,Anything-as-aService(XaaS)is supported by 5G-enhanced Mobile Broadband(eMBB)service.In the next phase,a weighted matching recommender model is proposed at the FCP sites based on a novel Ranking-Based Recommender(RBR)model based on the CU requests.In the final phase,based on the matching recommendations between the CU and the FCP,Smart Contracts(SC)are executed,and resource provisioning data is stored in the Interplanetary File Systems(IPFS)that expedite the block validations.The proposed scheme FedRec is compared in terms of SC evaluation and formal verification.In simulation,FedRec achieves a reduction of 27.55%in chain storage and a transaction throughput of 43.5074 Mbps at 150 blocks.For the IPFS,we have achieved a bandwidth improvement of 17.91%.In the RBR models,the maximum obtained hit ratio is 0.9314 at 200 million CU requests,showing an improvement of 1.2%in average servicing latency over non-RBR models and a maximization trade-off of QoE index of 2.7688 at the flow request 1.088 and at granted service price of USD 1.559 million to FCP for provided services.The obtained results indicate the viability of the proposed scheme against traditional approaches.展开更多
The response of rice to N fertilizer applicationhas shown that high rates of N application donot always ensure a proportional increase inyield due to high N losses. A model, ORYZA-0 was developed by ten Berge for desi...The response of rice to N fertilizer applicationhas shown that high rates of N application donot always ensure a proportional increase inyield due to high N losses. A model, ORYZA-0 was developed by ten Berge for designingoptimum N fertilizer management strategy inrice. We evaluated the performance ofORYZA-0 in Jinhua, Zhejiang Province. ORYZA-0 includes N uptakes, partition-ing of N among the organs, and utilization ofleaf N in converting solar energy to dry mat-ter. It can predict the amount and time of Nfertilizer application to achieve a maximumbiomass or yield combining with Price algo-rithm optimization procedure.展开更多
Citation network is often used for academic recommendation. However, it is difficult to achieve high recommendation accuracy and low time complexity because it is often very large and sparse and different citations ha...Citation network is often used for academic recommendation. However, it is difficult to achieve high recommendation accuracy and low time complexity because it is often very large and sparse and different citations have different purposes. What's more, some citations include unreasonable information, such as in case of intentional self-citation. To improve the accuracy of citation network-based academic recommendation and reduce the time complexity, we propose an academic recommendation method for recommending authors and papers. In which, an author-paper bilayer citation network is built, then an enhanced topic model, Author Community Topic Time Model(ACTTM) is proposed to detect high quality author communities in the author layer, and a set of attributes are proposed to comprehensively depict the author/paper nodes in the bilayer citation network. Experimental results prove that the proposed ACTTM can detect high quality author communities and facilitate low time complexity, and the proposed academic recommendation method can effectively improve the recommendation accuracy.展开更多
Point-of-interest(POI) recommendation is a popular topic on location-based social networks(LBSNs).Geographical proximity,known as a unique feature of LBSNs,significantly affects user check-in behavior.However,most of ...Point-of-interest(POI) recommendation is a popular topic on location-based social networks(LBSNs).Geographical proximity,known as a unique feature of LBSNs,significantly affects user check-in behavior.However,most of prior studies characterize the geographical influence based on a universal or personalized distribution of geographic distance,leading to unsatisfactory recommendation results.In this paper,the personalized geographical influence in a two-dimensional geographical space is modeled using the data field method,and we propose a semi-supervised probabilistic model based on a factor graph model to integrate different factors such as the geographical influence.Moreover,a distributed learning algorithm is used to scale up our method to large-scale data sets.Experimental results based on the data sets from Foursquare and Gowalla show that our method outperforms other competing POI recommendation techniques.展开更多
With the development of the Internet of Things(Io T), people's lives have become increasingly convenient. It is desirable for smart home(SH) systems to integrate and leverage the enormous information available fro...With the development of the Internet of Things(Io T), people's lives have become increasingly convenient. It is desirable for smart home(SH) systems to integrate and leverage the enormous information available from IoT. Information can be analyzed to learn user intentions and automatically provide the appropriate services. However, existing service recommendation models typically do not consider the services that are unavailable in a user's living environment. In order to address this problem, we propose a series of semantic models for SH devices. These semantic models can be used to infer user intentions. Based on the models, we proposed a service recommendation probability model and an alternative-service recommending algorithm. The algorithm is devoted to providing appropriate alternative services when the desired service is unavailable. The algorithm has been implemented and achieves accuracy higher than traditional Hidden Markov Model(HMM). The maximum accuracy achieved is 68.3%.展开更多
The existing search engines are lack of the consideration of personalization and display the same search results for different users despite their differences in interesting and purpose. By analyzing user's dynamic s...The existing search engines are lack of the consideration of personalization and display the same search results for different users despite their differences in interesting and purpose. By analyzing user's dynamic search behavior, the paper introduces a new method of using a keyword query graph to express user's dynamic search behavior, and uses Bayesian network to construct the prior probability of keyword selection and the migration probability between keywords for each user. To reflect the dynamic changes of the user's preference, the paper introduces non-lineal gradual forgetting collaborative filtering strategy into the personalized search recommendation model. By calculating the similarity between each two users, the model can do the recommendation based on neighbors and be used to construct the personalized search engine.展开更多
Generally, predicting whether an item will be liked or disliked by active users, and how much an item will be liked, is a main task of collaborative filtering systems or recommender systems. Recently, predicting most ...Generally, predicting whether an item will be liked or disliked by active users, and how much an item will be liked, is a main task of collaborative filtering systems or recommender systems. Recently, predicting most likely bought items for a target user, which is a subproblem of the rank problem of collaborative filtering, became an important task in collaborative filtering. Traditionally, the prediction uses the user item co-occurrence data based on users' buying behaviors. However, it is challenging to achieve good prediction performance using traditional methods based on single domain information due to the extreme sparsity of the buying matrix. In this paper, we propose a novel method called the preference transfer model for effective cross-domain collaborative filtering. Based on the preference transfer model, a common basis item-factor matrix and different user-factor matrices are factorized.Each user-factor matrix can be viewed as user preference in terms of browsing behavior or buying behavior. Then,two factor-user matrices can be used to construct a so-called ‘preference dictionary' that can discover in advance the consistent preference of users, from their browsing behaviors to their buying behaviors. Experimental results demonstrate that the proposed preference transfer model outperforms the other methods on the Alibaba Tmall data set provided by the Alibaba Group.展开更多
With the rapid development of location-based networks, point-of-interest(POI) recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel o...With the rapid development of location-based networks, point-of-interest(POI) recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity(GTSCP) to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.展开更多
Making medication prescriptions in response to the patient's diagnosis is a challenging task.The number of pharmaceutical companies,their inventory of medicines,and the recommended dosage confront a doctor with th...Making medication prescriptions in response to the patient's diagnosis is a challenging task.The number of pharmaceutical companies,their inventory of medicines,and the recommended dosage confront a doctor with the well-known problem of information and cognitive overload.To assist a medical practitioner in making informed decisions regarding a medical prescription to a patient,researchers have exploited electronic health records(EHRs)in automatically recommending medication.In recent years,medication recommendation using EHRs has been a salient research direction,which has attracted researchers to apply various deep learning(DL)models to the EHRs of patients in recommending prescriptions.Yet,in the absence of a holistic survey article,it needs a lot of effort and time to study these publications in order to understand the current state of research and identify the best-performing models along with the trends and challenges.To fill this research gap,this survey reports on state-of-the-art DL-based medication recommendation methods.It reviews the classification of DL-based medication recommendation(MR)models,compares their performance,and the unavoidable issues they face.It reports on the most common datasets and metrics used in evaluating MR models.The findings of this study have implications for researchers interested in MR models.展开更多
The rapid development of location-based social networks(LBSNs) has provided an unprecedented opportunity for better location-based services through point-of-interest(POI) recommendation. POI recommendation is pers...The rapid development of location-based social networks(LBSNs) has provided an unprecedented opportunity for better location-based services through point-of-interest(POI) recommendation. POI recommendation is personalized, location-aware, and context depended. However, extreme sparsity of user-POI matrix creates a severe challenge. In this paper we propose a textual-geographical-social aware probabilistic matrix factorization method for POI recommendation. Our model is textual-geographical-social aware probabilistic matrix factorization called TGS-PMF, it exploits textual information, geographical information, social information, and incorporates these factors effectively. First, we exploit an aggregated latent Dirichlet allocation(LDA) model to learn the interest topics of users and infer the interest POIs by mining textual information associated with POIs and generate interest relevance score. Second, we propose a kernel estimation method with an adaptive bandwidth to model the geographical correlations and generate geographical relevance score. Third, we build social relevance through the power-law distribution of user social relations to generate social relevance score. Then, our exploit probabilistic matrix factorization model(PMF) to integrate the interest, geographical, social relevance scores for POI recommendation. Finally, we implement experiments on a real LBSN check-in dataset. Experimental results show that TGS-PMF achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.展开更多
文摘The emergence of on-demand service provisioning by Federated Cloud Providers(FCPs)to Cloud Users(CU)has fuelled significant innovations in cloud provisioning models.Owing to the massive traffic,massive CU resource requests are sent to FCPs,and appropriate service recommendations are sent by FCPs.Currently,the FourthGeneration(4G)-Long Term Evolution(LTE)network faces bottlenecks that affect end-user throughput and latency.Moreover,the data is exchanged among heterogeneous stakeholders,and thus trust is a prime concern.To address these limitations,the paper proposes a Blockchain(BC)-leveraged rank-based recommender scheme,FedRec,to expedite secure and trusted Cloud Service Provisioning(CSP)to the CU through the FCP at the backdrop of base 5G communication service.The scheme operates in three phases.In the first phase,a BCintegrated request-response broker model is formulated between the CU,Cloud Brokers(BR),and the FCP,where a CU service request is forwarded through the BR to different FCPs.For service requests,Anything-as-aService(XaaS)is supported by 5G-enhanced Mobile Broadband(eMBB)service.In the next phase,a weighted matching recommender model is proposed at the FCP sites based on a novel Ranking-Based Recommender(RBR)model based on the CU requests.In the final phase,based on the matching recommendations between the CU and the FCP,Smart Contracts(SC)are executed,and resource provisioning data is stored in the Interplanetary File Systems(IPFS)that expedite the block validations.The proposed scheme FedRec is compared in terms of SC evaluation and formal verification.In simulation,FedRec achieves a reduction of 27.55%in chain storage and a transaction throughput of 43.5074 Mbps at 150 blocks.For the IPFS,we have achieved a bandwidth improvement of 17.91%.In the RBR models,the maximum obtained hit ratio is 0.9314 at 200 million CU requests,showing an improvement of 1.2%in average servicing latency over non-RBR models and a maximization trade-off of QoE index of 2.7688 at the flow request 1.088 and at granted service price of USD 1.559 million to FCP for provided services.The obtained results indicate the viability of the proposed scheme against traditional approaches.
文摘The response of rice to N fertilizer applicationhas shown that high rates of N application donot always ensure a proportional increase inyield due to high N losses. A model, ORYZA-0 was developed by ten Berge for designingoptimum N fertilizer management strategy inrice. We evaluated the performance ofORYZA-0 in Jinhua, Zhejiang Province. ORYZA-0 includes N uptakes, partition-ing of N among the organs, and utilization ofleaf N in converting solar energy to dry mat-ter. It can predict the amount and time of Nfertilizer application to achieve a maximumbiomass or yield combining with Price algo-rithm optimization procedure.
基金supported by the grants from Natural Science Foundation of China (Project No.61471060)
文摘Citation network is often used for academic recommendation. However, it is difficult to achieve high recommendation accuracy and low time complexity because it is often very large and sparse and different citations have different purposes. What's more, some citations include unreasonable information, such as in case of intentional self-citation. To improve the accuracy of citation network-based academic recommendation and reduce the time complexity, we propose an academic recommendation method for recommending authors and papers. In which, an author-paper bilayer citation network is built, then an enhanced topic model, Author Community Topic Time Model(ACTTM) is proposed to detect high quality author communities in the author layer, and a set of attributes are proposed to comprehensively depict the author/paper nodes in the bilayer citation network. Experimental results prove that the proposed ACTTM can detect high quality author communities and facilitate low time complexity, and the proposed academic recommendation method can effectively improve the recommendation accuracy.
基金supported by National Key Basic Research Program of China(973 Program) under Grant No.2014CB340404National Natural Science Foundation of China under Grant Nos.61272111 and 61273216Youth Chenguang Project of Science and Technology of Wuhan City under Grant No. 2014070404010232
文摘Point-of-interest(POI) recommendation is a popular topic on location-based social networks(LBSNs).Geographical proximity,known as a unique feature of LBSNs,significantly affects user check-in behavior.However,most of prior studies characterize the geographical influence based on a universal or personalized distribution of geographic distance,leading to unsatisfactory recommendation results.In this paper,the personalized geographical influence in a two-dimensional geographical space is modeled using the data field method,and we propose a semi-supervised probabilistic model based on a factor graph model to integrate different factors such as the geographical influence.Moreover,a distributed learning algorithm is used to scale up our method to large-scale data sets.Experimental results based on the data sets from Foursquare and Gowalla show that our method outperforms other competing POI recommendation techniques.
基金supported by the National Key Research and Development Program(No.2016YFB0800302)
文摘With the development of the Internet of Things(Io T), people's lives have become increasingly convenient. It is desirable for smart home(SH) systems to integrate and leverage the enormous information available from IoT. Information can be analyzed to learn user intentions and automatically provide the appropriate services. However, existing service recommendation models typically do not consider the services that are unavailable in a user's living environment. In order to address this problem, we propose a series of semantic models for SH devices. These semantic models can be used to infer user intentions. Based on the models, we proposed a service recommendation probability model and an alternative-service recommending algorithm. The algorithm is devoted to providing appropriate alternative services when the desired service is unavailable. The algorithm has been implemented and achieves accuracy higher than traditional Hidden Markov Model(HMM). The maximum accuracy achieved is 68.3%.
基金supported by the National Natural Science Foundation of China (60432010)the National Basic Research Program of China (2007CB307103)+1 种基金the Fundamental Research Funds for the Central Universities (2009RC0507)Important Science & Technology Specific Project of Guizhou Province (【2007】6017)
文摘The existing search engines are lack of the consideration of personalization and display the same search results for different users despite their differences in interesting and purpose. By analyzing user's dynamic search behavior, the paper introduces a new method of using a keyword query graph to express user's dynamic search behavior, and uses Bayesian network to construct the prior probability of keyword selection and the migration probability between keywords for each user. To reflect the dynamic changes of the user's preference, the paper introduces non-lineal gradual forgetting collaborative filtering strategy into the personalized search recommendation model. By calculating the similarity between each two users, the model can do the recommendation based on neighbors and be used to construct the personalized search engine.
基金supported by the National Basic Research Program(973)of China(No.2012CB316400)the National Natural Science Foundation of China(No.61571393)
文摘Generally, predicting whether an item will be liked or disliked by active users, and how much an item will be liked, is a main task of collaborative filtering systems or recommender systems. Recently, predicting most likely bought items for a target user, which is a subproblem of the rank problem of collaborative filtering, became an important task in collaborative filtering. Traditionally, the prediction uses the user item co-occurrence data based on users' buying behaviors. However, it is challenging to achieve good prediction performance using traditional methods based on single domain information due to the extreme sparsity of the buying matrix. In this paper, we propose a novel method called the preference transfer model for effective cross-domain collaborative filtering. Based on the preference transfer model, a common basis item-factor matrix and different user-factor matrices are factorized.Each user-factor matrix can be viewed as user preference in terms of browsing behavior or buying behavior. Then,two factor-user matrices can be used to construct a so-called ‘preference dictionary' that can discover in advance the consistent preference of users, from their browsing behaviors to their buying behaviors. Experimental results demonstrate that the proposed preference transfer model outperforms the other methods on the Alibaba Tmall data set provided by the Alibaba Group.
基金supported by the National Key Project of Scientific and Technical Supporting Programs of China(2014BAK15B01)
文摘With the rapid development of location-based networks, point-of-interest(POI) recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity(GTSCP) to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.
基金funded by Southeast University-China Mobile Research Institute Joint Innovation Center undergrantno.CMYJY-202200475。
文摘Making medication prescriptions in response to the patient's diagnosis is a challenging task.The number of pharmaceutical companies,their inventory of medicines,and the recommended dosage confront a doctor with the well-known problem of information and cognitive overload.To assist a medical practitioner in making informed decisions regarding a medical prescription to a patient,researchers have exploited electronic health records(EHRs)in automatically recommending medication.In recent years,medication recommendation using EHRs has been a salient research direction,which has attracted researchers to apply various deep learning(DL)models to the EHRs of patients in recommending prescriptions.Yet,in the absence of a holistic survey article,it needs a lot of effort and time to study these publications in order to understand the current state of research and identify the best-performing models along with the trends and challenges.To fill this research gap,this survey reports on state-of-the-art DL-based medication recommendation methods.It reviews the classification of DL-based medication recommendation(MR)models,compares their performance,and the unavoidable issues they face.It reports on the most common datasets and metrics used in evaluating MR models.The findings of this study have implications for researchers interested in MR models.
基金supported by the National Key Project of Scientific and Technical Supporting Programs of China (2014BAH26F00)
文摘The rapid development of location-based social networks(LBSNs) has provided an unprecedented opportunity for better location-based services through point-of-interest(POI) recommendation. POI recommendation is personalized, location-aware, and context depended. However, extreme sparsity of user-POI matrix creates a severe challenge. In this paper we propose a textual-geographical-social aware probabilistic matrix factorization method for POI recommendation. Our model is textual-geographical-social aware probabilistic matrix factorization called TGS-PMF, it exploits textual information, geographical information, social information, and incorporates these factors effectively. First, we exploit an aggregated latent Dirichlet allocation(LDA) model to learn the interest topics of users and infer the interest POIs by mining textual information associated with POIs and generate interest relevance score. Second, we propose a kernel estimation method with an adaptive bandwidth to model the geographical correlations and generate geographical relevance score. Third, we build social relevance through the power-law distribution of user social relations to generate social relevance score. Then, our exploit probabilistic matrix factorization model(PMF) to integrate the interest, geographical, social relevance scores for POI recommendation. Finally, we implement experiments on a real LBSN check-in dataset. Experimental results show that TGS-PMF achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.