Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for mo...Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation.The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator.Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences,enhancing the model’s capacity to discern and focus on distinctions among input gene pairs.The model,i.e.,DNA Pretrained Cross-Immunity Protection Inference model(DPCIPI),outperforms state-of-theart(SOTA)models in predicting hemagglutination inhibition titer from influenza viral gene sequences only.Improvement in binary cross-immunity prediction is 1.58%in F1,2.34%in precision,1.57%in recall,and 1.57%in Accuracy.For multilevel cross-immunity improvements,the improvement is 2.12%in F1,3.50%in precision,2.19%in recall,and 2.19%in Accuracy.Our study showcases the potential of pre-trained gene models to improve predictions of antigenic variation and cross-immunity.With expanding gene data and advancements in pre-trained models,this approach promises significant impacts on vaccine development and public health.展开更多
In order to measure the uncertain information of a type- 2 intuitionistic fuzzy set （T21FS）, an entropy measure of T21FS is presented by using the constructive principles. The proposed entropy measure is also proved...In order to measure the uncertain information of a type- 2 intuitionistic fuzzy set （T21FS）, an entropy measure of T21FS is presented by using the constructive principles. The proposed entropy measure is also proved to satisfy all of the constructive principles. Further, a novel concept of the type-2 triangular in- tuitionistic trapezoidal fuzzy set （T2TITrFS） is developed, and a geometric interpretation of the T2TITrFS is given to comprehend it completely or correctly in a more intuitive way. To deal with a more general uncertain complex system, the constructive principles of an entropy measure of T2TITrFS are therefore proposed on the basis of the axiomatic definition of the type-2 intuitionisic fuzzy entropy measure. This paper elicits a formula of type-2 triangular intuitionistic trapezoidal fuzzy entropy and verifies that it does sa- tisfy the constructive principles. Two examples are given to show the efficiency of the proposed entropy of T2TITrFS in describing the uncertainty of the type-2 intuitionistic fuzzy information and illustrate its application in type-2 triangular intuitionistic trapezodial fuzzy decision making problems.展开更多
In this paper, we study a single-period two-product inventory model with stochastic demands and downward substitution. The optimal order quantities are presented and some properties are provided. Comparing with newsbo...In this paper, we study a single-period two-product inventory model with stochastic demands and downward substitution. The optimal order quantities are presented and some properties are provided. Comparing with newsboy model, we prove that both the profit and the fill rate can be improved by using the substitution policy.展开更多
High-quality data are the foundation to monitor the progress and evaluate the effects of road traffic injury prevention measures.Unfortunately,official road traffic injury statistics delivered by governments worldwide...High-quality data are the foundation to monitor the progress and evaluate the effects of road traffic injury prevention measures.Unfortunately,official road traffic injury statistics delivered by governments worldwide,are often believed somewhat unreliable and invalid.We summarized the reported problems concerning the road traffic injury statistics through systematically searching and reviewing the literature.The problems include absence of regular data,under-reporting,low specificity,distorted cause spectrum of road traffic injury,inconsistency,inaccessibility,and delay of data release.We also explored the mechanisms behind the problematic data and proposed the solutions to the addressed challenges for road traffic statistics.展开更多
This study focuses on inventory strategies of Internet retailers (etailers). The etailer faces options of holding her own inventory or outsourcing through the third party(ies). We assess etailer inventory strategies t...This study focuses on inventory strategies of Internet retailers (etailers). The etailer faces options of holding her own inventory or outsourcing through the third party(ies). We assess etailer inventory strategies through mathematical modeling and numerical experiments. When ordering and holding her own stock, the etailer has full control of the order fulfillment process but bears the inventory-related risk. When outsourcing stock, etailer’s orders may not get an equal priority as for those of the third party’s own. Built upon simple operations research models, the numerical experiments suggest that the etailer is better off relying on others to fulfill orders if her demand (profit margin) is low, but should revert to the strategy of maintaining her own inventory if her sales volume (profit margin) is relatively high. Other factors are also investigated. These findings seem to confirm what are being practiced in the industry.展开更多
Location-based social network （LBSN） is at the forefront of emerging trends in social network services （SNS） since the users in LBSN are allowed to ＂check-in＂ the places （locations） when they visit them. The a...Location-based social network （LBSN） is at the forefront of emerging trends in social network services （SNS） since the users in LBSN are allowed to ＂check-in＂ the places （locations） when they visit them. The accurate geographi- cal and temporal information of these check-in actions are provided by the end-user GPS-enabled mobile devices, and recorded by the LBSN system. In this paper, we analyze and mine a big LBSN data, Gowalla, collected by us. First, we investigate the relationship between the spatio-temporal co- occurrences and social ties, and the results show that the co- occurrences are strongly correlative with the social ties. Sec- ond, we present a study of predicting two users whether or not they will meet （co-occur） at a place in a given future time, by exploring their check-in habits. In particular, we first intro- duce two new concepts, bag-of-location and bag-of-time-lag, to characterize user＇s check-in habits. Based on such bag rep- resentations, we define a similarity metric called habits sim- ilarity to measure the similarity between two users＇ check-in habits. Then we propose a machine !earning formula for pre- dicting co-occurrence based on the social ties and habits sim- ilarities. Finally, we conduct extensive experiments on our dataset, and the results demonstrate the effectiveness of the proposed method.展开更多
基金supported by the Bill & Melinda Gates Foundation and the Minderoo Foundation
文摘Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation.The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator.Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences,enhancing the model’s capacity to discern and focus on distinctions among input gene pairs.The model,i.e.,DNA Pretrained Cross-Immunity Protection Inference model(DPCIPI),outperforms state-of-theart(SOTA)models in predicting hemagglutination inhibition titer from influenza viral gene sequences only.Improvement in binary cross-immunity prediction is 1.58%in F1,2.34%in precision,1.57%in recall,and 1.57%in Accuracy.For multilevel cross-immunity improvements,the improvement is 2.12%in F1,3.50%in precision,2.19%in recall,and 2.19%in Accuracy.Our study showcases the potential of pre-trained gene models to improve predictions of antigenic variation and cross-immunity.With expanding gene data and advancements in pre-trained models,this approach promises significant impacts on vaccine development and public health.
基金supported by the National Natural Science Foundation of China(7137115670971017)the Research Grants Council of the Hong Kong Special Administrative Region,China(City U112111)
文摘In order to measure the uncertain information of a type- 2 intuitionistic fuzzy set （T21FS）, an entropy measure of T21FS is presented by using the constructive principles. The proposed entropy measure is also proved to satisfy all of the constructive principles. Further, a novel concept of the type-2 triangular in- tuitionistic trapezoidal fuzzy set （T2TITrFS） is developed, and a geometric interpretation of the T2TITrFS is given to comprehend it completely or correctly in a more intuitive way. To deal with a more general uncertain complex system, the constructive principles of an entropy measure of T2TITrFS are therefore proposed on the basis of the axiomatic definition of the type-2 intuitionisic fuzzy entropy measure. This paper elicits a formula of type-2 triangular intuitionistic trapezoidal fuzzy entropy and verifies that it does sa- tisfy the constructive principles. Two examples are given to show the efficiency of the proposed entropy of T2TITrFS in describing the uncertainty of the type-2 intuitionistic fuzzy information and illustrate its application in type-2 triangular intuitionistic trapezodial fuzzy decision making problems.
基金This work was supported partly by NSFC/RGC Joint Research Program under grant 79910161987the National Science Foundation of China(79825102,70231010,7032 1001)
文摘In this paper, we study a single-period two-product inventory model with stochastic demands and downward substitution. The optimal order quantities are presented and some properties are provided. Comparing with newsboy model, we prove that both the profit and the fill rate can be improved by using the substitution policy.
基金the Joint Research Scheme of National Natural Science Foundation of China/Research Grants Council of Hong Kong(Project No.71561167001&N_HKU707/15)the Natural Science Foundation of China(No.81573260 and No.713711921)the Hunan Provincial Innovation Foundation for Postgraduate(Grant No.CX2018B067).
文摘High-quality data are the foundation to monitor the progress and evaluate the effects of road traffic injury prevention measures.Unfortunately,official road traffic injury statistics delivered by governments worldwide,are often believed somewhat unreliable and invalid.We summarized the reported problems concerning the road traffic injury statistics through systematically searching and reviewing the literature.The problems include absence of regular data,under-reporting,low specificity,distorted cause spectrum of road traffic injury,inconsistency,inaccessibility,and delay of data release.We also explored the mechanisms behind the problematic data and proposed the solutions to the addressed challenges for road traffic statistics.
文摘This study focuses on inventory strategies of Internet retailers (etailers). The etailer faces options of holding her own inventory or outsourcing through the third party(ies). We assess etailer inventory strategies through mathematical modeling and numerical experiments. When ordering and holding her own stock, the etailer has full control of the order fulfillment process but bears the inventory-related risk. When outsourcing stock, etailer’s orders may not get an equal priority as for those of the third party’s own. Built upon simple operations research models, the numerical experiments suggest that the etailer is better off relying on others to fulfill orders if her demand (profit margin) is low, but should revert to the strategy of maintaining her own inventory if her sales volume (profit margin) is relatively high. Other factors are also investigated. These findings seem to confirm what are being practiced in the industry.
文摘Location-based social network （LBSN） is at the forefront of emerging trends in social network services （SNS） since the users in LBSN are allowed to ＂check-in＂ the places （locations） when they visit them. The accurate geographi- cal and temporal information of these check-in actions are provided by the end-user GPS-enabled mobile devices, and recorded by the LBSN system. In this paper, we analyze and mine a big LBSN data, Gowalla, collected by us. First, we investigate the relationship between the spatio-temporal co- occurrences and social ties, and the results show that the co- occurrences are strongly correlative with the social ties. Sec- ond, we present a study of predicting two users whether or not they will meet （co-occur） at a place in a given future time, by exploring their check-in habits. In particular, we first intro- duce two new concepts, bag-of-location and bag-of-time-lag, to characterize user＇s check-in habits. Based on such bag rep- resentations, we define a similarity metric called habits sim- ilarity to measure the similarity between two users＇ check-in habits. Then we propose a machine !earning formula for pre- dicting co-occurrence based on the social ties and habits sim- ilarities. Finally, we conduct extensive experiments on our dataset, and the results demonstrate the effectiveness of the proposed method.
