Information on species composition of an urban forest is essential for its management.However,to obtain this information becomes increasingly difficult due to limited taxonomic expertise.In this study,we tested the po...Information on species composition of an urban forest is essential for its management.However,to obtain this information becomes increasingly difficult due to limited taxonomic expertise.In this study,we tested the possibility of using plant identification applications running on mobile platforms to fill this vacuum.Five plant identification apps were compared for their potential in identifying urban tree species in China.An online survey was conducted to determine the features of apps that contributed to users’satisfaction.The results show that identification accuracy varied significantly among the apps.The best performer achieved an accuracy of 74.6%at the species level,which is comparable to the accuracy by professionals in field surveys.Among the features of apps,accuracy of identification was the most important factor that contributed to users’satisfaction.However,plant identification apps did not perform well when used on rare species or outside of the regions where they have been developed.Results indicate that plant identification apps have great potential in urban forest studies and management,but users need to be cautious when deciding which one to use.展开更多
Coverage of nominal 95% confidence intervals of a proportion estimated from a sample obtained under a complex survey design, or a proportion estimated from a ratio of two random variables, can depart significantly fro...Coverage of nominal 95% confidence intervals of a proportion estimated from a sample obtained under a complex survey design, or a proportion estimated from a ratio of two random variables, can depart significantly from its target. Effective calibration methods exist for intervals for a proportion derived from a single binary study variable, but not for estimates of thematic classification accuracy. To promote a calibration of confidence intervals within the context of land-cover mapping, this study first illustrates a common problem of under and over-coverage with standard confidence intervals, and then proposes a simple and fast calibration that more often than not will improve coverage. The demonstration is with simulated sampling from a classified map with four classes, and a reference class known for every unit in a population of 160,000 units arranged in a square array. The simulations include four common probability sampling designs for accuracy assessment, and three sample sizes. Statistically significant over- and under-coverage was present in estimates of user’s (UA) and producer’s accuracy (PA) as well as in estimates of class area proportion. A calibration with Bayes intervals for UA and PA was most efficient with smaller sample sizes and two cluster sampling designs.展开更多
AIM To assess the diagnostic accuracy of a new fecal test for detecting Helicobacter pylori(H. pylori), using ^(13)Curea breath test as the reference standard, and explore bacterial antibiotic resistance. METHODS We c...AIM To assess the diagnostic accuracy of a new fecal test for detecting Helicobacter pylori(H. pylori), using ^(13)Curea breath test as the reference standard, and explore bacterial antibiotic resistance. METHODS We conducted a prospective two-center diagnostic test accuracy study. We enrolled consecutive people≥ 18 years without previous diagnosis of H. pylori infection, referred for dyspepsia between February and October 2017. At enrollment, all participants underwent 13 C-urea breath test. Participants aged over 50 years were scheduled to undergo upper endoscopy with histology. Participants collected stool samples 1-3 d after enrollment for a new fecal investigation(THD fecal test). The detection of bacterial 23 S rRNA subunit gene indicated H. pylori infection. We also used the index diagnostic test to examine mutations conferring resistance to clarithromycin and levofloxacin. Independent investigators analyzed index test and reference test standard results blinded to the other test findings. We estimated sensitivity, specificity, positive(PPV) and negative(NPV) predictive value, diagnostic accuracy, positive and negative likelihood ratio(LR), together with 95% confidence intervals(CI).RESULTS We enrolled 294 consecutive participants(age: Median 37.0 years, IQR: 29.0-46.0 years; men: 39.8%). Ninetyfive(32.3%) participants had a positive ^(13)C-urea breath test. Twenty-three(7.8%) participants underwent upper endoscopy with histology, with a full concordance between ^(13)C-urea breath test and histology in detecting H. pylori infection. Four(1.4%) out of the 294 participants withdrew from the study after the enrollment visit and did not undergo THD fecal testing. In the 290 participants who completed the study, the THD fecal test sensitivity was 90.2%(CI: 84.2%-96.3%), specificity 98.5%(CI:96.8%-100%), PPV 96.5%(CI: 92.6%-100%), NPV 95.6%(CI: 92.8%-98.4%), accuracy 95.9%(CI: 93.6%-98.2%), positive LR 59.5(CI: 19.3-183.4), negative LR 0.10(CI: 0.05-0.18). Out of 83 infected participants identified with the THD fecal test, 34(41.0%) had bacterial genotypic changes consistent with antibiotic-resistant H. pylori infection. Of these, 27(32.5%) had bacterial strains resistant to clarithromycin, 3(3.6%) to levofloxacin, and 4(4.8%) to both antibiotics. CONCLUSION The THD fecal test has high performance for the non-invasive diagnosis of H. pylori infection while additionally enabling the assessment of bacterial antibiotic resistances.展开更多
The paper presents a design method that ensures the ingenuity of the product form as well as the whole and exact expression of user’s needs. The key idea is to establish an automatic design system which can transform...The paper presents a design method that ensures the ingenuity of the product form as well as the whole and exact expression of user’s needs. The key idea is to establish an automatic design system which can transform the user’s language needs into the product features in real-time. A rifle was taken as a research instance and soldiers were chosen as evaluation customers. The theory of fuzzy set and semantic difference are adopted to evaluate the relationship between user’s needs and product features as well as their alternatives. FAHP (fuzzy analytic hierarchy process) is utilized to judge the user’s satisfactory forms. This method can also be applied to other product form designs.展开更多
Methotrexate has been used an immunomodulator in many autoimmune diseases,including inflammatory bowel disease. However,many physicians are unfamiliar or uncomfortable with its use in the management of inflammatory bo...Methotrexate has been used an immunomodulator in many autoimmune diseases,including inflammatory bowel disease. However,many physicians are unfamiliar or uncomfortable with its use in the management of inflammatory bowel disease. We summarize the data for use of methotrexate in common clinical scenarios:(1) steroid dependant Crohn's disease(CD);(2) maintenance of remission in steroid free CD;(3) azathioprine failures in CD;(4) in combination therapy with Anti-TNF agents in CD;(5) decreasing antibody formation to Anti-TNF therapy in CD;(6) management of fistulizing disease in CD; and(7) as well as induction and maintenance of remission in ulcerative colitis. An easy to use algorithm is provided for the busy clinician to access and safely prescribe methotrexate for their inflammatory bowel disease patients.展开更多
Frequent itemset mining is an essential problem in data mining and plays a key role in many data mining applications.However,users’personal privacy will be leaked in the mining process.In recent years,application of ...Frequent itemset mining is an essential problem in data mining and plays a key role in many data mining applications.However,users’personal privacy will be leaked in the mining process.In recent years,application of local differential privacy protection models to mine frequent itemsets is a relatively reliable and secure protection method.Local differential privacy means that users first perturb the original data and then send these data to the aggregator,preventing the aggregator from revealing the user’s private information.We propose a novel framework that implements frequent itemset mining under local differential privacy and is applicable to user’s multi-attribute.The main technique has bitmap encoding for converting the user’s original data into a binary string.It also includes how to choose the best perturbation algorithm for varying user attributes,and uses the frequent pattern tree(FP-tree)algorithm to mine frequent itemsets.Finally,we incorporate the threshold random response(TRR)algorithm in the framework and compare it with the existing algorithms,and demonstrate that the TRR algorithm has higher accuracy for mining frequent itemsets.展开更多
Purpose: Taking Zhihu as the object for a case study, we intend to analyze the key factors that have affected users on adopting answers in social Q&A(SQA) websites.Design/methodology/approach: With information ado...Purpose: Taking Zhihu as the object for a case study, we intend to analyze the key factors that have affected users on adopting answers in social Q&A(SQA) websites.Design/methodology/approach: With information adoption model(IAM) as the theoretical foundation and widely accepted evaluation criteria for answer quality in SQA sites as variables, we constructed a factor model that has influenced SQA community users to adopt offered answers. With the partial least squares(PLS) technique, our model was then empirically tested through a sample of 311 Zhihu users.Findings: Our results showed that answer usefulness is the most effective variable, and answer interactivity and answer entertainment both have positive and significant impacts on users' attitude to adopt answers in an SQA community. Except for novelty, other three components of answer quality, i.e. knowledge, reliability, and solution to the problem have all significant effect on answer usefulness.Research limitations: First, due to the limited sample size, it is still questionable if our research results based on Zhihu could be applied to other SQA communities. Second, our questionnaires were mainly designed to investigate how users felt about the answers in an SQA site, but did not differentiate the content of the answer itself.Practical implications: As a three-year-old SQA platform, Zhihu has developed very quickly with its high-quality answers and public intellectual users, and has been regarded as one of the representatives of fast emerging Chinese SQA communities in recent years. Our studycould help shed light on users' information sharing and knowledge adoption behaviors in a Chinese SQA site, such as Zhihu. Originality/value: Compared with previous studies on answer quality assessments in SQA sites and on information adoption model, to the best of our knowledge, this is one of the pioneer studies which combined answer qualities with users' intention of adopting SQA answers. Our study on user answer adoption in Zhihu community could further develop the theory of IAM. This study showed that answer usefulness is the most important motivation of Zhihu users in the process of adopting answers.展开更多
Considering characteristics of Chinese urban mixed traffic,the author develops a combinatorial model involving the mixed deterministic traffic volume distribution and user’s equilibrium (UE) assignment on the basis o...Considering characteristics of Chinese urban mixed traffic,the author develops a combinatorial model involving the mixed deterministic traffic volume distribution and user’s equilibrium (UE) assignment on the basis of symmetrical link travel time function (or deterrence).Its uniqueness and equivalance to the Wardropian principle of UE are also proved.Finally,we give the algorithm of model.展开更多
Collaborative filtering algorithms(CF)and mass diffusion(MD)algorithms have been successfully applied to recommender systems for years and can solve the problem of information overload.However,both algorithms suffer f...Collaborative filtering algorithms(CF)and mass diffusion(MD)algorithms have been successfully applied to recommender systems for years and can solve the problem of information overload.However,both algorithms suffer from data sparsity,and both tend to recommend popular products,which have poor diversity and are not suitable for real life.In this paper,we propose a user internal similarity-based recommendation algorithm(UISRC).UISRC first calculates the item-item similarity matrix and calculates the average similarity between items purchased by each user as the user’s internal similarity.The internal similarity of users is combined to modify the recommendation score to make score predictions and suggestions.Simulation experiments on RYM and Last.FM datasets,the results show that UISRC can obtain better recommendation accuracy and a variety of recommendations than traditional CF and MD algorithms.展开更多
By periodically aggregating local learning updates from edge users, federated edge learning (FEEL) is envisioned as a promising means to reap the benefit of local rich da?ta and protect users'privacy. However, the...By periodically aggregating local learning updates from edge users, federated edge learning (FEEL) is envisioned as a promising means to reap the benefit of local rich da?ta and protect users'privacy. However, the scarce wireless communication resource greatly limits the number of participated users and is regarded as the main bottleneck which hin?ders the development of FEEL. To tackle this issue, we propose a user selection policy based on data importance for FEEL system. In order to quantify the data importance of each user, we first analyze the relationship between the loss decay and the squared norm of gradi?ent. Then, we formulate a combinatorial optimization problem to maximize the learning effi?ciency by jointly considering user selection and communication resource allocation. By problem transformation and relaxation, the optimal user selection policy and resource alloca?tion are derived, and a polynomial-time optimal algorithm is developed. Finally, we deploy two commonly used deep neural network (DNN) models for simulation. The results validate that our proposed algorithm has strong generalization ability and can attain higher learning efficiency compared with other traditional algorithms.展开更多
With the popularity of mobile intelligent terminal, user comments of App software is viewed as one of the research interests of social computing. Faced with the massive App software, most users usually view the other ...With the popularity of mobile intelligent terminal, user comments of App software is viewed as one of the research interests of social computing. Faced with the massive App software, most users usually view the other users’ comments and marks to selecting the desired App software. Due to the freedom and randomness of the network comments, the inconsistence between the user’s comment and mark makes it difficult to choose App software. This paper presents a method by analyzing the relationships among user’s comment information, the user’s mark and App software information. Firstly, the consistency between user’s comment information and App software information is judged. Then, through analyzing the grammar relationships among the feature-words, adverbs and the feature-sentiment-words in App software’s feature-sentimentword- pairs, the user’s emotional tendency about App software is quantified quantified combining with the dictionary and the network sentiment words. After calculating the user’s comprehensive score of App software, the consistency of App software’s user comment is judged by comparing this score and the user’s mark. Finally, the experimental results show that the method is effective.展开更多
Purpose:The paper aims to build an index model for measuring microblog users’influence by taking microbloggers of Sina Weibo as a research sample.Design/methodology/approach:Our user influence index model emphasizes ...Purpose:The paper aims to build an index model for measuring microblog users’influence by taking microbloggers of Sina Weibo as a research sample.Design/methodology/approach:Our user influence index model emphasizes link analysis and user activities in the microblogging network.We conduct experiments to investigate the performance of our model by using data crawled from Sina Weibo.Findings:User influence is correlated to the attention that a user has received from his/her audience,the user’s activities and his/her tweets’influence.Experimental results show that our model can reflect microbloggers’influence in a more reasonable way.Research limitations:More factors need to be considered to identify different influential users at different time periods.Practical implications:The results of the study provide us with insights both into the way to measure microblog users’influence and to rank users based on their influence.Originality/value:By combining link analysis and user activities,this index model can reduce the impact of dummy follower accounts on user influence,reflecting a user’s real influence in the microblog system.展开更多
To realize data sharing,and to fully use the data value,breaking the data island between institutions to realize data collaboration has become a new sharing mode.This paper proposed a distributed data security sharing...To realize data sharing,and to fully use the data value,breaking the data island between institutions to realize data collaboration has become a new sharing mode.This paper proposed a distributed data security sharing scheme based on C/S communication mode,and constructed a federated learning architecture that uses differential privacy technology to protect training parameters.Clients do not need to share local data,and they only need to upload the trained model parameters to achieve data sharing.In the process of training,a distributed parameter update mechanism is introduced.The server is mainly responsible for issuing training commands and parameters,and aggregating the local model parameters uploaded by the clients.The client mainly uses the stochastic gradient descent algorithm for gradient trimming,updates,and transmits the trained model parameters back to the server after differential processing.To test the performance of the scheme,in the application scenario where many medical institutions jointly train the disease detection system,the model is tested from multiple perspectives by taking medical data as an example.From the testing results,we can know that for this specific test dataset,when the parameters are properly configured,the lowest prediction accuracy rate is 90.261%and the highest accuracy rate is up to 94.352.It shows that the performance of the model is good.The results also show that this scheme realizes data sharing while protecting data privacy,completes accurate prediction of diseases,and has a good effect.展开更多
The prediction of mild cognitive impairment or Alzheimer’s disease(AD)has gained the attention of huge researchers as the disease occurrence is increasing,and there is a need for earlier prediction.Regrettably,due to...The prediction of mild cognitive impairment or Alzheimer’s disease(AD)has gained the attention of huge researchers as the disease occurrence is increasing,and there is a need for earlier prediction.Regrettably,due to the highdimensionality nature of neural data and the least available samples,modelling an efficient computer diagnostic system is highly solicited.Learning approaches,specifically deep learning approaches,are essential in disease prediction.Deep Learning(DL)approaches are successfully demonstrated for their higher-level performance in various fields like medical imaging.A novel 3D-Convolutional Neural Network(3D-CNN)architecture is proposed to predict AD with Magnetic resonance imaging(MRI)data.The proposed model predicts the AD occurrence while the existing approaches lack prediction accuracy and perform binary classification.The proposed prediction model is validated using the Alzheimer’s disease Neuro-Imaging Initiative(ADNI)data.The outcomes demonstrate that the anticipated model attains superior prediction accuracy and works better than the brain-image dataset’s general approaches.The predicted model reduces the human effort during the prediction process and makes it easier to diagnose it intelligently as the feature learning is adaptive.Keras’experimentation is carried out,and the model’s superiority is compared with various advanced approaches for multi-level classification.The proposed model gives better prediction accuracy,precision,recall,and F-measure than other systems like Long Short Term Memory-Recurrent Neural Networks(LSTM-RNN),Stacked Autoencoder with Deep Neural Networks(SAE-DNN),Deep Convolutional Neural Networks(D-CNN),Two Dimensional Convolutional Neural Networks(2D-CNN),Inception-V4,ResNet,and Two Dimensional Convolutional Neural Networks(3D-CNN).展开更多
基金supported financially by China National Natural Science Foundation(grant number 31570458)Microsoft Research Lab-Asia(grant number 041902008).
文摘Information on species composition of an urban forest is essential for its management.However,to obtain this information becomes increasingly difficult due to limited taxonomic expertise.In this study,we tested the possibility of using plant identification applications running on mobile platforms to fill this vacuum.Five plant identification apps were compared for their potential in identifying urban tree species in China.An online survey was conducted to determine the features of apps that contributed to users’satisfaction.The results show that identification accuracy varied significantly among the apps.The best performer achieved an accuracy of 74.6%at the species level,which is comparable to the accuracy by professionals in field surveys.Among the features of apps,accuracy of identification was the most important factor that contributed to users’satisfaction.However,plant identification apps did not perform well when used on rare species or outside of the regions where they have been developed.Results indicate that plant identification apps have great potential in urban forest studies and management,but users need to be cautious when deciding which one to use.
文摘Coverage of nominal 95% confidence intervals of a proportion estimated from a sample obtained under a complex survey design, or a proportion estimated from a ratio of two random variables, can depart significantly from its target. Effective calibration methods exist for intervals for a proportion derived from a single binary study variable, but not for estimates of thematic classification accuracy. To promote a calibration of confidence intervals within the context of land-cover mapping, this study first illustrates a common problem of under and over-coverage with standard confidence intervals, and then proposes a simple and fast calibration that more often than not will improve coverage. The demonstration is with simulated sampling from a classified map with four classes, and a reference class known for every unit in a population of 160,000 units arranged in a square array. The simulations include four common probability sampling designs for accuracy assessment, and three sample sizes. Statistically significant over- and under-coverage was present in estimates of user’s (UA) and producer’s accuracy (PA) as well as in estimates of class area proportion. A calibration with Bayes intervals for UA and PA was most efficient with smaller sample sizes and two cluster sampling designs.
文摘AIM To assess the diagnostic accuracy of a new fecal test for detecting Helicobacter pylori(H. pylori), using ^(13)Curea breath test as the reference standard, and explore bacterial antibiotic resistance. METHODS We conducted a prospective two-center diagnostic test accuracy study. We enrolled consecutive people≥ 18 years without previous diagnosis of H. pylori infection, referred for dyspepsia between February and October 2017. At enrollment, all participants underwent 13 C-urea breath test. Participants aged over 50 years were scheduled to undergo upper endoscopy with histology. Participants collected stool samples 1-3 d after enrollment for a new fecal investigation(THD fecal test). The detection of bacterial 23 S rRNA subunit gene indicated H. pylori infection. We also used the index diagnostic test to examine mutations conferring resistance to clarithromycin and levofloxacin. Independent investigators analyzed index test and reference test standard results blinded to the other test findings. We estimated sensitivity, specificity, positive(PPV) and negative(NPV) predictive value, diagnostic accuracy, positive and negative likelihood ratio(LR), together with 95% confidence intervals(CI).RESULTS We enrolled 294 consecutive participants(age: Median 37.0 years, IQR: 29.0-46.0 years; men: 39.8%). Ninetyfive(32.3%) participants had a positive ^(13)C-urea breath test. Twenty-three(7.8%) participants underwent upper endoscopy with histology, with a full concordance between ^(13)C-urea breath test and histology in detecting H. pylori infection. Four(1.4%) out of the 294 participants withdrew from the study after the enrollment visit and did not undergo THD fecal testing. In the 290 participants who completed the study, the THD fecal test sensitivity was 90.2%(CI: 84.2%-96.3%), specificity 98.5%(CI:96.8%-100%), PPV 96.5%(CI: 92.6%-100%), NPV 95.6%(CI: 92.8%-98.4%), accuracy 95.9%(CI: 93.6%-98.2%), positive LR 59.5(CI: 19.3-183.4), negative LR 0.10(CI: 0.05-0.18). Out of 83 infected participants identified with the THD fecal test, 34(41.0%) had bacterial genotypic changes consistent with antibiotic-resistant H. pylori infection. Of these, 27(32.5%) had bacterial strains resistant to clarithromycin, 3(3.6%) to levofloxacin, and 4(4.8%) to both antibiotics. CONCLUSION The THD fecal test has high performance for the non-invasive diagnosis of H. pylori infection while additionally enabling the assessment of bacterial antibiotic resistances.
文摘The paper presents a design method that ensures the ingenuity of the product form as well as the whole and exact expression of user’s needs. The key idea is to establish an automatic design system which can transform the user’s language needs into the product features in real-time. A rifle was taken as a research instance and soldiers were chosen as evaluation customers. The theory of fuzzy set and semantic difference are adopted to evaluate the relationship between user’s needs and product features as well as their alternatives. FAHP (fuzzy analytic hierarchy process) is utilized to judge the user’s satisfactory forms. This method can also be applied to other product form designs.
文摘Methotrexate has been used an immunomodulator in many autoimmune diseases,including inflammatory bowel disease. However,many physicians are unfamiliar or uncomfortable with its use in the management of inflammatory bowel disease. We summarize the data for use of methotrexate in common clinical scenarios:(1) steroid dependant Crohn's disease(CD);(2) maintenance of remission in steroid free CD;(3) azathioprine failures in CD;(4) in combination therapy with Anti-TNF agents in CD;(5) decreasing antibody formation to Anti-TNF therapy in CD;(6) management of fistulizing disease in CD; and(7) as well as induction and maintenance of remission in ulcerative colitis. An easy to use algorithm is provided for the busy clinician to access and safely prescribe methotrexate for their inflammatory bowel disease patients.
基金This paper is supported by the Inner Mongolia Natural Science Foundation(Grant Number:2018MS06026,Sponsored Authors:Liu,H.and Ma,X.,Sponsors’Websites:http://kjt.nmg.gov.cn/)the Science and Technology Program of Inner Mongolia Autonomous Region(Grant Number:2019GG116,Sponsored Authors:Liu,H.and Ma,X.,Sponsors’Websites:http://kjt.nmg.gov.cn/).
文摘Frequent itemset mining is an essential problem in data mining and plays a key role in many data mining applications.However,users’personal privacy will be leaked in the mining process.In recent years,application of local differential privacy protection models to mine frequent itemsets is a relatively reliable and secure protection method.Local differential privacy means that users first perturb the original data and then send these data to the aggregator,preventing the aggregator from revealing the user’s private information.We propose a novel framework that implements frequent itemset mining under local differential privacy and is applicable to user’s multi-attribute.The main technique has bitmap encoding for converting the user’s original data into a binary string.It also includes how to choose the best perturbation algorithm for varying user attributes,and uses the frequent pattern tree(FP-tree)algorithm to mine frequent itemsets.Finally,we incorporate the threshold random response(TRR)algorithm in the framework and compare it with the existing algorithms,and demonstrate that the TRR algorithm has higher accuracy for mining frequent itemsets.
基金jointly supported by National Social Science Foundation of China(Grant No.14BTQ044)Wuhan University Academic Development Plan for Scholars after 1970s
文摘Purpose: Taking Zhihu as the object for a case study, we intend to analyze the key factors that have affected users on adopting answers in social Q&A(SQA) websites.Design/methodology/approach: With information adoption model(IAM) as the theoretical foundation and widely accepted evaluation criteria for answer quality in SQA sites as variables, we constructed a factor model that has influenced SQA community users to adopt offered answers. With the partial least squares(PLS) technique, our model was then empirically tested through a sample of 311 Zhihu users.Findings: Our results showed that answer usefulness is the most effective variable, and answer interactivity and answer entertainment both have positive and significant impacts on users' attitude to adopt answers in an SQA community. Except for novelty, other three components of answer quality, i.e. knowledge, reliability, and solution to the problem have all significant effect on answer usefulness.Research limitations: First, due to the limited sample size, it is still questionable if our research results based on Zhihu could be applied to other SQA communities. Second, our questionnaires were mainly designed to investigate how users felt about the answers in an SQA site, but did not differentiate the content of the answer itself.Practical implications: As a three-year-old SQA platform, Zhihu has developed very quickly with its high-quality answers and public intellectual users, and has been regarded as one of the representatives of fast emerging Chinese SQA communities in recent years. Our studycould help shed light on users' information sharing and knowledge adoption behaviors in a Chinese SQA site, such as Zhihu. Originality/value: Compared with previous studies on answer quality assessments in SQA sites and on information adoption model, to the best of our knowledge, this is one of the pioneer studies which combined answer qualities with users' intention of adopting SQA answers. Our study on user answer adoption in Zhihu community could further develop the theory of IAM. This study showed that answer usefulness is the most important motivation of Zhihu users in the process of adopting answers.
文摘Considering characteristics of Chinese urban mixed traffic,the author develops a combinatorial model involving the mixed deterministic traffic volume distribution and user’s equilibrium (UE) assignment on the basis of symmetrical link travel time function (or deterrence).Its uniqueness and equivalance to the Wardropian principle of UE are also proved.Finally,we give the algorithm of model.
基金supported by the National Natural Science Foundation of China(Grant No.61703212).
文摘Collaborative filtering algorithms(CF)and mass diffusion(MD)algorithms have been successfully applied to recommender systems for years and can solve the problem of information overload.However,both algorithms suffer from data sparsity,and both tend to recommend popular products,which have poor diversity and are not suitable for real life.In this paper,we propose a user internal similarity-based recommendation algorithm(UISRC).UISRC first calculates the item-item similarity matrix and calculates the average similarity between items purchased by each user as the user’s internal similarity.The internal similarity of users is combined to modify the recommendation score to make score predictions and suggestions.Simulation experiments on RYM and Last.FM datasets,the results show that UISRC can obtain better recommendation accuracy and a variety of recommendations than traditional CF and MD algorithms.
基金This work was supported in part by the National Natural Science Founda⁃tion of China under Grant No.61671407.
文摘By periodically aggregating local learning updates from edge users, federated edge learning (FEEL) is envisioned as a promising means to reap the benefit of local rich da?ta and protect users'privacy. However, the scarce wireless communication resource greatly limits the number of participated users and is regarded as the main bottleneck which hin?ders the development of FEEL. To tackle this issue, we propose a user selection policy based on data importance for FEEL system. In order to quantify the data importance of each user, we first analyze the relationship between the loss decay and the squared norm of gradi?ent. Then, we formulate a combinatorial optimization problem to maximize the learning effi?ciency by jointly considering user selection and communication resource allocation. By problem transformation and relaxation, the optimal user selection policy and resource alloca?tion are derived, and a polynomial-time optimal algorithm is developed. Finally, we deploy two commonly used deep neural network (DNN) models for simulation. The results validate that our proposed algorithm has strong generalization ability and can attain higher learning efficiency compared with other traditional algorithms.
基金This research is sponsored by the National Science Foundation of China No. 60703116, 61063006 and 61462049, and the Application Basic Research Plan in Yunnan Province of China No. 2013FZ020.
文摘With the popularity of mobile intelligent terminal, user comments of App software is viewed as one of the research interests of social computing. Faced with the massive App software, most users usually view the other users’ comments and marks to selecting the desired App software. Due to the freedom and randomness of the network comments, the inconsistence between the user’s comment and mark makes it difficult to choose App software. This paper presents a method by analyzing the relationships among user’s comment information, the user’s mark and App software information. Firstly, the consistency between user’s comment information and App software information is judged. Then, through analyzing the grammar relationships among the feature-words, adverbs and the feature-sentiment-words in App software’s feature-sentimentword- pairs, the user’s emotional tendency about App software is quantified quantified combining with the dictionary and the network sentiment words. After calculating the user’s comprehensive score of App software, the consistency of App software’s user comment is judged by comparing this score and the user’s mark. Finally, the experimental results show that the method is effective.
基金supported by the Natural Science Foundation of Hebei Province of China(Grant No.:F2011203219)
文摘Purpose:The paper aims to build an index model for measuring microblog users’influence by taking microbloggers of Sina Weibo as a research sample.Design/methodology/approach:Our user influence index model emphasizes link analysis and user activities in the microblogging network.We conduct experiments to investigate the performance of our model by using data crawled from Sina Weibo.Findings:User influence is correlated to the attention that a user has received from his/her audience,the user’s activities and his/her tweets’influence.Experimental results show that our model can reflect microbloggers’influence in a more reasonable way.Research limitations:More factors need to be considered to identify different influential users at different time periods.Practical implications:The results of the study provide us with insights both into the way to measure microblog users’influence and to rank users based on their influence.Originality/value:By combining link analysis and user activities,this index model can reduce the impact of dummy follower accounts on user influence,reflecting a user’s real influence in the microblog system.
基金This work was supported by Funding of the Nanjing Institute of Technology(No.KE21-451).
文摘To realize data sharing,and to fully use the data value,breaking the data island between institutions to realize data collaboration has become a new sharing mode.This paper proposed a distributed data security sharing scheme based on C/S communication mode,and constructed a federated learning architecture that uses differential privacy technology to protect training parameters.Clients do not need to share local data,and they only need to upload the trained model parameters to achieve data sharing.In the process of training,a distributed parameter update mechanism is introduced.The server is mainly responsible for issuing training commands and parameters,and aggregating the local model parameters uploaded by the clients.The client mainly uses the stochastic gradient descent algorithm for gradient trimming,updates,and transmits the trained model parameters back to the server after differential processing.To test the performance of the scheme,in the application scenario where many medical institutions jointly train the disease detection system,the model is tested from multiple perspectives by taking medical data as an example.From the testing results,we can know that for this specific test dataset,when the parameters are properly configured,the lowest prediction accuracy rate is 90.261%and the highest accuracy rate is up to 94.352.It shows that the performance of the model is good.The results also show that this scheme realizes data sharing while protecting data privacy,completes accurate prediction of diseases,and has a good effect.
文摘The prediction of mild cognitive impairment or Alzheimer’s disease(AD)has gained the attention of huge researchers as the disease occurrence is increasing,and there is a need for earlier prediction.Regrettably,due to the highdimensionality nature of neural data and the least available samples,modelling an efficient computer diagnostic system is highly solicited.Learning approaches,specifically deep learning approaches,are essential in disease prediction.Deep Learning(DL)approaches are successfully demonstrated for their higher-level performance in various fields like medical imaging.A novel 3D-Convolutional Neural Network(3D-CNN)architecture is proposed to predict AD with Magnetic resonance imaging(MRI)data.The proposed model predicts the AD occurrence while the existing approaches lack prediction accuracy and perform binary classification.The proposed prediction model is validated using the Alzheimer’s disease Neuro-Imaging Initiative(ADNI)data.The outcomes demonstrate that the anticipated model attains superior prediction accuracy and works better than the brain-image dataset’s general approaches.The predicted model reduces the human effort during the prediction process and makes it easier to diagnose it intelligently as the feature learning is adaptive.Keras’experimentation is carried out,and the model’s superiority is compared with various advanced approaches for multi-level classification.The proposed model gives better prediction accuracy,precision,recall,and F-measure than other systems like Long Short Term Memory-Recurrent Neural Networks(LSTM-RNN),Stacked Autoencoder with Deep Neural Networks(SAE-DNN),Deep Convolutional Neural Networks(D-CNN),Two Dimensional Convolutional Neural Networks(2D-CNN),Inception-V4,ResNet,and Two Dimensional Convolutional Neural Networks(3D-CNN).
