With the frequent occurrence of telecommunications and networkfraud crimes in recent years, new frauds have emerged one after another whichhas caused huge losses to the people. However, due to the lack of an effective...With the frequent occurrence of telecommunications and networkfraud crimes in recent years, new frauds have emerged one after another whichhas caused huge losses to the people. However, due to the lack of an effectivepreventive mechanism, the police are often in a passive position. Usingtechnologies such as web crawlers, feature engineering, deep learning, andartificial intelligence, this paper proposes a user portrait fraudwarning schemebased on Weibo public data. First, we perform preliminary screening andcleaning based on the keyword “defrauded” to obtain valid fraudulent userIdentity Documents (IDs). The basic information and account information ofthese users is user-labeled to achieve the purpose of distinguishing the typesof fraud. Secondly, through feature engineering technologies such as avatarrecognition, Artificial Intelligence (AI) sentiment analysis, data screening,and follower blogger type analysis, these pictures and texts will be abstractedinto user preferences and personality characteristics which integrate multidimensionalinformation to build user portraits. Third, deep neural networktraining is performed on the cube. 80% percent of the data is predicted basedon the N-way K-shot problem and used to train the model, and the remaining20% is used for model accuracy evaluation. Experiments have shown thatFew-short learning has higher accuracy compared with Long Short TermMemory (LSTM), Recurrent Neural Networks (RNN) and ConvolutionalNeural Network (CNN). On this basis, this paper develops a WeChat smallprogram for early warning of telecommunications network fraud based onuser portraits. When the user enters some personal information on the frontend, the back-end database can perform correlation analysis by itself, so as tomatch the most likely fraud types and give relevant early warning information.The fraud warning model is highly scaleable. The data of other Applications(APPs) can be extended to further improve the efficiency of anti-fraud whichhas extremely high public welfare value.展开更多
In order to quickly and accurately find the implementer of the network crime,based on the user portrait technology,a rapid detection method for users with abnormal behaviors is proposed.This method needs to construct ...In order to quickly and accurately find the implementer of the network crime,based on the user portrait technology,a rapid detection method for users with abnormal behaviors is proposed.This method needs to construct the abnormal behavior rule base on various kinds of abnormal behaviors in advance,and construct the user portrait including basic attribute tags,behavior attribute tags and abnormal behavior similarity tags for network users who have abnormal behaviors.When a network crime occurs,firstly get the corresponding tag values in all user portraits according to the category of the network crime.Then,use the Naive Bayesian method matching each user portrait,to quickly locate the most likely network criminal suspects.In the case that no suspect is found,all users are audited comprehensively through matching abnormal behavior rule base.The experimental results show that,the accuracy rate of using this method for fast detection of network crimes is 95.9%,and the audit time is shortened to 1/35 of that of the conventional behavior audit method.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
A new method to evaluate fuzzily user＇s relevance on the basis of cloud models has been proposed. All factors of personalized information retrieval system are taken into account in this method. So using this method f...A new method to evaluate fuzzily user＇s relevance on the basis of cloud models has been proposed. All factors of personalized information retrieval system are taken into account in this method. So using this method for personalized information retrieval （PIR） system can efficiently judge multi-value relevance, such as quite relevant, comparatively relevant, commonly relevant, basically relevant and completely non-relevant, and realize a kind of transform of qualitative concepts and quantity and improve accuracy of relevance judgements in PIR system. Experimental data showed that the method is practical and valid. Evaluation results are more accurate and approach to the fact better.展开更多
For telecommunication operators, how to improve the utilization of bandwidth resources is always a problem which worthy of study, nowadays, this issue has become more and more important, since the traffic load burstin...For telecommunication operators, how to improve the utilization of bandwidth resources is always a problem which worthy of study, nowadays, this issue has become more and more important, since the traffic load bursting in the mobile Internet. So the key to solving this problem is that we need to find a kind of traffic model to predict the traffic load that users need. According to the predicted traffic load to allocate bandwidth to each base station dynamically.But the traffic consumption behavior of a single base station is random, it is difficult to predict[ 1 ]. For this reason, we based on reality that, when the user moves, it may get traffic load from different base stations, therefore, there will have some kind of relationship between those base stations.We use this relationship to establish a kind of Spatial Collaborative Network.consequently, we make use of stability algorithm to divided those base station cluster into different communities, According to the traffic load usage rules which these communities indicated to us, we get a traffic model.At the same time, we studied bow to use this traffic model in the future networks to dynamically allocate bandwidth resources, then we propose a new kind of EPS architecture based on SDN, on this platform, we can deploy our strategy through it＇s programmable interface.Finally, we designed an experiment to test the performance of our dynamic strategy, and the result shows that our method enables bandwidth utilization has been greatly improved.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
文摘With the frequent occurrence of telecommunications and networkfraud crimes in recent years, new frauds have emerged one after another whichhas caused huge losses to the people. However, due to the lack of an effectivepreventive mechanism, the police are often in a passive position. Usingtechnologies such as web crawlers, feature engineering, deep learning, andartificial intelligence, this paper proposes a user portrait fraudwarning schemebased on Weibo public data. First, we perform preliminary screening andcleaning based on the keyword “defrauded” to obtain valid fraudulent userIdentity Documents (IDs). The basic information and account information ofthese users is user-labeled to achieve the purpose of distinguishing the typesof fraud. Secondly, through feature engineering technologies such as avatarrecognition, Artificial Intelligence (AI) sentiment analysis, data screening,and follower blogger type analysis, these pictures and texts will be abstractedinto user preferences and personality characteristics which integrate multidimensionalinformation to build user portraits. Third, deep neural networktraining is performed on the cube. 80% percent of the data is predicted basedon the N-way K-shot problem and used to train the model, and the remaining20% is used for model accuracy evaluation. Experiments have shown thatFew-short learning has higher accuracy compared with Long Short TermMemory (LSTM), Recurrent Neural Networks (RNN) and ConvolutionalNeural Network (CNN). On this basis, this paper develops a WeChat smallprogram for early warning of telecommunications network fraud based onuser portraits. When the user enters some personal information on the frontend, the back-end database can perform correlation analysis by itself, so as tomatch the most likely fraud types and give relevant early warning information.The fraud warning model is highly scaleable. The data of other Applications(APPs) can be extended to further improve the efficiency of anti-fraud whichhas extremely high public welfare value.
基金This research is supported by The National Natural Science Foundation of China under Grant(No.61672101)Beijing Key Laboratory of Internet Culture and Digital Dissemination Research(No.ICDDXN004)Key Lab of Information Network Security of Ministry of Public Security(No.C18601).
文摘In order to quickly and accurately find the implementer of the network crime,based on the user portrait technology,a rapid detection method for users with abnormal behaviors is proposed.This method needs to construct the abnormal behavior rule base on various kinds of abnormal behaviors in advance,and construct the user portrait including basic attribute tags,behavior attribute tags and abnormal behavior similarity tags for network users who have abnormal behaviors.When a network crime occurs,firstly get the corresponding tag values in all user portraits according to the category of the network crime.Then,use the Naive Bayesian method matching each user portrait,to quickly locate the most likely network criminal suspects.In the case that no suspect is found,all users are audited comprehensively through matching abnormal behavior rule base.The experimental results show that,the accuracy rate of using this method for fast detection of network crimes is 95.9%,and the audit time is shortened to 1/35 of that of the conventional behavior audit method.
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.
文摘A new method to evaluate fuzzily user＇s relevance on the basis of cloud models has been proposed. All factors of personalized information retrieval system are taken into account in this method. So using this method for personalized information retrieval （PIR） system can efficiently judge multi-value relevance, such as quite relevant, comparatively relevant, commonly relevant, basically relevant and completely non-relevant, and realize a kind of transform of qualitative concepts and quantity and improve accuracy of relevance judgements in PIR system. Experimental data showed that the method is practical and valid. Evaluation results are more accurate and approach to the fact better.
基金part of the National Natural Science Foundation of China(NSFC)under Grant No.61371126the Independent Research Program of Central Universities under Grant No.2042014kf0256+2 种基金the National High Technology Research and Development Program of China(863 Program)under Grant No.2014AA01A707the National Key Basic Research Program of China(973 Program)under Grant No.2011CB707106Applied Basic Research Programs of Wuhan under Grant No.2014010101010026
文摘For telecommunication operators, how to improve the utilization of bandwidth resources is always a problem which worthy of study, nowadays, this issue has become more and more important, since the traffic load bursting in the mobile Internet. So the key to solving this problem is that we need to find a kind of traffic model to predict the traffic load that users need. According to the predicted traffic load to allocate bandwidth to each base station dynamically.But the traffic consumption behavior of a single base station is random, it is difficult to predict[ 1 ]. For this reason, we based on reality that, when the user moves, it may get traffic load from different base stations, therefore, there will have some kind of relationship between those base stations.We use this relationship to establish a kind of Spatial Collaborative Network.consequently, we make use of stability algorithm to divided those base station cluster into different communities, According to the traffic load usage rules which these communities indicated to us, we get a traffic model.At the same time, we studied bow to use this traffic model in the future networks to dynamically allocate bandwidth resources, then we propose a new kind of EPS architecture based on SDN, on this platform, we can deploy our strategy through it＇s programmable interface.Finally, we designed an experiment to test the performance of our dynamic strategy, and the result shows that our method enables bandwidth utilization has been greatly improved.
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.
