At present, the intelligent translation of computer is developing rapidly. In this paper, the overall design of interactive intelligent auxiliary translation platform based on multi-strategy is studied. In this paper,...
详细信息
At present, the intelligent translation of computer is developing rapidly. In this paper, the overall design of interactive intelligent auxiliary translation platform based on multi-strategy is studied. In this paper, the algorithm of similarity of sentences is deeply studied. According to the needs of English-Chinese translation memory system, the similarity between sentences is calculated from the sentence syntax and semantic based on syntactic and semantic English sentence similarity calculation method. Finally, the author uses the English-Chinese translation of Navigator 7.0 manual to examine the effect of the algorithm platform developed in this paper. The experimental results show that the proposed algorithm improves the speed of translation by about 35%.
Alarm is important in industrial safety management. The technique to capture the correlation information of alarm variables, especially from historical alarm data, is very beneficial for risk prediction and prevention...
详细信息
Alarm is important in industrial safety management. The technique to capture the correlation information of alarm variables, especially from historical alarm data, is very beneficial for risk prediction and prevention, but the task is very difficult because many alarm tags are associated with a single process variable and often alarm tags are tackled with any specific process variables. In this paper, a general weight-based multi-state sequential algorithm for correlation analysis is applied for alarm data to improve the validity and accuracy of alarm clustering combined with the traditional agglomerative hierarchical clustering algorithm. To make the direction between alarm variables, this paper proposes a vector correlation concept and use conditional probability to measure the alarm correlation among different tags comparable. The method breaks through the limitations of the traditional research on alarm variables correlation that distinguishes sequential alarms with non sequential alarms, or treats differently between regular and irregular alarms. Furthermore, a two-dimensional matrix is used to show the vector correlation of alarm variables intuitively and visually. The data mining algorithm is shown to be able to find out the vector correlation of alarm variables effectively and correctly when applied in the analysis of power plant alarm data.
Aiming at the sparsity problem existing in the traditional collaborative filtering algorithm, this paper proposed an improved similarity computing method that integrated user rating behavior and item attributes. The s...
详细信息
Aiming at the sparsity problem existing in the traditional collaborative filtering algorithm, this paper proposed an improved similarity computing method that integrated user rating behavior and item attributes. The sparse matrix is evaluated and predicted by the similarity calculation method, then the prediction rating was filled in the sparse matrix. At the same time, in the context of big data, the data scale was too large to affect the execution efficiency of the recommendation system. Hadoop platform was adopted to implement collaborative filtering recommendation algorithm based on the improved similarity model. Based on large-scale data segmentation, the distributed parallel processing was carried out. The proposed improved algorithm is verified by Movielens which was an internationally standard data set. The verification results show that the personalized recommendation system based on Hadoop platform and improved recommendation algorithm has better recommendation performance.
In view of the existing circumstances and problems in the medical services of chronic disease health consulting and guidance, an intelligent question-answering (QA) system based on B/S pattern is proposed in this pape...
详细信息
ISBN:
(纸本)9783037856949
In view of the existing circumstances and problems in the medical services of chronic disease health consulting and guidance, an intelligent question-answering (QA) system based on B/S pattern is proposed in this paper. The system adopts a way combining automatic intelligent searching with semi-automatic assistant QA technology. Firstly, a structural model is established, and then the function of each module is discussed. Besides, an improved similarity algorithm is put forward and illustrated to have a good matching effect by experiment analysis.
作者：
He, AgaYunnan Univ
Sch Phys & Astron Kunming 650504 Yunnan Peoples R China
A method of automatic focus searching is present that calculates the similarity degree of the two amplitude terms reconstructed with a fixed interval. It is based on the optical field distribution characteristics in a...
详细信息
ISBN:
(数字)9781510622357
ISBN:
(纸本)9781510622357
A method of automatic focus searching is present that calculates the similarity degree of the two amplitude terms reconstructed with a fixed interval. It is based on the optical field distribution characteristics in a diffraction-limited system, as which a digital holography imaging can be described. The supportive theory is briefed in this paper, and then several typical similarity algorithms are introduced that are used as the focus degree measurement. The autofocus procedure and precisely focus searching of this proposed autofocusing method are given. Each similarity algorithm based autofocusing is validated in simulation. The results demonstrate their applicability and reliability.
Quantitative prediction of soil urea conversion is crucial in determining the mechanism of nitrogen transformation and understanding the dynamics of soil nutrients. This study aimed to establish a combinatorial predic...
详细信息
Quantitative prediction of soil urea conversion is crucial in determining the mechanism of nitrogen transformation and understanding the dynamics of soil nutrients. This study aimed to establish a combinatorial prediction model (MCA-F-ANN) for soil urea conversion and quantify the relative importance degrees (RIDs) of influencing factors with the MCA-F-ANN method. Data samples were obtained from laboratory culture experiments, and soil nitrogen content and physicochemical properties were measured every other day. Results showed that when MCA-F-ANN was used, the mean-absolute percent error values of NH4+-N, NO3--N, and NH3 contents were 3.180%, 2.756%, and 3.656%, respectively. MCA-F-ANN predicted urea transformation under multi-factor coupling conditions more accurately than traditional models did. The RIDs of reaction time (RT), electrical conductivity (EC), temperature (T), pH, nitrogen application rate (F), and moisture content (W) were 32.2%-36.5%, 24.0%-28.9%, 12.8%-15.2%, 9.8%-12.5%, 7.8%-11.0%, and 3.5%-6.0%, respectively. The RIDs of the influencing factors in a descending order showed the pattern RT > EC > T> pH > F> W. RT and EC were the key factors in the urea conversion process. The prediction accuracy of urea transformation process was improved, and the RIDs of the influencing factors were quantified. (C) 2018 Elsevier Ltd. All rights reserved.
Currently, the era where social media can present various facilities can answer the needs of the community for information and utilization for socio-economic interests. But the other impact of the presence of social m...
详细信息
Currently, the era where social media can present various facilities can answer the needs of the community for information and utilization for socio-economic interests. But the other impact of the presence of social media opens an ample space for the existence of information or hoax news about an event that is troubling the public. The hoax also provides cynical provocation, which is inciting hatred, anger, incitement to many people, directly influencing behavior so that it responds as desired by the hoax makers. Fake news is playing an increasingly dominant role in spreading Misinformation by influencing people's Perceptions or knowledge to distort their awareness and decision-making. A framework is develope dataset collection of hoax gathered using web crawlers from several websites, using classification techniques. This hoax news will be categorized into several detection parameters including, page URL, title hoax news, publish date, author, and content. Matching each word hoax using the similarity algorithm to produce the accuracy of the hoax news uses the rule-based detection method. Experiments were carried out on eleven thousand-hoax news used as training datasets and testing data sets;this data set for validation using similarity algorithms, to produce the highest accuracy of hoax text similarity. In this study, each hoax news will label into four categories, namely, Fact, Hoax, Information, Unknown. Contributions propose Automatic detection of hoax news, Automatic Multilanguage Detection, and a collection of datasets that we gather ourselves and validation that results in four categories of hoax news that have measured in terms of text similarity using similarity techniques. Further research can be continued by adding objects hate speech, black campaign, blockchain technique to ward off hoaxes, or can produce algorithms that produce better text accuracy.
Obstetric Knowledge Graph describes the obstetric diseases and the body parts, drugs, etc. as well as the relations between them, which is an important knowledge base for intelligent auxiliary diagnosis. In this paper...
详细信息
ISBN:
(数字)9781728109749
ISBN:
(纸本)9781728109749
Obstetric Knowledge Graph describes the obstetric diseases and the body parts, drugs, etc. as well as the relations between them, which is an important knowledge base for intelligent auxiliary diagnosis. In this paper, the hierarchical structure of Medical Subject Headings(MeSH) is taken as the ontology prototype of the Knowledge Graph. According to the naming criterion of Chinese obstetric diseases and the practical application of the disease diagnosis in obstetric electronic medical records. And the ontology structure of obstetric diseases is extended. Moreover, the possible relation categories between obstetric entities and knowledge description system are defined to form the schema layer of Obstetric Knowledge Graph. The obstetric disease attributes of heterogeneous data are derived from medical specifications, classic textbooks, and medical online website by using rules-based and wrapper methods. And then they are fused by the Simhash-TF-IDF algorithm. The relations between entities in the knowledge graph are extracted by combining Bootstrapping and SVM algorithms. Then the Obstetric Knowledge Graph data layer is completed. The schema layer and data layer are automatically imported into Protege to visualize the Obstetric Knowledge graph. The constructed Obstetric Knowledge Graph contains 625 entities, 2456 attributes and 1407 relations, which covers the most diseases in obstetrics and related entities.
Personalized recommendation method is one of the representative solutions to solve the contradiction between information diversification and user demand specificity. Due to the limitations of the algorithm and the dif...
详细信息
Personalized recommendation method is one of the representative solutions to solve the contradiction between information diversification and user demand specificity. Due to the limitations of the algorithm and the difficulty of item feature extraction, the recommendation results of content-based recommendation system are too specialized to provide users with novel recommendation items. This paper tries to find a method of interest and preference diffusion to improve the recommendation specialization. In this paper, a comprehensive recommendation method based on information hierarchy distance and information loss distance in domain ontology is proposed. This method comprehensively calculates the similarity between items through similarity algorithms based on information hierarchy distance and information loss distance. The research shows that: the information loss distance in the domain ontology can have a great impact on the recommendation results, and the comprehensive recommendation method based on the information hierarchy distance and information loss distance can effectively improve the diversity and usefulness of the recommendation results.
Era of knowledge economy, how to effectively mining, the use of knowledge is the enterprise growing concern. CBR system from the field of artificial intelligence is a self-learning system to manage tacit knowledge (ca...
详细信息
Era of knowledge economy, how to effectively mining, the use of knowledge is the enterprise growing concern. CBR system from the field of artificial intelligence is a self-learning system to manage tacit knowledge (case). Case retrieval link is the core link, the advantages and disadvantages of search methods directly affect the efficiency of case retrieval and case matching accuracy. Therefore, this paper proposes a new case matching process: when the size of the case database is small, it searches based on the case similarity algorithm;when the case database is large, it searches based on the FCM secondary retrieval model. And illustrates the fastness and efficiency of FCM in matching large-scale case database. (C) 2017 The Authors. Published by Elsevier Lid.
暂无评论