Abstract A new classification algorithm based on multi-ant and pheromone repulsion principles is studied and proposed in this paper to improve the prediction accuracy of the classification rule based on the traditional Ant-Miner algorithm. The proposed algorithm uses multiant colony construction method to reduce dependence on random initial term. The volatile coefficient of pheromone update is added to prevent premature convergence. The new state transition function based on pheromone repulsion... A new classification algorithm based on multi-ant and pheromone repulsion principles is studied and proposed in this paper to improve the prediction accuracy of the classification rule based on the traditional Ant-Miner algorithm. The proposed algorithm uses multiant colony construction method to reduce dependence on random initial term. The volatile coefficient of pheromone update is added to prevent premature convergence. The new state transition function based on pheromone repulsion principle is also presented to avoid falling into local optimum, whereas a rule quality formula is improved. Several aspects of the proposed algorithm are investigated by experimenting of benchmark data sets from the University of California at Irvine repository. We study the performance of our proposed approach and compare it with several commonly used classification algorithms, such as Ant-Miner and Ant-Miner with graphical user interface. Experimental results indicate that the proposed approach builds more accurate models than the compared algorithms. The high accuracy supplemented by the comprehensibility of the discovered rule sets is the main advantage of this method.A new classification algorithm based on multi-ant and pheromone repulsion principles is studied and proposed in this paper to improve the prediction accuracy of the classification rule based on the traditional Ant-Miner algorithm. The proposed algorithm uses multiant colony construction method to reduce dependence on random initial term. The volatile coefficient of pheromone update is added to prevent premature convergence. The new state transition function based on pheromone repulsion principle is also presented to avoid falling into local optimum, whereas a rule quality formula is improved. Several aspects of the proposed algorithm are investigated by experimenting of benchmark data sets from the University of California at Irvine repository. We study the performance of our proposed approach and compare it with several commonly used classification algorithms, such as Ant-Miner and Ant-Miner with graphical user interface. Experimental results indicate that the proposed approach builds more accurate models than the compared algorithms. The high accuracy supplemented by the comprehensibility of the discovered rule sets is the main advantage of this method.A new classification algorithm based on multi-ant and pheromone repulsion principles is studied and proposed in this paper to improve the prediction accuracy of the classification rule based on the traditional Ant-Miner algorithm. The proposed algorithm uses multiant colony construction method to reduce dependence on random initial term. The volatile coefficient of pheromone update is added to prevent premature convergence. The new state transition function based on pheromone repulsion principle is also presented to avoid falling into local optimum, whereas a rule quality formula is improved. Several aspects of the proposed algorithm are investigated by experimenting of benchmark data sets from the University of California at Irvine repository. We study the performance of our proposed approach and compare it with several commonly used classification algorithms, such as Ant-Miner and Ant-Miner with graphical user interface. Experimental results indicate that the proposed approach builds more accurate models than the compared algorithms. The high accuracy supplemented by the comprehensibility of the discovered rule sets is the main advantage of this method. Read More Read Less

Abstract Biomedical named entity recognition (Bio- NER) is the fundamental task of biomedical text mining. Machine-learning-based approaches, such as conditional random fields (CRFs), have been widely applied in this area, but the accuracy of these systems is limited because of the finite annotated corpus. In this study, word embedding features are generated from an unlabeled corpus, which as extra word features are induced into the CRFs system for Bio-NER.... Biomedical named entity recognition (Bio- NER) is the fundamental task of biomedical text mining. Machine-learning-based approaches, such as conditional random fields (CRFs), have been widely applied in this area, but the accuracy of these systems is limited because of the finite annotated corpus. In this study, word embedding features are generated from an unlabeled corpus, which as extra word features are induced into the CRFs system for Bio-NER. To further improved performance, a post-processing algorithm is employed after the named entity recognition task. Experimental results show that the word embedding features generated from a larger unlabeled corpus achieves higher performance, and the use of word embedding features increases F-measure on INLPBA04 data from 71.50% to 71.77%. After applying the post-processing algorithm, the F-measure reaches 71.85%, which is superior to the results in most existing systems. Read More Read Less

Abstract This study proposed a port logistics information platform based on Java2 Platform Enterprise Edition(J2EE), which was integrated with three levels: client, Web, and business logic. These levels aimed to resolve the low-level informationization, low sharing information, information risk, and other problems of Dushan Port logistics. Seven function modules based on JavaScript, CSS + HTML technology, and business demand were developed, such as the public information service module and the... This study proposed a port logistics information platform based on Java2 Platform Enterprise Edition(J2EE), which was integrated with three levels: client, Web, and business logic. These levels aimed to resolve the low-level informationization, low sharing information, information risk, and other problems of Dushan Port logistics. Seven function modules based on JavaScript, CSS + HTML technology, and business demand were developed, such as the public information service module and the e-port module of the harbor. The practical operation results show that, the establishment of a port logistics information platform efficiently can improve customs clearance speed, reduce logistics costs, and improve government administration efficiency. As a result, the utilization rate of information and the safety of port logistics information management can be enhanced. Read More Read Less

Abstract Software development life cycle is systematic way of developing software which describes phases of the software development and the sequence in which these phases are executed. Each phase generates deliverables required by the next phase in the life cycle. Requirements are translated into design. Code is produced according to the design which is called development phase. After coding and development the testing verifies the deliverable of the implementation phase... Software development life cycle is systematic way of developing software which describes phases of the software development and the sequence in which these phases are executed. Each phase generates deliverables required by the next phase in the life cycle. Requirements are translated into design. Code is produced according to the design which is called development phase. After coding and development the testing verifies the deliverable of the implementation phase against requirements. Almost all software development models contain software testing as one phase but testing require at each phase of SDLC. Different testing technique can apply on different phases based on software quality attributes. Software testing majorly categorized in to functional and structural testing each of them focus on different aspect of software. Both play vital role in software development life cycle by assuring software quality, each of them can use to measure different quality attributes. Since, both structural and functional testing faces a lot of challenges during manual conduction .Focus of this research paper is to find out significance of structural testing in SDLC along with challenges of structural testing methodology “DD path testing” in manual environment and suggest suitable solution to face these challenges. Suggested solution describes which steps involve in DD path testing and how they can automate. Read More Read Less

Abstract The method based on semantic knowledge is the most dynamic research direction in rule-based techniques. This method has been proven effective in studying English and Chinese word sense disambiguation. This study proposes two methods for selecting the correct Chinese meaning of Tibetan ambiguous words from Tibetan sentences in Tibetan-Chinese parallel corpora using semantic knowledge from HowNet and translation information from the aforementioned corpora. We can use these methods to... The method based on semantic knowledge is the most dynamic research direction in rule-based techniques. This method has been proven effective in studying English and Chinese word sense disambiguation. This study proposes two methods for selecting the correct Chinese meaning of Tibetan ambiguous words from Tibetan sentences in Tibetan-Chinese parallel corpora using semantic knowledge from HowNet and translation information from the aforementioned corpora. We can use these methods to build Tibetan-Chinese parallel corpora with word sense tagging. The two proposed methods are 1) the word sense disambiguation method based on HowNet and Tibetan-Chinese parallel corpora, and; 2) the semantic knowledge-based method of network diagram word sense disambiguation. Read More Read Less

Abstract This paper used China's urban clusters as case studies, and a model of the information network was constructed using Baidu index search data. In this model, the urban clusters were considered nodes, and the search intensity between them were regarded as edges. Based on complex network theory and city flow theory, the structure of geographical space was visualized in the form of a network. Analysis results show... This paper used China's urban clusters as case studies, and a model of the information network was constructed using Baidu index search data. In this model, the urban clusters were considered nodes, and the search intensity between them were regarded as edges. Based on complex network theory and city flow theory, the structure of geographical space was visualized in the form of a network. Analysis results show that, first, the network density of the core contact is only at 3.62%, and 69.2% of the connection strengths between urban clusters are relatively weak on a national scale. Next, the abilities of absorbing information are greater than those of giving off for more developed urban clusters. Last, compared with the ability of giving off information, the variability of absorption is more obvious for all 24 urban clusters. Based on these conclusions, we analyzed spatial influences from the perspective of urban flows and present strategies with space optimization. Read More Read Less

Abstract The research aimed to put forward a kind of new network structure on the basis of extension theory, namely extension neural networks (ENN), in order to improve the accuracy of atmospheric pollution assessment, and solve the contradictory interval division problem, avoid falling into the defect of local optimum, improve the speed of network training, and also shorten the operation time. This study collected historical monitoring data of 12... The research aimed to put forward a kind of new network structure on the basis of extension theory, namely extension neural networks (ENN), in order to improve the accuracy of atmospheric pollution assessment, and solve the contradictory interval division problem, avoid falling into the defect of local optimum, improve the speed of network training, and also shorten the operation time. This study collected historical monitoring data of 12 districts in Beijing as samples, considered principal pollutants including SO2, NO2 and inhalable particle PM10 as network input, and also set up and tested network taking extension distance as measure tool. The results showed that prediction results basically met the requirements of accurate assessment compared with the actual results, which confirmed the feasibility, accuracy and effectiveness of the algorithm. In addition, compared with structure and training speed, ENN network had more obvious superiority than BP network. Read More Read Less

Abstract Document files are history that records that human understanding and transformation of the world that formed directly in the social practice, is a precious historical and cultural wealth. International advanced archives service work are positioning on the basis of socialization, based on a highly efficient and reliable digital platform, to realize centralized management of the national archives of the and the social sharing. However, judging from the domestic... Document files are history that records that human understanding and transformation of the world that formed directly in the social practice, is a precious historical and cultural wealth. International advanced archives service work are positioning on the basis of socialization, based on a highly efficient and reliable digital platform, to realize centralized management of the national archives of the and the social sharing. However, judging from the domestic situation, comprehensive archives management system is still blank, for documents and archives, the most important and most valuable social resources are only just beginning. This research purpose of this subject is to build a documents digitization management platform that can comprehensive collect and manage social archives document resources, using uniform standards and with high scalability. Read More Read Less

Abstract Model computing system for emergent infectious disease prevention and control ability evaluation of medical building network establishes evaluation framework according to fuzzy comprehensive evaluation method, selects evaluation indexes during prevention, treatment and recovery of emergent infectious disease based on the theory of crisis management, and calculates weight coefficient of indexes based on analytic hierarchy process. With the help of data processing and analysis functions of statistical analysis software SPSS,... Model computing system for emergent infectious disease prevention and control ability evaluation of medical building network establishes evaluation framework according to fuzzy comprehensive evaluation method, selects evaluation indexes during prevention, treatment and recovery of emergent infectious disease based on the theory of crisis management, and calculates weight coefficient of indexes based on analytic hierarchy process. With the help of data processing and analysis functions of statistical analysis software SPSS, fuzzy comprehensive evaluation matrix model of medical building system was established. Then the model was used for practically evaluating the prevention and control ability of medical building network on emergent infectious disease in typical cities of China. The advantages and disadvantages of cities facing with emergent infectious disease were concluded by stimulating the response process of medical building system when emergent infectious disease burst out in the cities. Finally, the measurement method and application range of model computing system for emergent infectious disease prevention and control ability evaluation of medical building network were clarified. Read More Read Less

Abstract The real traffic databases are highly susceptible to noisy, missing, and inconsistent data. As reason of processing the discrepant data, a model is built based on square support vector machine which is good at dissolving the problems such as small samples, nonlinear and pattern recognition. Utilizing of the SVM, the inaccurate data can be detected by calculating the difference value between the real and prediction data. Comparing with... The real traffic databases are highly susceptible to noisy, missing, and inconsistent data. As reason of processing the discrepant data, a model is built based on square support vector machine which is good at dissolving the problems such as small samples, nonlinear and pattern recognition. Utilizing of the SVM, the inaccurate data can be detected by calculating the difference value between the real and prediction data. Comparing with the method of threshold theory, the model is proved to be better for the accurate data detection online and database cleaning. Read More Read Less

Abstract This paper proposes a practical and effective predicting model for resource allocation and usage for server. The approach rests on virtualization technique to simulate a heterogeneous virtual machine environment. The study is confined to management of number of CPUs and memory units being allocated on three servers to serve user's requests. The objective is fast response time to attain as high user satisfaction as possible. The algorithm employs... This paper proposes a practical and effective predicting model for resource allocation and usage for server. The approach rests on virtualization technique to simulate a heterogeneous virtual machine environment. The study is confined to management of number of CPUs and memory units being allocated on three servers to serve user's requests. The objective is fast response time to attain as high user satisfaction as possible. The algorithm employs exponential smoothing technique to analyze trend of data and the relationship among them. Assessment was compared with association rules and ARIMA. The findings reveal that the proposed technique yields more accurate prediction results than other predicting models, having the least MSE and acceptable system response time. Read More Read Less