Abstract Computer 3D reconstruction consisting of reconstruction of 3D point clouds and images plays an important role in computer graphics, computer image processing and computer vision research. Image based 3D reconstruction includes reconstruction of single image and multiple images. Compared to obtain 3D mode by modeling software or scan tester traditionally, image-based 3D reconstruction is featured by strong sense of reality, low cost, vivid... Computer 3D reconstruction consisting of reconstruction of 3D point clouds and images plays an important role in computer graphics, computer image processing and computer vision research. Image based 3D reconstruction includes reconstruction of single image and multiple images. Compared to obtain 3D mode by modeling software or scan tester traditionally, image-based 3D reconstruction is featured by strong sense of reality, low cost, vivid image and broader market demand. Moreover, image based 3D reconstruction is practically an inverse problem of computer graphics. In medical field, 3D reconstruction of medical images is to create 3D information based on a 2D image and then form a vivid 3D image. It transforms 2D fault data sequence obtained from Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) into 3D data, which is valuable in demonstrating tissues and organs of human body. 3D reconstruction technology concerning medicine is widely applied in medical diagnosis, surgical planning, analog simulation and plastic surgery. Therefore, computer 3D reconstruction technology is of important academic and practical value to reconstruction of 2D medical images. Research of 3D reconstruction of medical images focuses on preprocessing of medical images, such as filtering and interpolation, and segmentation and extraction of tissue and organ. This study analyzes design concept and method of cross-platform medical image 3D reconstruction system, development status, market demand and prospect of computer 3D reconstruction technology, medical volume data visualization technology, acquisition of medical images and several kinds of medical image preprocessing technologies. In the study, region growing algorithm is used to segment liver tissues. Volume rendering technology provides 3D special description for 2D medical fault images, to make its internal 3D structure become clearer. Principles and application scope of marching cubes based surface rendering algorithm is emphatically introduced. Based on traditional edge extraction theory, a new edge measurement and calculation method is designed, which makes edge smoother. Read More Read Less

Abstract This study proposes a cloud-based government procurement information integration platform, which includes layers of physical resources, virtual resources control, and cloud services, to solve problems in government procurement information resources management, such as low shared utilization, uncommunicated information, information risk, and other issues. The cloud service layer is designed for four categories of government procurement cloud service mode, namely, infrastructure cloud, data... This study proposes a cloud-based government procurement information integration platform, which includes layers of physical resources, virtual resources control, and cloud services, to solve problems in government procurement information resources management, such as low shared utilization, uncommunicated information, information risk, and other issues. The cloud service layer is designed for four categories of government procurement cloud service mode, namely, infrastructure cloud, data resources cloud, and core business cloud and application cloud, which provide the IaaS, PaaS, and SaaS services, respectively. The establishment of the cloud platform plays a significant role in government procurement information storage, sharing, opening, and searching, thus cutting government spending and improving management efficiency. Such outcomes are also beneficial to the integration and sharing of government procurement information resources and business collaboration, thereby promoting innovative information resource utilization and improving information management and security. Read More Read Less

Abstract This paper describes the initial work on developing an all-hazards emergency event detector using messages obtained in near-real-time from the public timeline of the Chinese Sina Weibo microblogging service. The system filters target keywords corresponding to emergency events of earthquakes, floods, typhoons, fires and storms and then uses classifiers to identify messages from people experiencing the corresponding emergency event. Then, this study carried... This paper describes the initial work on developing an all-hazards emergency event detector using messages obtained in near-real-time from the public timeline of the Chinese Sina Weibo microblogging service. The system filters target keywords corresponding to emergency events of earthquakes, floods, typhoons, fires and storms and then uses classifiers to identify messages from people experiencing the corresponding emergency event. Then, this study carried out experiments that compare the performance of four different classification methods and also explore to improve the classifier by the new training data captured by SWIM recently. After Chinese text pre-processing, feature selection and training set size, the experimental results demonstrate Random forests classifier could get best performance but need more long time to run in R, thus the potential to improve this classifier for setting up the SWIM system need to be explored in the future. While similar work has been reported using Twitter content, this is the first time these techniques have been applied to the Sina Weibo microblogging service for multiple emergency event types. This paper also outline the experience of accessing Sina Weibo messages, provide a summary of their structure and content, note the challenges faced in processing this text using Natural Language Processing packages and outline the developed website for users to view the processed messages. The long term aim is to develop a general emergency notification and monitoring system for various disaster event types in China reported by the public on Sina Weibo which can be used by the appropriate emergency services as a source of improved situational awareness. Read More Read Less

Abstract Tibetan text clustering has potential in Tibetan information processing domain. In this paper, clustering research across Chinese and Tibetan texts is proposed to benefit Chinese and Tibetan machine translation and sentence alignment. A Tibetan and Chinese keyword table is the main way to implement the text clustering across these two languages. Improved Kmeans and improved density-based spatial clustering of applications with... Tibetan text clustering has potential in Tibetan information processing domain. In this paper, clustering research across Chinese and Tibetan texts is proposed to benefit Chinese and Tibetan machine translation and sentence alignment. A Tibetan and Chinese keyword table is the main way to implement the text clustering across these two languages. Improved Kmeans and improved density-based spatial clustering of applications with noise (DBSCAN) algorithm are proposed. Experiments show that improved K-means algorithm gains stable text clustering result and performs better than traditional K-means after eliminating the limitation of random selection of initial k data. The improved DBSCAN algorithm obtains good performance through reasonable parameter setting. Improved DBSCAN performs better than improved K-means. The study is helpful and meaningful for the parallel corpus construction of Chinese and Tibetan texts. Read More Read Less

Abstract Imbalanced data problem is often encountered in application of text classification. Feature selection, which could reduce the dimensionality of feature space and improve the performance of the classifier, is widely used in text classification. This paper presents a new feature selection method named NFS, which selects class information words rather than terms with high document frequency. To improve classifier performance further, we combine a feature selection method (NFS) with... Imbalanced data problem is often encountered in application of text classification. Feature selection, which could reduce the dimensionality of feature space and improve the performance of the classifier, is widely used in text classification. This paper presents a new feature selection method named NFS, which selects class information words rather than terms with high document frequency. To improve classifier performance further, we combine a feature selection method (NFS) with data resampling technology to solve the problem of imbalanced data. Experiments were evaluated on Reuters- 21578 Collection, and results show that the NFS method performs better than chi-square statistics and mutual information on the original dataset when the number of selected features is greater than 1000. The maximum value of Macro-F1 is 0.7792 when the NFS method is applied to the resampling dataset, which represents an increase in Macro-F1 by 4.02% given the original dataset. Thus, our proposed method effectively improves minority class performance. Read More Read Less

Abstract Online recommendations are considered as a useful approach to encourage consumer purchases and drive product sales in e-commerce. This paper uses a multimodal approach to examine the effectiveness of online recommendations using the lenses of econometric modeling and text mining. Applying data on Amazon's 'customers who bought this item also bought' recommendation, commonly referred to as the co-purchase network, this study presents several... Online recommendations are considered as a useful approach to encourage consumer purchases and drive product sales in e-commerce. This paper uses a multimodal approach to examine the effectiveness of online recommendations using the lenses of econometric modeling and text mining. Applying data on Amazon's 'customers who bought this item also bought' recommendation, commonly referred to as the co-purchase network, this study presents several findings. First, the effects of direct co-purchase recommendations on product sales are essentially strong, regardless of other potential factors that can also affect those sales. Second, the sales of one product can have positive effect on the sales of another, when the latter is suggested in co-purchase recommendations. Moreover, the similarity of the customer base between the two co-purchased products, which can be extracted using text mining from online reviews, will affect that product's sales. This finding leads to the conclusion that online recommendations achieve by recommending related products to like-minded consumers, and that recommendation effect is significant. These results contribute to academics and practitioners by providing clear economic evidence of the value of using text mining approaches for online recommendations. Read More Read Less

Abstract With the development of information technology age, most patterns of college piano teaching have not adopted to talent cultivation demand in new period. Therefore, we need a brand new teaching pattern based on information technology. This paper discussed the development trend of future college piano teaching pattern combined with teaching practice, and conceived and analyzed four new teaching models including pattern of participation... With the development of information technology age, most patterns of college piano teaching have not adopted to talent cultivation demand in new period. Therefore, we need a brand new teaching pattern based on information technology. This paper discussed the development trend of future college piano teaching pattern combined with teaching practice, and conceived and analyzed four new teaching models including pattern of participation and experience, pattern of exploration and inspiration, pattern of self-study and guidance and pattern of cooperation and competition. Read More Read Less

Abstract In recent years, with the development of digital environment, one of the concepts that has been particularly important is digital identification of objects in this environment by digital identifier systems. The main objective of this study is to answer this important and basic question: How and on what framework can distinguish a digital object identifier system from other identifier systems? To achieve... In recent years, with the development of digital environment, one of the concepts that has been particularly important is digital identification of objects in this environment by digital identifier systems. The main objective of this study is to answer this important and basic question: How and on what framework can distinguish a digital object identifier system from other identifier systems? To achieve this goal, a comparative framework which consisted of 7 main characteristics of digital identifiers in three major domains (namely identifier features, digital coverage and comprehensiveness of scope) was proposed. Two major characteristics of the proposed framework are its inclusiveness and considering the differences between the uniqueness and persistency notions in general and in the digital environment. Then, an illustrative comparison of 23 well-known worldwide identifiers was carried out. Results of this study revealed that six identifier systems of DOI, Handle, UCI, ARK, URN and PURL can be regarded as the best choices of digital identifiers in public areas identified in the digital space and four identifier systems of ORCID, MIRIAM, ISNI and NBN are the best options to be used in certain specialized areas. These results can help information technology specialists to identify and effectively use of digital identifier systems in actual and potential practical areas. Read More Read Less