The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The research proposes an approach of story segmentation for news video using multimodal analysis. The approach detects the topic-caption frames, and integrates them with silence clips detection, as well as shot segmentation to locate news story boundaries. On test data with 135,400 frames, the accuracy rate 87.9% and the recall rate 98.7% are obtained. The experimental results show the approach is...
Semantic soccer video analysis has attracted more and more attention recently. In this paper, we present a football event detection method by using multiple feature extraction and fusion. Instead of using low-level features, the proposed method is built upon visual, auditory features, text and audio keywords. Promising event detection results have been achieved. By using the proposed method, we have...
Parameters control problem was crucial in rolling industrial, but the mechanical properties forecasting of strip steel was an information space incompletely and non-linear complex system which was hard for traditional method. Artificial neural networks was a non-linear system with strong non-linear modeling ability, but the traditional BP neural networks has many shortcomings like easily step into...
In this paper, we propose a set of semantic cohesion metrics for ontology measurement, which can be used to assess the quality of evolving ontologies in the context of dynamic and changing Web. We argue that these metrics are stable and can be used to measure ontology semantics rather than ontology structures. Measuring ontology quality with semantic inconsistencies caused by ontology evolutions,...
A new method is emerging in the field of high-rise building in recent years. That is water supply of non-negative pressure. For the reasons of used quantity of water cannot be predicted and non-equilibrium and other reasons, the water pressure is changed notable, it cannot meet the requirements of users by water pressure. The digital PID control is the common control method in the process of manufacture...
This paper is about the establishment and application of GIS database in neighborhood renewal. It first mines the needed data for database establishment from literature review. Then, the GIS database will be designed for neighborhood renewal, which integrates land use, public and commercial service, road, building, infrastructure, and environment six major variables. Finally, a case of Huangjiadun...
Adaptive PID controller based on back propagation(BP) neural network has many merits like that simple algorithm of PID controller and self-study and adaptive functions of neural network. According the requirements of system output performance, the BP neural network can autoadjust its weights to vary kp, kj and kd. The simulation adjust its weights to vary k results of an electro-hydraulic position...
Resource management in distributed and heterogeneous databases is an urgent problem nowadays. In this paper, a framework is proposed to give an efficient method to solve this problem. This framework has two main parts. First, the Web service architecture is given by analyzing many metadata standards and databases. By using Web service technology, the ontology-based framework of is proposed to address...
In view of the problem that it is difficult to predict the output in an oilfield which affected by multiple variables, a back propagation (BP) neural network model is built to predict the output in oilfield because the classic statistical method and static model cannot meet the demand of precision for the nonlinear and uncertain system. Effective depth, permeability, porosity and water content are...
In view of the deficiency of the traditional methods, a BP neural network model is proposed to evaluate water quality. The proposed model was applied to evaluate the water quality of 20 sections in Suzhou river. The evaluation result was compared with that of the RBF neural network method and the reported results in Suzhou river. It indicated that the performance of proposed neural network model is...
Based on the theory of core competence, the paper analyzes construction enterprise's core competence from the perspective of knowledge capital. It establishes evaluation index system of construction enterprise's core competence, and then uses BP neural network to set the model of calculating construction enterprise's core competence. This model avoids subjectivity and uncertainty brought about by...
The mobile robot simultaneous localization and mapping (SLAM) in unknown environments has been considered to be an important and fundamental problem in the mobile robotics research domain. Nowadays most methods for SLAM are focused on probabilistic Bayesian estimation, this paper propose an unscented Kalman filter (UKF) assistant-proposal distribution (UKF-APD) particle algorithm,compute the Euclidean...
Business process model and data model play important roles in information system construction. They represent two different perspectives of business knowledge, and are closely related. A trouble to the model quality is the inconsistency between business process model and data model, which can often conduce to interaction errors. While finding such inconsistency is a meaningful problem, it receives...
UML is a universal, standard modeling language. It can be applied to the modeling of any system with static framework and dynamic action. However, UML lacks precise semantics which might lead to problems, such as inconsistencies, redundancies and so on. In order to detect the UML behavior diagrams, a dynamic description logic and a sound and complete tableau-based satisfiability-checking decidable...
The special distribution, sampling strategy and responding mechanism of human photoreceptor cells are significant for visual system. Photoreceptor cells layer is the connection between the preceding and the following in visual system, in one hand, it could sample and represent the outside information, in other hand, it could process the data in its specific way and transfer processed data to following...
Classification is a famous branch of machine learning. We have tried many ways to invent and improve algorithms to get better results from given data. However, few have been done on how to revise data to adapt machine learning. In this paper, the same classifiers are implemented on same object sets which are different in the granularity of classification to show different classification can make great...
With the trend of globalization, increased customer demand and advancement in technology development, firms are experiencing ever intense pressure to collaborate with their trading partners to compete with other supply chains. Firms are seeking to collaborate with their partners at greater extent in the areas such as knowledge management to exploit the potentials of an efficient and effective supply...
Aiming at the low level of automation of case retrieval in case- based design the retrieval model design used in case- based fixture design was studied in detail. On the analysis of the functional surfaces of work piece, the design requirement is extracted whereby the functional mode of work piece is presented, and the prototype of fixture assembling based on the theory of General-location is constructed...
Firstly, we give the definition of an L-bifuzzy Scott closed subset and prove its related properties, then, we give the definition of an L-bifuzzy Scott co-topological space, study its properties and equivalently characterize it which is a generalization of the Scott co-topological space in the classical topology theory. Finally, we establish the relationships of L-bifuzzy domain, L-bifuzzy lower...
This paper considers a swarm model with a general attraction-repulsion function involving variable communication time lags and an attractant/repellent. It is proved that for Gaussian attractant/repellent profiles the individuals of the swarm with time delays will aggregate and form a cohesive cluster of finite size in a finite time. Moreover, all the swarm individuals will converge to more favorable...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.