Advanced Materials Research Vols. 433-440

Abstract: Artificial immune system (AIS) based classification approach is relatively new in the field of pattern recognition (PR). The capability of AIS for learning new information, recalling what has been learned and recognizing a decentralized pattern are reasons why numerous models have been developed, implemented and used in various types of problems. This paper explores this paradigm in the context of recognition of handwritten Kannada numerals. In this paper, the AIS is used for training the extracted features of handwritten Kannada numerals. Zonal based feature extraction algorithm is being used and K-Nearest Neighbor (K-NN) classifier is used for classification. The performance of the proposed algorithm has been investigated in detail on nearly 1250 samples of Handwritten Kannada Numerals and an recognition accuracy of 98.11% has been obtained.

Abstract: Although the use of earnings prediction in supporting investment decisions has been prevailing in practice, an accounting-based analysis for modeling the key accounting components by time-delay machine learning technique is unexplored. Traditional time-series techniques fail to handle complex data structure, and the fundamental analysis approach cannot model multiple periods’ data effectively. Thus, this study aims to explore the crucial relationships among future earnings and the main historical accounting components, i.e. cash-flow and accrual components. The research method leverages the flexible learning capability of artificial neural network (ANN) with time-delay data structure. The major findings suggested that adding accrual components is helpful for better earnings prediction, and the proposed 5-period time-delay ANN model may capture the future earnings in a positive way. The results of this study may help to support investment decisions and better understanding for the role of accruals in earnings.

Abstract: The myoelectric signal (MES) with broad applications in various areas especially in prosthetics and myoelectric control, is one of the biosignals utilized in helping humans to control equipments. In this paper, a technique for feature extraction of forearm electromyographic (EMG) signals using wavelet packet transform (WPT) and singular value decomposition (SVD) is proposed. In the first step, the WPT is employed to generate a wavelet decomposition tree from which features are extracted. In the second step, an algorithm based on singular value decomposition (SVD) method is introduced to compute the feature vectors for every hand motion. This technique can successfully identify eight hand motions including forearm pronation, forearm supination, wrist flexion, wrist abduction, wrist adduction, chuck grip, spread fingers and rest state. These motions can be obtained by measuring the surface EMG signal through sixteen electrodes mounted on the pronator and supinator teres, flexor digitorum, sublimas, extensor digitorum communis, and flexor and extensor carpi ulnaris. Moreover, through quantitative comparison with other feature extraction methods like entropy concept in this paper, SVD method has a better performance. The results showed that proposed technique can achieve a classification recognition accuracy of over 96% for the eight hand motions.

Abstract: RoboCupRescue Simulation System is a platform for designing and implementing various artificial intelligent issues, and it is a very good test bed for solving Multiagent problems. One of the most important aspects of agent design in AI is the way agent acts or responds to the environment that the agent acting upon. An effective action selection and behavioral method requires a good priority extraction method for finding the best actions. In rescue simulation environments, Firebrigades should select fire points in a collaborative manner such that the total achieved result is optimized. In this work we are going to compare two different methods of fire selection in Firebrigade agents in RoboCupRescue Simulation. The first one is priority extraction using delayed rewards and the other one is Fuzzy Neural Network Based Fire Planning.

Abstract: Among more than three hundred cities in China, half of them are located in the earthquake zone where the seismic basic intensity is seven or even more than seven degrees, such as Beijing, Tianjin, Xi'an and other major cities which are located in the high-intensity earthquake zone of eight degrees. Since most areas of China are seismic fortified areas, the anti-seismic design of the underground structure and its safety evaluation have become the increasingly important issues that engineering designers are concerned about. In this paper, it studies and analyzes the dynamic response of the underground structure for a subway station under seismic loads, and preliminarily analyzes the law of its dynamic response, in the hope of benefiting the actual engineering constructions.

Abstract: As members of the supply chain have separate objectives and different information, there are some conflicts for interest and moral hazard between the supply chain members. These problems often lead to the abatement of supply chain performance and overall profits. Therefore, this paper explores the supply chain risk causes, with this understanding formulates the moral hazard model on the hidden action, and finally puts forward suggestions to solve moral hazard.

Abstract: The paper constructed an coordination evaluation model which measures the coordinated development status of the development system of Chinese greenfood industry and its subsystems,and established an index evaluation system from the perspective of system. A DEA approach is used to provide evidence for the coordinated development of the scale subsystem and the structure-efficiency subsystem based on the data from the greenfood industry in Heilongjiang province. The results suggest that there exists a dramatic fluctuation of the coordination of the greenfood industry system and its subsystem,and that the coordination degree of the greenfood industry is not so satisfying,in particular there is a downtrend in the coordinated development of the greenfood industry. Further research suggest that it’s feasible to transform the mode of industry development and to enhance the coordination degree of the subsystems,especially the structure-efficiency subsystem to realize the coordinated and sustainable development of the Chinese greenfood industry.

Abstract: This paper describes the creation of the national environment in Shenyang city in the process model, green city status and created some problems, and analyzed the causes of these problems, finally, to solve the problems of the measures proposed.

Abstract: The paper introduces the WorldFIP field bus and its application in the computer supervisory and control system(CSCS) of BAOQUAN pumped storage power station.

Abstract: Numerical weather prediction models as well as the atmosphere itself can be viewed as nonlinear dynamical systems in which the evolution depends sensitively on the initial conditions. Any small error in the initial condition will lead to forecast errors that grow with increasing forecast time. The methods of ensemble forecasting are developed to generate a representative sample of the possible future states of a dynamical system. For an efficient ensemble forecasting, the initial perturbations to the control analysis should adequately sample the possible analysis errors. The analysis cycle is similar to a breeding cycle, which acts as a nonlinear perturbation model upon the evolution of the real atmosphere. This paper proposes a breeding method for generating ensemble perturbations that can effectively represent the uncertainties in the observed meteorological data. In order to simulate the possible states of northeast monsoon over Southeast Asia under the influence of global warming, selected data from the Intergovernmental Panel on Climate Change (IPCC) are used for testing the generation of initial perturbations in the breeding process by integration of a shallow water model. The results from this research showed the effectiveness of the breeding method in generating ensemble perturbations for short-range weather forecast.