Recent developments of mobile Internet and wireless technologies bring new opportunities and challenges to GIS research and applications. In this paper, we propose a new framework for accessing and integrating distrib...
详细信息
Generalized learning is a kind of integrated machine learning methods, which combines symbolic learning with connective learning, fuzzy learning and evolutionlearning. This paper discusses the fundamental principle fo...
详细信息
ISBN:
(纸本)0780384075
Generalized learning is a kind of integrated machine learning methods, which combines symbolic learning with connective learning, fuzzy learning and evolutionlearning. This paper discusses the fundamental principle for generalized learning first. Then the generalized learning is introduced to remote sensing image recognition system (RSIRS for short) to obtain certain knowledge from training sample set for classification. The experiment result has shown the validity of generalized learning in knowledge discovering.
An artificial Ants Sleeping Model (ASM) and Adaptive Artificial Ants Clustering Algorithm (A4C) are presented to resolve the clustering problem in data mining by simulating the behaviors of gregarious ant colonies. In...
详细信息
ISBN:
(纸本)0780384032
An artificial Ants Sleeping Model (ASM) and Adaptive Artificial Ants Clustering Algorithm (A4C) are presented to resolve the clustering problem in data mining by simulating the behaviors of gregarious ant colonies. In the ASM mode, each data is represented by an agent The agents' environment is a two-dimensional grid. In A4C, the agents can be formed into high-quality clusters by making simple move according to little local neighborhood information and the parameters are selected and adjusted adaptively. Experimental results on standard clustering benchmarks demonstrate the ASM and A4C are more direct, easy to implement, and more efficient than previous methods.
The main difficulty arising in designing an efficient congestion control scheme lies in the large propagation delay in data transfer which usually leads to a mismatch between the network resources and the amount of ad...
详细信息
In the next fifty years, the main problem of AI is "the solution of Mutil-Agent in the dynamic and un-forecast environment", the standard problem is the robot vs. robot or human vs. robot competition. This p...
详细信息
ISBN:
(纸本)0780384032
In the next fifty years, the main problem of AI is "the solution of Mutil-Agent in the dynamic and un-forecast environment", the standard problem is the robot vs. robot or human vs. robot competition. This paper discusses the problem of collab.ration and coordination in RoboCup Agent based on reinforcement learning and shows our experiment results.
The work present a recurrent neural network-based approach for modal parameters identification of structure-unknown systems. The proposed approach involves two steps. The first step is to build a recurrent neural netw...
详细信息
ISBN:
(纸本)0780384032
The work present a recurrent neural network-based approach for modal parameters identification of structure-unknown systems. The proposed approach involves two steps. The first step is to build a recurrent neural network to map the complex nonlinear relation between the excitations and responses of the structure-unknown system by off-line learning. The second step is to propose a procedure to determine the modal parameters of the system from the trained neural networks. The dynamic characteristics of the structure are directly evaluated from the weighting matrices of the trained recurrent neural network. Furthermore, an illustrative example demonstrates the feasibility of using the proposed method to identify modal parameters of structure-unknown systems. The method proposed can be used to research on fault diagnosis of engineer structure.
With the development of well drilling technique and the reform on drill bit technique, each oil field has adopted new PDC drill bit to smash rock cuttings. However, the severely mixed cuttings have greatly increased t...
详细信息
ISBN:
(纸本)0780384032
With the development of well drilling technique and the reform on drill bit technique, each oil field has adopted new PDC drill bit to smash rock cuttings. However, the severely mixed cuttings have greatly increased the difficulty in collecting samples through traditional geochemical logging technique. Based on the further study on geochemical logging and gas logging techniques, a new approach is presented in the paper to analyze rock cutting samples by hydrocarbon component through complete degasification. In addition, using PLC programmed control, an automatic degasification system of hydrocarbon component in rock cuttings is developed, which has achieved good testing results. The precision of exploration for petroleum and natural gas is hereby enhanced.
Spoofing source IP addresses is always utilized to perform Distributed Denial-of-Service (DDoS) attacks. Most of current detection and prevention methods against DDoS ignore the innocent side, whose IP is utilized as ...
详细信息
Presented herein is an efficient simulation technique enabling systematic investigation of the soft programming over-erased flash EEPROM cells. The simulation provides a method by which to find the optimal soft progra...
详细信息
Adapted from the concept of views in databases, workflow views are derived form workflows as a fundamental support for workflow inter-operability and visibility by external parties in a web services environment. Howev...
详细信息
暂无评论