Establishment of constitutive relationship model for 2519 aluminum alloy based on BP artificial neural network

An isothermal compressive experiment using Gleeble 1500 thermal simulator was studied to acquire flow stress at different deformation temperatures, strains and strain rates. The artificial neural networks with the error back propagation(BP) algorithm was used to establish constitutive model of 2519 aluminum alloy based on the experiment data. The model results show that the systematical error is small(δ=3.3%) when the value of objective function is 0.2, the number of nodes in the hidden layer is 5 and the learning rate is 0.1. Flow stresses of the material under various thermodynamic conditions are predicted by the neural network model, and the predicted results correspond with the experimental results. A knowledge-based constitutive relation model is developed.

The pH control optimization in the crop fertigation system using ANN

pH regulation is a complicated and comprehensive technique in the crop fertigation system. In this paper, a method is put forward to improve the quality of pH regulation, using artificial neural network to map a nonlinear relationship between pH interfering factor and the switching frequency of pH control valve, which achieves the dynamic feedforward compensation to the main control system.

Investigation of Image Fusion Between High-Resolution Image and Multi-spectral Image

On the basis of a thorough understanding of the physical characteristics of remote sensing image, this paper employs the theories of wavelet transform and signal sampling to develop a new image fusion algorithm. The algorithm has been successfully applied to the image fusion of SPOT PAN and TM of Guangdong province, China. The experimental results show that a perfect image fusion can be built up by using the image analytical solution and re-construction in the image frequency domain based on the physical characteristics of the image formation. The method has demonstrated that the results of the image fusion do not change spectral characteristics of the original image.

Intelligent PID controller based on ant system algorithm and fuzzy inference and its application to bionic artificial leg

A designing method of intelligent proportional-integral-derivative(PID) controllers was proposed based on the ant system algorithm and fuzzy inference. This kind of controller is called Fuzzy-ant system PID controller. It consists of an off-line part and an on-line part. In the off-line part, for a given control system with a PID controller,by taking the overshoot, setting time and steady-state error of the system unit step response as the performance indexes and by using the ant system algorithm, a group of optimal PID parameters K*p , Ti* and T*d can be obtained, which are used as the initial values for the on-line tuning of PID parameters. In the on-line part, based on Kp* , Ti*and Td* and according to the current system error e and its time derivative, a specific program is written, which is used to optimize and adjust the PID parameters on-line through a fuzzy inference mechanism to ensure that the system response has optimal transient and steady-state performance. This kind of intelligent PID controller can be used to control the motor of the intelligent bionic artificial leg designed by the authors. The result of computer simulation experiment shows that the controller has less overshoot and shorter setting time.

Metamorphic Algorithm of Self-reconfigurable Modular Robotic System

A self-reconfigurable robot is a non-linear complex system composed of a large number of modules. The complexity caused by non-linearity makes it difficult to solve the problem of module motion planning and shape-changing control with the traditional algorithm. In this paper, a full-discrete metamorphic algorithm is proposed. The modules concurrently process the local sensing information, update their eigenvector, and act by the same predetermined logical rules. Then a reasonable motion sequence for modules and the global metamorphosis can be obtained. Therefore, the complexity of metamorphic algorithm is reduced, the metamorphic procedure is simplified, and the self-organizing metamorphosis can be obtained. The algorithm cases of several typical systems are studied and evaluated through simulation program of 2-D planar homogeneous modular systems.

Ship motion extreme short time prediction of ship pitch based on diagonal recurrent neural network

A DRNN (diagonal recurrent neural network) and its RPE (recurrent prediction error) learning algorithm are proposed in this paper .Using of the simple structure of DRNN can reduce the capacity of calculation. The principle of RPE learning algorithm is to adjust weights along the direction of Gauss-Newton. Meanwhile, it is unnecessary to calculate the second local derivative and the inverse matrixes, whose unbiasedness is proved. With application to the extremely short time prediction of large ship pitch, satisfactory results are obtained. Prediction effect of this algorithm is compared with that of auto-regression and periodical diagram method, and comparison results show that the proposed algorithm is feasible.

Analysis of Shape and General Arrangement for a UUV

The construction and shape of UUVs are described in the paper. UUV design is the shape of the overall design of unmanned underwater vehicle should first be resolved UUV underwater vehicle directly affects the shape of the resistance and noise, which is related to energy, payload, maneuverability and concealment UUV problem The main characteristic and parameter tables for foreign torpedo shape, fiat shape and anomalous shape are also given in the paper. The general layout of typical foreign UUVs is analyzed in detail. And the total layout figure and interior constructive figure are introduced. Torpedo-type because of its good water power and low noise, no one has been the main form of underwater vehicle-like, and many designers are now highly favored because of its stable performance, anti-environmental interference capability. Other irregular shapes designed primarily for the completion of a specific task, according to the specific environment and mission requirements. According to comparing and summarizing, some suggestions and conclusions are oresented.

A neural network method to evaluate consolidation coefficient

Many methods to calculate the consolidation coefficient of soil depend on judgment of testing curves of consolidation, and the calculation result is influenced by artificial factors. In this work, based on the main principle of back propagation neural network, a neural network model to determine the consolidation coefficient is established. The essence of the method is to simulate a serial of compression ratio and time factor curves because the neural network is able to process the nonlinear problems. It is demonstrated that this BP model has high precision and fast convergence. Such method avoids artificial influence factor successfully and is adapted to computer processing.

The Algorithm for Rule-base Refinement on Fuzzy Set

In the course of running an artificial intelligent system many redundant rules are often produced. To refine the knowledge base, viz. to remove the redundant rules, can accelerate the reasoning and shrink the rule base. The purpose of the paper is to present the thinking on the topic and design the algorithm to remove the redundant rules from the rule base. The “abstraction” of “state variable”, redundant rules and the least rule base are discussed in the paper. The algorithm on refining knowledge base is also presented.

Challenges and Strategies for Courtroom Interpreter： A Case Study

Courtroom interpreting has now attracted more attentions due to the fast growth of interpreting as a profession and the development of globalization. Courtroom interpreting is different from other interpreting modes in that it involves both legal knowledge and interpreting capability. Misinterpreting in courtroom can pose a threat to the human rights and sometimes can be a matter of life and death. This paper discusses some common challenges faced by courtroom interpreters and proposes coping tactics guided by ethical principles

Knowledge representation and rule-based solution system for dynamic programming model

A knowledge representation has been proposed using the state space theory of Artificial Intelligence for Dynamic Programming Model, in which a model can be defined as a six tuple M=(I,G,O,T,D,S). A building block modeling method uses the modules of a six tuple to form a rule based solution model. Moreover, a rule based system has been designed and set up to solve the Dynamic Programming Model. This knowledge based representation can be easily used to express symbolical knowledge and dynamic characteristics for Dynamic Programming Model, and the inference based on the knowledge in the process of solving Dynamic Programming Model can also be conveniently realized in computer.

Retrieval Snow Depth by Artificial Neural Network Methodology from Integrated AMSR-E and In-situ Data——A Case Study in Qinghai-Tibet Plateau

On the basis of artificial neural network (ANN) model, this paper presents an algorithm for inversing snow depth with use of AMSR-E (Advanced Microwave Scanning Radiometer-Earth Observing System (EOS)) dataset, i.e., brightness temperature at 18.7 and 36.5GHz in Qinghai-Tibet Plateau during the snow season of 2002-2003. In order to overcome the overfitting problem in ANN modeling, this methodology adopts a Bayesian regularization approach. The experiments are performed to compare the results obtained from the ANN-based algorithm with those obtained from other existing algorithms, i.e., Chang algorithm, spectral polarization difference (SPD) algorithm, and temperature gradient (TG) algorithm. The experimental results show that the presented algorithm has the highest accuracy in estimating snow depth. In addition, the effects of the noises in datasets on model fitting can be decreased due to adopting the Bayesian regularization approach.

Religious Ethos and Political Discourse, the Case of Senegalese Politicians

The population finds more and more difficulties to assess the scope and content of political declaration especially in terms of plausibility and the real intentions of the speakers. This is especially true for the Senegalese public who more and more loses confidence in the political class. The public tends to look at the identity of the political personality and its personal values （morality credibility） to determine what to make of his/her words. On their side, politicians also begin promoting their image through their speeches. At this level, religious ethics seems to be unanimously considered a criterion of good morality among Senegalese politicians. We will try to look through Perelman＇s theory of argumentation, which Amossy redefined, how, in order to reach the audience, politicians adapt their words to the public, and enhance principles cherished by the populations to win the battle of the image and confidence.

The Conflict between Patient Autonomy and the Dying Patient Law in Israel

The Dying Patient Law is very controversial in Israel; there are opinions that the reason for the Law was to prevent the court from making decisions on the subject of end of life according to democratic principles. I decided to do this study because I wanted to know if the legal principles of the Law are democratic as were the court rulings or they are only, or mostly, Jewish principles and meant to prevent a democratic ruling in the courts. The work is a review of the Law and the Dying Patient Committee discussions as well as the chairman＇s writings on the Law, critique articles, and a review of democratic and bioethical principles. In this project, I have seen that the underlying basis of the Dying Patient Law is Jewish principles and not democratic principles, although Israel is a declared democratic state. This law illustrates the problem in Israel being both a democratic and a Jewish state. It raises the question： What can be done to resolve the conflict between the Jewish principles and democratic and/or bioethical principles？

A new accelerating algorithm for multi-agent reinforcement learning

In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents’ behaviors. However, joint-action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by joint-action. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm.

Retaining Truth, Seeking Goodness and Preserving Beauty： Principles of Translating Tsangyang Gyatso＇s Poems Into English

Tsangyang Gyatso＇s poems were widely circulated and still enjoy popularity. He was an influential living Buddha （Renpoche） in Tibetan Buddhism and a talented and legendary historical figure. Nowadays, more and more scholars, poets and translators have devoted to the study of his works. Here we will focus on discussing the English translation of his poems and their value. We analyze texts of the Tsangyang Gyatso＇s Poems （Chinese-English） and seek to further study the translation principles such as ＂retaining truth, seeking goodness and preserving beauty＂. By doing this, we strive to improve the quality of translation, give consideration to the construction of the four elements such as poetic meaning, emotion, tone and intention, to enable the reader to achieve the senses and the acquisition of images, to provide more perfect translation in the ＂Tsangyang Gyatso Vogue＂, to promote the dissemination and sharing of Tibetan culture and to inject new vitality.

THE ALGORITHMS OF AN INTEGER PARTITIONING WITH ITS APPLICATIONS

In the light of the ideals of Artificial Intelligence(AI), three algorithms of an integer partitioning have been given in this paper:generate and test algorithm,and two heuristic algorithms about forward partition and backward partition. PROLOG has been used to deseribe dsorithms,it is reasonable,direct and simple. In the sight of describing algorithms,it is a new and valid try. At last,some intresting appllcations of the algorithms mentioned in the paper have been presented.

Cognitive Heuristics and Dual Process Models A Perspective for Management Accounting （MA）？

Classical management accounting （MA） Focusing on the facilitating perspective, focuses on decision facilitating and influencing （Demski ＆ Feltham, 1976）. MA has to provide information to managers and depending on the problem complexity, they have to solve problems in a dyadic way. A dual process model, the heuristic systematic model （HSM）, expands this so-called manager-accountant-dyad and shows different cases of actual human information processing. Managers and accountants either process systematically or heuristically. So far, many concepts have been designed in relation to the normative concept of the economical rational principle. Consequently, recent research only uses systematic information processing, based on the principle of the economic man. In this paper, a decision-behavior oriented approach tries to describe actual decision makers such as managers and accountants and shows new possibilities within MA. Therefore, the potential of heuristic information processing is analyzed, based on the phenomenon of ecological rationality as one shape of bounded rationality. Thus, different cognitive heuristics in business economics are identified and analyzed. Furthermore, the outstanding performance of heuristics compared with more complex calculations is shown. Unfortunately, these findings have been limited to marketing and investments so far. Significant research is needed, regarding conditions for applications and success factors of heuristics in business economics. New empirical findings have to be explicitly transferred to MA.

Development and Application of Interactive College English Mobile learning Platform

Abstract： For the feature of Android system, a college English interactive platform is designed in this paper. According to the designing rules of study interface, design principles and learning function design of learning interaction, corresponding rules are set first. Then the overall system structure are analyzed and sub-modules of system are designed. whicb is packaged each. The database of system is also designcd and detailed realization scheme is provided. During the process of application, the fimction module is realized respectively and all the modules get organic combination by module calling. the system performance test indicate thai our scheme can satisfy the demand of users and it improve the study efficiency for graduates in interactive English learning.

Lethal Autonomous Weapon Systems and Responsibility Gaps

This paper argues that delegation of lethal decisions to autonomous weapon systems opens an unacceptable responsibility gap, which cannot be effectively countered unless we enforce a preemptive ban on lethal autonomous weapon systems （LAWS）. Initially, the promises and perils of artificial intelligence are brought forward in pointing out （1） that it remains an open question whether moral decision making, understood as situated ethical judgement, is computationally tractable, and （2） that the kind of artificial intelligence, which would be required to cause ethical reasoning, would imply a system capable of operating as an independent reasoner in novel contexts （sec. 2）. In continuation thereof, issues of responsibility are discussed （sec. 3 and 3.1） and it is claimed that unacceptable responsibility gaps may occur since unpredictability would presumably follow full system autonomy. These circumstances call for a strong precautionary principle, in the form of a preemptive ban.