Efficient implementation of a generalized polak-ribière algorithm for nonlinear optimization

We have recently developed a new conjugate gradient type method, the Generalized Polak-Ribière (GPR) method, for unconstrained minimization. It is based on search directions that are parallel to the Newton direction of the restriction of the objective function f on the two dimensional subspace span{?g p}, with p a suitable direction in span{? g,s^?}, where g and s ^? are the current gradient and previous search direction respectively. The new approach proved to be considerably more efficient than the original Polak-Ribière method.

In this paper, various implementations of the GPR method are compared with a currently available standard NAG software routine and also with the Nocedal, Buckley-LeNir and Shanno's limited memory algorithms. The results demonstrate the general effectiveness of the new algorithm. We also give a very brief discussion of extensions of the GPR method that generate search directions parallel to Newton directions in subspaces of dimension greater than two.     

Inverse problem of fracture mechanics for a circular disc under mixed boundary conditions

Solution method for the problem of prevention of early brittle fracture of a circular disc with mixed boundary conditions was proposed. Theoretical analysis on determination of normal displacement of points on the boundary of a circular disc weakened by arbitrarily allocated rectilinear cracks was carried out. A closed system of algebraic equations permitting to provide minimization of fracture parameters (stress intensity factors) subject to geometrical and mechanical characteristics of a disc was constructed. Minimization of the stress intensity factors in a circular disc was carried out. They found normal displacement of points on the boundary of the circular disc increases carrying capacity of the disc.     

On the point of truncation of bayes sequential tests for a discrete univariate distribution of the exponential type

A theoretical result due to S. N. Ray (1965) and Mann and Bratcher (1979) is refined and applied to several discrete one dimensional univariate distributions of the exponential type. In these cases a means of obtaining upper bounds to the exact stage of truncation of a Bayes sequential test is given.     

船用相继增压柴油机高温燃气阀的设计

论述了船用柴油机相继增压系统高温燃气阀及其执行机构的工况条件、设计要求和结构特点,介绍了阀门性能测试用相关标准和方法。     

MILP-based initialization strategies for the optimal design of water-using networks

The optimal design of water-using systems involves necessarily the exploitation of all possible water reuse and recycling alternatives. The general problem can be formulated as a non-convex nonlinear program (NLP), but due to the presence of bilinear terms, it may be difficult for local optimization solvers to attain global optimal solutions. To overcome this difficulty, this paper presents two mixed integer linear programming (MILP)-based procedures to generate a few structurally different starting points for the NLP. In both, the problem is decomposed into calculation stages by assuming that the water streams progress in series through the water-using units, with the binary variables selecting which unit belongs to a certain stage. Their main difference concerns the way fixed flowrate units are handled, either separately or in conjunction with a fixed load operation, since the former comprise a linear subsystem. The two algorithms are compared to a closely related LP-based method taken from the literature and to the one employed by the global optimization solver BARON. The results from a large set of example problems confirm their effectiveness in avoiding local solutions despite the small number of starting points. In contrast to the previous method they are easily scalable and, for some of the larger problems, could find better solutions than BARON with significantly fewer computational resources. The results have also shown that the option of tackling one unit at a time is the most favorable.     

A type of isomorphism between linear and nonlinear signature analyzers

It is proved that an automaton that is state and input isomorphic to a linear primitive automaton is only state isomorphic to the latter automaton. A criterion of state isomorphism between an irredundant signature analyzer (SA) and some linear SA with the zero initial state is found. This work was supported by the Russian Foundation for Basic Research under grant 98-01-00113. Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 41–46, July–August, 2000.     

带趋势序贯指示模拟方法在东濮凹陷薄砂岩储层预测中的应用

带趋势序贯指示模拟方法是一种基于地质统计学的随机模拟方法，其基础工作是三维地震资料精细解释和测井资料的标准化处理。实现此方法的主要步骤中，除了井约束波阻抗反演的子波提取、层位精细标定、地质框架模型建立、波阻抗反演约束参数选取以外，还有单井岩性曲线的形成、趋势模型建立、储层参数空间分布规律和空间相关性分析，以及储层参数模型的可靠性评价与优选等。与井约束波阻抗反演相比，该方法不仅使纵向分辨率明显提高，能精细地刻画储层特征，而且可对储层参数空间分布的非均质性和不确定性进行定量评价。对东濮凹陷QB块的应用表明，该方法查清了该区有利的含油气砂体分布范围及厚度的空间变化规律。     

Calculation of the probability of trouble-free operation of a main oil pipeline by an analytical-statistical method (a sequential model)

A serial model of a main oil pipeline system is investigated. Lifetime and repair time distribution functions of components are assumed to be of a general form. A new analytical-statistical method, enabling one to construct high-acuracy estimates and to evaluate the contribution of every component to system failure, is proposed. A numerical example is given. Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 132–145, July–August, 2000.     

Integration of discriminative and generative models for activity recognition in smart homes

Activity recognition in smart homes enables the remote monitoring of elderly and patients. In healthcare systems, reliability of a recognition model is of high importance. Limited amount of training data and imbalanced number of activity instances result in over-fitting thus making recognition models inconsistent. In this paper, we propose an activity recognition approach that integrates the distance minimization (DM) and probability estimation (PE) approaches to improve the reliability of recognitions. DM uses distances of instances from the mean representation of each activity class for label assignment. DM is useful in avoiding decision biasing towards the activity class with majority instances; however, DM can result in over-fitting. PE on the other hand has good generalization abilities. PE measures the probability of correct assignments from the obtained distances, while it requires a large amount of data for training. We apply data oversampling to improve the representation of classes with less number of instances. Support vector machine (SVM) is applied to combine the outputs of both DM and PE, since SVM performs better with imbalanced data and further improves the generalization ability of the approach. The proposed approach is evaluated using five publicly available smart home datasets. The results demonstrate better performance of the proposed approach compared to the state-of-the-art activity recognition approaches.     

A note on the CFR inequality for sequential estimation

Considering the regu1ar j.i.d. case, this note points out that Govindarajalu and Vincze(1989) are mistaken in claiming that their lower bound for the variance of sequential estimators is better than that of Wolfowitz (1847) by showing that the two bounds are identical.