Handwriting style classification

This paper describes an independent handwriting style classifier that has been designed to select the best recognizer for a given style of writing. For this purpose a definition of handwriting legibility has been defined and a method implemented that can predict this legibility. The technique consists of two phases. In the feature-extraction phase, a set of 36 features is extracted from the image contour. In the classification phase, two nonparametric classification techniques are applied to the extracted features in order to compare their effectiveness in classifying words into legible, illegible, and middle classes. In the first method, a multiple discriminant analysis (MDA) is used to transform the space of extracted features (36 dimensions) into an optimal discriminant space for a nearest mean based classifier. In the second method, a probabilistic neural network (PNN) based on the Bayes strategy and nonparametric estimation of probability density function is used. The experimental results show that the PNN method gives superior classification results when compared with the MDA method. For the legible, illegible, and middle handwriting the method provides 86.5% (legible/illegible), 65.5% (legible/middle), and 90.5% (middle/illegible) correct classification for two classes. For the three-class legibility classification the rate of correct classification is 67.33% using a PNN classifier.Received: 6 September 2002, Accepted: 19 September 2002, Published online: 6 June 2003     

A SOCIOLOGICAL PERSPECTIVE ON THE REORDERING PROBLEM IN MULTIPATH ROUTING

The term multipath routing means using multiple paths concurrently to transport data over network. The main problem of this routing scheme is the difference among the delays of selected paths, which causes reordering of a single flow's packets. In this paper, this problem is analyzed through a sociological perspective. We show that reordering problem is not inherently related to multipath routing, rather caused by the dominant capitalist view of the problem. then, the problem is addressed through a Marxism perspective. We theoretically prove that by this perspective, there exists a routing scheme that minimizes latency and also the requirement of buffering at receiver.     

Determination of the flow stress of five AHSS sheet materials (DP 600, DP 780, DP 780-CR,DP 780-HY and TRIP 780) using the uniaxial tensile and the biaxial Viscous Pressure Bulge (VPB) tests

Room temperature uniaxial tensile and biaxial Viscous Pressure Bulge (VPB) tests were conducted for five Advanced High Strength Steels (AHSS) sheet materials, and the resulting flow stress curves were compared. Strain ratios (R-values) were also determined in the tensile test and used to correct the biaxial flow stress curves for anisotropy. The pressure vs. dome height raw data in the VPB test was extrapolated to the burst pressure to obtain the flow stress curve until fracture. Results of this work show that the flow stress data can be obtained to higher strain values under biaxial state of stress. Moreover, it was observed that some materials behave differently if subjected to different state of stress. These two conclusions, and the fact that the state of stress in actual stamping processes is almost always biaxial, suggest that the bulge test is a more suitable test for obtaining the flow stress of AHSS sheet materials for use as an input to Finite Element (FE) simulation models.     

Holographic memory-based Bayesian optimization algorithm (HM-BOA) in dynamic environments

This paper presents a new evolutionary dynamic optimization algorithm, holographic memory-based Bayesian optimization algorithm (HM-BOA), whose objective is to address the weaknesses of sequential memory-based dynamic optimization approaches. To this end, holographic associative neural memory is applied to one of the recent successful memory-based evolutionary methods, DBN-MBOA (memory-based BOA with dynamic Bayesian networks). Holographic memory is appropriate for encoding environmental changes since its stimulus and response data are represented by a vector of complex numbers such that the phase and the magnitude denote the information and its confidence level, respectively. In the learning process in HM-BOA, holographic memory is trained by probabilistic models at every environmental change. Its weight matrix contains abstract information obtained from previous changes and is used for constructing a new probabilistic model when the environment changes. The unique features of HM-BOA are: 1) the stored information can be generalized, and 2) a small amount of memory is required for storing the probabilistic models. Experimental results adduce grounds for its effectiveness especially in random environments.     

Sentinel 2 analysis of turbidity retrieval models in inland water bodies: The case study of Jordanian dams

This study investigates the potential of using Sentinel 2 multispectral satellite images to develop turbidity retrieval models and further estimate the turbidity values of inland water bodies in Jordan. Traditionally, laboratory analysis has been used to assess surface water quality, which is expensive, time-consuming, and requires accessing the field physically. In contrast, remote sensing technologies can detect the water contaminant level at a consistent spatial and temporal coverage. Turbidity is an essential indicator of inland water quality as it directly reflects under-water light penetration. This study was held in three Jordanian dams, King Talal Dam, Mujib Dam, and Wadi Al Arab Dam, which vary in their water quality level. Twenty water samples were collected from each dam. Forty samples were used to calibrate the models, and the rest samples were used to validate the predictive models. The results show that Sentinel 2 near-infrared band to green band (B8/B3) achieved high fitting accuracies with R² = 0.832 and root mean square error (RMSE) = 1.123 NTU. Overall, this study has demonstrated the ability of Sentinel 2 data to estimate the turbidity in different ranges of inland water bodies’ quality and indicates that remote sensing can be used as an efficient tool for monitoring inland water quality. This study presents empirical data that could act as a platform to extend future work to cover more sites and contexts.     

An Improved Algorithm for Multibridge Network Reduction

A simplified method for determining the numeric reliability of a complex network is presented. Many methods developed for systems with specific configuration require lengthy transformation or reduction procedure. The reliability of multibridge complex systems with independent components can be evaluated by using conditional probabilities for reliability of the connecting components between the intermediate vertices. An algorithm (COMPLEX) is designed for the reliability computation of multibridge network systems, and a Fortran program is given based on this algorithm.     

Probabilistic Models of Damaging Deflections for Floor Elements

In this paper a number of serviceability issues related mainly to excessive deflections of structural floor elements (beams and slabs) are discussed. Field data of serviceability damage caused by excessive deflections of structural floor elements have been collected from various sources and probabilistic models are developed. Current serviceability specifications for allowable deflection limits in Australian, U.S., and other concrete structure codes have been compared against these probabilistic distributions of damaging deflections. Preliminary results confirm that allowable deflection limits in these design codes represent realistic lower-bound values of damaging deflections.     

高等化工院校污染生态学课程教学实践

课题组对华东理工大学环境科学与工程专业平台课程“污染生态学”教学实践进行了探索性研究。本文对课程的发展思路、师资队伍和实验室建设、教学方法和教学管理改革措施等方面分别作了介绍，并对未来工作重点进行了展望。