A camera based digit location and recognition system for garment tracking

Garment information tracking is required for clean room garment management. In this paper, we present a camera-based robust system with implementation of Optical Character Reconition (OCR) techniques to fulfill garment label recognition. In the system, a camera is used for image capturing; an adaptive thresholding algorithm is employed to generate binary images; Connected Component Labelling (CCL) is then adopted for object detection in the binary image as a part of finding the ROI (Region of Interest); Artificial Neural Networks (ANNs) with the BP (Back Propagation) learning algorithm are used for digit recognition; and finally the system is verified by a system database. The system has been tested. The results show that it is capable of coping with variance of lighting, digit twisting, background complexity, and font orientations. The system performance with association to the digit recognition rate has met the design requirement. It has achieved real-time and error-free garment information tracking during the testing.

Comparison of extrasystolic ECG signal classifiers using discrete wavelet transforms

This work compares and contrasts results of classifying time-domain ECG signals with pathological conditions taken from the MITBIH arrhythmia database. Linear discriminant analysis and a multi-layer perceptron were used as classifiers. The neural network was trained by two different methods, namely back-propagation and a genetic algorithm. Converting the time-domain signal into the wavelet domain reduced the dimensionality of the problem at least 10-fold. This was achieved using wavelets from the db6 family as well as using adaptive wavelets generated using two different strategies. The wavelet transforms used in this study were limited to two decomposition levels. A neural network with evolved weights proved to be the best classifier with a maximum of 99.6% accuracy when optimised wavelet-transform ECG data wits presented to its input and 95.9% accuracy when the signals presented to its input were decomposed using db6 wavelets. The linear discriminant analysis achieved a maximum classification accuracy of 95.7% when presented with optimised and 95.5% with db6 wavelet coefficients. It is shown that the much simpler signal representation of a few wavelet coefficients obtained through an optimised discrete wavelet transform facilitates the classification of non-stationary time-variant signals task considerably. In addition, the results indicate that wavelet optimisation may improve the classification ability of a neural network. (c) 2005 Elsevier B.V. All rights reserved.

Simple adaptive momentum: new algorithm for training multilayer perceptrons

The speed of convergence while training is an important consideration in the use of neural nets. The authors outline a new training algorithm which reduces both the number of iterations and training time required for convergence of multilayer perceptrons, compared to standard back-propagation and conjugate gradient descent algorithms.

A combined engineering and statistical model of UK domestic appliance electrical load profiles

The development of a combined engineering and statistical Artificial Neural Network model of UK domestic appliance load profiles is presented. The model uses diary-style appliance use data and a survey questionnaire collected from 51 suburban households and 46 rural households during the summer of 2010 and2011 respectively. It also incorporates measured energy data and is sensitive to socioeconomic, physical dwelling and temperature variables. A prototype model is constructed in MATLAB using a two layer feed forward network with back propagation training which has a 12:10:24 architecture. Model outputs include appliance load profiles which can be applied to the fields of energy planning (microrenewables and smart grids), building simulation tools and energy policy.

Variability and trends in Laptev Sea ice outflow between 1992-2011

Variability and trends in seasonal and interannual ice area export out of the Laptev Sea between 1992 and 2011 are investigated using satellite-based sea ice drift and concentration data. We found an average total winter (Octo- ber to May) ice area transport across the northern and east- ern Laptev Sea boundaries (NB and EB) of 3.48 × 10 5 km 2 . The average transport across the NB (2.87 × 10 5 km 2 ) is thereby higher than across the EB (0.61 × 10 5 km 2 ), with a less pronounced seasonal cycle. The total Laptev Sea ice area flux significantly increased over the last decades (0.85 × 10 5 km 2 decade − 1 , p> 0 . 95), dominated by increas- ing export through the EB (0.55 × 10 5 km 2 decade − 1 , p> 0 . 90), while the increase in export across the NB is smaller (0.3 × 10 5 km 2 decade − 1 ) and statistically not significant. The strong coupling between across-boundary SLP gradient and ice drift velocity indicates that monthly variations in ice area flux are primarily controlled by changes in geostrophic wind velocities, although the Laptev Sea ice circulation shows no clear relationship with large-scale atmospheric in- dices. Also there is no evidence of increasing wind velocities that could explain the overall positive trends in ice export. The increased transport rates are rather the consequence of a changing ice cover such as thinning and/or a decrease in con- centration. The use of a back-propagation method revealed that most of the ice that is incorporated into the Transpolar Drift is formed during freeze-up and originates from the cen- tral and western part of the Laptev Sea, while the exchange with the East Siberian Sea is dominated by ice coming from the central and southeastern Laptev Sea. Furthermore, our re- sults imply that years of high ice export in late winter (Febru- ary to May) have a thinning effect on the ice cover, which in turn preconditions the occurence of negative sea ice extent anomalies in summer.

Evolving graphs: dynamical models, inverse problems and propagation

Applications such as neuroscience, telecommunication, online social networking, transport and retail trading give rise to connectivity patterns that change over time. In this work, we address the resulting need for network models and computational algorithms that deal with dynamic links. We introduce a new class of evolving range-dependent random graphs that gives a tractable framework for modelling and simulation. We develop a spectral algorithm for calibrating a set of edge ranges from a sequence of network snapshots and give a proof of principle illustration on some neuroscience data. We also show how the model can be used computationally and analytically to investigate the scenario where an evolutionary process, such as an epidemic, takes place on an evolving network. This allows us to study the cumulative effect of two distinct types of dynamics.

Tissue culture propagation alters plant-microbe interactions in tobacco rhizosphere

We have compared properties of roots from different lines (genotypes) of tobacco raised either in tissue culture or grown from seed. The different lines included unmodified plants and plants modified to express reduced activity of the enzyme cinnamoyl-CoA reductase, which has a pivotal role in lignin biosynthesis. The size and structure of the rhizosphere microbial community, characterized by adenosine triphosphate and phospholipid fatty acid analyses, were related to root chemistry (specifically the soluble carbohydrate concentration) and decomposition rate of the roots. The root material from unmodified plants decomposed faster following tissue culture compared with seed culture, and the faster decomposing material had significantly higher soluble carbohydrate concentrations. These observations are linked to the larger microbial biomass and greater diversity of the rhizosphere communities of tissue culture propagated plants.

Putting the pieces back together again: an illustration of the problem of interpreting development indicators using an African case study

Indicators are commonly recommended as tools for assessing the attainment of development, and the current vogue is for aggregating a number of indicators together into a single index. It is claimed that such indices of development help facilitate maximum impact in policy terms by appealing to those who may not necessarily have technical expertise in data collection, analysis and interpretation. In order to help counter criticisms of over-simplification, those advocating such indices also suggest that the raw data be provided so as to allow disaggregation into component parts and hence facilitate a more subtle interpretation if a reader so desires. This paper examines the problems involved with interpreting indices of development by focusing on the United Nations Development Programmes (UNDP) Human Development Index (HDI) published each year in the Human Development Reports (HDRs). The HDI was intended to provide an alternative to the more economic based indices, such as GDP, commonly used within neo-liberal development agendas. The paper explores the use of the HDI as a gauge of human development by making comparisons between two major political and economic communities in Africa (ECOWAS and SADC). While the HDI did help highlight important changes in human development as expressed by the HDI over 10 years, it is concluded that the HDI and its components are difficult to interpret as methodologies have changed significantly and the 'averaging' nature of the HDI could hide information unless care is taken. The paper discusses the applicability of alternative models to the HDI such as the more neo-populist centred methods commonly advocated for indicators of sustainable development. (C) 2003 Elsevier Ltd. All rights reserved.

Tissue culture propagation alters plant-microbe interactions in tobacco rhizosphere

We have compared properties of roots from different lines (genotypes) of tobacco raised either in tissue culture or grown from seed. The different lines included unmodified plants and plants modified to express reduced activity of the enzyme cinnamoyl-CoA reductase, which has a pivotal role in lignin biosynthesis. The size and structure of the rhizosphere microbial community, characterized by adenosine triphosphate and phospholipid fatty acid analyses, were related to root chemistry (specifically the soluble carbohydrate concentration) and decomposition rate of the roots. The root material from unmodified plants decomposed faster following tissue culture compared with seed culture, and the faster decomposing material had significantly higher soluble carbohydrate concentrations. These observations are linked to the larger microbial biomass and greater diversity of the rhizosphere communities of tissue culture propagated plants.