The dual-tree complex wavelet transform (DTCWT) solves the problems of shift variance and low directional selectivity in two and higher dimensions found with the commonly used discrete wavelet transform (DWT). It has been proposed for applications such as texture classification and content-based image retrieval. In this paper, the performance of the dual-tree complex wavelet transform for fabric defect detection is evaluated. As experimental samples, the fabric images from TILDA, a textile texture database from the Workgroup on Texture Analysis of the German Research Council (DFG), are used. The mean energies of real and imaginary parts of complex wavelet coefficients taken separately are identified as effective features for the purpose of fabric defect detection. Then it is shown that the use of the dual-tree complex wavelet transform yields greater performance as compared to the undecimated wavelet transform (UDWT) with a detection rate of 4.5% to 15.8% higher depending on the fabric type.

Unreliability of the data streams generated by RFID readers is among the primary factors which limit the widespread adoption of the RFID technology. RFID data cleaning is, therefore, an essential task in the RFID middleware systems in order to reduce reading errors, and to allow these data streams to be used to make a correct interpretation and analysis of the physical world they are representing. In this paper we propose an adaptive sliding-window based approach called WSTD which is capable of efficiently coping with both environmental variation and tag dynamics. Our experimental results demonstrate the efficacy of the proposed approach.

As the world is moving into the 4th Industrial revolution, commonly referred to as Industry 4.0, mass production is giving way to mass customization. This shift necessitates a change in the design of the assembly line with flexibility and multi variant manufacturing taking precedence. These kind of assembly lines that can manufacture multiple models without a predetermined manufacturing time are referred to as mixed model stochastic assembly lines. This paper looks at how such a mixed model stochastic assembly line can be modelled. This is done by taking the case study of a water bottling plant that is being developed at the university where this research is conducted. The water bottling plant needs to produce 500 ml and 750 ml bottles of clean drinking water which can be used within the university or be sold externally. The primary aim of this paper is to develop a MATLAB model for the water bottling plant and study the results from the simulations. These results will shed light on how the model can be optimized thereby contribute to the niche area of Mixed Model Stochastic Assembly Line Balancing.