Intelligent animal fiber classification with artificial neural networks

Artificial neural networks (ANN) are increasingly used to solve many problems related to pattern recognition and object classification. In this paper, we report on a study using artificial neural networks to classify two kinds of animal fibers: merino and mohair. We have developed two different models, one extracting nine scale parameters with image processing, and the other using an unsupervised artificial neural network to extract features automatically, which are determined in accordance with the complexity of the scale structure and the accuracy of the model. Although the first model can achieve higher accuracy, it requires more effort for image processing and more prior knowledge, since the accuracy of the ANN largely depends on the parameters selected. The second model is more robust than the first, since only raw images are used. Because only ordinary optical images taken with a microscope are employed, we can use the approach for many textile applications without expensive equipment such as scanning electron microscopy.

Predicting worsted spinning performance with an artificial neural network model

For a given fiber spun to pre-determined yarn specifications, the spinning performance of the yarn usually varies from mill to mill. For this reason, it is necessary to develop an empirical model that can encompass all known processing variables that exist in different spinning mills, and then generalize this information and be able to accurately predict yarn quality for an individual mill. This paper reports a method for predicting worsted spinning performance with an artificial neural network (ANN) trained with backpropagation. The applicability of artificial neural networks for predicting spinning performance is first evaluated against a well established prediction and benchmarking tool (Sirolan YarnspecTM). The ANN is then subsequently trained with commercial mill data to assess the feasibility of the method as a mill-specific performance prediction tool. Incorporating mill-specific data results in an improved fit to the commercial mill data set, suggesting that the proposed method has the ability to predict the spinning performance of a specific mill accurately.

Predicting the pilling propensity of fabrics through artificial neural network modeling

Fabric pilling is affected by many interacting factors. This study uses artificial neural networks to model the multi-linear relationships between fiber, yarn and fabric properties and their effect on the pilling propensity of pure wool knitted fabrics. This tool shall enable the user to gauge the expected pilling performance of a fabric from a number of given inputs. It will also provide a means of improving current products by offering alternative material specification and/or selection. In addition to having the capability to predict pilling performance, the model will allow for clarification of major fiber, yarn and fabric attributes affecting fabric pilling.

Knowledge extraction from a mixed transfer function artificial neural network

One of the main problems with Artificial Neural Networks (ANNs) is that their results are not intuitively clear. For example, commonly used hidden neurons with sigmoid activation function can approximate any continuous function, including linear functions, but the coefficients (weights) of this approximation are rather meaningless. To address this problem, current paper presents a novel kind of a neural network that uses transfer functions of various complexities in contrast to mono-transfer functions used in sigmoid and hyperbolic tangent networks. The presence of transfer functions of various complexities in a Mixed Transfer Functions Artificial Neural Network (MTFANN) allow easy conversion of the full model into user-friendly equation format (similar to that of linear regression) without any pruning or simplification of the model. At the same time, MTFANN maintains similar generalization ability to mono-transfer function networks in a global optimization context. The performance and knowledge extraction of MTFANN were evaluated on a realistic simulation of the Puma 560 robot arm and compared to sigmoid, hyperbolic tangent, linear and sinusoidal networks.

Predicting the distribution of discrete spatial events using artificial neural networks

Although the development of geographic information system (GIS) technology and digital data manipulation techniques has enabled practitioners in the geographical and geophysical sciences to make more efficient use of resource information, many of the methods used in forming spatial prediction models are still inherently based on traditional techniques of map stacking in which layers of data are combined under the guidance of a theoretical domain model. This paper describes a data-driven approach by which Artificial Neural Networks (ANNs) can be trained to represent a function characterising the probability that an instance of a discrete event, such as the presence of a mineral deposit or the sighting of an endangered animal species, will occur over some grid element of the spatial area under consideration. A case study describes the application of the technique to the task of mineral prospectivity mapping in the Castlemaine region of Victoria using a range of geological, geophysical and geochemical input variables. Comparison of the maps produced using neural networks with maps produced using a density estimation-based technique demonstrates that the maps can reliably be interpreted as representing probabilities. However, while the neural network model and the density estimation-based model yield similar results under an appropriate choice of values for the respective parameters, the neural network approach has several advantages, especially in high dimensional input spaces.

Knowledge extraction from a mixed transfer function artificial neural network

One of the big problems with Artificial Neural Networks (ANN) is that their results are not intuitively clear. For example, if we use the traditional neurons, with a sigmoid activation function, we can approximate any function, including linear functions, but the coefficients (weights) in this approximation will be rather meaningless. To resolve this problem, this paper presents a novel kind of ANN with different transfer functions mixed together. The aim of such a network is to i) obtain a better generalization than current networks ii) to obtain knowledge from the networks without a sophisticated knowledge extraction algorithm iii) to increase the understanding and acceptance of ANNs. Transfer Complexity Ratio is defined to make a sense of the weights associated with the network. The paper begins with a review of the knowledge extraction from ANNs and then presents a Mixed Transfer Function Artificial Neural Network (MTFANN). A MTFANN contains different transfer functions mixed together rather than mono-transfer functions. This mixed presence has helped to obtain high level knowledge and similar generalization comparatively to monotransfer function nets in a global optimization context.

Artificial formation forces for stable aggregation of multi-agent system

This paper introduces, a robust and stable algorithm based on artificial formation forces, for multi-agent system (MAS) aggregation in 2D space. The MAS model with artificial forces; consists of inter-member collision avoidance element, formation generation element and a velocity based damping element; is analysed for stability and convergence. Computer simulations are used to illustrate stability and convergence, and to demonstrate effectiveness of the algorithm.

Geometric formations in swarm aggregation: an artificial formation force based approach

Cooperative control of multiple mobile robots is an attractive and challenging problem which has drawn considerable attention in the recent past. This paper introduces a scalable decentralized control algorithm to navigate a group of mobile robots (swarm) into a predefined shape in 2D space. The proposed architecture uses artificial forces to control mobile agents into the shape and spread them inside the shape while avoiding inter-member collisions. The theoretical analysis of the swarm behavior describes the motion of the complete swarm and individual members in relevant situations. We use computer simulated case studies to verify the theoretical assertions and to demonstrate the robustness of the swarm under external disturbances such as death of agents, change of shape etc.

Learning to detect texture objects by artificial immune approaches

This paper introduces a novel method to detect texture objects from satellite images. First, a hierarchical strategy is developed to extract texture objects according to their roughness. Then, an artificial immune approach is presented to automatically generate segmentation thresholds and texture filters, which are used in the hierarchical strategy. In this approach, texture objects are regarded as antigens, and texture object filters and segmentation thresholds are regarded as antibodies. The clonal selection algorithm inspired by human immune system is employed to evolve antibodies. The population of antibodies is iteratively evaluated according to a statistical performance index corresponding to object detection ability, and evolves into the optimal antibody using the evolution principles of the clonal selection. Experimental results of texture object detection on satellite images are presented to illustrate the merit and feasibility of the proposed method.

The effect of artificial defects on the compressive properties of hollow sphere cellular aluminium (HSCA)

Hollow sphere cellular aluminium (HSCA) samples were fabricated by bonding together two kinds of single aluminium hollow spheres with the same outside diameter of 4 mm but different wall thicknesses of 0.1 mm and 0.3 mm, in which the hollow spheres with the thinner sphere wall thickness were used as artificial defects. Four types of HSCA samples with the same relative density but various distributions of artificial defects were prepared by simple cubic packing. For comparing, HSCA sample without defective hollow spheres inside was also prepared. The effects of the distribution of the artificial defects on the deformation behaviours and mechanical properties were investigated by compressive tests. Results indicated that the nominal stress - nominal strain curve and the deformation behavior of the HSCA samples varied with the distribution of the artificial defects in spite of the same relative density. It is therefore suggested that the deformation behavior and mechanical property of cellular materials were also significantly affected by the distribution of defects. In particular, the plateau stress of the HSCA samples increased with the decrease in number of contact points between the normal hollow spheres and the defective hollow spheres in the loading direction during deformation.

Improving the quality of die castings by using artificial neural networks for porosity defect modelling

The aim of this work is to improve the quality of castings by minimizing defects and scrap through the analysis of the data generated by High Pressure Die Casting (HPDC) Machines using computational intelligence techniques. Casting is a complex process that is affected by the interdependence of die casting process parameters on each other such that changes in one parameter results in changes in other parameters. Computational intelligence techniques have the potential to model accurately this complex relationship. The project has the potential to generate optimal configurations for HPDC Machines and explain the relationships between die casting process parameters.

The use of artificial biofilms to strip nutrients from an industrial smelters waste water under conditions of low temperature and high pH

The Victorian Environment Protection Authority (EPA) has identified Alcoa’s Point Henry aluminium smelter as being a major source of recognized pollutant input due to its disposal of effluent into Corio Bay. Historically, the water quality parameters that have most often exceeded Point Henry’s EPA limits have been pH and suspended solids from the smelter’s discharge points. These waste water discharges also experience high nitrogen and phosphorus concentrations which result in algal blooms that occur at the onset of warm weather. The main hypothesis of this study was that “prevention of algal blooming with the onset of warm weather by removal of nutrients during the cooler months, and continued removal thereafter, is better than curing the problems chemically”. Biofilms have been used to remove nutrients from waste waters, but not under the conditions experienced at Point Henry. The aim of this study, therefore, was to determine if significant biofilm growth would be observed on floating structures suspended in the Point Henry waste water stream during the cooler, winter months of the year. Statistically significant biofilm growth occurred on all suspended structures in all discharge ponds during the winter and early spring of 2000. The use of suspended structures, such as AquaMatTM, as an artificial substrate to attract and support periphyton and bacterial communities (biofilms), which are then able to out-compete phytoplankton communities for available nutrients, is therefore a viable option for the Point Henry smelter. However, further research on the competitive performance of biofilms in the Point Henry ponds during the summer months is required before adequate biofilm management strategies can be developed.

Constructing artificial images of facial expressions

This paper presents a method for construction of artificial images of facial expressions. The proposed fractal-based synthesis procedure called pixel-based correspondence works on 2D images and does not require any depth information. This method can generate artificial images of an object when only a single image is given. Using the proposed method, effective example-based facial analysis systems can be trained and utilised in various applications.

Artificial hand - from a robotic perspective

The human hand provides proof that the anthropomorphic configuration, properly controlled, is successful and gives a target to aim at for artificial hand/robot hand researchers. In this paper we discuss the human hand physiology and grasp capabilities. We then provide design on a double thumb, two finger robotic hand. Architecture of the hand, fingers and their dynamic modelling is discussed. Finally, results are reported on the performance of a finger in the hand.