An investigation into the use of physical modelling for the prediction of various feature types visible from different view points

This paper describes a general purpose flexible technique which uses physical modelling techniques for determining the features of a 3D object that are visible from any predefined view. Physical modelling techniques are used to determine which of many different types of features are visible from a complete set of viewpoints. The power of this technique lies in its ability to detect and parameterise object features, regardless of object complexity. Raytracing is used to simulate the physical process by which object features are visible so that surface properties (eg specularity, transparency) as well as object boundaries can be used in the recognition process. Using this technique occluding and non-occluding edge based features are extracted using image processing techniques and then parameterised. Features caused by specularity are also extracted and qualitative descriptions for these are defined.

On the classification of image features

While the primary purpose of edge detection schemes is to be able to produce an edge map of a given image, the ability to distinguish between different feature types is also of importance. In this paper we examine feature classification based on local energy detection and show that local energy measures are intrinsically capable of making this classification because of the use of odd and even filters. The advantage of feature classification is that it allows for the elimination of certain feature types from the edge map, thus simplifying the task of object recognition.

Learning sparse latent representation and distance metric for image retrieval

The performance of image retrieval depends critically on the semantic representation and the distance function used to estimate the similarity of two images. A good representation should integrate multiple visual and textual (e.g., tag) features and offer a step closer to the true semantics of interest (e.g., concepts). As the distance function operates on the representation, they are interdependent, and thus should be addressed at the same time. We propose a probabilistic solution to learn both the representation from multiple feature types and modalities and the distance metric from data. The learning is regularised so that the learned representation and information-theoretic metric will (i) preserve the regularities of the visual/textual spaces, (ii) enhance structured sparsity, (iii) encourage small intra-concept distances, and (iv) keep inter-concept images separated. We demonstrate the capacity of our method on the NUS-WIDE data. For the well-studied 13 animal subset, our method outperforms state-of-the-art rivals. On the subset of single-concept images, we gain 79:5% improvement over the standard nearest neighbours approach on the MAP score, and 45.7% on the NDCG.

Fault detection in a cold forging process through feature extraction with a neural network

This paper investigates the application of neural networks to the recognition of lubrication defects typical to an industrial cold forging process employed by fastener manufacturers. The accurate recognition of lubrication errors, such as coating not being applied properly or damaged during material handling, is very important to the quality of the final product in fastener manufacture. Lubrication errors lead to increased forging loads and premature tool failure, as well as to increased defect sorting and the re-processing of the coated rod. The lubrication coating provides a barrier between the work material and the die during the drawing operation; moreover it needs be sufficiently robust to remain on the wire during the transfer to the cold forging operation. In the cold forging operation the wire undergoes multi-stage deformation without the application of any additional lubrication. Four types of lubrication errors, typical to production of fasteners, were introduced to a set of sample rods, which were subsequently drawn under laboratory conditions. The drawing force was measured, from which a limited set of features was extracted. The neural network based model learned from these features is able to recognize all types of lubrication errors to a high accuracy. The overall accuracy of the neural network model is around 98% with almost uniform distribution of errors between all four errors and the normal condition.

Use of log polar space for foveation and feature recognition

The finding and maintaining of high accuracy foveation points for several types of recognised feature in log polar space such as a line, circular or elliptical arc is considered. Log polar space is preferred over cartesian space as it provides a high resolution and a wide viewing angle; feature invariance in the fovea simplifies foveation; it allows multi-resolution analysis; and rotation and scale are linear translations in log polar space.

2-D edge feature extraction to subpixel accuracy using the generalized energy approach

Precision edge feature extraction is a very important step in vision, Researchers mainly use step edges to model an edge at subpixel level. In this paper we describe a new technique for two dimensional edge feature extraction to subpixel accuracy using a general edge model. Using six basic edge types to model edges, the edge parameters at subpixel level are extracted by fitting a model to the image signal using least-.squared error fitting technique.

Using feature selection for intrusion detection system

A good intrusion system gives an accurate and efficient classification results. This ability is an essential functionality to build an intrusion detection system. In this paper, we focused on using various training functions with feature selection to achieve high accurate results. The data we used in our experiments are NSL-KDD. However, the training and testing time to build the model is very high. To address this, we proposed feature selection based on information gain, which can detect several attack types with high accurate result and low false rate. Moreover, we executed experiments to category each of the five classes (probe, denial of service (DoS), user to super-user (U2R), and remote to local (R2L), normal). Our proposed outperform other state-of-art methods.

Stable feature selection for clinical prediction: Exploiting ICD tree structure using Tree-Lasso

Modern healthcare is getting reshaped by growing Electronic Medical Records (EMR). Recently, these records have been shown of great value towards building clinical prediction models. In EMR data, patients' diseases and hospital interventions are captured through a set of diagnoses and procedures codes. These codes are usually represented in a tree form (e.g. ICD-10 tree) and the codes within a tree branch may be highly correlated. These codes can be used as features to build a prediction model and an appropriate feature selection can inform a clinician about important risk factors for a disease. Traditional feature selection methods (e.g. Information Gain, T-test, etc.) consider each variable independently and usually end up having a long feature list. Recently, Lasso and related l1-penalty based feature selection methods have become popular due to their joint feature selection property. However, Lasso is known to have problems of selecting one feature of many correlated features randomly. This hinders the clinicians to arrive at a stable feature set, which is crucial for clinical decision making process. In this paper, we solve this problem by using a recently proposed Tree-Lasso model. Since, the stability behavior of Tree-Lasso is not well understood, we study the stability behavior of Tree-Lasso and compare it with other feature selection methods. Using a synthetic and two real-world datasets (Cancer and Acute Myocardial Infarction), we show that Tree-Lasso based feature selection is significantly more stable than Lasso and comparable to other methods e.g. Information Gain, ReliefF and T-test. We further show that, using different types of classifiers such as logistic regression, naive Bayes, support vector machines, decision trees and Random Forest, the classification performance of Tree-Lasso is comparable to Lasso and better than other methods. Our result has implications in identifying stable risk factors for many healthcare problems and therefore can potentially assist clinical decision making for accurate medical prognosis.

Feature nodes : an interaction construct for sharing initiative in design exploration

Exploration with formal design systems comprises an iterative process of specifying problems, finding plausible and alternative solutions, judging the validity of solutions relative to problems and reformulating problems and solutions. Recent advances in formal generative design have developed the mathematics and algorithms to describe and perform conceptual design tasks. However, design remains a human enterprise: formalisms are part of a larger equation comprising human computer interaction. To support the user in designing with formal systems, shared representations that interleave initiative of the designer and the design formalism are necessary. The problem of devising representational structures in which initiative is sometimes taken by the designer and sometimes by a computer in working on a shared design task is reported in this paper. To address this problem, the requirements, representation and
implementation of a shared interaction construct, the feature node, is
described. The feature node facilitates the sharing of initiative in formulating and reformulating problems, generating solutions, making
choices and navigating the history of exploration.

Weaning of Australian shortfin glass eels (Anguilla Australis): a comparison on the effectiveness of four types of fish roe

Eel culture is solely dependent on wild seed stock, caught in estuaries during the freshwater migratory phase as glass eels. The methods used for weaning glass eels are very variable, and range from the use of live zooplankton to fish roe to fines of commercial fish feeds. The present experiments were conducted on glass eels of the Australian shortfin eel, when the effectiveness of four types of readily available fish roe (European carp, mirror dory, orange roughy and warehou) were evaluated over a 42-day period, in the laboratory.

After 28 days the eels did not show an interest in orange roughy and mirror dory roe, and these two treatments were discontinued to avoid mortality. In all treatments there was a decrease in mean weight during this period, but the survival was over 99%. In the 28th to 42nd day period the mean weight and specific growth rate of glass eels reared on European carp and warehou roe increased, but the differences between these two treatments were not significant.

The physical features of the roe and the oocytes thereof, the proximate composition, amino acid and fatty acid composition indicated major differences amongst the roe types, particularly with regard to the amount of n−6 polyunsaturated fatty acids (PUFA) and the ratio of n−3 to n−6. European carp and warehou roe (and oocytes) had a significantly higher arachidonic acid (AA-20:4n−6; over 60% of PUFA) content and a considerably lower n−3 to n−6 ratio (n−3 to n−6 ratio being 1.32, 5.92, 3.77 and 2.67 for roe types, and 1.25, 4.83, 2.91 and 2.42 for oocytes, of European carp, mirror dory, orange roughy and warehou, respectively), than in the other two roe types. The fatty acid profiles of European carp and warehou roe were similar to that of metamorphosing glass eels.

Lipid and fatty acid digestibility of three oil types in the Australian shortfin eel, Anguilla australis

The lipid and fatty acid digestibilities of three semi-purified, isonitrogenous (48.9–50.8% protein) and isocalorific (19.1–20.8 kJ g⁻¹) diets, in which the lipid source was either cod liver oil (CLO), linseed oil (LO) or sunflower oil (SFO), were estimated in the Australian shortfin eel (Anguilla australis) using chromic oxide as an external marker. Apparent percent protein and energy digestibilities of the diets were not significantly (P>0.05) affected by the lipid source, but the lipid digestibility was. The percent apparent lipid digestibility was lowest in the LO diet (90.2±0.6) and highest in the CLO diet (95.6±0.2).

Not all the fatty acids present in any one diet were recovered in the faecal samples. In diets with CLO, only three saturates (out of five), five monoenes and six (out of 11) PUFAs were detected in faecal samples. With all the diets, 20:0 and 22:0, and none of the n−6 HUFA were detected in the faecal samples. The digestibility of all the fatty acids, except 18:3n−3, was lowest in the diet with LO, and significantly so (P>0.05) from the other diets.

In shortfin eel, there was a trend for the digestibility of saturated fatty acids of diets with the animal oil as the lipid source to decrease with increasing chain length, and in diets with vegetable oil to increase initially and then decrease. A somewhat comparable trend was also evident in respect of monoenes.

When the digestibility of different categories of fatty acids is considered, the digestibility of saturates, monoenes, unsaturates, n−6, PUFA, HUFA and total fatty acid digestibilities of LO diet were the lowest, and differed significantly (P<0.05) from those of the CLO and SFO diets, except in the case of n−3 fatty acids.

Some unusual applications of the `Error-bar` feature in Excel spreadsheets

This paper demonstrates how the "error-bar" feature can be used to extend the utility of "worldware" spreadsheet packages in producing high-quality graphs for university teaching and learning, and for research. To further utilize the advantages of spreadsheets in university education, this paper seeks to overcome some of the earlier reservations about the lack of scientific plotting capabilities of spreadsheet applications. Specific examples of educational material in the areas of enzyme kinetics, vibrational spectroscopy, vibronic spectroscopy, and mass spectrometry are discussed. It is argued that, where practical, university educators should use "worldware" packages to prepare teaching aids, since these would better prepare their students for future employment. The use of software features for purposes that were not envisioned by the programmers has additional educational benefits in fostering flexibility and innovation. Other graphing packages can also use the "error-bar" feature in a manner similar to that described here for Excel.