Using a virtual environment to assess cognition in the elderly

Early diagnosis of Alzheimer’s disease (AD) is essential if treatments are to be administered at an earlier point in time before neurons degenerate to a stage beyond repair. In order for early detection to occur tools used to detect the disorder must be sensitive to the earliest of cognitive impairments. Virtual reality technology offers opportunities to provide products which attempt to mimic daily life situations, as much as is possible, within the computational environment. This may be useful for the detection of cognitive difficulties. We develop a virtual simulation designed to assess visuospatial memory in order to investigate cognitive function in a group of healthy elderly participants and those with a mild cognitive impairment (MCI). Participants were required to guide themselves along a virtual path to reach a virtual destination which they were required to remember. The preliminary results indicate that this virtual simulation has the potential to be used for detection of early AD since significant correlations of scores on the virtual environment with existing neuropsychological tests were found. Furthermore, the test discriminated between healthy elderly participants and those with a MCI.     

Covering photo-realistic properties of outdoor components with the effects of sky color in mixed reality

Outdoor rendering is an attractive topic in computer graphics. In this paper our main concern is to reveal the interaction between sky color and virtual objects in Mixed Reality environments. Although registration and tracking are two of the main issues in building effective Augmented Reality (AR) systems the creation of more realistic virtual objects indistinguishable from their real-world counterparts is our target which is currently the ultimate goal in AR. Two classes of sky color generation are employed to reveal the outdoor-element interaction. Virtual Sky Modelling (VSM) based on the Perez Model is capable of generating the sky color in a specific location, date and time. The second technique is to generate a virtual model based on the real image of the sky which is called in this paper Real Sky Modelling (RSM). Subsequently, preprocessing of the sky color bleeding is based on the radiosity technique to give the sky color effect to the virtual objects as well as the real ones. Through designing a test AR set-up and applying software and hardware the goal of a robust generation of realistic virtual objects with effect of sky color is achieved.     

A quadratic spline approximation using detail multi-layer for soft shadow generation in augmented reality

Implementation of shadows is crucial to enhancement of images in AR environments. Without shadows, virtual objects would look floating over the scene resulting in unrealistic rendering of AR environments. Casting hard shadows would provide only spatial information while soft shadows help improve realism of AR environments. Several algorithms have been proposed to render realistic shadows which often incurred high computational costs. Little attention has been directed towards the balanced trade-off between shadow quality and computational costs. In this study, two approaches are proposed: Quadratic Spline Interpolation (QSI) to soften the outline of the shadow and Detail Multi-Layer (DML) technique to optimize the volume of computations for the generation of soft shadows based on real light sources. QSI estimates boarder hard shadow samples while DML involves three main phases: real light sources estimation, soft shadow production and reduction of the complexity of 3-Dimensional objects’ shadows. To be more precise, a reflective hemisphere is used to capture real light and to create an environment map. The Median Cut algorithm is implemented to locate the direction of real light sources on the environment map. Subsequently, the original hard shadows are retrieved and a sample of multilayer hard shadows is produced where each layer has its unique size and colour. These layers overlap to produce soft shadows based on the real light sources’ directions. Finally, the Level of Details (LOD) algorithm is implemented to increase the efficiency of soft shadows by decreasing the complexity of vertex transformations. The proposed technique is tested using three samples of multilayer hard shadows with varying numbers of light sources generated from the Median Cut algorithm. The experimental results show that the proposed technique successfully produces realistic soft shadows at low computational costs.     

Modification of oil palm empty fruit bunches with maleic anhydride: The effect on the tensile and dimensional stability properties of empty fruit bunch/polypropylene composites

Oil palm empty fruit bunch (EFB)‐filled polypropylene (PP) composites were produced. The EFB filler was chemically modified with maleic anhydride (MAH). The effects of the filler size and chemical modification of EFBs on the tensile and dimensional stability properties of EFB–PP composites were studied. The composites with MAH‐treated EFBs showed higher tensile strengths than those with untreated EFBs. This was attributed to the enhanced compatibility between the MAH‐treated EFBs and PP matrix, as shown in a scanning electron microscopy study. Fourier transform infrared analysis showed evidence of C?C and C?O bonds from MAH at 1630 and 1730 cm^?1, respectively. The MAH‐treated PP composites showed lower water absorption and thickness swelling than those with untreated EFBs. © 2002 Wiley Periodicals, Inc. J Appl Polym Sci 87: 827–835, 2003     

On the in‐situ polymerization of cyclic butylene terephthalate oligomers: DSC and rheological studies

The thermal and rheological behaviors of cyclic butylene terephthalate (CBT) were studied with differential scanning calorimetry (DSC) and plate–plate rheometry, respectively. DSC scans were taken at different heating rates. The related first‐heat thermograms indicated crystallization and melting of the resulting poly (butylene terephthalate) (PBT) only at very low heating rate (0.5°C/min). As the crystallization and melting enthalpies were closely matched, one could conclude that the polymerization is essentially athermic. The polymerization was accompanied by a steep increase of the melt viscosity in isothermal rheological tests performed in the temperature range T = 145–210°C. Changes in the viscoelasticity of the polymerizing CBT and crystallizing PBT could be best followed by considering the changes in the phase angle. Viscosity increased with the conversion exponentially in the first approximation. POLYM. ENG. SCI., 46:743–750, 2006. © 2006 Society of Plastics Engineers     

Robust face recognition against expressions and partial occlusions

Facial features under variant-expressions and partial occlusions could have degrading effect on overall face recognition performance. As a solution, we suggest that the contribution of these features on final classification should be determined. In order to represent facial features contribution according to their variations, we propose a feature selection process that describes facial features as local independent component analysis(ICA) features. These local features are acquired using locally lateral subspace(LLS) strategy.Then, through linear discriminant analysis(LDA) we investigate the intraclass and interclass representation of each local ICA feature and express each feature s contribution via a weighting process. Using these weights, we define the contribution of each feature at local classifier level. In order to recognize faces under single sample constraint, we implement LLS strategy on locally linear embedding(LLE) along with the proposed feature selection. Additionally, we highlight the efficiency of the implementation of LLS strategy. The overall accuracy achieved by our approach on datasets with different facial expressions and partial occlusions such as AR, JAFFE,FERET and CK+ is 90.70%. We present together in this paper survey results on face recognition performance and physiological feature selection performed by human subjects.     

Employing both gender and emotion cues to enhance speaker identification performance in emotional talking environments

Speaker recognition performance in emotional talking environments is not as high as it is in neutral talking environments. This work focuses on proposing, implementing, and evaluating a new approach to enhance the performance in emotional talking environments. The new proposed approach is based on identifying the unknown speaker using both his/her gender and emotion cues. Both Hidden Markov Models (HMMs) and Suprasegmental Hidden Markov Models (SPHMMs) have been used as classifiers in this work. This approach has been tested on our collected emotional speech database which is composed of six emotions. The results of this work show that speaker identification performance based on using both gender and emotion cues is higher than that based on using gender cues only, emotion cues only, and neither gender nor emotion cues by 7.22 %, 4.45 %, and 19.56 %, respectively. This work also shows that the optimum speaker identification performance takes place when the classifiers are completely biased towards suprasegmental models and no impact of acoustic models in the emotional talking environments. The achieved average speaker identification performance based on the new proposed approach falls within 2.35 % of that obtained in subjective evaluation by human judges.     

Color image segmentation using adaptive unsupervised clustering approach

This paper presents the Region Splitting and Merging-Fuzzy C-means Hybrid Algorithm (RFHA), an adaptive unsupervised clustering approach for color image segmentation, which is important in image analysis and in understanding pattern recognition and computer vision field. Histogram thresholding technique is applied in the formation of all possible cells, used to split the image into multiple homogeneous regions. The merging technique is applied to merge perceptually close homogeneous regions and obtain better initialization for the Fuzzy C-means clustering approach. Experimental results have demonstrated that the proposed scheme could obtain promising segmentation results, with 12% average improvement in clustering quality and 63% reduction in classification error compared with other existing segmentation approaches.     

A multi-objective strategy in genetic algorithms for gene selection of gene expression data

A microarray machine offers the capacity to measure the expression levels of thousands of genes simultaneously. It is used to collect information from tissue and cell samples regarding gene expression differences that could be useful for cancer classification. However, the urgent problems in the use of gene expression data are the availability of a huge number of genes relative to the small number of available samples, and the fact that many of the genes are not relevant to the classification. It has been shown that selecting a small subset of genes can lead to improved accuracy in the classification. Hence, this paper proposes a solution to the problems by using a multiobjective strategy in a genetic algorithm. This approach was tried on two benchmark gene expression data sets. It obtained encouraging results on those data sets as compared with an approach that used a single-objective strategy in a genetic algorithm. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Selecting informative genes from microarray data by using hybrid methods for cancer classification

Gene expression technology, namely microarrays, offers the ability to measure the expression levels of thousands of genes simultaneously in biological organisms. Microarray data are expected to be of significant help in the development of an efficient cancer diagnosis and classification platform. A major problem in these data is that the number of genes greatly exceeds the number of tissue samples. These data also have noisy genes. It has been shown in literature reviews that selecting a small subset of informative genes can lead to improved classification accuracy. Therefore, this paper aims to select a small subset of informative genes that are most relevant for cancer classification. To achieve this aim, an approach using two hybrid methods has been proposed. This approach is assessed and evaluated on two well-known microarray data sets, showing competitive results. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008