A genetic algorithm-based multi-objective optimization of an artificial neural network classifier for breast cancer diagnosis

The conventional technique for diagnosing the breast cancer disease relies on human experiences to identify the presence of certain pattern from the database. It is time-consuming and incurs unnecessary burden to radiologists. This work proposes a genetic algorithm-based multi-objective optimization of an Artificial Neural Network classifier, namely GA-MOO-NN, for the automatic breast cancer diagnosis. It performs a simultaneous search for the significant feature subsets and the optimum architecture of the network. The combination of ANN’s parameters with feature selection to be optimized by Genetic Algorithm is novel. The Pareto-optimality with new ranking approach is applied for simultaneous minimizations of two competing objectives: the number of network‘s connections and squared error percentage of the validation data. Result shows that the algorithm with the proposed combination of objectives has achieved the best and average, 98.85 and 98.10 % accuracy of classification, respectively, on breast cancer dataset which outperform most systems of other works found in the literature.     

Statistical Modeling of the 3D Geometry and Topology of Botanical Trees

We propose a framework for statistical modeling of the 3D geometry and topology of botanical trees. We treat botanical trees as points in a tree‐shape space equipped with a proper metric that captures the geometric and the topological differences between trees. Geodesics in the tree‐shape space correspond to the optimal sequence of deformations, i.e. bending, stretching, and topological changes, which align one tree onto another. In this way, the 3D tree modeling and synthesis problem becomes a problem of exploring the tree‐shape space either in a controlled fashion, using statistical regression, or randomly by sampling from probability distributions fitted to populations in the tree‐shape space. We show how to use this framework for (1) computing statistical summaries, e.g. the mean and modes of variations, of a population of botanical trees, (2) synthesizing random instances of botanical trees from probability distributions fitted to a population of botanical trees, and (3) modeling, interactively, 3D botanical trees using a simple sketching interface. The approach is fast and only requires as input 3D botanical tree models with a known upright orientation.     

Effects of Ageing on Selected Cooking Quality Parameters of Rice

Ageing can improve cooking quality of rice by influencing major cooking quality parameters i.e., kernel expansion, water absorption, alkali digestion value, and gelatinization temperature along with changes in internal structure of rice grains. In this research, the effects of natural and artificial ageing on the selected cooking quality parameters of two Malaysian rice cultivars, named Mahsuri and Puteri, were studied. A relation was observed between water absorption and elongation ratio in both varieties under different aging conditions. Alkali digestion value and gelatinization temperature were also influenced by varieties and ageing conditions. This study revealed the potentiality of ageing for the improvement of rice cooking quality.     

Kernel elongation in rice

Kernel elongation after cooking is an important character of fine rice and most rice consumers prefer length‐wise elongation. Although improvement of aromatic rice began early in the 1970s, until now the mechanisms and genetics of kernel elongation has remained unrevealed. Kernel elongation is considered as a physical phenomenon and is influenced by several physicochemical and genetic factors, including genotypes, aging temperature, aging time, water uptake, amylose content and gelatinization temperature. Recently the complete genetic map of fine rice has been created and the gene responsible for kernel length identified; moreover, this gene is tightly linked with the cooked kernel elongation trait. Several molecular markers linked with cooked kernel elongation have been developed. These tools will be helpful for the improvement of this important trait. For the proper study of cooked kernel elongation of rice, this review paper will provide the basis and directional materials for further studies.© 2012 Society of Chemical Industry     

Effect of foaming temperature and rubber grades on properties of natural rubber foams

Foaming temperature and grade of dry natural rubber were varied to evaluate their effects on the morphology and mechanical properties of natural rubber (NR) foams. Three different grades of NR were used; namely ENR‐25, SMR‐L, and SMR‐10. NR foams from these grades were produced at three different foaming temperatures, i.e. 140, 150, and 160°C. The study was carried out using formulated compositions containing sodium bicarbonate as the chemical blowing agent and were expanded using conventional compression molding technique via a heat transfer foaming process. The NR foams were characterized with respect to their relative foam density, density of crosslinking, cell size, compression stress, and compression set. Increase in foaming temperature resulted in lower relative density and larger cell size. It was also discovered that the crosslink density slightly decrease with increasing foaming temperature. For mechanical properties, the highest foam density resulted in the highest compression stress. Compression stress at 50% strain increased with increasing foaming temperature and ENR‐25 foam has the highest compression stress among the produced foams. The results showed that the morphology, physical, and mechanical properties of the rubber foams can be controlled closely by the foaming temperature and rubber grades. © 2007 Wiley Periodicals, Inc. J Appl Polym Sci, 2008     

The Proteomic Landscape of Resting and Activated CD4+ T Cells Reveal Insights into Cell Differentiation and Function

CD4+ T cells (T helper cells) are cytokine-producing adaptive immune cells that activate or regulate the responses of various immune cells. The activation and functional status of CD4+ T cells is important for adequate responses to pathogen infections but has also been associated with auto-immune disorders and survival in several cancers. In the current study, we carried out a label-free high-resolution FTMS-based proteomic profiling of resting and T cell receptor-activated (72 h) primary human CD4+ T cells from peripheral blood of healthy donors as well as SUP-T1 cells. We identified 5237 proteins, of which significant alterations in the levels of 1119 proteins were observed between resting and activated CD4+ T cells. In addition to identifying several known T-cell activation-related processes altered expression of several stimulatory/inhibitory immune checkpoint markers between resting and activated CD4+ T cells were observed. Network analysis further revealed several known and novel regulatory hubs of CD4+ T cell activation, including IFNG, IRF1, FOXP3, AURKA, and RIOK2. Comparison of primary CD4+ T cell proteomic profiles with human lymphoblastic cell lines revealed a substantial overlap, while comparison with mouse CD+ T cell data suggested interspecies proteomic differences. The current dataset will serve as a valuable resource to the scientific community to compare and analyze the CD4+ proteome.     

Photopyroelectric Spectroscopic Studies of ZnO-MnO(2)-Co(3)O(4)-V(2)O(5) Ceramics

Photopyroelectric (PPE) spectroscopy is a nondestructive tool that is used to study the optical properties of the ceramics (ZnO + 0.4MnO(2) + 0.4Co(3)O(4) + xV(2)O(5)), x = 0-1 mol%. Wavelength of incident light, modulated at 10 Hz, was in the range of 300-800 nm. PPE spectrum with reference to the doping level and sintering temperature is discussed. Optical energy band-gap (E(g)) was 2.11 eV for 0.3 mol% V(2)O(5) at a sintering temperature of 1025 °C as determined from the plot (ρhυ)(2)versushυ. With a further increase in V(2)O(5), the value of E(g) was found to be 2.59 eV. Steepness factor 'σ(A)' and 'σ(B)', which characterize the slope of exponential optical absorption, is discussed with reference to the variation of E(g). XRD, SEM and EDAX are also used for characterization of the ceramic. For this ceramic, the maximum relative density and grain size was observed to be 91.8% and 9.5 μm, respectively.