Portfolio selection using artificial intelligence

The application of artificial intelligence in finance is relatively new area of research. This project employed artificial neural networks (ANNs) that use both fundamental and technical inputs to predict future prices of widely held Australian stocks and use these predicted prices for stock portfolio selection over a long investment horizon. The research involved the creation and testing of a large number of possible network configurations and draws conclusions about ANN architectures and their overall suitability for the purpose of stock portfolio selection.

Recent advances in the design of artificial corneas

Purpose of review: Artificial corneas are being developed to meet a shortage of donor corneas as well as to address cases where allografting is contraindicated. A range of artificial corneas has been developed. Here we review several newer designs and especially those inspired by naturally occurring biomaterials found with the human body and elsewhere. Recent findings: Recent trends in the development of artificial corneas indicate a move towards the use of materials derived from native sources including decellularized corneal tissue and tissue substitutes synthesized by corneal cells in vitro when grown either on their own, or in conjunction with novel protein-based scaffolds. Biologically inspired materials are also being considered for implantation on their own with the view to promoting endogenous corneal tissue. Summary: More recent attempts at making artificial corneas have taken a more nature-based or nature-inspired approach. Several will in the near future be likely to be available clinically.

An Artificial Neutral Network (ANN) model for predicting biodiesel kinetic viscosity as a function of temperature and chemical compositions

An Artificial Neural Network (ANN) is a computational modeling tool which has found extensive acceptance in many disciplines for modeling complex real world problems. An ANN can model problems through learning by example, rather than by fully understanding the detailed characteristics and physics of the system. In the present study, the accuracy and predictive power of an ANN was evaluated in predicting kinetic viscosity of biodiesels over a wide range of temperatures typically encountered in diesel engine operation. In this model, temperature and chemical composition of biodiesel were used as input variables. In order to obtain the necessary data for model development, the chemical composition and temperature dependent fuel properties of ten different types of biodiesels were measured experimentally using laboratory standard testing equipments following internationally recognized testing procedures. The Neural Networks Toolbox of MatLab R2012a software was used to train, validate and simulate the ANN model on a personal computer. The network architecture was optimised following a trial and error method to obtain the best prediction of the kinematic viscosity. The predictive performance of the model was determined by calculating the absolute fraction of variance (R2), root mean squared (RMS) and maximum average error percentage (MAEP) between predicted and experimental results. This study found that ANN is highly accurate in predicting the viscosity of biodiesel and demonstrates the ability of the ANN model to find a meaningful relationship between biodiesel chemical composition and fuel properties at different temperature levels. Therefore the model developed in this study can be a useful tool in accurately predict biodiesel fuel properties instead of undertaking costly and time consuming experimental tests.

Integrin-functionalized artificial membranes as test platforms for monitoring small integrin ligand binding by surface plasmon-enhanced fluorescence spectroscopy

The design and synthesis of molecularly or supramolecularly defined interfacial architectures have seen in recent years a remarkable growth of interest and scientific research activities for various reasons. On the one hand, it is generally believed that the construction of an interactive interface between the living world of cells, tissue, or whole organisms and the (inorganic or organic) materials world of technical devices such as implants or medical parts requires proper construction and structural (and functional) control of this organism–machine interface. It is still the very beginning of generating a better understanding of what is needed to make an organism tolerate implants, to guarantee bidirectional communication between microelectronic devices and living tissue, or to simply construct interactive biocompatibility of surfaces in general. This exhaustive book lucidly describes the design, synthesis, assembly and characterization, and bio-(medical) applications of interfacial layers on solid substrates with molecularly or supramolecularly controlled architectures. Experts in the field share their contributions that have been developed in recent years.

Estimation of biodiesel properties from chemical composition – An artificial neural network (ANN) approach

Biodiesel, produced from renewable feedstock represents a more sustainable source of energy and will therefore play a significant role in providing the energy requirements for transportation in the near future. Chemically, all biodiesels are fatty acid methyl esters (FAME), produced from raw vegetable oil and animal fat. However, clear differences in chemical structure are apparent from one feedstock to the next in terms of chain length, degree of unsaturation, number of double bonds and double bond configuration-which all determine the fuel properties of biodiesel. In this study, prediction models were developed to estimate kinematic viscosity of biodiesel using an Artificial Neural Network (ANN) modelling technique. While developing the model, 27 parameters based on chemical composition commonly found in biodiesel were used as the input variables and kinematic viscosity of biodiesel was used as output variable. Necessary data to develop and simulate the network were collected from more than 120 published peer reviewed papers. The Neural Networks Toolbox of MatLab R2012a software was used to train, validate and simulate the ANN model on a personal computer. The network architecture and learning algorithm were optimised following a trial and error method to obtain the best prediction of the kinematic viscosity. The predictive performance of the model was determined by calculating the coefficient of determination (R2), root mean squared (RMS) and maximum average error percentage (MAEP) between predicted and experimental results. This study found high predictive accuracy of the ANN in predicting fuel properties of biodiesel and has demonstrated the ability of the ANN model to find a meaningful relationship between biodiesel chemical composition and fuel properties. Therefore the model developed in this study can be a useful tool to accurately predict biodiesel fuel properties instead of undertaking costly and time consuming experimental tests.

THE quest for alpha : can artificial neural networks help?

The application of artificial neural networks (ANN) in finance is relatively new area of research. We employed ANNs that used both fundamental and technical inputs to predict future prices of widely held Australian stocks and used these predicted prices for stock portfolio selection over a 10-year period (2001-2011). We found that the ANNs generally do well in predicting the direction of stock price movements. The stock portfolios selected by the ANNs with median accuracy are able to generate positive alpha over the 10-year period. More importantly, we found that a portfolio based on randomly selected network configuration had zero chance of resulting in a significantly negative alpha but a 27% chance of yielding a significantly positive alpha. This is in stark contrast to the findings of the research on mutual fund performance where active fund managers with negative alphas outnumber those with positive alphas.

Rational design of artificial cellular niches for tissue engineering

Tissue Engineering is a promising emerging field that studies the intrinsic regenerative potential of the human body and uses it to restore functionality of damaged organs or tissues unable of self-healing due to illness or ageing. In order to achieve regeneration using Tissue Engineering strategies, it is first necessary to study the properties of the native tissue and determine the cause of tissue failure; second, to identify an optimum population of cells capable of restoring its functionality; and third, to design and manufacture a cellular microenvironment in which those specific cells are directed towards the desired cellular functions. The design of the artificial cellular niche has a tremendous importance, because cells will feel and respond to both its biochemical and biophysical properties very differently. In particular, the artificial niche will act as a physical scaffold for the cells, allowing their three-dimensional spatial organization; also, it will provide mechanical stability to the artificial construct; and finally, it will supply biochemical and mechanical cues to control cellular growth, migration, differentiation and synthesis of natural extracellular matrix. During the last decades, many scientists have made great contributions to the field of Tissue Engineering. Even though this research has frequently been accompanied by vast investments during extended periods of time, yet too often these efforts have not been enough to translate the advances into new clinical therapies. More and more scientists in this field are aware of the need of rational experimental designs before carrying out complex, expensive and time-consuming in vitro and in vivo trials. This review highlights the importance of computer modeling and novel biofabrication techniques as critical key players for a rational design of artificial cellular niches in Tissue Engineering.

The effect of exercise on the skeletal muscle phospholipidome of rats fed a high-fat diet

The aim of this study was to examine the effect of endurance training on skeletal muscle phospholipid molecular species from high-fat fed rats. Twelve female Sprague-Dawley rats were fed a high-fat diet (78.1% energy). The rats were randomly divided into two groups, a sedentary control group and a trained group (125 min of treadmill running at 8 m/min, 4 days/wk for 4 weeks). Forty-eight hours after their last training bout phospholipids were extracted from the red and white vastus lateralis and analyzed by electrospray-ionization mass spectrometry. Exercise training was associated with significant alterations in the relative abundance of a number of phospholipid molecular species. These changes were more prominent in red vastus lateralis than white vastus lateralis. The largest observed change was an increase of similar to 30% in the abundance of 1-palmitoyl-2-linoleoyl phosphatidylcholine ions in oxidative fibers. Reductions in the relative abundance of a number of phospholipids containing long-chain n-3 polyunsaturated fatty acids were also observed. These data suggest a possible reduction in phospholipid remodeling in the trained animals. This results in a decrease in the phospholipid n-3 to n-6 ratio that may in turn influence endurance capacity.

Phospholipid composition of the rat lens is independent of diet

Dietary fatty acids are known to influence the phospholipid composition of many tissues in the body, with lipid turnover occurring rapidly. The aim of this study was to investigate whether changes in the fatty acid composition of the diet can affect the phospholipid composition of the lens. Male Sprague-Dawley rats were fed three diets with distinct profiles in both essential and non-essential fatty acids. After 8 weeks, lenses and skeletal muscle were removed, and the lenses sectioned into nuclear and cortical regions. In these experiments, the lens cortex was synthesised during the course of the variable lipid diet. Phospholipids were then identified by electrospray ionisation tandem mass spectrometry, and quantified via the use of internal standards. The phospholipid compositions of the nuclear and cortical regions of the lens differed slightly between the two regions, but comparison of the equivalent regions across the diet groups showed remarkable similarity. In contrast, the phospholipid composition of skeletal muscle (medial gastrocnemius) in these rats varied significantly. This study provides the first direct evidence to show that the phospholipid composition of the lens is tightly regulated and thus appears to be independent of diet. As phospholipids determine membrane fluidity and influence the activity and function of integral membrane proteins, regulation of their composition may be important for the function of the lens. Crown Copyright (C) 2008 Published by Elsevier Ltd. All rights reserved.

Activation of matrix metalloproteinase-2 (MMP-2) by membrane type 1 matrix metalloproteinase through an artificial receptor for ProMMP-2 generates active MMP-2

The suggested model for pro-matrix metalloproteinase-2 (proMMP-2) activation by membrane type 1 MMP (MT1-MMP) implicates the complex between MT1-MMP and tissue inhibitor of MMP-2 (TIMP-2) as a receptor for proMMP-2. To dissect this model and assess the pathologic significance of MMP-2 activation, an artificial receptor for proMMP-2 was created by replacing the signal sequence of TIMP-2 with cytoplasmic/transmembrane domain of type II transmembrane mosaic serine protease (MSP-T2). Unlike TIMP-2, MSP-T2 served as a receptor for proMMP-2 without inhibiting MT1-MMP, and generated TIMP-2-free active MMP-2 even at a low level of MT1-MMP. Thus, MSP-T2 did not affect direct cleavage of the substrate testican-1 by MT1-MMP, whereas TIMP-2 inhibited it even at the level that stimulates proMMP-2 processing. Expression of MSP-T2 in HT1080 cells enhanced MMP-2 activation by endogenous MT1-MMP and caused intensive hydrolysis of collagen gel. Expression of MSP-T2 in U87 glioma cells, which express a trace level of endogenous MT1-MMP, induced MMP-2 activation and enhanced cell-associated protease activity, activation of extracellular signal-regulated kinase, and metastatic ability into chick embryonic liver and lung. MT1-MMP can exert both maximum MMP-2 activation and direct cleavage of substrates with MSP-T2, which cannot be achieved with TIMP-2. These results suggest that MMP-2 activation by MT1-MMP potentially amplifies protease activity, and combination with direct cleavage of substrate causes effective tissue degradation and enhances tumor invasion and metastasis, which highlights the complex role of TIMP-2. MSP-T2 is a unique tool to analyze physiologic and pathologic roles of MMP-2 and MT1-MMP in comparison with TIMP-2.

Artificial neural networks to predict activity type and energy expenditure in youth

Previous studies have demonstrated that pattern recognition approaches to accelerometer data reduction are feasible and moderately accurate in classifying activity type in children. Whether pattern recognition techniques can be used to provide valid estimates of physical activity (PA) energy expenditure in youth remains unexplored in the research literature. Purpose: The objective of this study is to develop and test artificial neural networks (ANNs) to predict PA type and energy expenditure (PAEE) from processed accelerometer data collected in children and adolescents. Methods: One hundred participants between the ages of 5 and 15 yr completed 12 activity trials that were categorized into five PA types: sedentary, walking, running, light-intensity household activities or games, and moderate-to-vigorous intensity games or sports. During each trial, participants wore an ActiGraph GTIM on the right hip, and (V) Over dotO(2) was measured using the Oxycon Mobile (Viasys Healthcare, Yorba Linda, CA) portable metabolic system. ANNs to predict PA type and PAEE (METs) were developed using the following features: 10th, 25th, 50th, 75th, and 90th percentiles and the lag one autocorrelation. To determine the highest time resolution achievable, we extracted features from 10-, 15-, 20-, 30-, and 60-s windows. Accuracy was assessed by calculating the percentage of windows correctly classified and root mean square en-or (RMSE). Results: As window size increased from 10 to 60 s, accuracy for the PA-type ANN increased from 81.3% to 88.4%. RMSE for the MET prediction ANN decreased from 1.1 METs to 0.9 METs. At any given window size, RMSE values for the MET prediction ANN were 30-40% lower than the conventional regression-based approaches. Conclusions: ANNs can be used to predict both PA type and PAEE in children and adolescents using count data from a single waist mounted accelerometer.

Randomized trial of a clinic-based, community-supported, lifestyle intervention to improve physical activity and diet : The North Carolina enhanced WISEWOMAN project

Objective To determine if a clinic-based behavioral intervention program for low-income mid-life women that emphasizes use of community resources will increase moderate intensity physical activity (PA) and improve dietary intake. Methods Randomized trial conducted from May 2003 to December 2004 at one community health center in Wilmington, NC. A total of 236 women, ages 40–64, were randomized to receive an Enhanced Intervention (EI) or Minimal Intervention (MI). The EI consisted of an intensive phase (6 months) including 2 individual counseling sessions, 3 group sessions, and 3 phone calls from a peer counselor followed by a maintenance phase (6 months) including 1 individual counseling session and 7 monthly peer counselor calls. Both phases included efforts to increase participants' use of community resources that promote positive lifestyle change. The MI consisted of a one-time mailing of pamphlets on diet and PA. Outcomes, measured at 6 and 12 months, included the comparison of moderate intensity PA between study groups as assessed by accelerometer (primary outcome) and questionnaire, and dietary intake assessed by questionnaire and serum carotenoids (6 months only). Results For accelerometer outcomes, follow-up was 75% at 6 months and 73% at 12 months. Though moderate intensity PA increased in the EI and decreased in the MI, the difference between groups was not statistically significant (p = 0.45; multivariate model, p = 0.08); however, moderate intensity PA assessed by questionnaire (92% follow-up at 6 months and 75% at 12 months) was greater in the EI (p = 0.01; multivariate model, p = 0.001). For dietary outcomes, follow-up was 90% for questionnaire and 92% for serum carotenoids at 6 months and 74% for questionnaire at 12 months. Dietary intake improved more in the EI compared to the MI (questionnaire at 6 and 12 months, p < 0.001; serum carotenoid index, p = 0.05; multivariate model, p = 0.03). Conclusion The EI did not improve objectively measured PA, but was associated with improved self-reported and objective measures of dietary intake.

Offspring of mothers fed a high fat diet display hepatic cell cycle inhibition and associated changes in gene expression and DNA methylation

The association between an adverse early life environment and increased susceptibility to later-life metabolic disorders such as obesity, type 2 diabetes and cardiovascular disease is described by the developmental origins of health and disease hypothesis. Employing a rat model of maternal high fat (MHF) nutrition, we recently reported that offspring born to MHF mothers are small at birth and develop a postnatal phenotype that closely resembles that of the human metabolic syndrome. Livers of offspring born to MHF mothers also display a fatty phenotype reflecting hepatic steatosis and characteristics of non-alcoholic fatty liver disease. In the present study we hypothesised that a MHF diet leads to altered regulation of liver development in offspring; a derangement that may be detectable during early postnatal life. Livers were collected at postnatal days 2 (P2) and 27 (P27) from male offspring of control and MHF mothers (n = 8 per group). Cell cycle dynamics, measured by flow cytometry, revealed significant G0/G1 arrest in the livers of P2 offspring born to MHF mothers, associated with an increased expression of the hepatic cell cycle inhibitor Cdkn1a. In P2 livers, Cdkn1a was hypomethylated at specific CpG dinucleotides and first exon in offspring of MHF mothers and was shown to correlate with a demonstrable increase in mRNA expression levels. These modifications at P2 preceded observable reductions in liver weight and liver:brain weight ratio at P27, but there were no persistent changes in cell cycle dynamics or DNA methylation in MHF offspring at this time. Since Cdkn1a up-regulation has been associated with hepatocyte growth in pathologic states, our data may be suggestive of early hepatic dysfunction in neonates born to high fat fed mothers. It is likely that these offspring are predisposed to long-term hepatic dysfunction.