Real-Time Gene-Expression Extraction with Fast Classification (FC) Networks

Fast Classification (FC) networks were inspired by a biologically plausible mechanism for short term memory where learning occurs instantaneously. Both weights and the topology for an FC network are mapped directly from the training samples by using a prescriptive training scheme. Only two presentations of the training data are required to train an FC network. Compared with iterative learning algorithms such as Back-propagation (which may require many hundreds of presentations of the training data), the training of FC networks is extremely fast and learning convergence is always guaranteed. Thus FC networks may be suitable for applications where real-time classification is needed. In this paper, the FC networks are applied for the real-time extraction of gene expressions for Chlamydia microarray data. Both the classification performance and learning time of the FC networks are compared with the Multi-Layer Proceptron (MLP) networks and support-vector-machines (SVM) in the same classification task. The FC networks are shown to have extremely fast learning time and comparable classification accuracy.

An implementation of genetic algorithms as a basis for a trading system on the foreign exchange market

Foreign exchange trading has emerged in recent times as a significant activity in many countries. As with most forms of trading, the activity is influenced by many random parameters so that the creation of a system that effectively emulates the trading process is very helpful. In this paper, we try to create such a system with a genetic algorithm engine to emulate trader behaviour on the foreign exchange market and to find the most profitable trading strategy.

Identification of residues controlling transport through the yeast aquaglyceroporin Fps1 using a genetic screen

Aquaporins and aquaglyceroporins mediate the transport of water and solutes across biological membranes. Saccharomyces cerevisiae Fps1 is an aquaglyceroporin that mediates controlled glycerol export during osmoregulation. The transport function of Fps1 is rapidly regulated by osmotic changes in an apparently unique way and distinct regions within the long N- and C-terminal extensions are needed for this regulation. In order to learn more about the mechanisms that control Fps1 we have set up a genetic screen for hyperactive Fps1 and isolated mutations in 14 distinct residues, all facing the inside of the cell. Five of the residues lie within the previously characterized N-terminal regulatory domain and two mutations are located within the approach to the first transmembrane domain. Three mutations cause truncation of the C-terminus, confirming previous studies on the importance of this region for channel control. Furthermore, the novel mutations identify two conserved residues in the channel-forming B-loop as critical for channel control. Structural modelling-based rationalization of the observed mutations supports the notion that the N-terminal regulatory domain and the B-loop could interact in channel control. Our findings provide a framework for further genetic and structural analysis to better understand the mechanism that controls Fps1 function by osmotic changes.

Evolutionary neural networks : models and applications

The scaling problems which afflict attempts to optimise neural networks (NNs) with genetic algorithms (GAs) are disclosed. A novel GA-NN hybrid is introduced, based on the bumptree, a little-used connectionist model. As well as being computationally efficient, the bumptree is shown to be more amenable to genetic coding lthan other NN models. A hierarchical genetic coding scheme is developed for the bumptree and shown to have low redundancy, as well as being complete and closed with respect to the search space. When applied to optimising bumptree architectures for classification problems the GA discovers bumptrees which significantly out-perform those constructed using a standard algorithm. The fields of artificial life, control and robotics are identified as likely application areas for the evolutionary optimisation of NNs. An artificial life case-study is presented and discussed. Experiments are reported which show that the GA-bumptree is able to learn simulated pole balancing and car parking tasks using only limited environmental feedback. A simple modification of the fitness function allows the GA-bumptree to learn mappings which are multi-modal, such as robot arm inverse kinematics. The dynamics of the 'geographic speciation' selection model used by the GA-bumptree are investigated empirically and the convergence profile is introduced as an analytical tool. The relationships between the rate of genetic convergence and the phenomena of speciation, genetic drift and punctuated equilibrium arc discussed. The importance of genetic linkage to GA design is discussed and two new recombination operators arc introduced. The first, linkage mapped crossover (LMX) is shown to be a generalisation of existing crossover operators. LMX provides a new framework for incorporating prior knowledge into GAs.Its adaptive form, ALMX, is shown to be able to infer linkage relationships automatically during genetic search.

DNA Simulation of Genetic Algorithms: Fitness Computation

* This work has been partially supported by Spanish Project TIC2003-9319-c03-03 “Neural Networks and Networks of Evolutionary Processors”.

Optimization of ATM Telecommunication Networks

ATM network optimization problems defined as combinatorial optimization problems are considered. Several approximate algorithms for solving such problems are developed. Results of their comparison by experiments on a set of problems with random input data are presented.

Offline Handwriting Recognition Using Genetic Algorithm

In this paper, a new method for offline handwriting recognition is presented. A robust algorithm for handwriting segmentation has been described here with the help of which individual characters can be segmented from a word selected from a paragraph of handwritten text image which is given as input to the module. Then each of the segmented characters are converted into column vectors of 625 values that are later fed into the advanced neural network setup that has been designed in the form of text files. The networks has been designed with quadruple layered neural network with 625 input and 26 output neurons each corresponding to a character from a-z, the outputs of all the four networks is fed into the genetic algorithm which has been developed using the concepts of correlation, with the help of this the overall network is optimized with the help of genetic algorithm thus providing us with recognized outputs with great efficiency of 71%.

Operational issues in access networks:past, present, and future

Future network operation will be influenced by business and ownership models and the regulatory environment as future superfast and flexible broadband networks emerge. This paper discusses the issues affecting operators and network operations as network evolution progresses.

A novel regulatory role for tissue transglutaminase in epithelial-mesenchymal transition in cystic fibrosis

Cystic fibrosis (CF) is a genetic disorder caused by mutation of the cystic fibrosis transmembrane conductance regulator (CFTR) for which there is no overall effective treatment. Recent work indicates tissue transglutaminase (TG2) plays a pivotal intracellular role in proteostasis in CF epithelia and that the pan TG inhibitor cysteamine improves CFTR stability. Here we show TG2 has another role in CF pathology linked with TGFβ1 activation and signalling, induction of epithelial-mesenchymal transition (EMT), CFTR stability and induction of matrix deposition. We show that increased TG2 expression in normal and CF bronchial epithelial cells increases TGFβ1 levels, promoting EMT progression, and impairs tight junctions as measured by Transepithelial Electric Resistance (TEER) which can be reversed by selective inhibition of TG2 with an observed increase in CFTR stability. Our data indicate that selective inhibition of TG2 provides a potential therapeutic avenue for reducing fibrosis and increasing CFTR stability in CF.

The regulatory environment of the section of the non-standardized goods market - The findings of an interview research on Hungarian construction industry small enterprises

In this paper the behavior of economic actors shown in the uncertain quality goods markets is examined from the perspective of the sociology of markets. The analysis uses the findings of in-depth interviews conducted in 2011 and 2012 respectively amongst small and medium size entrepreneurs working in construction industry. In the Hungarian construction industry neither formal rules, nor vocational chambers, are able to create a safe environment for entrepreneurs. Nevertheless, networks created as a result of micro-selection steps might be able to enforce the quality of services, observe deadlines and what is more, ensure payment discipline. In this market, the typical high risk can be reduced by relationships. Networks reduce also the cost of transactions, since the important part of the services in this field could only be standardized at significant costs.

Development of local homeland security networks in the state of Florida: A social network analysis approach

How do local homeland security organizations respond to catastrophic events such as hurricanes and acts of terrorism? Among the most important aspects of this response are these organizations ability to adapt to the uncertain nature of these "focusing events" (Birkland 1997). They are often behind the curve, seeing response as a linear process, when in fact it is a complex, multifaceted process that requires understanding the interactions between the fiscal pressures facing local governments, the institutional pressures of working within a new regulatory framework and the political pressures of bringing together different levels of government with different perspectives and agendas. ^ This dissertation has focused on tracing the factors affecting the individuals and institutions planning, preparing, responding and recovering from natural and man-made disasters. Using social network analysis, my study analyzes the interactions between the individuals and institutions that respond to these "focusing events." In practice, it is the combination of budgetary, institutional, and political pressures or constraints interacting with each other which resembles a Complex Adaptive System (CAS). ^ To investigate this system, my study evaluates the evolution of two separate sets of organizations composed of first responders (Fire Chiefs, Emergency Management Coordinators) and community volunteers organized in the state of Florida over the last fifteen years. Using a social network analysis approach, my dissertation analyzes the interactions between Citizen Corps Councils (CCCs) and Community Emergency Response Teams (CERTs) in the state of Florida from 1996–2011. It is the pattern of interconnections that occur over time that are the focus of this study. ^ The social network analysis revealed an increase in the amount and density of connections between these organizations over the last fifteen years. The analysis also exposed the underlying patterns in these connections; that as the networks became more complex they also became more decentralized though not in any uniform manner. The present study brings to light a story of how communities have adapted to the ever changing circumstances that are sine qua non of natural and man-made disasters.^