Prediction of Structural and Functional Aspects of Protein

To predict the structure of protein from a primary amino acid sequence is computationally difficult. An investigation of the methods and algorithms used to predict protein structure and a thorough knowledge of the function and structure of proteins are critical for the advancement of biology and the life sciences as well as the development of better drugs, higher-yield crops, and even synthetic bio-fuels. To that end, this chapter sheds light on the methods used for protein structure prediction. This chapter covers the applications of modeled protein structures and unravels the relationship between pure sequence information and three-dimensional structure, which continues to be one of the greatest challenges in molecular biology. With this resource, it presents an all-encompassing examination of the problems, methods, tools, servers, databases, and applications of protein structure prediction, giving unique insight into the future applications of the modeled protein structures. In this chapter, current protein structure prediction methods are reviewed for a milieu on structure prediction, the prediction of structural fundamentals, tertiary structure prediction, and functional imminent. The basic ideas and advances of these directions are discussed in detail.

Conjugate Gradient Trained Neural Network for Intelligent Sensing of Manhole Gases to Avoid Human Fatality

Computational Intelligence offers solution to various real life problems. Artificial Neural Network (ANN) has the capability of solving highly complex and nonlinear problems. The present chapter demonstrates the application of these tools to provide solutions to the manhole gas detection problem. Manhole, the access point across sewer pipeline system, contains various toxic and explosive gases. Hence, predetermination of these gases before accessing manholes is becoming imperative. The problem is treated as a pattern recognition problem. ANN, devised for solving this problem, is trained using a supervised learning algorithm. The conjugate gradient method is used as an alternative of back propagation neural network learning algorithm for training of the ANN. The chapter offers comprehensive performance analysis of the learning algorithm used for the training of ANN followed by discussion on the methods of presenting the system result. The authors discuss different variants of Conjugate Gradient and propose two new variants of it.

Genetic Algorithms

Genetic Algorithms are important techniques to solve many NP-Complete problems related to distributed computing and its application domains. Genetic algorithm-based fault diagnoses in distributed computing systems have been a feasible methodology to solve diagnosis problems recently. Distributed embedded systems consisting of sensors, actuators, processors/microcontrollers, and interconnection networks are one class of distributed computing systems that have long been used, staring from small-scale home appliances to large-scale satellite systems. Some of their applications are in safety-critical systems where occurrence of faults can result in catastrophic situations for which fault diagnosis in such systems are very important. In this chapter, different types of faults, which are likely to occur in distributed embedded systems and a GA-based methodology to solve these problems along with the performance analysis of fault diagnosis algorithm have been presented. Nevertheless, the diagnosis algorithm presented here is well suitable for general purpose distributed computing systems with appropriate modification over system and fault model. In fact, this book chapter will enable the reader not only to study various aspects of fault diagnosis techniques but will also provide insight to build robust systems to allow for continued normal service despite the occurrence of failures.

Design Issues of 4G-Network Mobility Management

Fourth Generation wireless networking (4G network) is expected to provide global roaming across different types of wireless and mobile networks. In this environment, roaming is seamless and users are always connected to the best network. Moreover, 4G networks will be packet switched systems entirely based on the IPv6 protocol. The essentiality of Quality of Service (QoS) and the heterogeneous nature of 4G pose high demands onto the mobility management technology. Due to this, one of the most challenging research areas for the 4G network is the design of intelligent mobility management techniques that take advantage of IP-based technologies to achieve global roaming among various access technologies. In order to address the issue of heterogeneity of the networks, IEEE 802.21 working group proposed Media Independent Handover (MIH). The scope of the IEEE 802.21 MIH standard is to develop a specification that provides link layer intelligence and other related network information to upper layers to optimize handovers between heterogeneous media. The IEEE 802.21 group defines the media independent handover function that will help mobile devices to roam across heterogeneous networks and stationary devices to switch over to any of the available heterogeneous networks around it.

Detection of Non-Technical Losses

The MIDAS project began in 2006 as collaboration between Endesa, Sadiel, and the University of Seville. The objective of the MIDAS project is the detection of Non-Technical Losses (NTLs) on power utilities. The NTLs represent the non-billed energy due to faults or illegal manipulations in clients’ facilities. Initially, research lines study the application of techniques of data mining and neural networks. After several researches, the studies are expanded to other research fields: expert systems, text mining, statistical techniques, pattern recognition, etc. These techniques have provided an automated system for detection of NTLs on company databases. This system is in the test phase, and it is applied in real cases in company databases.

Characterizing Intelligent Intrusion Detection and Prevention Systems Using Data Mining

Intrusion Detection and Prevention Systems (IDPS) are being widely implemented to prevent suspicious threats in computer networks. Intrusion detection and prevention systems are security systems that are used to detect and prevent security threats to computer networks. In order to understand the security risks and IDPS, in this chapter, the authors make a quick review on classification of the IDPSs and categorize them in certain groups. Further, in order to improve accuracy and security, data mining techniques have been used to analyze audit data and extract features that can distinguish normal activities from intrusions. Experiments have been conducted for building efficient intrusion detection and prevention systems by combining online detection and offline data mining. During online data examination, real-time data are captured and are passed through a detection engine that uses a set of rules and parameters for analysis. During offline data mining, necessary knowledge is extracted about the process of intrusion.

Multi-Granular Computing through Rough Sets

Granular Computing has emerged as a framework in which information granules are represented and manipulated by intelligent systems. Granular Computing forms a unified conceptual and computing platform. Rough set theory put forth by Pawlak is based upon single equivalence relation taken at a time. Therefore, from a granular computing point of view, it is single granular computing. In 2006, Qiang et al. introduced a multi-granular computing using rough set, which was called optimistic multigranular rough sets after the introduction of another type of multigranular computing using rough sets called pessimistic multigranular rough sets being introduced by them in 2010. Since then, several properties of multigranulations have been studied. In addition, these basic notions on multigranular rough sets have been introduced. Some of these, called the Neighborhood-Based Multigranular Rough Sets (NMGRS) and the Covering-Based Multigranular Rough Sets (CBMGRS), have been added recently. In this chapter, the authors discuss all these topics on multigranular computing and suggest some problems for further study.

Predictive Analytics and Data Mining

High dimensional databases are proving to be a major concern among the researches to extract relevant information for futuristic decision making. Real world data is high dimensional in nature and comprises of irrelevant features, missing values, and redundancy, which requires serious concerns. Utilizing all such features can mislead the results for emergent prediction. Therefore, such databases are critical in nature to determine optimal solutions. To deal with such issues, the authors have developed and implemented a Cluster Analysis Study Behavior of School Children from Large Databases (CABS) framework to retrieve effective and efficient clusters from high dimensional human behavior datasets for school children in US. They have applied feature selection technique and hierarchical agglomerative clustering technique to discover clusters of vivid shape and size to retrieve knowledge from large databases. This study was conducted for Health Behavior in School-Aged Children (HBSC) using Correlation-Based Feature Selection (CFS) technique to reduce the inconsistent data records and select relevant features that will eventually extract the appropriate data to merge similar data and retrieve clusters. However, predictive analytics can facilitate a more thorough extraction of knowledge to facilitate better quality and faster decisions. The authors have implemented the current framework in R language where the clustering was emphasized using pvclust package. The proposed framework is highly efficient in discovering hidden and implicit knowledge from large databases due to its accessibility to handling and discovering clusters of variant shapes.

Neural Network Model to Estimate and Predict Cell Mass Concentration in Lipase Fermentation

Lipase is an industrially important enzyme with major use in food industries. The demand of lipase is increasing every year. An online prediction of cell mass concentration is of great value in real time process involving the production of lipase. In the current work, the use of a back-propagation multilayer neural network to predict cell mass during lipase production by Rhizopus delemar NRRL 1472 is targeted. Network training data with respect to time is generated by carrying out experiments in laboratory. The fungus is grown in erlenmeyer flasks at initial pH of 5.6, temperature of 30ºC, and at 150 rpm. During the experiments, readings for cell mass growth are collected in specific period of time. By the training data, an artificial neural network model programmed in MATLAB for Windows is trained and used for prediction of cell mass. The Levenberg-Marquardt algorithm with back-propagation is used in the network to get the optimized weights. The optimum network configuration with different activation function and the number of nodes in the hidden layer are identified by trial and error method. Sigmoid unipolar activation function is 2-5-1, whereas logarithmoid and sigmoid bipolar is 2-3-1. These are chosen according to the values of Sum of Square of Errors (SSE), Root Mean Square (RMS) training and testing. The sigmoid unipolar activation function gives a good fit for estimated value with network configuration 2-5-1, which could be used for generalization.

Artificial Neural Network Modeling for Electrical Discharge Machining Parameters

The objective of the chapter is to present the application of Artificial Neural Network (ANN) modelling of the Electrical Discharge Machining (EDM) process. It establishes the best ANN model by comparing the prediction from different models under the effect of process parameters. In EDM, the motivation is frequently to get better Material Removal Rate (MRR) with fulfilling better surface quality of machined components. The vital requirements are as small a radial overcut with minimal tool wear rate. The quality of a machined surface is very important to fulfilling the growing demands of higher component performance, durability, and reliability. To improve the reliability of the machine component, it is necessary to have in depth knowledge of the effect of parameters on the aforesaid responses of the components. An extensive chain of experiments has been conducted over a wide range of input parameters, using the full factorial design. More than 150 experiments have been conducted on AISI D2 work piece materials using copper electrodes to get the data for training and testing. The additional experiments were obtained to validate the model predictions. The performance of three neural network models is discussed in the evaluation of the generalization ability of the trained neural network. It was observed that the artificial neural network models could predict the process performance with reasonable accuracy, under varying machining conditions.