Narendra S. Chaudhari

Cascaded Bidirectional Recurrent Neural Networks for Protein Secondary Structure Prediction

Protein secondary structure (PSS) prediction is an important topic in bioinformatics. Our study on a large set of nonhomologous proteins shows that long-range interactions commonly exist and negatively affect PSS prediction. Besides, we also reveal strong correlations between secondary structure (SS) elements. In order to take into account the long-range interactions and SS-SS correlations, we propose a novel prediction system based on a cascaded bidirectional recurrent neural network (BRNN). We compare the cascaded BRNN against two other BRNN architectures, namely, the original BRNN architecture used for speech recognition and Pollastris BRNN, which was proposed for PSS prediction. Our cascaded BRNN achieves an overall three-state accuracy Q3 of 74.38 percent and reaches a high Segment Overlap (SOV) of 66.0455. It outperforms the original BRNN and Pollastris BRNN in both Q3 and SOV. Specifically, it improves the SOV score by 4-6 percent.

Nonlinear channel equalization with QAM signal using Chebyshev artificial neural network

A computational efficient artificial neural network for adaptive channel equalization in a digital communication system with 4-QAM signal constellation is purposed. We proposed a single layer Chebyshev neural network (ChNN) by expanding the input pattern by Chebyshev polynomials. Performance comparison was carried out through extensive computer simulations with two other neural networks: an MLP and a functional link ANN together with a linear LIMS-based equalizer. It is shown that the ChNN provides satisfactory results in terms of convergence rate, MSE floor and BER over a wide range of EVR, SNR and nonlinear conditions with substantial reduction in the computational complexity.

Bidirectional segmented-memory recurrent neural network for protein secondary structure prediction

The formation of protein secondary structure especially the regions of β-sheets involves long-range interactions between amino acids. We propose a novel recurrent neural network architecture called segmented-memory recurrent neural network (SMRNN) and present experimental results showing that SMRNN outperforms conventional recurrent neural networks on long-term dependency problems. In order to capture long-term dependencies in protein sequences for secondary structure prediction, we develop a predictor based on bidirectional segmented-memory recurrent neural network (BSMRNN), which is a noncausal generalization of SMRNN. In comparison with the existing predictor based on bidirectional recurrent neural network (BRNN), the BSMRNN predictor can improve prediction performance especially the recognition accuracy of β-sheets.

EasySMS: A Protocol for End-to-End Secure Transmission of SMS

Nowadays, short message service (SMS) is being used in many daily life applications, including healthcare monitoring, mobile banking, mobile commerce, and so on. But when we send an SMS from one mobile phone to another, the information contained in the SMS transmit as plain text. Sometimes this information may be confidential like account numbers, passwords, license numbers, and so on, and it is a major drawback to send such information through SMS while the traditional SMS service does not provide encryption to the information before its transmission. In this paper, we propose an efficient and secure protocol called EasySMS, which provides end-to-end secure communication through SMS between end users. The working of the protocol is presented by considering two different scenarios. The analysis of the proposed protocol shows that this protocol is able to prevent various attacks, including SMS disclosure, over the air modification, replay attack, man-in-the-middle attack, and impersonation attack. The EasySMS protocol generates minimum communication and computation overheads as compared with existing SMSSec and PK-SIM protocols. On an average, the EasySMS protocol reduces 51% and 31% of the bandwidth consumption and reduces 62% and 45% of message exchanged during the authentication process in comparison to SMSSec and PK-SIM protocols respectively. Authors claim that EasySMS is the first protocol completely based on the symmetric key cryptography and retain original architecture of cellular network.

Neural-network-based smart sensor framework operating in a harsh environment

We present an artificial neural-network- (NN-) based smart interface framework for sensors operating in harsh environments. The NN-based sensor can automatically compensate for the nonlinear response characteristics and its nonlinear dependency on the environmental parameters, with high accuracy. To show the potential of the proposed NN-based framework, we provide results of a smart capacitive pressure sensor (CPS) operating in a wide temperature range of 0 to . Through simulated experiments, we have shown that the NN-based CPS model is capable of providing pressure readout with a maximum full-scale (FS) error of only over this temperature range. A novel scheme for estimating the ambient temperature from the sensor characteristics itself is proposed. For this purpose, a second NN is utilized to estimate the ambient temperature accurately from the knowledge of the offset capacitance of the CPS. A microcontroller-unit- (MCU-) based implementation scheme is also provided.

Performance evaluation of SVM based semi-supervised classification algorithm

To construct decision boundaries for two-class classification, SVM approach is attractive due to its efficiency. However, this approach is useful for 2-class classification and when the classes (labels) for the data are known. In practice, we have collection of labeled as well as unlabelled data, and it gives rise to semi-supervised classification problem. In this paper, we give a semi-supervised classification algorithm based on support vector machine (SVM). Novel feature of our approach is the formulation of spherical decision boundaries and the exploitation of the dynamical system associated with support function to obtain the number of clusters. The experimental results on a few well-known datasets, namely, Iris dataset, Shuttle landing control dataset, Wisconsin Breast cancer dataset, glass dataset, and balance scale dataset, indicate that our approach results in satisfactory classification as well as generalization accuracy.

Binary neural network training algorithms based on linear sequential learning.

A key problem in Binary Neural Network learning is to decide bigger linear separable subsets. In this paper we prove some lemmas about linear separability. Based on these lemmas, we propose Multi-Core Learning (MCL) and Multi-Core Expand-and-Truncate Learning (MCETL) algorithms to construct Binary Neural Networks. We conclude that MCL and MCETL simplify the equations to compute weights and thresholds, and they result in the construction of simpler hidden layer. Examples are given to demonstrate these conclusions.

Privacy preserving association rule mining by introducing concept of impact factor

Association Rules discovered by association rule mining may contain some sensitive rules, which may cause potential threats towards privacy and security. Many of the researchers in this area have recently made efforts to preserve privacy for sensitive association rules in statistical database. In this paper, we propose a heuristic based association rule hiding using oracle real application clusters by introducing the concept of impact factor of transaction on the rule. The impact factor of a transaction is equal to number of itemsets that are present in those itemsets which represents sensitive association rule. Higher the impact factor of a transaction, higher is its sensitivity. Proposed algorithm exhibits the concept of impact factor to hide several rules by modifying fewer transactions. As modifications are fewer, data quality is very less affected. Use of clustering aids in increasing performance by running operations in parallel.

Selecting useful features for personal credit risk analysis

The recent credit crisis has renewed regulatory concerns of industrial interest in credit risk analysis. To reduce exposure to credit default, it thus becomes a crucial motive to select vital features to analyse the customers credit profiles. This desired set of features can be generated through data mining techniques such as feature selection methods. However, each feature selection method has its advantages and limitations. In practice, using a single method inevitably introduces undesirable estimation bias. Instead, this paper proposes a bagging feature selection model, which is an ensemble learning approach, to identify the most significant features that determine the credit worthiness of customers. The experimental results demonstrate promising results using bagging feature selection model as compared to fundamental models for personal credit risk analysis.

Advances in Games Technology: Software, Models, and Intelligence

Games technology has undergone tremendous development. In this article, the authors report the rapid advancement that has been observed in the way games software is being developed, as well as in the development of games content using game engines. One area that has gained special attention is modeling the game environment such as terrain and buildings. This article presents the continuous level of detail terrain modeling techniques that can help generate and render realistic terrain in real time. Deployment of characters in the environment is increasingly common. This requires strategies to map scalable behavior characteristics for characters as well. The authors present two important aspects of crowd simulation: the realism of the crowd behavior and the computational overhead involved. A good simulation of crowd behavior requires delicate balance between these aspects. The focus in this article is on human behavior representation for crowd simulation. To enhance the player experience, the authors present the concept of player adaptive entertainment computing, which provides a personalized experience for each individual when interacting with the game. The current state of game development involves using very small percentage (typically 4% to 12%) of CPU time for game artificial intelligence (AI). Future game AI requires developing computational strategies that have little involvement of CPU for online play, while using CPU’s idle capacity when the game is not being played, thereby emphasizing the construction of complex game AI models offline. A framework of such nonconventional game AI models is introduced.