N. V. Subba Reddy

Two-tier architecture for unconstrained handwritten character recognition

In this paper, we propose an approach that combines the unsupervised and supervised learning techniques for unconstrained handwritten numeral recognition. This approach uses the Kohonen self-organizing neural network for data classification in the first stage and the learning vector quantization (LVQ) model in the second stage to improve classification accuracy. The combined architecture performs better than the Kohonen self-organizing map alone. In the proposed approach, the collection of centroids at different phases of training plays a vital role in the performance of the recognition system. Four experiments have been conducted and experimental results show that the collection of centroids in the middle of the training gives high performance in terms of speed and accuracy. The systems developed also resolve the confusion between handwritten numerals.

Exploiting heterogeneous features to improve in silico prediction of peptide status – amyloidogenic or non-amyloidogenic

BackgroundPrediction of short stretches in protein sequences capable of forming amyloid-like fibrils is important in understanding the underlying cause of amyloid illnesses thereby aiding in the discovery of sequence-targeted anti-aggregation pharmaceuticals. Due to the constraints of experimental molecular techniques in identifying such motif segments, it is highly desirable to develop computational methods to provide better and affordable in silico predictions.ResultsAccurate in silico prediction techniques of amyloidogenic peptide regions rely on the cooperation between informative features and classifier design. In this research article, we propose one such efficient fibril prediction implementation exploiting heterogeneous features based on bio-physio-chemical (BPC) properties, auto-correlation function of carefully selected amino acid indices and atomic composition within a protein fragment of amino acids in a window. In an attempt to get an optimal number of BPC features, an evolutionary Support Vector Machine (SVM) integrating a novel implementation of hybrid Genetic Algorithm termed Memetic Algorithm and SVM is utilized. Five prediction modules designed using Artificial Neural Network (ANN) models are trained with independent and integrated features in order to validate the fibril forming motifs. The results provide evidence that incorporating new feature namely auto-correlation function besides BPC, attempt to strengthen the sequence interaction effect in forming the feature vector thereby obtaining better prediction quality in terms of sensitivity, specificity, Mathews Correlation Coefficient and Area under the Receiver Operating Characteristics curve.ConclusionA significant improvement in performance is observed by introducing features like auto-correlation function that maintains sequence order effect, in addition to the conventional BPC properties selected through a novel optimization strategy to predict the peptide status – amyloidogenic or non-amyloidogenic. The proposed approach achieves acceptable results, comparable to most online predictors. Besides, it compensates the lacuna in existing amyloid fibril prediction tools by maintaining equilibrium between sensitivity and specificity.

Knowledge Discovery from Web Usage Data: A Survey of Web Usage Pre-processing Techniques

Knowledge discovery from Web Usage Data has become very critical in order to understand and better serve the needs of Web based applications. Web usage mining consists of three phases, namely prepro cessing, pattern discovery and pattern analysis. A survey of Web Usage Preprocessing techniques is presented in this paper.

An Evaluation of Feature Selection Approaches in Finding Amyloidogenic Regions in Protein Sequences

Amyloidogenic regions in polypeptide chains are associated with a number of diseases. Experimental evidence is compelling in favor of the hypothesis that small segments of proteins are responsible for its amyloidogenic behavior. Thus, identifying these short peptides is critical for understanding diseases associated with protein misfolding and developing sequencetargeted anti-aggregation drugs. The in silico approaches using phenomenological models based on bio-physio-chemical properties of amino acids suffer from “curse of dimensionality”. Therefore, before adopting standard classification algorithms to predict such fibril motifs, the “curse of dimensionality” needs to be solved. The present study evaluates the performance of feature selection algorithms namely filter, wrapper and embedded models in conjunction with Support Vector Machine classifier. We also propose a novel integrated feature selection strategy based on Genetic Algorithm and Support Vector Machine to get an optimal number of features in predicting the amyloid fibril-forming short stretches of peptides. In addition, we investigated the performances of feature selection models that resulted in new and complementary set of properties and concludes that the proposed integrated dimensionality reduction technique outperforms all other methods and achieves the highest sensitivity and specificity of 86% and 82% respectively.

A Two-stage Hybrid Model for Intrusion Detection

As the number of networked computers grows, intrusion detection is an essential component in keeping networks secure. Various approaches to intrusion detection are currently being in use with each one has its own merits and demerits. This paper presents a hybrid approach for modeling intrusion detection system (IDS). Rule based classifier and simple K-means clustering are combined as a hybrid intelligent system. The initial prototype developed by the rule base classifier improves the performance of K-means clustering. The results show that the developed hybrid model provides better IDS.

Development of Genetic Algorithm Embedded KNN for Fingerprint Recognition

A Kohonen self-organizing neural network embedded with genetic algorithm for fingerprint recognition is proposed in this paper. The genetic algorithm is embedded to initiate the Kohonen classifers. By the proposed approach, the neural network learning performance and accuracy are greatly enhanced. In addition, the genetic algorithm can successfully avoid the neural network from being trapped in a local minimum. The proposed method was tested for the recognition of fingerprints. The results were promising to applications.

Knowledge Discovery from Web Usage Data: An Efficient Implementation of Web Log Preprocessing Techniques

Web Usage Mining (WUM) refers to extraction of knowledge from the web log data by application of data mining techniques. WUM generally consists of Web Log Preprocessing, Web Log Knowledge Discovery and Web Log Pattern Analysis. Web Log Preprocessing is a major and complex task of WUM. Elimination of noise and irrelevant data, thereby reducing the burden on the system leads to efficient discovery of patterns by further stages of WUM. In this paper, Web Log Preprocessing Methods to efficiently identify users and user sessions have been implemented and results have been analyzed.

Machine Learning Study of Classifiers Trained with Biophysiochemical Properties of Amino Acids to Predict Fibril Forming Peptide Motifs

It is important to understand the cause of amyloid illnesses by predicting the short protein fragments capable of forming amyloid-like fibril motifs aiding in the discovery of sequence-targeted anti-aggregation drugs. It is extremely desirable to design computational tools to provide affordable in silico predictions owing to the limitations of molecular techniques for their identification. In this research article, we tried to study, from a machine learning perspective, the performance of several machine learning classifiers that use heterogenous features based on biochemical and biophysical properties of amino acids to discriminate between amyloidogenic and non-amyloidogenic regions in peptides. Four conventional machine learning classifiers namely Support Vector Machine, Neural network, Decision tree and Random forest were trained and tested to find the best classifier that fits the problem domain well. Prior to classification, novel implementations of two biologically-inspired feature optimization techniques based on evolutionary algorithms and methodologies that mimic social life and a multivariate method based on projection are utilized in order to remove the unimportant and uninformative features. Among the dimenionality reduction algorithms considered under the study, prediction results show that algorithms based on evolutionary computation is the most effective. SVM best suits the problem domain in its fitment among the classifiers considered. The best classifier is also compared with an online predictor to evidence the equilibrium maintained between true positive rates and false positive rates in the proposed classifier. This exploratory study suggests that these methods are promising in providing amyloidogenity prediction and may be further extended for large-scale proteomic studies.

Performance analysis of human gesture recognition techniques

Today, a lot of research is being done in the area of human gesture recognition due to its various uses such as traffic management, surveillance, healthcare management etc. In this paper the performance of different filters, namely Gabor and Canny for edge detection during preprocessing of image sequences has been studied. Subsequently, the preprocessed images are used for human gesture recognition. The focus is mainly on two gestures-walk and bend. The different classifiers that are used are KNN (K-Nearest Neighbour), NN (Nearest Neighbour) and SVM (Support Vector Machine). The results are then compared for different training dataset sizes for each model. It is found that in general, the Gabor filter gave better results than the Canny edge detection method.

Semi-automated intelligent systems

An intelligent system uses machine learning algorithms to provide outputs to every input provided. The introduction of emotions in intelligent systems is required to create systems that are more similar to human beings and thus more reliable. In this paper, the idea of introducing the emotion ‘uncertainty’ in Intelligent Systems is proposed. A Semi-Automated Intelligent System is introduced in this paper, which combines a Naïve Bayesian Classifier, a Random Forest Classifier and a Multi Layer Perceptron using a Multi Model Strategy to introduce uncertainty. When used individually the classifiers had errors in the range of 6–7% but when combined as the Semi-Automated Intelligent System, the false predictions were kept under 0.2%. The paper also discusses several preprocessing techniques that were applied on the text documents to ensure effective analysis of data.