Qualification: 
Ph.D, M.Tech
Email: 
b_binoy@cb.amrita.edu

Dr. Binoy B. Nair currently serves as Assistant Professor (Selection Grade) at the Department of Electronics and Communication Engineering, Amrita School of Engineering, Coimbatore Campus. He has been with Amrita Vishwa Vidyapeetham since 2007. He received his PhD in Electronics and Communication Engineering and M.Tech in Power Electronics from Amrita Vishwa Vidyapeetham, Coimbatore in 2015 and 2006 respectively. He completed his B.Tech. in Instrumentation and Control Engineering from Calicut University in 2004. He is an Associate Member of IETE.

His current research interests include applications of data analytics in condition monitoring, smart grids, video content analysis and finance.

Research Expertise

As in July 2016, the number of students working at various levels under his supervision are:

  • PhD -1 (video content analysis)
  • M.Tech – 3 (video content analysis, condition monitoring)
  • B.Tech – 8 (video content analysis)

Prospective researchers are welcome to contact him at the official e-mail ID given below.

Funded Projects

Project Title: Design and Evaluation of DRFM Mitigation System
Role: Co-Investigator (Principal Investigator- Dr. GA Shanmugha Sundaram, PHD)
Funding Agency: National Instruments (funded under NI Academic Research Grant)
Funding Amount: USD 118,000.00
Duration: Three years

Teaching

A partial list of the courses taught at both the UG and PG level over the years, is given below:

  1. Pattern Recognition Techniques and Algorithms
  2. Introduction to Data mining
  3. Soft Computing
  4. Agent Based Modelling
  5. Signal Processing for Business Applications
  6. Automotive Control Systems
  7. Control Systems
  8. Electronic Measurements and Measuring Instruments

Publications

Publication Type: Journal Article

Year of Publication Publication Type Title

2017

Journal Article

A. A. John, Dr. Binoy B. Nair, and Kumar, P. N., “Application of clustering techniques for video summarization - An empirical study”, Advances in Intelligent Systems and Computing, vol. 573, pp. 494-506, 2017.[Abstract]


Identification of relevant frames from a video which can then be used as a summary of the video itself, is a challenging task. An attempt has been made in this study to empirically evaluate the effectiveness of data mining techniques in video summarization. Video Summarization systems based on histogram and entropy features extracted from three different color spaces: RGB, HSV and YCBCR and clustered using K-Means, FCM, GM and SOM were empirically evaluated on fifty video datasets from the VSUMM [1] database. Results indicate that clustering based video summarizations techniques can be effectively used for generating video summaries. © Springer International Publishing AG 2017.

More »»

2017

Journal Article

J. A. Balaji, Dr. Harish Ram D. S., and Dr. Binoy B. Nair, “Machine learning approaches to electricity consumption forecasting in automated metering infrastructure (AMI) systems: An empirical study”, Advances in Intelligent Systems and Computing, vol. 574, pp. 254-263, 2017.[Abstract]


In a Smart grid, implementation of value-added services such as distribution automation (DA) and Demand Response (DR) [1] rely heavily on the availability of accurate electricity consumption forecasts. Machine learning based forecasting systems, due to their ability to handle nonlinear patterns, appear promising for the purpose. An empirical evaluation of eight machine learning based systems for electricity consumption forecasting, based on Extreme Learning machines (ELM), Ensemble Regression Trees (ERT), Artificial Neural Network (ANNs) and regression is presented in this study. Forecasting systems thus designed, are validated on consumption data collected from 5275 users. Result indicate that ELM based electricity consumption forecasting systems are not only more accurate than other systems considered, they are considerably faster as well. © Springer International Publishing AG 2017.

More »»

2016

Journal Article

Dr. Binoy B. Nair, “Forecasting short-term stock prices using sentiment analysis and Artificial Neural Networks”, Journal of Chemical and Pharmaceutical Sciences , vol. 9, no. 1, pp. 533 - 536, 2016.[Abstract]


Short-term fluctuations in stock prices are generally considered to be extremely difficult to predict, primarily due to their nonlinear nature. The authors believe that one of the reasons for such seemingly unpredictable fluctuations is the type of sentiment prevailing amongst traders at that point in time. An attempt has been made in this study to forecast the stock returns using the sentiments expressed on social media and Artificial Neural Networks. The proposed system is validated on stocks drawn from the Indian stock markets. Results indicate that the proposed technique can indeed be successfully used for short-term forecasting of stock prices. More »»

2016

Journal Article

J. A. Balaji, Dr. Harish Ram D. S., and Dr. Binoy B. Nair, “Modeling of consumption data for forecasting in automated metering infrastructure (AMI) systems”, Advances in Intelligent Systems and Computing, vol. 466, pp. 165-173, 2016.[Abstract]


The Smart Grid is a new paradigm that aims at improving the efficiency, reliability and economy of the power grid by integrating ICT infrastructure into the legacy grid networks at the generation, transmission and distribution levels. Automatic Metering Infrastructure (AMI) systems comprise the entire gamut of resources from smart meters to heterogeneous communication networks that facilitate two-way dissemination of energy consumption information and commands between the utilities and consumers. AMI is integral to the implementation of smart grid distribution services such as Demand Response (DR) and Distribution Automation (DA). The reliability of these services is heavily dependent on the integrity of the AMI data. This paper investigates the modeling of AMI data using machine learning approaches with the objective of load forecasting of individual consumers. The model can also be extended for detection of anomalies in consumption patterns introduced by false data injection attacks, electrical events and unauthorized load additions or usage modes. © Springer International Publishing Switzerland 2016.

More »»

2015

Journal Article

Dr. Binoy B. Nair and Mohandas, V. P., “Artificial intelligence applications in financial forecasting-a survey and some empirical results”, Intelligent Decision Technologies, vol. 9, pp. 99-140, 2015.[Abstract]


Financial forecasting is an area of research which has been attracting a lot of attention recently from practitioners in the field of artificial intelligence. Apart from the economic benefits of accurate financial prediction, the inherent nonlinearities in financial data make the task of analyzing and forecasting an extremely challenging task. This paper presents a survey of more than 100 articles published over two centuries (from 1933 up to 2013) in an attempt to identify the developments and trends in the field of financial forecasting with focus on application of artificial intelligence for the purpose. The findings from the survey indicate that artificial intelligence and signal processing based techniques are more efficient when compared to traditional financial forecasting techniques and these techniques appear well suited for the task of financial forecasting. Some of the issues that need addressing are discussed in brief. A novel technique for selection of the input dataset size for ensuring best possible forecast accuracy is also presented. The results confirm the effectiveness of the proposed technique in improving the accuracy of forecasts. © 2015 - IOS Press and the authors. All rights reserved.

More »»

2015

Journal Article

Dr. Binoy B. Nair and Mohandas, V. P., “An intelligent recommender system for stock trading”, Intelligent Decision Technologies, vol. 9, pp. 243–269, 2015.[Abstract]


Generating consistent profits from stock markets is considered to be a challenging task, especially due to the nonlinear nature of the stock price movements. Traders need to have a deep understanding of the market behavior patterns in order to trade successfully. In this study, a GA optimized technical indicator decision tree-SVM based intelligent recommender system is proposed, which can learn patterns from the stock price movements and then recommend appropriate one-day-ahead trading strategy. The recommender system takes the task of identifying stock price patterns on itself, allowing even a lay-user, who is not well versed in stock market behavior, to trade profitably on a consistent basis. The efficacy of the proposed system is validated on four different stocks belonging to two different stock markets (India and UK) over three different time frames for each stock. Performance of the proposed system is validated using fifteen different measures. Performance is compared with traditional technical indicator based trading and the traditional buy and hold strategy. Results indicate that the proposed system is capable of generating profits for all the stocks in both the stock markets considered.

More »»

2015

Journal Article

A. Sumesh, Thekkuden, D. Thomas, Dr. Binoy B. Nair, Rameshkumar, K., and Mohandas, K., “Acoustic Signature Based Weld Quality Monitoring for SMAW Process Using Data Mining Algorithms”, Advances in Mechanical Engineering, vol. 813-814, pp. 1104-1113, 2015.[Abstract]


The quality of weld depends upon welding parameters and exposed environment conditions. Improper selection of welding process parameter is one of the important reasons for the occurrence of weld defect. In this work, arc sound signals are captured during the welding of carbon steel plates. Statistical features of the sound signals are extracted during the welding process. Data mining algorithms such as Naive Bayes, Support Vector Machines and Neural Network were used to classify the weld conditions according to the features of the sound signal. Two weld conditions namely good weld and weld with defects namely lack of fusion, and burn through were considered in this study. Classification efficiencies of machine learning algorithms were compared. Neural network is found to be producing better classification efficiency comparing with other algorithms considered in this study. More »»

2015

Journal Article

Dr. Binoy B. Nair, “GA-wavelet based multi-patient heart sound monitoring system”, International Journal of Applied Engineering Research, vol. 10, pp. 37469 - 37473, 2015.[Abstract]


A novel portable wireless heart sound monitoring system that can help the healthcare professional monitor the heart sounds of multiple patients is presented in this study. This system will allow a single healthcare professional to monitor the heart sounds of a large number of patients, as and when needed and thus significantly improve the quality of healthcare available to the patients and at the same time drastically reducing the need for making frequent rounds to the patients’ bedsides. The proposed system employs GA-optimized wavelet based denoising to ensure that the heart sounds received by the healthcare giver is as free from noise as possible. The proposed system is empirically validated on a total of 2560 heart sound signals. The results indicate that the proposed system is indeed capable of being an asset to healthcare providers in improving the quality of healthcare that they can provide. More »»

2015

Journal Article

Dr. Binoy B. Nair, MOHANDAS, V. P., Nayanar, N., Teja, E. S. R., Vigneshwari, S., and Teja, K. V. N. S., “A Stock Trading Recommender System Based on Temporal Association Rule Mining”, SAGE Open, vol. 5, 2015.[Abstract]


Recommender systems capable of discovering patterns in stock price movements and generating stock recommendations based on the patterns thus discovered can significantly supplement the decision-making process of a stock trader. Such recommender systems are of great significance to a layperson who wishes to profit by stock trading even while not possessing the skill or expertise of a seasoned trader. A genetic algorithm optimized Symbolic Aggregate approXimation (SAX)–Apriori based stock trading recommender system, which can mine temporal association rules from the stock price data set to generate stock trading recommendations, is presented in this article. The proposed system is validated on 12 different data sets. The results indicate that the proposed system significantly outperforms the passive buy-and-hold strategy, offering scope for a layperson to successfully invest in capital markets. More »»

2014

Journal Article

Dr. Binoy B. Nair, Xavier, N., Mohandas, V. P., Sathyapal, A., Anusree, E. G., Kumar, P., and Ravikumar, V., “A GA-optimized SAX-ANN based Stock Level Prediction System”, International Journal of Computer Applications, vol. 106, 2014.[Abstract]


Forecasting stock price movements is of immense importance to any stock trader. However, traditionally, this has been accomplished using technical analysis tools. In this study, an attempt has been made to employ data mining to identify the one-day-ahead stock price levels. Two different approaches are considered. The two approaches are empirically validated on twelve stock price datasets, with the stocks drawn from the Indian, US and UK stock markets. Results indicate that both the approaches proposed in the present study are capable of successfully forecasting the one-day-ahead stock price levels. More »»

2014

Journal Article

Dr. Sakthivel N.R., Dr. Binoy B. Nair, Dr. Elangovan M., Sugumaran, V., and Saravanmurugan, S., “Comparison of dimensionality reduction techniques for the fault diagnosis of mono block centrifugal pump using vibration signals”, Engineering Science and Technology, an International Journal, vol. 17, pp. 30 - 38, 2014.[Abstract]


Abstract Bearing fault, Impeller fault, seal fault and cavitation are the main causes of breakdown in a mono block centrifugal pump and hence, the detection and diagnosis of these mechanical faults in a mono block centrifugal pump is very crucial for its reliable operation. Based on a continuous acquisition of signals with a data acquisition system, it is possible to classify the faults. This is achieved by the extraction of features from the measured data and employing data mining approaches to explore the structural information hidden in the signals acquired. In the present study, statistical features derived from the vibration data are used as the features. In order to increase the robustness of the classifier and to reduce the data processing load, dimensionality reduction is necessary. In this paper dimensionality reduction is performed using traditional dimensionality reduction techniques and nonlinear dimensionality reduction techniques. The effectiveness of each dimensionality reduction technique is also verified using visual analysis. The reduced feature set is then classified using a decision tree. The results obtained are compared with those generated by classifiers such as Naïve Bayes, Bayes Net and kNN. The effort is to bring out the better dimensionality reduction technique–classifier combination. More »»

2013

Journal Article

Dr. Binoy B. Nair, Mohandas, V. P., Varun, G., Chaitanya, I., K Krishna, S., S Karthik, M., and B Kumar, J. Vishnu, “A temporal association rule mining based decision support system for stock trading”, International Research Journal of Finance and Economics, vol. 117, pp. 67–79, 2013.

2012

Journal Article

Dr. Sakthivel N.R., Dr. Binoy B. Nair, and Sugumaran, V., “Soft computing approach to fault diagnosis of centrifugal pump”, Applied Soft Computing, vol. 12, pp. 1574 - 1581, 2012.[Abstract]


Fault detection and isolation in rotating machinery is very important from an industrial viewpoint as it can help in maintenance activities and significantly reduce the down-time of the machine, resulting in major cost savings. Traditional methods have been found to be not very accurate. Soft computing based methods are now being increasingly employed for the purpose. The proposed method is based on a genetic programming technique which is known as gene expression programming (GEP). \{GEP\} is somewhat a new member of the genetic programming family. The main objective of this paper is to compare the classification accuracy of the proposed evolutionary computing based method with other pattern classification approaches such as support vector machine (SVM), Wavelet-GEP, and proximal support vector machine (PSVM). For this purpose, six states viz., normal, bearing fault, impeller fault, seal fault, impeller and bearing fault together, cavitation are simulated on centrifugal pump. Decision tree algorithm is used to select the features. The results obtained using \{GEP\} is compared with the performance of Wavelet-GEP, support vector machine (SVM) and proximal support vector machine (PSVM) based classifiers. It is observed that both \{GEP\} and \{SVM\} equally outperform the other two classifiers (PSVM and Wavelet-GEP) considered in the present study. More »»

2012

Journal Article

Dr. Sakthivel N.R., Sugumaran, V., and Dr. Binoy B. Nair, “Automatic rule learning using roughset for fuzzy classifier in fault categorization of mono-block centrifugal pump”, Applied Soft Computing, vol. 12, pp. 196 - 203, 2012.[Abstract]


Rule learning based approach to fault detection and diagnosis is becoming very popular, mainly due to their high accuracy when compared to older statistical methods. Fault detection and diagnosis of various mechanical components of centrifugal pump is essential to increase the productivity and reduce the breakdowns. This paper presents the use of rough sets to generate the rules from statistical features extracted from vibration signals under good and faulty conditions of a centrifugal pump. A fuzzy inference system (FIS) is built using rough set rules and tested using test data. The effect of different types of membership functions on the \{FIS\} performance is also presented. Finally, the performance of this classifier is compared to that of a fuzzy-antminer classifier and to multi-layer perceptron (MLP) based classifiers.

More »»

2012

Journal Article

Dr. Sakthivel N.R., Dr. Binoy B. Nair, Sugumaran, V., and Roy, R. S., “Application of standalone system and hybrid system for fault diagnosis of centrifugal pump using time domain signals and statistical features”, International Journal of Data Mining, Modelling and Management, vol. 4, pp. 74-104, 2012.[Abstract]


Centrifugal pumps are a crucial part of many industrial plants. Early detection of faults in pumps can increase their reliability, reduce energy consumption, service and maintenance costs, and increase their life-cycle and safety, thus providing a significant reduction in life-time costs. Vibration-based condition monitoring and analysis using machine learning approach is gaining momentum. Vibration monitoring can identify a number of potential pump problems such as bearing fault, impeller fault, seal fault, loose joints or fasteners, and cavitation issues. This paper compares the fault classification efficiency of standalone decision tree classifier, standalone rough set classifier with hybrid systems such as decision tree-fuzzy classifier and rough set-fuzzy classifier. The results obtained using standalone systems are compared with the performance of hybrid systems. It is observed that standalone systems outperform the hybrid systems. More »»

2011

Journal Article

Dr. Sakthivel N.R., Dr. Binoy B. Nair, Sugumaran, V., and Rai, R. S., “Decision support system using artificial immune recognition system for fault classification of centrifugal pump”, International Journal of Data Analysis Techniques and Strategies, vol. 3, pp. 66-84, 2011.[Abstract]


Centrifugal pumps are a crucial part of many industrial plants. Early detection of faults in pumps can increase their reliability, reduce energy consumption, service and maintenance costs, and increase their life-cycle and safety, thus resulting in a significant reduction in life-time costs. Vibration analysis is a very popular tool for condition monitoring of machinery like pumps, turbines and compressors. The proposed method is based on a novel immune inspired supervised learning algorithm which is known as artificial immune recognition system (AIRS). This paper compares the fault classification efficiency of AIRS with hybrid systems such as principle component analysis (PCA)-Naïve Bayes and PCA-Bayes Net. The robustness of the proposed method is examined using its classification accuracy and kappa statistics. It is observed that the AIRS-based system outperforms the other two methods considered in the present study. More »»

2011

Journal Article

Dr. Binoy B. Nair, Sai, S. G., Naveen, A. N., Lakshmi, A., Venkatesh, G. S., and Mohandas, V. P., “A GA-artificial neural network hybrid system for financial time series forecasting”, Communications in Computer and Information Science, vol. 147 CCIS, pp. 499-506, 2011.[Abstract]


Accurate prediction of financial time series, such as those generated by stock markets, is a highly challenging task due to the highly nonlinear nature of such series. A novel method of predicting the next day's closing value of a stock market is proposed and empirically validated in the present study. The system uses an adaptive artificial neural network based system to predict the next day's closing value of a stock market index. The proposed system adapts itself to the changing market dynamics with the help of genetic algorithm which tunes the parameters of the neural network at the end of each trading session so that best possible accuracy is obtained. The effectiveness of the proposed system is established by testing on five international stock indices using ten different performance measures. © 2011 Springer-Verlag. More »»

2011

Journal Article

Dr. Binoy B. Nair, Mohandas, V. P., and Dr. Sakthivel N.R., “Predicting stock market trends using hybrid ant-colony-based data mining algorithms: an empirical validation on the Bombay Stock Exchange”, International Journal of Business Intelligence and Data Mining, vol. 6, pp. 362-381, 2011.[Abstract]


Ant Colony Optimisation (ACO) algorithms use simple mutually cooperating agents (ants) to produce a robust and adaptive search system, which can be used for knowledge discovery. In this paper, a Support Vector Machine (SVM)-cAnt-Miner-based system for predicting the next-day’s trend in stock markets is proposed. The trend predicted by the proposed system is then used to identify the appropriate time to buy and sell securities. Performance of the proposed system is evaluated against SVM-Ant-Miner, SVM-Ant-Miner2, Naïve-Bayes and an Artificial Neural Network (ANN)-based trend prediction system. The results indicate that the proposed system outperforms all the other techniques considered. More »»

2011

Journal Article

Dr. Binoy B. Nair, Preetam, M. T. Vamsi, Panicker, V. R., Kumar, G., and Tharanya, A., “A Novel Feature Selection method for Fault Detection and Diagnosis of Control Valves”, International Journal of Computer Science Issues, 2011.[Abstract]


In this paper, a novel method for feature selection and its application to fault detection and Isolation (FDI) of control valves is presented. The proposed system uses an artificial bee colony (ABC) optimized minimum redundancy maximum relevance (mRMR) based feature selection method to identify the important features from the measured control valve parameters. The selected features are then given to a naïve Bayes classifier to detect nineteen different types of faults. The performance of the proposed feature selection system is compared to that of six other feature selection techniques and the proposed system is found to be superior. More »»

2011

Journal Article

Dr. Sakthivel N.R., Indira, V., Dr. Binoy B. Nair, and Sugumaran, V., “Use of histogram features for decision tree-based fault diagnosis of monoblock centrifugal pump”, International Journal of Granular Computing, Rough Sets and Intelligent Systems, vol. 2, pp. 23-36, 2011.[Abstract]


Monoblock centrifugal pumps are a crucial part of many industrial plants. Early detection of faults in pumps can increase their reliability, reduce energy consumption, service and maintenance costs, and increase their life-cycle and safety, thus resulting in a significant reduction in life-time costs. It is clear that the fault diagnosis and condition monitoring of pumps are important issues that cannot be ignored. Machine learning-based approach to fault detection and diagnosis is becoming very popular, mainly due to their high accuracy when compared to older statistical methods. There are set of related activities involved in machine learning approach namely, data acquisition from the monoblock centrifugal pump, feature extraction from the acquired data, feature selection, and finally feature classification. This paper presents the use of C4.5 decision tree algorithm for fault diagnosis through histogram feature extracted from vibration signals of good and faulty conditions of monoblock centrifugal pump. The performance of the proposed system is compared to that of a Naïve Bayes-based system to validate the superiority of the proposed system. More »»

2010

Journal Article

Dr. Sakthivel N.R., Sugumaran, V., and Dr. Binoy B. Nair, “Comparison of decision tree-fuzzy and rough set-fuzzy methods for fault categorization of mono-block centrifugal pump”, Mechanical Systems and Signal Processing, vol. 24, pp. 1887 - 1906, 2010.[Abstract]


Mono-block centrifugal pumps are widely used in a variety of applications. In many applications the role of mono-block centrifugal pump is critical and condition monitoring is essential. Vibration based continuous monitoring and analysis using machine learning approach is gaining momentum. Particularly, artificial neural networks, fuzzy logic have been employed for continuous monitoring and fault diagnosis. This paper presents the use of decision tree and rough sets to generate the rules from statistical features extracted from vibration signals under good and faulty conditions of a mono-block centrifugal pump. A fuzzy classifier is built using decision tree and rough set rules and tested using test data. The results obtained using decision tree rules and those obtained using rough set rules are compared. Finally, the accuracy of a principle component analysis based decision tree-fuzzy system is also evaluated. The study reveals that overall classification accuracy obtained by the decision tree-fuzzy hybrid system is to some extent better than the rough set-fuzzy hybrid system. More »»

2010

Journal Article

Dr. Binoy B. Nair, Mohandas, V. P., and Dr. Sakthivel N.R., “A decision tree—rough set hybrid system for stock market trend prediction”, International Journal of Computer Applications, vol. 6, pp. 1–6, 2010.[Abstract]


Prediction of stock market trends has been an area of great interest both to those who wish to profit by trading stocks in the stock market and for researchers attempting to uncover the information hidden in the stock market data. Applications of data mining techniques for stock market prediction, is an area of research which has been receiving a lot of attention recently. This work presents the design and performance evaluation of a hybrid decision tree- rough set based system for predicting the next days‟ trend in the Bombay Stock Exchange (BSESENSEX). Technical indicators are used in the present study to extract features from the historical SENSEX data. C4.5 decision tree is then used to select the relevant features and a rough set based system is then used to induce rules from the extracted features. Performance of the hybrid rough set based system is compared to that of an artificial neural network based trend prediction system and a naive bayes based trend predictor. It is observed from the results that the proposed system outperforms both the neural network based system and the naive bayes based trend prediction system. More »»

2010

Journal Article

Dr. Binoy B. Nair, Mohandas, V. P., and Dr. Sakthivel N.R., “A genetic algorithm optimized decision tree-SVM based stock market trend prediction system”, International Journal on Computer Science and Engineering, vol. 2, pp. 2981–2988, 2010.[Abstract]


Prediction of stock market trends has been an area of great interest both to researchers attempting to uncover the information hidden in the stock market data and for those who wish to profit by trading stocks. The extremely nonlinear nature of the stock market data makes it very difficult to design a system that can predict the future direction of the stock market with sufficient accuracy. This work presents a data mining based stock market trend prediction system, which produces highly accurate stock market forecasts. The proposed system is a genetic algorithm optimized decision tree-support vector machine (SVM) hybrid, which can predict one-day-ahead trends in stock markets. The uniqueness of the proposed system lies in the use of the hybrid system which can adapt itself to the changing market conditions and in the fact that while most of the attempts at stock market trend prediction have approached it as a regression problem, present study converts the trend prediction task into a classification problem, thus improving the prediction accuracy significantly. Performance of the proposed hybrid system is validated on the historical time series data from the Bombay stock exchange sensitive index (BSE-Sensex). The system performance is then compared to that of an artificial neural network (ANN) based system and a naïve Bayes based system. It is found that the trend prediction accuracy is highest for the hybrid system and the genetic algorithm optimized decision treeSVM hybrid system outperforms both the artificial neural network and the naïve bayes based trend prediction systems. More »»

2010

Journal Article

Dr. Sakthivel N.R., Sugumaran, V., and Dr. Binoy B. Nair, “Application of Support Vector Machine (SVM) and Proximal Support Vector Machine (PSVM) for fault classification of monoblock centrifugal pump”, International Journal of Data Analysis Techniques and Strategies, vol. 2, pp. 38-61, 2010.[Abstract]


Monoblock centrifugal pumps are widely used in a variety of applications. Defects and malfunctions (faults) of these pumps result in significant economic loss. Therefore, the pumps must be under constant monitoring. When a possible fault is detected, diagnosis is carried out to pinpoint it. In many applications, the role of monoblock centrifugal pumps is critical and condition monitoring is essential. Vibration-based condition monitoring and analysis using the machine-learning approach is gaining momentum. In particular, Artificial Neural Networks (ANNs), fuzzy logic and roughsets have been employed for condition monitoring and fault diagnosis. While it is difficult to train the neural network-based fault classifier, the classification accuracy in case of fuzzy logic- and roughest-based fault classifiers is not very high. This paper presents the use of Support Vector Machines (SVMs) and Proximal Support Vector Machines (PSVMs) for classifying faults using statistical features extracted from vibration signals under good and faulty conditions of a monoblock centrifugal pump. The Decision Tree (DT) algorithm is used to select prime features. These features are fed as inputs for training and testing SVMs and PSVMs and their fault classification accuracy is compared. The results are found to be better than neural network-, fuzzy- and roughest-based methods. More »»

Publication Type: Conference Paper

Year of Publication Publication Type Title

2015

Conference Paper

Dr. Elangovan M., Dr. Sakthivel N.R., Saravanamurugan, S., Dr. Binoy B. Nair, and Sugumaran, V., “Machine Learning Approach to the Prediction of Surface Roughness Using Statistical Features of Vibration Signal Acquired in Turning”, in Procedia Computer Science, 2015, vol. 50, pp. 282–288.[Abstract]


Abstract Prediction of surface roughness is always considered important in the manufacturing field. A product may require a particular roughness that may be specified by the designer for various reasons, either functional requirement or aesthetic appeal. While modern manufacturing systems and machines have always contributed towards better control of surface quality, better computational facilities and the availability of newer algorithms attract researchers to understand the prediction of quality in a better manner. In this paper, prediction of surface roughness by multiple regression analysis is presented. The predictors are cutting parameters, tool wear and the statistical parameters extracted from the vibration signals of a turning centre. The contribution of various statistical parameters in prediction of surface roughness is studied. A Machine learning approach using feature reduction using principle component analysis is attempted to achieve higher predictability and low computational effort. More »»

2013

Conference Paper

Dr. Binoy B. Nair, “Improving returns from the Markowitz model using GA- An empirical validation on the BSE”, in International Conference on Advances in Computer Science (AETACS), 2013.

2013

Conference Paper

A. Ravisankar, Agarwal, A., Kulkarni, A., Kumar, M. A. A., Ram, B. B., Sivasubramaniam, S., and Dr. Binoy B. Nair, “A GPS-less Navigation System”, in India Educators' Conference (TIIEC), 2013 Texas Instruments, 2013.[Abstract]


GPS receivers have a major drawback: they don't work properly under multi-storey concrete structures, for e.g. in underground car parks, University buildings, shopping malls, factory complexes etc. A navigation system for such huge enclosed spaces, which does not rely on a GPS is very desirable for visitors to such places who do not know the layout of the place. This paper presents the design and development of a low-cost GPS-less navigation system based on TI Stellaris-LM3S3748, which could help visitors find their way around such places.

More »»

2013

Conference Paper

Dr. Binoy B. Nair, “Low-cost PC Based Potentiostat for Student Laboratory Applications”, in Amrita Bio Quest , 2013.

2013

Conference Paper

Dr. Binoy B. Nair, “PC Based Heart Sound Monitoring System”, in Amrita Bio Quest 2013, 2013.

2012

Conference Paper

Dr. Binoy B. Nair, Patturajan, M., Mohandas, V. P., and Sreenivasan, R. R., “Predicting the BSE sensex: Performance comparison of adaptive linear element, feed forward and time delay neural networks”, in 2012 International Conference on Power, Signals, Controls and Computation, EPSCICON 2012, Thrissur, Kerala, 2012.[Abstract]


Accurate prediction of financial time series (which can be considered as nonlinear systems) especially in relation to emerging markets like India assumes prominence in that, these markets offer significantly higher opportunities for wealth creation for the investor. This paper compares the effectiveness of different types of Adaptive network architectures in one-step ahead prediction of the daily returns of Bombay Stock Exchange Sensitive Index (SENSEX). The performance of each network is evaluated using 17 different performance measures to find the best network architecture. Also, an empirical evaluation of the weak form of Efficient Market Hypothesis (EMH) for the data in reference is carried out here. © 2012 IEEE.

More »»

2010

Conference Paper

Dr. Binoy B. Nair, Dharini, N. M., and Mohandas, V. P., “A stock market trend prediction system using a hybrid decision tree-neuro-fuzzy system”, in Proceedings - 2nd International Conference on Advances in Recent Technologies in Communication and Computing, ARTCom 2010, Kottayam, 2010, pp. 381-385.[Abstract]


Stock market prediction is of great interest to stock traders and applied researchers. Main issues in developing a fully automated stock market prediction system are: feature extraction from the stock market data, feature selection for highest prediction accuracy, the dimensionality reduction of the selected feature set and the accuracy and robustness of the prediction system. In this paper, an automated decision tree-adaptive neuro-fuzzy hybrid automated stock market trend prediction system is proposed. The proposed system uses technical analysis (traditionally used by stock traders) for feature extraction and decision tree for feature selection. Selected features are then subjected to dimensionality reduction and the reduced dataset is then applied to the adaptive neuro-fuzzy system for the next-day stock market trend prediction. The proposed system is tested on four major international stock markets. The results show that the proposed hybrid system produces much higher accuracy when compared to stand-alone decision tree based system and ANFIS based system without feature selection and dimensionality reduction. © 2010 IEEE. More »»

2010

Conference Paper

Dr. Binoy B. Nair, Keerthana, T., Barani, P. R., Kaushik, A., Sathees, A., and Sreekumaran A Nair, “A GSM-based versatile Unmanned Ground Vehicle”, in International Conference on "Emerging Trends in Robotics and Communication Technologies", INTERACT-2010, Chennai, 2010, pp. 356-361.[Abstract]


Operations like radioactive waste handling, bomb disposal, surveillance, search and rescue are today performed mostly by humans at great risk to their own safety and well-being. In order to minimize direct human intervention in such operations, the design of a remotely operated versatile Unmanned Ground Vehicle (UGV) mounted with a robotic manipulator is presented in this paper. The robustness, range and security of the communication link between the remote base station and the robot, obstacle avoidance and the real time control of the robot are some of the major issues encountered while deploying such robots in the above scenarios. In this paper, the design of a versatile UGV which leverages the already existing GSM mobile telephony network to establish a long-range, secure, fast and reliable connection with the remote base station is presented. The UGV is also mounted with a robotic manipulator with four degrees of freedom with a gripper type end-effector, which can be used for grabbing objects and thus help in search and rescue type operations. The robot is equipped with IR sensors and camera for obstacle detection and avoidance. The camera is also used to send the visual information back to the base station in real-time, allowing accurate control of and monitoring over long distances. © 2010 IEEE. More »»

2010

Conference Paper

Dr. Binoy B. Nair, Mohandas, V. P., Dr. Sakthivel N.R., Nagendran, S., Nareash, A., Nishanth, R., Ramkumar, S., and Kumar, M. D., “Application of hybrid adaptive filters for stock market prediction”, in Proceedings of 2010 International Conference on Communication and Computational Intelligence, INCOCCI-2010, Perundurai, Erode, 2010, pp. 443-447.[Abstract]


Prediction of stock market trends has been an area of great interest both to those who wish to profit by trading stocks in the stock market and for researchers attempting to uncover the information hidden in the stock market data. Traditional techniques such technical analysis and signal processing techniques such as moving averages and regression have had limited success in predicting markets, which could be attributed to the dynamic behavior of the markets. In signal processing, adaptive filters have been widely used for efficient filtering of signals. However, the utilization of adaptive filters for prediction, especially of financial signals, has not received much attention in literature. In this study, hybrid adaptive filters are introduced for prediction to obtain highly accurate results. The hybrid filters used are DCT-LMS, DCT-NLMS, DCT-RLS and Kalman filters. The proposed method is used to predict the values of five of the largest stock markets, namely, BSE100, NASDAQ, NIKKEI225, S&P NIFTY, and FTSE100. The performance of hybrid adaptive filters is compared against the conventional filters like autoregressive (AR), Moving Average (MA) filters and adaptive filters like LMS, NLMS etc. The base technique considered is the Random Walk (RW) process which acts as the benchmark technique. The results show a high degree of prediction accuracy for the hybrid adaptive filters, which is very high when compared to conventional filters, thus indicating that hybrid adaptive filters can be successfully used for stock market prediction. © 2010 Kongu Engineering College. More »»

2010

Conference Paper

D. P. Soni, Ranjana, M., Gokul, N. A., Swaminathan, S., and Dr. Binoy B. Nair, “Autonomous arecanut tree climbing and pruning robot”, in International Conference on "Emerging Trends in Robotics and Communication Technologies", INTERACT-2010, Chennai, 2010, pp. 278-282.[Abstract]


This paper presents the design and development of a versatile autonomous tree climbing & pruning robot for arecanut farming. The robot has a linear frictional force based non-linear self-regulatory system with 9 DOF that adapts itself to changing trunk diameter. The robot chassis is made rigid and light-weight. An on-board battery is the power source. The motion is provided by two DC motors fitted to spiked wheels. A 5 DOF PUMA arm is mounted on the robot for cutting and pruning purpose. The intelligence is based on Digital Image Processing using Object Recognition techniques. Machine vision is through a guiding camera mounted over the Robotic Arm that feeds the OMAP 32-bit Micro-controller made of ARM CORTEX-M3 and Da Vinci processor which has Wavelet based JPEG compression and noise elimination module. A manual override with a display screen allows user to view and control the robot when necessary. © 2010 IEEE. More »»

2010

Conference Paper

B. Sujithra, Dr. Binoy B. Nair, Minuvarthini, M., and Mohandas, V. P., “Stock market prediction using a hybrid neuro-fuzzy system”, in Proceedings - 2nd International Conference on Advances in Recent Technologies in Communication and Computing, ARTCom 2010, Kottayam, 2010, pp. 243-247.[Abstract]


Stock market prediction is an important area of financial forecasting, which is of great interest to stock investors, stock traders and applied researchers. Main issues in developing a fully automated stock market prediction system are: feature extraction from the stock market data, feature selection for highest prediction accuracy, the dimensionality reduction of the selected feature set and the accuracy and robustness of the prediction system. In this paper, an automated decision tree-adaptive neuro-fuzzy hybrid automated stock market prediction system is proposed. The proposed system uses technical analysis (traditionally used by stock traders) for feature extraction and decision tree for feature selection. Dimensionality reduction is carried out using fifteen different dimensionality reduction techniques. The dimensionality reduction technique producing the best prediction accuracy is selected to produce the reduced dataset. The reduced dataset is then applied to the adaptive neuro-fuzzy system for the next-day stock market prediction. The neuro-fuzzy system forms the stock market model adaptively, based on the features present in the reduced dataset. The proposed system is tested on the Bombay Stock Exchange sensitive index (BSE-SENSEX). The results show that the proposed hybrid system produces much higher accuracy when compared to stand-alone decision tree based system and ANFIS based system without feature selection and dimensionality reduction. © 2010 IEEE. More »»
207
PROGRAMS
OFFERED
5
AMRITA
CAMPUSES
15
CONSTITUENT
SCHOOLS
A
GRADE BY
NAAC, MHRD
9th
RANK(INDIA):
NIRF 2017
150+
INTERNATIONAL
PARTNERS
  • Amrita on Social Media

  • Contact us

    Amrita Vishwa Vidyapeetham
    Amritanagar, Coimbatore - 641 112
    Tamilnadu, India