Dr. Manjula Bairam | Kakatiya University (original) (raw)
Papers by Dr. Manjula Bairam
International Journal of Engineering and Advanced Technology, 2019
increasingly, the data is increasing day by day and storage capacity is expanding more and more, ... more increasingly, the data is increasing day by day and storage capacity is expanding more and more, this allowing the field of SA to growing and developing faster in research and prospecting for different opinions and emotions to be combed and technically treated to be more accurate. In our present, data can be a wealth where major global companies and development, research and crime detection centers benefit from it. In this paper we focused on the current apprises of research in this field which contributed to various improvements in the field of sentiment analysis. We have tackles comprehensive overviews for different fields which related to the Sentiment Analysis (Transfer Learning (TL), Building Resource (BR), Emotion Detection (ED)) which have the popularity of researchers has gained in recent times and attracted them. We have the aim of this survey which is to give a clear and accurate picture about the techniques of analyzing emotions and related fields
Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers... more Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers' Association is considered to be one of Asia’s fastest stock exchanges and oldest stock exchange in the South Asia region. On 31 August 1957, the BSE became the first stock exchange to be recognized by the Indian Government under the Securities Contracts Regulation Act 1956. In this paper, we developed a novel framework that can achieve parallel time series prediction using Hadoop. By implementing the proposed framework, the system should be able to deal with massive amount of time series data, either regular or irregular. The proposed system can handle the optimization, parameter selection and also model combination through K-mean clustering. In this paper, experiment is carried to forecast the company’s next bid accurately based on the other companies that have similar trend with it.
The hardware-software partitioning problem is a key aspect of co-design of digital electronic sys... more The hardware-software partitioning problem is a key aspect of co-design of digital electronic systems; extensive research has been performed with diverse definitions of partitioning problems. However, existent partitioning solutions are not applicable to many real-time applications partly because of restricted input specification or insufficient constraints. By using the off-loading technique, a fundamental problem is to partition the dynamic computation of application involved in between the mobile device and cloud. In this paper, we proposed three approaches for mobile cloud applications: Extending the access to cloud services to mobile devices, to enabling mobile devices to work collaboratively as cloud resource providers, to enhance the execution of mobile applications on portable devices using available cloud resources. Suitable framework is providing for runtime support with dynamic computation of the application was proposed. This is different from existing mechanism, the fra...
In the field of digital watermarking, digital image watermarking for copyright protection has att... more In the field of digital watermarking, digital image watermarking for copyright protection has attracted a lot of attention in the research community. Digital watermarking contains varies techniques for protecting the digital content. Among all those techniques,Discrete Wavelet Transform (DWT) provides higher image imperceptibility and robustness. Over the years, researchers have been designing watermarking techniques with robustness in mind, in order for the watermark to be resistant against any image processing techniques. Furthermore, the requirements of a good watermarking technique includes a tradeoff between robustness, image quality (imperceptibility) and capacity. In this paper, we have done an extensive literature review for the existing DWT techniques and those combined with other techniques such as Neural Networks. In addition to that, we have discuss the contribution of Neural Networks in copyright protection. Finally we reached our goal in which we identified the researc...
Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers... more Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers' Association is considered to be one of Asia’s fastest stock exchanges and oldest stock exchange in the South Asia region. On 31 August 1957, the BSE became the first stock exchange to be recognized by the Indian Government under the Securities Contracts Regulation Act 1956. In this paper, we developed a novel framework that can achieve parallel time series prediction using Hadoop. By implementing the proposed framework, the system should be able to deal with massive amount of time series data, either regular or irregular. The proposed system can handle the optimization, parameter selection and also model combination through K-mean clustering. In this paper, experiment is carried to forecast the company’s next bid accurately based on the other companies that have similar trend with it.
The hardware-software partitioning problem is a key aspect of co-design of digital electronic sys... more The hardware-software partitioning problem is a key aspect of co-design of digital electronic systems; extensive research has been performed with diverse definitions of partitioning problems. However, existent partitioning solutions are not applicable to many real-time applications partly because of restricted input specification or insufficient constraints. By using the off-loading technique, a fundamental problem is to partition the dynamic computation of application involved in between the mobile device and cloud. In this paper, we proposed three approaches for mobile cloud applications: Extending the access to cloud services to mobile devices, to enabling mobile devices to work collaboratively as cloud resource providers, to enhance the execution of mobile applications on portable devices using available cloud resources. Suitable framework is providing for runtime support with dynamic computation of the application was proposed. This is different from existing mechanism, the fra...
In digital image watermarking, many techniques are used for obtaining optimal image representatio... more In digital image watermarking, many techniques are used for obtaining optimal image representation; image decomposition as a standard set in the frequency domain is not necessary (DCT, DWT, and DFT). Therefore, another representation of transform was explored which is about using algebra methods and algorithms with watermarking like singular value decomposition algorithm based on watermarking. SVD algorithms have shown that they are highly strong against extensive range of attacks. In addition to that, Genetic Algorithm (GA) is used with SVD to optimize the watermarking. Many techniques and algorithms have already been proposed on the using of SVD and GA on digital watermarking. In this paper, we introduce a general survey on those techniques along with analysis for them based on the two measures, transparency and robustness.
Scientific reports, Sep 1, 2016
Although our knowledge of aging has greatly expanded in the past decades, it remains elusive why ... more Although our knowledge of aging has greatly expanded in the past decades, it remains elusive why and how aging contributes to the development of age-related diseases (ARDs). In particular, a global mechanistic understanding of the connections between aging and ARDs is yet to be established. We rely on a network modelling named "GeroNet" to study the connections between aging and more than a hundred diseases. By evaluating topological connections between aging genes and disease genes in over three thousand subnetworks corresponding to various biological processes, we show that aging has stronger connections with ARD genes compared to non-ARD genes in subnetworks corresponding to "response to decreased oxygen levels", "insulin signalling pathway", "cell cycle", etc. Based on subnetwork connectivity, we can correctly "predict" if a disease is age-related and prioritize the biological processes that are involved in connecting to multiple...
Predicting stock data with traditional time series analysis has neural network may be more suitab... more Predicting stock data with traditional time series analysis has neural network may be more suitable for the task, because no assumption a has to be made prior to forecasting. Furthermore, a neural network has the ability to extract useful information from large sets of data, which often is required for a satisfying description of a financial time series. Subsequently an Error Correction Network is defined and implemented for an empirical study. Technical as well as fundamental data are used as input to the network. One stocks of the BSE are predicted using t standard Error Correction Network whereas an extension of the Error Correction Network is used for weekly predictions. The results on the stocks are less convincing; nevertheless the net strategy.
International …
Mobile ad-hoc network (MANET) is a wireless network without infrastructure. Nodes can commutate e... more Mobile ad-hoc network (MANET) is a wireless network without infrastructure. Nodes can commutate each other without central infrastructure; because they are self organised and self configurable with easy deployment. To commutative each other it is required efficient routing protocols in MANET technology. In these we find out an efficient routing protocols for routing, and we had considered differ approaches like routing load, end to end packet delivery and performance of protocols. To analysis this we implemented two different routing protocols which are proactive and reactive. To analysis these aspects we used HTTP high and lower load traffic. And we conclude the efficiency of a network can be achieved by choosing the best suitable protocols based on the network requirement.
Predicting stock data with traditional time series analysis has neural network may be more suitab... more Predicting stock data with traditional time series analysis has neural network may be more suitable for the task, because no assumption a has to be made prior to forecasting. Furthermore, a neural network has the ability to extract useful information from large sets of data, which often is required for a satisfying description of a financial time series. Subsequently an Error Correction Network is defined and implemented for an empirical study. Technical as well as fundamental data are used as input to the network. One stocks of the BSE are predicted using t standard Error Correction Network whereas an extension of the Error Correction Network is used for weekly predictions. The results on the stocks are less convincing; nevertheless the net strategy.
The generation of profitable trading rules for stock market investments is a difficult task but a... more The generation of profitable trading rules for stock market investments is a difficult task but admired problem. First stage is classifying the prone direction of the price for BSE index (India cements stock price index (ICSPI)) futures with several technical indicators using artificial intelligence techniques. And second stage is mining the trading rules to determined conflict among the outputs of the first stage using the evolve learning. We have found trading rule which would have yield the highest return over a certain time period using historical data. These groundwork results suggest that genetic algorithms are promising model yields highest profit than other comparable models and buy-and-sell strategy. Experimental results of buying and selling of trading rules were outstanding.
International Journal of Computer Applications, 2012
The generation of profitable trading rules for stock market investments is a difficult task but a... more The generation of profitable trading rules for stock market investments is a difficult task but admired problem. First stage is classifying the prone direction of the price for India cements stock price index (ICSPI) futures with several technical indicators using artificial intelligence techniques. And second stage is mining the trading rules to determined conflict among the outputs of the first stage using the evolve learning. We have found trading rule which would have yield the highest return over a certain time period using historical data. These groundwork results suggest that genetic algorithms are promising model yields highest profit than other comparable models and buy-and-sell strategy. Experimental results of buying and selling of trading rules were outstanding.
Genetic algorithms (GA) are optimization techniques inspired from natural evolution processes. Th... more Genetic algorithms (GA) are optimization techniques inspired from natural evolution processes. They handle a population of individuals that evolve with the help of information exchange procedures. In this paper we proposed genetic algorithms (GA) approach to optimize of connection weights and instance selection for artificial neural networks (ANNs) to predict the stock price index. ANN has preeminent learning ability, but often exhibit inconsistent and unpredictable performance for noisy data. In this paper GA is employed not only to improve the learning algorithm, but also to reduce the complexity in feature space. GA optimizes simultaneously the connection weights between layers and a selection of relevant instances. This study applies the proposed model to India Cements Stock Price Index (ICSPI) analysis. Experimental results show that the GA approach is a promising method for instance selection and optimize the connection weight between layers.
ijcttjournal.org
Abstract---One of the most important facts in higher education system is quality. It concerns wit... more Abstract---One of the most important facts in higher education system is quality. It concerns with all the circumstances to enhance the higher educational organizations. One way to reach the highest level of quality in higher education systems is implementing the key ...
ijaest.iserp.org
... R. Lakshman Naik Department of CSE, BITS, Warangal, AP, India lakshman432@yahoo.com G. Shruth... more ... R. Lakshman Naik Department of CSE, BITS, Warangal, AP, India lakshman432@yahoo.com G. Shruthi Department of CSE, JITS, Warangal, AP, India shruthiguda@gmail.com ... j j ) R v ( s j s f y (4) Where vj is the weight between the hidden layer and the output layer. ...
International journal of engineering research and technology, 2018
Due to the digitization of data and advances in technology, it has become extremely easy to obtai... more Due to the digitization of data and advances in technology, it has become extremely easy to obtain and store large quantities of data, particularly Multimedia data. Mining Image data is the one of the essential features in this present scenario since image data plays vital role in every aspect of the system such as business for marketing, hospital for surgery, engineering for construction, Web for publication and so on. Feature selection and extraction is the pre-processing step of Image Mining. Obviously this is a critical step in the entire scenario of Image Mining. To extract patterns and derive knowledge from large collections of images, deals mainly with identification and extraction of unique features for a particular domain. There are various features available in the image, to identify the best features and thereby extract relevant information from the images. In this paper, we have proposed three effective methods of image mining techniques (QBIR, BTA, and clustering algorithm) for extracting the features of the web image.
Data mining is a technique of discovering interesting patterns from large amount of data, where t... more Data mining is a technique of discovering interesting patterns from large amount of data, where the data can be stored in database, data warehouse, or other information repositories; Because it is an emerging discipline, many challenges remain in data mining. Due to large volume of data acquired on an everyday basis, it becomes imperative to find an algorithm that determines the technique to select and type of mining to do. Data sets are often inaccurate, incomplete, and/or have redundant or insufficient information. It would be desirable to have mining tools that can switch to multiple techniques and support multiple outcomes. The book contains an excellent detail of data mining techniques and applications, business trends, forecast analysis, instance selection and how to improve the trading rules. The book focuses on the application of data mining techniques such Error Correction Network (ECN), Artificial Neural Network (ANN) and Genetic Algorithm (GA). This book mainly focuses on...
Advances in Intelligent Systems and Computing, 2016
International Journal of Engineering and Advanced Technology, 2019
increasingly, the data is increasing day by day and storage capacity is expanding more and more, ... more increasingly, the data is increasing day by day and storage capacity is expanding more and more, this allowing the field of SA to growing and developing faster in research and prospecting for different opinions and emotions to be combed and technically treated to be more accurate. In our present, data can be a wealth where major global companies and development, research and crime detection centers benefit from it. In this paper we focused on the current apprises of research in this field which contributed to various improvements in the field of sentiment analysis. We have tackles comprehensive overviews for different fields which related to the Sentiment Analysis (Transfer Learning (TL), Building Resource (BR), Emotion Detection (ED)) which have the popularity of researchers has gained in recent times and attracted them. We have the aim of this survey which is to give a clear and accurate picture about the techniques of analyzing emotions and related fields
Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers... more Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers' Association is considered to be one of Asia’s fastest stock exchanges and oldest stock exchange in the South Asia region. On 31 August 1957, the BSE became the first stock exchange to be recognized by the Indian Government under the Securities Contracts Regulation Act 1956. In this paper, we developed a novel framework that can achieve parallel time series prediction using Hadoop. By implementing the proposed framework, the system should be able to deal with massive amount of time series data, either regular or irregular. The proposed system can handle the optimization, parameter selection and also model combination through K-mean clustering. In this paper, experiment is carried to forecast the company’s next bid accurately based on the other companies that have similar trend with it.
The hardware-software partitioning problem is a key aspect of co-design of digital electronic sys... more The hardware-software partitioning problem is a key aspect of co-design of digital electronic systems; extensive research has been performed with diverse definitions of partitioning problems. However, existent partitioning solutions are not applicable to many real-time applications partly because of restricted input specification or insufficient constraints. By using the off-loading technique, a fundamental problem is to partition the dynamic computation of application involved in between the mobile device and cloud. In this paper, we proposed three approaches for mobile cloud applications: Extending the access to cloud services to mobile devices, to enabling mobile devices to work collaboratively as cloud resource providers, to enhance the execution of mobile applications on portable devices using available cloud resources. Suitable framework is providing for runtime support with dynamic computation of the application was proposed. This is different from existing mechanism, the fra...
In the field of digital watermarking, digital image watermarking for copyright protection has att... more In the field of digital watermarking, digital image watermarking for copyright protection has attracted a lot of attention in the research community. Digital watermarking contains varies techniques for protecting the digital content. Among all those techniques,Discrete Wavelet Transform (DWT) provides higher image imperceptibility and robustness. Over the years, researchers have been designing watermarking techniques with robustness in mind, in order for the watermark to be resistant against any image processing techniques. Furthermore, the requirements of a good watermarking technique includes a tradeoff between robustness, image quality (imperceptibility) and capacity. In this paper, we have done an extensive literature review for the existing DWT techniques and those combined with other techniques such as Neural Networks. In addition to that, we have discuss the contribution of Neural Networks in copyright protection. Finally we reached our goal in which we identified the researc...
Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers... more Bombay Stock Exchange (BSE) Limited, established in 1875 as the Native Share and Stock Brokers' Association is considered to be one of Asia’s fastest stock exchanges and oldest stock exchange in the South Asia region. On 31 August 1957, the BSE became the first stock exchange to be recognized by the Indian Government under the Securities Contracts Regulation Act 1956. In this paper, we developed a novel framework that can achieve parallel time series prediction using Hadoop. By implementing the proposed framework, the system should be able to deal with massive amount of time series data, either regular or irregular. The proposed system can handle the optimization, parameter selection and also model combination through K-mean clustering. In this paper, experiment is carried to forecast the company’s next bid accurately based on the other companies that have similar trend with it.
The hardware-software partitioning problem is a key aspect of co-design of digital electronic sys... more The hardware-software partitioning problem is a key aspect of co-design of digital electronic systems; extensive research has been performed with diverse definitions of partitioning problems. However, existent partitioning solutions are not applicable to many real-time applications partly because of restricted input specification or insufficient constraints. By using the off-loading technique, a fundamental problem is to partition the dynamic computation of application involved in between the mobile device and cloud. In this paper, we proposed three approaches for mobile cloud applications: Extending the access to cloud services to mobile devices, to enabling mobile devices to work collaboratively as cloud resource providers, to enhance the execution of mobile applications on portable devices using available cloud resources. Suitable framework is providing for runtime support with dynamic computation of the application was proposed. This is different from existing mechanism, the fra...
In digital image watermarking, many techniques are used for obtaining optimal image representatio... more In digital image watermarking, many techniques are used for obtaining optimal image representation; image decomposition as a standard set in the frequency domain is not necessary (DCT, DWT, and DFT). Therefore, another representation of transform was explored which is about using algebra methods and algorithms with watermarking like singular value decomposition algorithm based on watermarking. SVD algorithms have shown that they are highly strong against extensive range of attacks. In addition to that, Genetic Algorithm (GA) is used with SVD to optimize the watermarking. Many techniques and algorithms have already been proposed on the using of SVD and GA on digital watermarking. In this paper, we introduce a general survey on those techniques along with analysis for them based on the two measures, transparency and robustness.
Scientific reports, Sep 1, 2016
Although our knowledge of aging has greatly expanded in the past decades, it remains elusive why ... more Although our knowledge of aging has greatly expanded in the past decades, it remains elusive why and how aging contributes to the development of age-related diseases (ARDs). In particular, a global mechanistic understanding of the connections between aging and ARDs is yet to be established. We rely on a network modelling named "GeroNet" to study the connections between aging and more than a hundred diseases. By evaluating topological connections between aging genes and disease genes in over three thousand subnetworks corresponding to various biological processes, we show that aging has stronger connections with ARD genes compared to non-ARD genes in subnetworks corresponding to "response to decreased oxygen levels", "insulin signalling pathway", "cell cycle", etc. Based on subnetwork connectivity, we can correctly "predict" if a disease is age-related and prioritize the biological processes that are involved in connecting to multiple...
Predicting stock data with traditional time series analysis has neural network may be more suitab... more Predicting stock data with traditional time series analysis has neural network may be more suitable for the task, because no assumption a has to be made prior to forecasting. Furthermore, a neural network has the ability to extract useful information from large sets of data, which often is required for a satisfying description of a financial time series. Subsequently an Error Correction Network is defined and implemented for an empirical study. Technical as well as fundamental data are used as input to the network. One stocks of the BSE are predicted using t standard Error Correction Network whereas an extension of the Error Correction Network is used for weekly predictions. The results on the stocks are less convincing; nevertheless the net strategy.
International …
Mobile ad-hoc network (MANET) is a wireless network without infrastructure. Nodes can commutate e... more Mobile ad-hoc network (MANET) is a wireless network without infrastructure. Nodes can commutate each other without central infrastructure; because they are self organised and self configurable with easy deployment. To commutative each other it is required efficient routing protocols in MANET technology. In these we find out an efficient routing protocols for routing, and we had considered differ approaches like routing load, end to end packet delivery and performance of protocols. To analysis this we implemented two different routing protocols which are proactive and reactive. To analysis these aspects we used HTTP high and lower load traffic. And we conclude the efficiency of a network can be achieved by choosing the best suitable protocols based on the network requirement.
Predicting stock data with traditional time series analysis has neural network may be more suitab... more Predicting stock data with traditional time series analysis has neural network may be more suitable for the task, because no assumption a has to be made prior to forecasting. Furthermore, a neural network has the ability to extract useful information from large sets of data, which often is required for a satisfying description of a financial time series. Subsequently an Error Correction Network is defined and implemented for an empirical study. Technical as well as fundamental data are used as input to the network. One stocks of the BSE are predicted using t standard Error Correction Network whereas an extension of the Error Correction Network is used for weekly predictions. The results on the stocks are less convincing; nevertheless the net strategy.
The generation of profitable trading rules for stock market investments is a difficult task but a... more The generation of profitable trading rules for stock market investments is a difficult task but admired problem. First stage is classifying the prone direction of the price for BSE index (India cements stock price index (ICSPI)) futures with several technical indicators using artificial intelligence techniques. And second stage is mining the trading rules to determined conflict among the outputs of the first stage using the evolve learning. We have found trading rule which would have yield the highest return over a certain time period using historical data. These groundwork results suggest that genetic algorithms are promising model yields highest profit than other comparable models and buy-and-sell strategy. Experimental results of buying and selling of trading rules were outstanding.
International Journal of Computer Applications, 2012
The generation of profitable trading rules for stock market investments is a difficult task but a... more The generation of profitable trading rules for stock market investments is a difficult task but admired problem. First stage is classifying the prone direction of the price for India cements stock price index (ICSPI) futures with several technical indicators using artificial intelligence techniques. And second stage is mining the trading rules to determined conflict among the outputs of the first stage using the evolve learning. We have found trading rule which would have yield the highest return over a certain time period using historical data. These groundwork results suggest that genetic algorithms are promising model yields highest profit than other comparable models and buy-and-sell strategy. Experimental results of buying and selling of trading rules were outstanding.
Genetic algorithms (GA) are optimization techniques inspired from natural evolution processes. Th... more Genetic algorithms (GA) are optimization techniques inspired from natural evolution processes. They handle a population of individuals that evolve with the help of information exchange procedures. In this paper we proposed genetic algorithms (GA) approach to optimize of connection weights and instance selection for artificial neural networks (ANNs) to predict the stock price index. ANN has preeminent learning ability, but often exhibit inconsistent and unpredictable performance for noisy data. In this paper GA is employed not only to improve the learning algorithm, but also to reduce the complexity in feature space. GA optimizes simultaneously the connection weights between layers and a selection of relevant instances. This study applies the proposed model to India Cements Stock Price Index (ICSPI) analysis. Experimental results show that the GA approach is a promising method for instance selection and optimize the connection weight between layers.
ijcttjournal.org
Abstract---One of the most important facts in higher education system is quality. It concerns wit... more Abstract---One of the most important facts in higher education system is quality. It concerns with all the circumstances to enhance the higher educational organizations. One way to reach the highest level of quality in higher education systems is implementing the key ...
ijaest.iserp.org
... R. Lakshman Naik Department of CSE, BITS, Warangal, AP, India lakshman432@yahoo.com G. Shruth... more ... R. Lakshman Naik Department of CSE, BITS, Warangal, AP, India lakshman432@yahoo.com G. Shruthi Department of CSE, JITS, Warangal, AP, India shruthiguda@gmail.com ... j j ) R v ( s j s f y (4) Where vj is the weight between the hidden layer and the output layer. ...
International journal of engineering research and technology, 2018
Due to the digitization of data and advances in technology, it has become extremely easy to obtai... more Due to the digitization of data and advances in technology, it has become extremely easy to obtain and store large quantities of data, particularly Multimedia data. Mining Image data is the one of the essential features in this present scenario since image data plays vital role in every aspect of the system such as business for marketing, hospital for surgery, engineering for construction, Web for publication and so on. Feature selection and extraction is the pre-processing step of Image Mining. Obviously this is a critical step in the entire scenario of Image Mining. To extract patterns and derive knowledge from large collections of images, deals mainly with identification and extraction of unique features for a particular domain. There are various features available in the image, to identify the best features and thereby extract relevant information from the images. In this paper, we have proposed three effective methods of image mining techniques (QBIR, BTA, and clustering algorithm) for extracting the features of the web image.
Data mining is a technique of discovering interesting patterns from large amount of data, where t... more Data mining is a technique of discovering interesting patterns from large amount of data, where the data can be stored in database, data warehouse, or other information repositories; Because it is an emerging discipline, many challenges remain in data mining. Due to large volume of data acquired on an everyday basis, it becomes imperative to find an algorithm that determines the technique to select and type of mining to do. Data sets are often inaccurate, incomplete, and/or have redundant or insufficient information. It would be desirable to have mining tools that can switch to multiple techniques and support multiple outcomes. The book contains an excellent detail of data mining techniques and applications, business trends, forecast analysis, instance selection and how to improve the trading rules. The book focuses on the application of data mining techniques such Error Correction Network (ECN), Artificial Neural Network (ANN) and Genetic Algorithm (GA). This book mainly focuses on...
Advances in Intelligent Systems and Computing, 2016
Due to the digitization of data and advances in technology, it has become extremely easy to obtai... more Due to the digitization of data and advances in technology, it has become extremely easy to obtain and store large quantities of data, particularly Multimedia data. Mining Image data is the one of the essential features in this present scenario since image data plays vital role in every aspect of the system such as business for marketing, hospital for surgery, engineering for construction, Web for publication and so on. Feature selection and extraction is the pre-processing step of Image Mining. Obviously this is a critical step in the entire scenario of Image Mining. To extract patterns and derive knowledge from large collections of images, deals mainly with identification and extraction of unique features for a particular domain. There are various features available in the image, to identify the best features and thereby extract relevant information from the images. In this paper, we have proposed three effective methods of image mining techniques (QBIR, BTA, and clustering algorithm) for extracting the features of the web image.
Existing up-gradation process is happening manually, which includes functionalities such as filte... more Existing up-gradation process is happening manually, which includes functionalities such as filtering data from old version database, extracting required metadata from old version database, writing scripts to run against newer version database, collecting scanned documents and uploading into new version system repository etc... In this paper, we proposed a tool to migrate old version database data into newer version database by mitigating manual effort with secure and appropriate error handling approach. With help of up-gradation process new version product supports old data without any uncertainty. The effort and time will be more with existing process. To avoid it, customized up-gradation tool has been developed to support all manual functionalities. Although we cannot completely rule out manual process in all scenarios, there appears to be a significant business advantage in being able to deliver a quick and less manual effort up-gradation mechanism, which allows us to achieve migration from older version to newer version with secure and proper error handling approach.
Mobile Cloud Computing (MCC) is persuasive paradigm enabling users to have the benefit of the mas... more Mobile Cloud Computing (MCC) is persuasive paradigm enabling users to have the benefit of the massive computation power and profuse network services ubiquitously with the support of remote cloud. MCC is emerging as the prime focus of next generation computing. One of the prime issues of MCC is to provide infrastructure support in terms of computing, seamless mobility, applications, middleware, network, user services, trust, security, and privacy. MCC is a convergent technology comprised of three foundation stone heterogeneous technologies, namely mobile computing, cloud computing, and networking. However, the wireless networks and mobile devices have to face many challenges due to the limited radio resources, battery power and communications capabilities, which may significantly impede the improvement of service qualities. This paper discusses the various challenges that are either caused or intensified by heterogeneity in providing infrastructure for next generation computing. Finally we outline open issues, which help in identifying new research directions in MCC.