Sulochana Sonkamble - Academia.edu (original) (raw)

Papers by Sulochana Sonkamble

International Journal of Advance Research, Ideas and Innovations in Technology, Dec 7, 2021

Over the year's we have experienced tremendous growth in the use of ECommerce Applications. Since... more Over the year's we have experienced tremendous growth in the use of ECommerce Applications. Since the pandemic, there has been an escalation in the use of these applications. Hence, we must understand the factors that are affecting the effectiveness of the services. In this paper, we will be analyzing different ecommerce applications on Google Play and App Store by performing sentiment analysis on user reviews by machine learning and then perform thematic analysis to identify the themes of reviews. Sentiment analysis is the process of identifying and categorizing opinions expressed in the text, especially when we want to determine whether the attitude of the customer concerning the services provided is positive, negative ,or neutral. Performing Sentiment analysis manually is a humongous task as there are millions of users. Hence we will be implementing different classifiers using supervised ML algorithms. These Classifiers will be trained and compared, then the classifier with the highest accuracy will be used to predict the sentiment polarity. Later on, we will be performing thematic analysis on positive and negative reviews to determine themes representing various factors affecting the effectiveness of ecommerce apps both positively and negatively. In the end, we will be proposing how to tackle the negative issues that are hampering the services

ARTICLE INFO In recent years, cloud computing gaining popularity due to its charming features suc... more ARTICLE INFO In recent years, cloud computing gaining popularity due to its charming features such as scalability, availability, low cost service. Individual and organizations are using cloud service to store large amount of data on cloud storage. By outsourcing data on cloud users gets relief from storage maintenance. But in this case the control of data is going towards cloud service provider. To gain control over the data the traditional technique is encrypt data at client side and outsource the data. In consumer centric cloud computing user wants to find most relevant product or data. Keyword search on encrypted data is difficult. The search techniques which are used on plain text cannot be used over encrypted data. There are some papers based on single keyword search, fuzzy keyword search and multi-keyword search on encrypted data. But these techniques are not supporting synonym based search. The semantic search allows search over encrypted data supporting synonym queries. So t...

CQA helpful in answering real world question's provided answer to human. Address recovery in ... more CQA helpful in answering real world question's provided answer to human. Address recovery in CQA can naturally and the most important and late inquiries that have been tackled by different clients. In existing system elective approach to address the word ambiguity and word miss match issues by exploiting conceivably rich semantic data drawn from different language. the translated words from other languages via non-negative matrix factorization. Contextual information is exploited during the translation from one language to another language by using Google Translate. Thus, word ambiguity can be solved when questions are translated. Multiple words that have similar meanings in one language may be translated into a unique word or a few words in a foreign language. It is a word-based translation language model for re trivial with query likelihood model for answer. If these translate the question word by word, it discards the contextual information. We would expect that such a transl...

Many of the bridges in cities built on the river are subject to weakening as their lifetime is ex... more Many of the bridges in cities built on the river are subject to weakening as their lifetime is expired but they are still in use. They are dangerous to bridge users. Due to high water level or pressure, heavy rains these bridges may get collapse which in turn leads to disaster. So, these bridges require continuous monitoring. So we are proposing a system which consists of a ultra-sonic sensor, led signals, servo motor and microcontroller. This system detects the water level, and cracks in the bride. If the water level, cracks on the bridge cross its threshold value then it generates the alert through LED signals and auto barrier. If it is necessary, then the admin assign the tasks to the employees for maintenance. Engineering structures are responsible for economic growth, development, and evolution of the nation. The structure includes buildings, roads, dams, and bridges which affect day to day a life of people. Along with their own weight, they are also affected by the environment...

Face identification introduces a challenging problem in the various domain areas like image analy... more Face identification introduces a challenging problem in the various domain areas like image analysis and computer vision. The number of the images available on internet among them most of the images is human facial images. Sometimes images not properly tagged with right names. So, Search-Based Face Annotation (SBFA) framework uses Content-Based Image Retrieval (CBIR) technique in mining web facial images for annotation. The main motive behind the SBFA is to assign right name labels to a given query facial image. K-means clustering algorithm proposed to improve scalability. The additional work of the system is recognition of the user by verified by email. To improve efficiency, system shows result such as the last login, compute total counts of login etc and finally an identification of person realized.

Big data centers in cloud, large amount of data needs to be transferred frequently among thousand... more Big data centers in cloud, large amount of data needs to be transferred frequently among thousands of interconnected servers. In which load balancing and flow scheduling is a challenging issue. The OpenFlow is a auspicious solution to balance data flows in big data center network through programmatic traffic controller. Existing solution can able to statically set up routes only at initialization stage of data transmissions, which experiences from dynamical ow distribution and network changing state so it results in decrease system performance. In this paper, we will propose a new dynamical load-balanced scheduling (DLBS) approach for increase the network throughput to dynamically balance workload. This approach formulate the DLBS problem, and then develop a set of improved heuristic scheduling algorithms for the two typical OpenFlow network models, which balance data flows time slot by time slot. Experimental results demonstrate that our DLBS approach signicantly outperforms other ...

International Journal of Innovative Research in Computer and Communication Engineering, 2015

For extracting useful knowledge which is hidden in large set of data, Data mining is a very impor... more For extracting useful knowledge which is hidden in large set of data, Data mining is a very important technology. There are some negative perceptions about data mining. This perception may contain unfairly treating people who belongs to some specific group. Classification rule mining technique has covered the way for making automatic decisions like loan granting/denial and insurance premium computation etc. These are automated data collection and data mining techniques. According to discrimination attributes if training data sets are biases then discriminatory decisions may ensue. Thus in data mining antidiscrimination techniques with discrimination discovery and prevention are included. It can be direct or indirect. When decisions are made based on sensitive attributes that time the discrimination is indirect. When decisions are made based on nonsensitive attributes which are strongly correlated with biased sensitive ones that time the discrimination is indirect. The proposed syste...

Now a day, many applications rely on the existence of small devices that can exchange information... more Now a day, many applications rely on the existence of small devices that can exchange information and form communication networks. And it is very challenging to provide security for such application. In a significant portion of such applications, the confidentiality and integrity of the communicated messages are of particular interest. In this work, we propose two novel techniques for authenticating short encrypted messages based on Advance Encryption cryptographic System that are directed to meet the requirements of mobile and pervasive applications. The encryption technique have the chance of the data misusing hence we add the password based authentication technique. By using Advance Encryption algorithm we are authenticating the message which is encrypted and we are improving the decryption speed and authentication accuracy to secure the communication the proposed message authentication technique is more efficient than the previous MAC algorithms and the aim of this proposed tech...

Cloud computing is the long dreamed vision of computing as a utility, where data owners can remot... more Cloud computing is the long dreamed vision of computing as a utility, where data owners can remotely store their data. The basic service provided by the Cloud is Data Storage. However, it is a difficult task for sharing data in multi-owner manner where group admin and all group members can store and modify data while preserving data and identity privacy from an untrusted cloud server, due to the frequent change of the membership. Therefore secure multi-owner data sharing scheme for dynamic groups in the cloud computing have been proposed which involve integration of group signature and broadcast encryption techniques. But this system also identified some limitations in terms of efficiency and security. Because multi-owner data storing and sharing in a dynamic environment dumps huge amount of data files in the cloud, which remains in cloud for indefinite period of time. The sensitive information stored may misused by service providers. To maintain cloud file’s security and privacy re...

ARTICLE INFO Mobile phone applications are becoming more and more popular. As the technology adva... more ARTICLE INFO Mobile phone applications are becoming more and more popular. As the technology advances, services like camera, accelerometers, compass, GPS, etc. are provided by the mobile phones. However, the more smart phones become smarter, the more the design of complex applications covering the various user needs becomes a complicated task. To support an End-User in the development of mobile applications we present a visual approach to enable End-Users to compose visually their own applications directly on their mobile phone. The methodology enables the end-user to develop applications and/or compose services on the smart phone, so making the way towards new scenarios where smart phones replace and overtake the Personal Computer, given their native possibility of wide connectivity, when augmented by features for interaction with remote systems and sensors. Moreover, the results of a preliminary usability study revealed a good satisfaction degree and the effectiveness and efficacy...

Various service provider systems or recommender systems have to manage the large amount of data r... more Various service provider systems or recommender systems have to manage the large amount of data regarding customer, service and information. This leads to Big Data analysis problem and its handling is also a challenging task. There are various organizations which serves user through service provider systems or recommender systems that provide efficient services in terms of set of good quality products or services to use by giving appropriate data as per their need. Hence the Decision Support System is used to determine the decision making activities in various organizations of recommender system which allows making certain planning, management and operations. This also helps to make decisions for structured and unstructured problem. It can be done in number of ways like descriptive, decision and prediction based. This paper will focus on Predictive Analysis of user behavior towards recommender system. The predictive analysis deals with the identification of relationship between spec...

The term Biometrics is becoming highly important in computer security world. The human physical c... more The term Biometrics is becoming highly important in computer security world. The human physical characteristics like fingerprints, face, hand geometry, voice and iris are known as biometrics. These features are used to provide an authentication for computer based security systems. The existing computer security systems used at various places like banking, passport, credit cards, smart cards, PIN , access control and network security are using username and passwords for person identification. The username and passwords can be replaced and/or provide double authentication by using any one of the biometric features. In this paper, the main focus is on the various biometrics, their applications and the existing biometrics recognition systems.

ARTICLE INFO Face recognition is very challenging area of research. The number of the images are ... more ARTICLE INFO Face recognition is very challenging area of research. The number of the images are available on the internet among them most of the images are human facial images which shared by the users. Some human facial images are not properly tagged with right name. So, Search-Based Face Annotation (SBFA) framework aims to deal with auto face annotation task and uses Content-Based Image Retrieval (CBIR) technique for face annotation. The main motive behind the SBFA is to assign right name label to a given query facial image. So K-means clustering-based algorithm used to improve scalability. This work also introduces the user is validated by their email. The efficiency of system improved by performing the verification of email, last login session of particular user, total counts of login etc. and finally the user account status is accomplished. Keywords— Face recognition, content-based image retrieval, face annotation. Article History Received: 19 th July 2016 Received in revised ...

International Journal of Radiation Oncology*Biology*Physics, 2017

Our ability to develop policies that increase the affordability and value of cancer care is limit... more Our ability to develop policies that increase the affordability and value of cancer care is limited because we do not understand what factors drive variation in spending. For patients with breast cancer, we described the extent that variation in spending is driven by observable patient/disease characteristics, treatment modalities, or residual patient and physician factors. Materials/Methods: We conducted a cross-sectional study of 24,818 women aged 66 years diagnosed 2010-11 with breast cancer using SEER-Medicare data. We used multi-level linear models to partition variation in monthly medical spending according to physician and patient factors. We then determined how much patient and physician driven variation is explained by patient/disease characteristics (age, stage, HER2/ hormone receptor status, comorbidity, geography), and treatment modalities (lumpectomy, mastectomy, radiation, biologics, chemotherapy, hospice). All models controlled for time. We examined spending for the initial year of treatment stratified by stage, and for the final 12 months of life among patients who died of breast cancer.

There are various techniques for crawling the web sites for searching the desired information. Th... more There are various techniques for crawling the web sites for searching the desired information. The paper titled “Intelligent Crawling Techniques For Locating the Sites” is focusing on the intelligent technique for searching the desired information which is available on the internet. The variety of information in the form of web pages on the internet is growing tremendously day to day. In this case searching relevant information on the Internet is a crucial and difficult task. This information is hidden behind query forms that interface to unexplored databases containing high quality structured data. Traditional search engines cannot access and index this hidden part of the information. A new term „Web Retrieving‟ arises to find this hidden information and become the challenge to the researcher. We have presented a two-stage framework, namely SmartCrawler, for effectively harvesting deep web interfaces. The first stage is called as Site Locating, and a second stage is called as In-Si...

International Journal of Engineering Research and, 2015

Traditional mouse and keyboard interaction is suitable for few applications like word processing ... more Traditional mouse and keyboard interaction is suitable for few applications like word processing but for drawing and designing, mouse becomes more difficult. As any user can draw a simple process on paper which can be implemented on desktop by interactive user interface and also creating infrared tracking interface like touch screen but more affordable than it. Further, this application provides extension to gesture control by other application. Major existing systems with widespread implementations are available but are limited to: Optical mice, capacitive touch panels, resistive touch panels, surface acoustic wave touch panels, etc. Touch panels move one step closer towards enhancing the interactivity of computing devices; however they have their own shortcomings. We present an alternative to the aforementioned traditional pointing devices which makes use of infrared radiations as a means of propagating user interactions between the computers and the users. The paper proposes a framework for a pointing device based on tracking of infrared light and determining its relative position and motion with respect to the computer system or device. The use of targeted infrared radiations as a medium of location information delivery forms the basis of the proposed framework.

International Journal of Engineering Research and, 2015

Traditional mouse and keyboard interaction is suitable for few applications like word processing ... more Traditional mouse and keyboard interaction is suitable for few applications like word processing but for drawing and designing, mouse becomes more difficult. As any user can draw a simple process on paper which can be implemented on desktop by interactive user interface and also creating infrared tracking interface like touch screen but more affordable than it. Further, this application provides extension to gesture control by other application. Major existing systems with widespread implementations are available but are limited to: Optical mice, capacitive touch panels, resistive touch panels, surface acoustic wave touch panels, etc. Touch panels move one step closer towards enhancing the interactivity of computing devices; however they have their own shortcomings. We present an alternative to the aforementioned traditional pointing devices which makes use of infrared radiations as a means of propagating user interactions between the computers and the users. The paper proposes a framework for a pointing device based on tracking of infrared light and determining its relative position and motion with respect to the computer system or device. The use of targeted infrared radiations as a medium of location information delivery forms the basis of the proposed framework.

Proceedings of the 8th …, 2009

In this paper, we are proposing a new classifier called support vector machines to classify the s... more In this paper, we are proposing a new classifier called support vector machines to classify the speech signals. We have achieved very good generalization performance by implementing the support vector machines with various kernel functions. The use One-vs-One Classifier with voting algorithm improves speech signal classification systems efficiency.

Journal of Computer Science, 2011

Problem statement: We proposed a new method for feature extraction of an Iris image for personal ... more Problem statement: We proposed a new method for feature extraction of an Iris image for personal identification system. Approach: This study purposed a new approach to extract the features of region of interest using the wavelet transform. The extracted Iris region could be normalizing into a rectangular block of fixed dimensions. The Gabor wavelet transform techniques had been applied on the data set to get feature vectors of an iris used for recognition. Results: Two Iris templates used for testing. The system performance score results in a false accept and false reject rate. Conclusion: The performance of the system "Efficient Feature Extraction Methodology Using wavelet transform for the development of personal identification system using iris biometrics" can be increased by training the more feature vectors of an extracted Iris images.

International Journal of Advance Research, Ideas and Innovations in Technology, Dec 7, 2021

Over the year's we have experienced tremendous growth in the use of ECommerce Applications. Since... more Over the year's we have experienced tremendous growth in the use of ECommerce Applications. Since the pandemic, there has been an escalation in the use of these applications. Hence, we must understand the factors that are affecting the effectiveness of the services. In this paper, we will be analyzing different ecommerce applications on Google Play and App Store by performing sentiment analysis on user reviews by machine learning and then perform thematic analysis to identify the themes of reviews. Sentiment analysis is the process of identifying and categorizing opinions expressed in the text, especially when we want to determine whether the attitude of the customer concerning the services provided is positive, negative ,or neutral. Performing Sentiment analysis manually is a humongous task as there are millions of users. Hence we will be implementing different classifiers using supervised ML algorithms. These Classifiers will be trained and compared, then the classifier with the highest accuracy will be used to predict the sentiment polarity. Later on, we will be performing thematic analysis on positive and negative reviews to determine themes representing various factors affecting the effectiveness of ecommerce apps both positively and negatively. In the end, we will be proposing how to tackle the negative issues that are hampering the services

ARTICLE INFO In recent years, cloud computing gaining popularity due to its charming features suc... more ARTICLE INFO In recent years, cloud computing gaining popularity due to its charming features such as scalability, availability, low cost service. Individual and organizations are using cloud service to store large amount of data on cloud storage. By outsourcing data on cloud users gets relief from storage maintenance. But in this case the control of data is going towards cloud service provider. To gain control over the data the traditional technique is encrypt data at client side and outsource the data. In consumer centric cloud computing user wants to find most relevant product or data. Keyword search on encrypted data is difficult. The search techniques which are used on plain text cannot be used over encrypted data. There are some papers based on single keyword search, fuzzy keyword search and multi-keyword search on encrypted data. But these techniques are not supporting synonym based search. The semantic search allows search over encrypted data supporting synonym queries. So t...

CQA helpful in answering real world question's provided answer to human. Address recovery in ... more CQA helpful in answering real world question's provided answer to human. Address recovery in CQA can naturally and the most important and late inquiries that have been tackled by different clients. In existing system elective approach to address the word ambiguity and word miss match issues by exploiting conceivably rich semantic data drawn from different language. the translated words from other languages via non-negative matrix factorization. Contextual information is exploited during the translation from one language to another language by using Google Translate. Thus, word ambiguity can be solved when questions are translated. Multiple words that have similar meanings in one language may be translated into a unique word or a few words in a foreign language. It is a word-based translation language model for re trivial with query likelihood model for answer. If these translate the question word by word, it discards the contextual information. We would expect that such a transl...

Many of the bridges in cities built on the river are subject to weakening as their lifetime is ex... more Many of the bridges in cities built on the river are subject to weakening as their lifetime is expired but they are still in use. They are dangerous to bridge users. Due to high water level or pressure, heavy rains these bridges may get collapse which in turn leads to disaster. So, these bridges require continuous monitoring. So we are proposing a system which consists of a ultra-sonic sensor, led signals, servo motor and microcontroller. This system detects the water level, and cracks in the bride. If the water level, cracks on the bridge cross its threshold value then it generates the alert through LED signals and auto barrier. If it is necessary, then the admin assign the tasks to the employees for maintenance. Engineering structures are responsible for economic growth, development, and evolution of the nation. The structure includes buildings, roads, dams, and bridges which affect day to day a life of people. Along with their own weight, they are also affected by the environment...

Face identification introduces a challenging problem in the various domain areas like image analy... more Face identification introduces a challenging problem in the various domain areas like image analysis and computer vision. The number of the images available on internet among them most of the images is human facial images. Sometimes images not properly tagged with right names. So, Search-Based Face Annotation (SBFA) framework uses Content-Based Image Retrieval (CBIR) technique in mining web facial images for annotation. The main motive behind the SBFA is to assign right name labels to a given query facial image. K-means clustering algorithm proposed to improve scalability. The additional work of the system is recognition of the user by verified by email. To improve efficiency, system shows result such as the last login, compute total counts of login etc and finally an identification of person realized.

Big data centers in cloud, large amount of data needs to be transferred frequently among thousand... more Big data centers in cloud, large amount of data needs to be transferred frequently among thousands of interconnected servers. In which load balancing and flow scheduling is a challenging issue. The OpenFlow is a auspicious solution to balance data flows in big data center network through programmatic traffic controller. Existing solution can able to statically set up routes only at initialization stage of data transmissions, which experiences from dynamical ow distribution and network changing state so it results in decrease system performance. In this paper, we will propose a new dynamical load-balanced scheduling (DLBS) approach for increase the network throughput to dynamically balance workload. This approach formulate the DLBS problem, and then develop a set of improved heuristic scheduling algorithms for the two typical OpenFlow network models, which balance data flows time slot by time slot. Experimental results demonstrate that our DLBS approach signicantly outperforms other ...

International Journal of Innovative Research in Computer and Communication Engineering, 2015

For extracting useful knowledge which is hidden in large set of data, Data mining is a very impor... more For extracting useful knowledge which is hidden in large set of data, Data mining is a very important technology. There are some negative perceptions about data mining. This perception may contain unfairly treating people who belongs to some specific group. Classification rule mining technique has covered the way for making automatic decisions like loan granting/denial and insurance premium computation etc. These are automated data collection and data mining techniques. According to discrimination attributes if training data sets are biases then discriminatory decisions may ensue. Thus in data mining antidiscrimination techniques with discrimination discovery and prevention are included. It can be direct or indirect. When decisions are made based on sensitive attributes that time the discrimination is indirect. When decisions are made based on nonsensitive attributes which are strongly correlated with biased sensitive ones that time the discrimination is indirect. The proposed syste...

Now a day, many applications rely on the existence of small devices that can exchange information... more Now a day, many applications rely on the existence of small devices that can exchange information and form communication networks. And it is very challenging to provide security for such application. In a significant portion of such applications, the confidentiality and integrity of the communicated messages are of particular interest. In this work, we propose two novel techniques for authenticating short encrypted messages based on Advance Encryption cryptographic System that are directed to meet the requirements of mobile and pervasive applications. The encryption technique have the chance of the data misusing hence we add the password based authentication technique. By using Advance Encryption algorithm we are authenticating the message which is encrypted and we are improving the decryption speed and authentication accuracy to secure the communication the proposed message authentication technique is more efficient than the previous MAC algorithms and the aim of this proposed tech...

Cloud computing is the long dreamed vision of computing as a utility, where data owners can remot... more Cloud computing is the long dreamed vision of computing as a utility, where data owners can remotely store their data. The basic service provided by the Cloud is Data Storage. However, it is a difficult task for sharing data in multi-owner manner where group admin and all group members can store and modify data while preserving data and identity privacy from an untrusted cloud server, due to the frequent change of the membership. Therefore secure multi-owner data sharing scheme for dynamic groups in the cloud computing have been proposed which involve integration of group signature and broadcast encryption techniques. But this system also identified some limitations in terms of efficiency and security. Because multi-owner data storing and sharing in a dynamic environment dumps huge amount of data files in the cloud, which remains in cloud for indefinite period of time. The sensitive information stored may misused by service providers. To maintain cloud file’s security and privacy re...

ARTICLE INFO Mobile phone applications are becoming more and more popular. As the technology adva... more ARTICLE INFO Mobile phone applications are becoming more and more popular. As the technology advances, services like camera, accelerometers, compass, GPS, etc. are provided by the mobile phones. However, the more smart phones become smarter, the more the design of complex applications covering the various user needs becomes a complicated task. To support an End-User in the development of mobile applications we present a visual approach to enable End-Users to compose visually their own applications directly on their mobile phone. The methodology enables the end-user to develop applications and/or compose services on the smart phone, so making the way towards new scenarios where smart phones replace and overtake the Personal Computer, given their native possibility of wide connectivity, when augmented by features for interaction with remote systems and sensors. Moreover, the results of a preliminary usability study revealed a good satisfaction degree and the effectiveness and efficacy...

Various service provider systems or recommender systems have to manage the large amount of data r... more Various service provider systems or recommender systems have to manage the large amount of data regarding customer, service and information. This leads to Big Data analysis problem and its handling is also a challenging task. There are various organizations which serves user through service provider systems or recommender systems that provide efficient services in terms of set of good quality products or services to use by giving appropriate data as per their need. Hence the Decision Support System is used to determine the decision making activities in various organizations of recommender system which allows making certain planning, management and operations. This also helps to make decisions for structured and unstructured problem. It can be done in number of ways like descriptive, decision and prediction based. This paper will focus on Predictive Analysis of user behavior towards recommender system. The predictive analysis deals with the identification of relationship between spec...

The term Biometrics is becoming highly important in computer security world. The human physical c... more The term Biometrics is becoming highly important in computer security world. The human physical characteristics like fingerprints, face, hand geometry, voice and iris are known as biometrics. These features are used to provide an authentication for computer based security systems. The existing computer security systems used at various places like banking, passport, credit cards, smart cards, PIN , access control and network security are using username and passwords for person identification. The username and passwords can be replaced and/or provide double authentication by using any one of the biometric features. In this paper, the main focus is on the various biometrics, their applications and the existing biometrics recognition systems.

ARTICLE INFO Face recognition is very challenging area of research. The number of the images are ... more ARTICLE INFO Face recognition is very challenging area of research. The number of the images are available on the internet among them most of the images are human facial images which shared by the users. Some human facial images are not properly tagged with right name. So, Search-Based Face Annotation (SBFA) framework aims to deal with auto face annotation task and uses Content-Based Image Retrieval (CBIR) technique for face annotation. The main motive behind the SBFA is to assign right name label to a given query facial image. So K-means clustering-based algorithm used to improve scalability. This work also introduces the user is validated by their email. The efficiency of system improved by performing the verification of email, last login session of particular user, total counts of login etc. and finally the user account status is accomplished. Keywords— Face recognition, content-based image retrieval, face annotation. Article History Received: 19 th July 2016 Received in revised ...

International Journal of Radiation Oncology*Biology*Physics, 2017

Our ability to develop policies that increase the affordability and value of cancer care is limit... more Our ability to develop policies that increase the affordability and value of cancer care is limited because we do not understand what factors drive variation in spending. For patients with breast cancer, we described the extent that variation in spending is driven by observable patient/disease characteristics, treatment modalities, or residual patient and physician factors. Materials/Methods: We conducted a cross-sectional study of 24,818 women aged 66 years diagnosed 2010-11 with breast cancer using SEER-Medicare data. We used multi-level linear models to partition variation in monthly medical spending according to physician and patient factors. We then determined how much patient and physician driven variation is explained by patient/disease characteristics (age, stage, HER2/ hormone receptor status, comorbidity, geography), and treatment modalities (lumpectomy, mastectomy, radiation, biologics, chemotherapy, hospice). All models controlled for time. We examined spending for the initial year of treatment stratified by stage, and for the final 12 months of life among patients who died of breast cancer.

There are various techniques for crawling the web sites for searching the desired information. Th... more There are various techniques for crawling the web sites for searching the desired information. The paper titled “Intelligent Crawling Techniques For Locating the Sites” is focusing on the intelligent technique for searching the desired information which is available on the internet. The variety of information in the form of web pages on the internet is growing tremendously day to day. In this case searching relevant information on the Internet is a crucial and difficult task. This information is hidden behind query forms that interface to unexplored databases containing high quality structured data. Traditional search engines cannot access and index this hidden part of the information. A new term „Web Retrieving‟ arises to find this hidden information and become the challenge to the researcher. We have presented a two-stage framework, namely SmartCrawler, for effectively harvesting deep web interfaces. The first stage is called as Site Locating, and a second stage is called as In-Si...

International Journal of Engineering Research and, 2015

Traditional mouse and keyboard interaction is suitable for few applications like word processing ... more Traditional mouse and keyboard interaction is suitable for few applications like word processing but for drawing and designing, mouse becomes more difficult. As any user can draw a simple process on paper which can be implemented on desktop by interactive user interface and also creating infrared tracking interface like touch screen but more affordable than it. Further, this application provides extension to gesture control by other application. Major existing systems with widespread implementations are available but are limited to: Optical mice, capacitive touch panels, resistive touch panels, surface acoustic wave touch panels, etc. Touch panels move one step closer towards enhancing the interactivity of computing devices; however they have their own shortcomings. We present an alternative to the aforementioned traditional pointing devices which makes use of infrared radiations as a means of propagating user interactions between the computers and the users. The paper proposes a framework for a pointing device based on tracking of infrared light and determining its relative position and motion with respect to the computer system or device. The use of targeted infrared radiations as a medium of location information delivery forms the basis of the proposed framework.

International Journal of Engineering Research and, 2015

Traditional mouse and keyboard interaction is suitable for few applications like word processing ... more Traditional mouse and keyboard interaction is suitable for few applications like word processing but for drawing and designing, mouse becomes more difficult. As any user can draw a simple process on paper which can be implemented on desktop by interactive user interface and also creating infrared tracking interface like touch screen but more affordable than it. Further, this application provides extension to gesture control by other application. Major existing systems with widespread implementations are available but are limited to: Optical mice, capacitive touch panels, resistive touch panels, surface acoustic wave touch panels, etc. Touch panels move one step closer towards enhancing the interactivity of computing devices; however they have their own shortcomings. We present an alternative to the aforementioned traditional pointing devices which makes use of infrared radiations as a means of propagating user interactions between the computers and the users. The paper proposes a framework for a pointing device based on tracking of infrared light and determining its relative position and motion with respect to the computer system or device. The use of targeted infrared radiations as a medium of location information delivery forms the basis of the proposed framework.

Proceedings of the 8th …, 2009

In this paper, we are proposing a new classifier called support vector machines to classify the s... more In this paper, we are proposing a new classifier called support vector machines to classify the speech signals. We have achieved very good generalization performance by implementing the support vector machines with various kernel functions. The use One-vs-One Classifier with voting algorithm improves speech signal classification systems efficiency.

Journal of Computer Science, 2011

Problem statement: We proposed a new method for feature extraction of an Iris image for personal ... more Problem statement: We proposed a new method for feature extraction of an Iris image for personal identification system. Approach: This study purposed a new approach to extract the features of region of interest using the wavelet transform. The extracted Iris region could be normalizing into a rectangular block of fixed dimensions. The Gabor wavelet transform techniques had been applied on the data set to get feature vectors of an iris used for recognition. Results: Two Iris templates used for testing. The system performance score results in a false accept and false reject rate. Conclusion: The performance of the system "Efficient Feature Extraction Methodology Using wavelet transform for the development of personal identification system using iris biometrics" can be increased by training the more feature vectors of an extracted Iris images.