From very recent past years have witnessed the requirement and evolution of a vibrant research Cr... more From very recent past years have witnessed the requirement and evolution of a vibrant research Crew on a large variation of online Social Media Network (SMN) platforms. Recognizing anonymous, same yet identical users among multiple SMNs is still a major problem. Clearly, saying that cross-platform exploration may help solve too many problems in social computing in both theory and applications. Up to now public profiles can be duplicated and easily impersonated by users with different purposes, most current user identification resolutions, which mainly focus on text mining of users ‘public profiles, fragile. Some studies have attempted to match users based on the location and timing of user content as well as writing style. However, the locations are sparse in the majority of SMNs, and writing style is difficult to discern from the short sentences of leading SMNs such as, Sina Micro blog and Twitter. Moreover, up to now online SMNs are quite symmetric, existing user identification sc...
Smart Street light is a computerized methodology that mechanizes the road path. The aim of Smart ... more Smart Street light is a computerized methodology that mechanizes the road path. The aim of Smart Street light is decreasing force utilization when are vehicles are not there. The Smart road light will gleam with high power when there are vehicles are moving and the power will stay diminish. With this progression of innovation, things become less difficult and it becomes simple for all people on the planet today. Robotization is a method of controlling human work in the creation of products.
This paper presents the design and development of an intelligent voice recognition chat bot. The ... more This paper presents the design and development of an intelligent voice recognition chat bot. The paper presents a technology demonstrator to verify a proposed framework required to support such a bot (a web service). While a black box approach is used, by controlling the communication structure, to and from the web-service, the web-service allows all types of clients to communicate to the server from any platform. The service provided is accessible through a generated interface which allows for seamless XML processing; whereby the extensibility improves the lifespan of such a service. By introducing an artificial brain, the web-based bot generates customized user responses, aligned to the desired character. Questions asked to the bot, which is not understood is further processed using a third-party expert system (an online intelligent research assistant), and the response is archived, improving the artificial brain capabilities for future generation of responses. Keyword: Chat Bot ,...
Data mining plays a very important role in our day-to-day life in extracting useful information f... more Data mining plays a very important role in our day-to-day life in extracting useful information from the raw data, analyzing the data, classifying and forming clusters of the data set, etc. One of the interesting issues that is raised is to secure the confidential data or to preserve the privacy of the data without compromising its accuracy. Many data perturbation methods have been proposed that distorts the confidential attribute and maintain the accuracy and security level of numerical data including Translation Data Perturbation, Scaling Data Perturbation, Hybrid Data Perturbation, Double Reflection Data Perturbation Method,etc. A novel data distortion method has been introduced in this paper in order to further improve the privacy level and accuracy of the numerical data. The experiments are demonstrated and the results are reported with a comparative analysis of the existing methods and the proposed method. The results prove that the novel distortion method gives better perform...
A widely studied perturbation-based PPDM approach introduces random perturbation to individual va... more A widely studied perturbation-based PPDM approach introduces random perturbation to individual values to conserve privacy before data are published. The data owner before publishing the data first perform changes to the data into n number of copies based on the access privilege and publishes. In that the high privilege data contains a smaller amount noise and low privilege data contains more additional noise. But the formal attackers have possibility to make diversity attack to rebuild the data using non-linear techniques. To overcome the problem, a novel approach has been introduced where the data owner after performing modification finds the noise of every copy and compare. If the noise is similar means there is no privacy in the modified data and the attacker have possibility to reconstruct the information. So the data owner adds further noise until there is no similarity.
Storage of secure records and recovering is one of the most bursting investigations heading in cl... more Storage of secure records and recovering is one of the most bursting investigations heading in cloud computing. In spite of the way that various available encryption plans have been proposed, very few of them support profitable recuperation over the records which are encoded reliant on their characteristics. Currently, progressive quality based encryption model is intended for a record collection. A lot of records can be encoded together on the off chance that they share an integrated access structure. For improving the search viability DFS algorithm is used for the ARF tree. It can be further improved using cloud computing. Our system can be implemented for the purpose of document collection by slightly modifying the ARF tree.
Because of data mining progress in biomedical and human services networks, precise investigation ... more Because of data mining progress in biomedical and human services networks, precise investigation of clinical data benefits early illness acknowledgment, persistent consideration and network administrations. At the point when the nature of clinical data is inadequate the precision of study is diminished. In addition, various locales display one of a kind appearances of certain territorial maladies, which may brings about debilitating the forecast of illness flare-ups. In the proposed framework, it gives AI calculations to viable forecast of different illness events in sickness visit social orders. It try the adjusted gauge models over genuine medical clinic data gathered. To beat the trouble of inadequate data, it utilize an inert factor model to reconstruct the missing data. It probe a territorial interminable sickness of cerebral dead tissue. Utilizing organized and unstructured data from emergency clinic it use Machine Learning Decision Tree calculation. It predicts likely infecti...
Phishing is a typical assault on unsuspecting individuals by making them to reveal their one-of-a... more Phishing is a typical assault on unsuspecting individuals by making them to reveal their one-of-a-kind data utilizing fake sites. The target of phishing site URLs is to purloin the individual data like client name, passwords and web based financial exchanges. Phishers utilize the sites which are outwardly and semantically like those genuine sites. As innovation keeps on developing, phishing strategies began to advance quickly and this should be forestalled by utilizing against phishing systems to recognize phishing. AI is a useful asset used to endeavor against phishing assaults. We as a whole know bunches of assaults are happening continuously situation in light of phishing URLS. There is no programmed procedure has been set up so far Multiple assaults of phishing URLs has not yet coordinated. In the proposed framework finding the phishing assaults/URLs, the System will identify various phishing assaults in equal succession and caution the ordinary clients with respect to phishing ...
The Internet impacts extraordinarily upon each part of our lives, and thus is a basic asset for e... more The Internet impacts extraordinarily upon each part of our lives, and thus is a basic asset for everybody. Any disturbance or inaccessibility of this asset may prompt genuine effects at different levels of our public. As the reliance on the Internet continues developing at an exponential rate, the dangers to the accessibility of network assets have likewise been expanding quickly. In this research, we focus on the detection deep learning procedures against DoS attacks and recommend a learning centric detect scheme for the discovery, proof of identity, categorization of network attack. mitigation of IoT DDoS attacks.
Wireless sensor networks have wide use in different fields such as medical, military defense. Thi... more Wireless sensor networks have wide use in different fields such as medical, military defense. This paper discusses the primary hidden protection framework for data privacy. The hidden key, remote node, and base station are used to connect and hack through secrets. We used fiber labeling technologies to secure data transmission Between the base station and the far node. We combined those techniques with Data slice, homomorphism, data privacy and data security defense encryption technology. The only way to obtain more than a sufficient number of different secrets That can decode data from base station to remote node. To order to protect data privacy, the homomorphism encryption technology Sets up a safe and powerful network of wireless sensors.
Bone fracture is one of the most ordinary problems in mortals because of accidents or other cause... more Bone fracture is one of the most ordinary problems in mortals because of accidents or other causes. Breaking bones can occur in our body, such as the wrist, heel, ankle, hip, rib, leg, chest, etc. Fractures cannot be seen with the naked eye, so X-ray/CT images are used to detect them. But sometimes these images lack sufficient detail for diagnosis. Today image processing plays an important role in detecting bone fractures. Image processing is important for the archiving and transmission of modern data, in particular for image transmission, video encoding, digital libraries, image databases, and remote sensing. This research paper presents detailed research on image processing methods for detecting bone fractures. The following research will help in studying various techniques that can be used to detect fractures in boned through the process of image processing and also includes updating of some new techniques as an improvement.
Wireless Sensor Network (WSN) is a fast evolving current technology which is being employed in va... more Wireless Sensor Network (WSN) is a fast evolving current technology which is being employed in various applications. Despite its wide usage, WSNs have a few challenges to overcome to be called as an ideal technology. Some of the challenges are battery life time, memory storage and deployment issues. Batteries are the primary source of power supply to WSN and one of the major challenges is the energy constraint. This paper aims to propose a few techniques to better the energy efficiency of the sensor networks by saving sensor energy using data compression methodology. In this paper, a modified chorological coded data compression methodology is proposed (MCDC). This algorithm deals with assigning the sequence value to the given input information. If the assigned sequence value is a double digit number, it is converted in to single digit number. Double digit numbers and single digit numbers are combined. Separate location tables are generated for all double digit and single digit numbe...
The Privacy Preserving Data Mining technique that is used widely to conserve security of data is ... more The Privacy Preserving Data Mining technique that is used widely to conserve security of data is a random perturbation method. The original data is modified and many copies are created according to the trust levels in each field. The addition of noise level also varies with each trust level. The amount of noise added to the lower order trust level is less, whereas it is high in the higher order trust level. There is a chance for the hackers to reconstruct the original data with some non linear techniques. This challenge is addressed by the proposal of a novel non linear technique. Here, the noise level of each copy is checked after perturbation of the actual data. If any similarity is found in the noise level, reconstruction of the original data is possible. Therefore, additional noise is included in the perturbed data. This process is repeated till zero percent of similarity of data is attained.
In the world, about 21 percent of death occurs in the age group of 28-72 years because of a cardi... more In the world, about 21 percent of death occurs in the age group of 28-72 years because of a cardiac arrest. Many people among us lose their life because of heart-attack. After the occurrence of heart-attack only, the patient can be monitored. To help our society from heart-attack, I am developing a system that helps to decrease the death rate and early detection of a heart attack. Thus, this system is used to save the life of many people. We detect the prior occurrence of heart-attack of a patient using their monitored lungs datasets using image processing along with IoT.
From very recent past years have witnessed the requirement and evolution of a vibrant research Cr... more From very recent past years have witnessed the requirement and evolution of a vibrant research Crew on a large variation of online Social Media Network (SMN) platforms. Recognizing anonymous, same yet identical users among multiple SMNs is still a major problem. Clearly, saying that cross-platform exploration may help solve too many problems in social computing in both theory and applications. Up to now public profiles can be duplicated and easily impersonated by users with different purposes, most current user identification resolutions, which mainly focus on text mining of users ‘public profiles, fragile. Some studies have attempted to match users based on the location and timing of user content as well as writing style. However, the locations are sparse in the majority of SMNs, and writing style is difficult to discern from the short sentences of leading SMNs such as, Sina Micro blog and Twitter. Moreover, up to now online SMNs are quite symmetric, existing user identification sc...
Smart Street light is a computerized methodology that mechanizes the road path. The aim of Smart ... more Smart Street light is a computerized methodology that mechanizes the road path. The aim of Smart Street light is decreasing force utilization when are vehicles are not there. The Smart road light will gleam with high power when there are vehicles are moving and the power will stay diminish. With this progression of innovation, things become less difficult and it becomes simple for all people on the planet today. Robotization is a method of controlling human work in the creation of products.
This paper presents the design and development of an intelligent voice recognition chat bot. The ... more This paper presents the design and development of an intelligent voice recognition chat bot. The paper presents a technology demonstrator to verify a proposed framework required to support such a bot (a web service). While a black box approach is used, by controlling the communication structure, to and from the web-service, the web-service allows all types of clients to communicate to the server from any platform. The service provided is accessible through a generated interface which allows for seamless XML processing; whereby the extensibility improves the lifespan of such a service. By introducing an artificial brain, the web-based bot generates customized user responses, aligned to the desired character. Questions asked to the bot, which is not understood is further processed using a third-party expert system (an online intelligent research assistant), and the response is archived, improving the artificial brain capabilities for future generation of responses. Keyword: Chat Bot ,...
Data mining plays a very important role in our day-to-day life in extracting useful information f... more Data mining plays a very important role in our day-to-day life in extracting useful information from the raw data, analyzing the data, classifying and forming clusters of the data set, etc. One of the interesting issues that is raised is to secure the confidential data or to preserve the privacy of the data without compromising its accuracy. Many data perturbation methods have been proposed that distorts the confidential attribute and maintain the accuracy and security level of numerical data including Translation Data Perturbation, Scaling Data Perturbation, Hybrid Data Perturbation, Double Reflection Data Perturbation Method,etc. A novel data distortion method has been introduced in this paper in order to further improve the privacy level and accuracy of the numerical data. The experiments are demonstrated and the results are reported with a comparative analysis of the existing methods and the proposed method. The results prove that the novel distortion method gives better perform...
A widely studied perturbation-based PPDM approach introduces random perturbation to individual va... more A widely studied perturbation-based PPDM approach introduces random perturbation to individual values to conserve privacy before data are published. The data owner before publishing the data first perform changes to the data into n number of copies based on the access privilege and publishes. In that the high privilege data contains a smaller amount noise and low privilege data contains more additional noise. But the formal attackers have possibility to make diversity attack to rebuild the data using non-linear techniques. To overcome the problem, a novel approach has been introduced where the data owner after performing modification finds the noise of every copy and compare. If the noise is similar means there is no privacy in the modified data and the attacker have possibility to reconstruct the information. So the data owner adds further noise until there is no similarity.
Storage of secure records and recovering is one of the most bursting investigations heading in cl... more Storage of secure records and recovering is one of the most bursting investigations heading in cloud computing. In spite of the way that various available encryption plans have been proposed, very few of them support profitable recuperation over the records which are encoded reliant on their characteristics. Currently, progressive quality based encryption model is intended for a record collection. A lot of records can be encoded together on the off chance that they share an integrated access structure. For improving the search viability DFS algorithm is used for the ARF tree. It can be further improved using cloud computing. Our system can be implemented for the purpose of document collection by slightly modifying the ARF tree.
Because of data mining progress in biomedical and human services networks, precise investigation ... more Because of data mining progress in biomedical and human services networks, precise investigation of clinical data benefits early illness acknowledgment, persistent consideration and network administrations. At the point when the nature of clinical data is inadequate the precision of study is diminished. In addition, various locales display one of a kind appearances of certain territorial maladies, which may brings about debilitating the forecast of illness flare-ups. In the proposed framework, it gives AI calculations to viable forecast of different illness events in sickness visit social orders. It try the adjusted gauge models over genuine medical clinic data gathered. To beat the trouble of inadequate data, it utilize an inert factor model to reconstruct the missing data. It probe a territorial interminable sickness of cerebral dead tissue. Utilizing organized and unstructured data from emergency clinic it use Machine Learning Decision Tree calculation. It predicts likely infecti...
Phishing is a typical assault on unsuspecting individuals by making them to reveal their one-of-a... more Phishing is a typical assault on unsuspecting individuals by making them to reveal their one-of-a-kind data utilizing fake sites. The target of phishing site URLs is to purloin the individual data like client name, passwords and web based financial exchanges. Phishers utilize the sites which are outwardly and semantically like those genuine sites. As innovation keeps on developing, phishing strategies began to advance quickly and this should be forestalled by utilizing against phishing systems to recognize phishing. AI is a useful asset used to endeavor against phishing assaults. We as a whole know bunches of assaults are happening continuously situation in light of phishing URLS. There is no programmed procedure has been set up so far Multiple assaults of phishing URLs has not yet coordinated. In the proposed framework finding the phishing assaults/URLs, the System will identify various phishing assaults in equal succession and caution the ordinary clients with respect to phishing ...
The Internet impacts extraordinarily upon each part of our lives, and thus is a basic asset for e... more The Internet impacts extraordinarily upon each part of our lives, and thus is a basic asset for everybody. Any disturbance or inaccessibility of this asset may prompt genuine effects at different levels of our public. As the reliance on the Internet continues developing at an exponential rate, the dangers to the accessibility of network assets have likewise been expanding quickly. In this research, we focus on the detection deep learning procedures against DoS attacks and recommend a learning centric detect scheme for the discovery, proof of identity, categorization of network attack. mitigation of IoT DDoS attacks.
Wireless sensor networks have wide use in different fields such as medical, military defense. Thi... more Wireless sensor networks have wide use in different fields such as medical, military defense. This paper discusses the primary hidden protection framework for data privacy. The hidden key, remote node, and base station are used to connect and hack through secrets. We used fiber labeling technologies to secure data transmission Between the base station and the far node. We combined those techniques with Data slice, homomorphism, data privacy and data security defense encryption technology. The only way to obtain more than a sufficient number of different secrets That can decode data from base station to remote node. To order to protect data privacy, the homomorphism encryption technology Sets up a safe and powerful network of wireless sensors.
Bone fracture is one of the most ordinary problems in mortals because of accidents or other cause... more Bone fracture is one of the most ordinary problems in mortals because of accidents or other causes. Breaking bones can occur in our body, such as the wrist, heel, ankle, hip, rib, leg, chest, etc. Fractures cannot be seen with the naked eye, so X-ray/CT images are used to detect them. But sometimes these images lack sufficient detail for diagnosis. Today image processing plays an important role in detecting bone fractures. Image processing is important for the archiving and transmission of modern data, in particular for image transmission, video encoding, digital libraries, image databases, and remote sensing. This research paper presents detailed research on image processing methods for detecting bone fractures. The following research will help in studying various techniques that can be used to detect fractures in boned through the process of image processing and also includes updating of some new techniques as an improvement.
Wireless Sensor Network (WSN) is a fast evolving current technology which is being employed in va... more Wireless Sensor Network (WSN) is a fast evolving current technology which is being employed in various applications. Despite its wide usage, WSNs have a few challenges to overcome to be called as an ideal technology. Some of the challenges are battery life time, memory storage and deployment issues. Batteries are the primary source of power supply to WSN and one of the major challenges is the energy constraint. This paper aims to propose a few techniques to better the energy efficiency of the sensor networks by saving sensor energy using data compression methodology. In this paper, a modified chorological coded data compression methodology is proposed (MCDC). This algorithm deals with assigning the sequence value to the given input information. If the assigned sequence value is a double digit number, it is converted in to single digit number. Double digit numbers and single digit numbers are combined. Separate location tables are generated for all double digit and single digit numbe...
The Privacy Preserving Data Mining technique that is used widely to conserve security of data is ... more The Privacy Preserving Data Mining technique that is used widely to conserve security of data is a random perturbation method. The original data is modified and many copies are created according to the trust levels in each field. The addition of noise level also varies with each trust level. The amount of noise added to the lower order trust level is less, whereas it is high in the higher order trust level. There is a chance for the hackers to reconstruct the original data with some non linear techniques. This challenge is addressed by the proposal of a novel non linear technique. Here, the noise level of each copy is checked after perturbation of the actual data. If any similarity is found in the noise level, reconstruction of the original data is possible. Therefore, additional noise is included in the perturbed data. This process is repeated till zero percent of similarity of data is attained.
In the world, about 21 percent of death occurs in the age group of 28-72 years because of a cardi... more In the world, about 21 percent of death occurs in the age group of 28-72 years because of a cardiac arrest. Many people among us lose their life because of heart-attack. After the occurrence of heart-attack only, the patient can be monitored. To help our society from heart-attack, I am developing a system that helps to decrease the death rate and early detection of a heart attack. Thus, this system is used to save the life of many people. We detect the prior occurrence of heart-attack of a patient using their monitored lungs datasets using image processing along with IoT.
Uploads
Papers by Viji Mary