Harish Kandala | VIT University (original) (raw)
Research Publications - Journals/Conferences/Books by Harish Kandala
Web Browsers are one of the most used client-side software in today's world and maintaining the d... more Web Browsers are one of the most used client-side software in today's world and maintaining the details of the user's search is one of the primary tasks of today's browsers. However, the browsing history management methodologies that are currently used to save and visualize the details of the user's search can be improved by a great extent to make it a lot easier for the user to browse data over the internet. The techniques used by the modern browsers in doing so are, to an extent, inefficient due to the fact that they only show a serial list of URLs the user queried for and the time at which they were queried with no details of how the user actually ended up reaching a particular page. The primary issue with such methodologies is that the browsers do not maintain the details of the relationship between various history items. This paper provides a solution to this issue with a practical implementation of a client-side browser history management extension that solves the above-mentioned problems and hence describes how the user's browsing experience can be enhanced.
This paper elucidates the energy optimization problem in routing data packets applicable to heter... more This paper elucidates the energy optimization problem in routing data packets applicable to heterogeneous wireless sensor networks using the artificial bee colony algorithm for utilizing the collective intelligence of the swarm of sensors and a mobile sink. The applications of Wireless Sensor Networks are far and wide with sensing, computing and communicating capabilities embedded but are restricted by their battery lifetime. To overcome this we are using the shortest path with nodes containing the most energy in the cluster to route the data packets from sensors to elected cluster heads. This way the hops taken by packets from other nodes to reach the cluster head would cost the least loss in the lifetime for the network. This algorithm proves to be especially effective in heterogeneous networks and gives a robust performance. The proposed algorithm is compared to the results from existing techniques to show superior performance.
2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Oct 18, 2018
Handwriting is a skill developed by humans from the very early stage in the order to represent hi... more Handwriting is a skill developed by humans from the very early stage in the order to represent his/her thoughts visually using letters and making meaningful words and sentences. Every person improves this skill by practicing and develops his/her own style of writing. Because of the distinctiveness of handwriting style, it is frequently used as a measure to identify a forgery. Even though the applications of synthesizing of handwriting is less, this problem can be generalized and can be functionally applied to other more practical problems. Synthesizing the handwriting is a quite complicated task to achieve. Deep recurrent neural networks specifically Deep LSTM cells can be used along with a Mixture Density Network to generate artificial handwriting data. But using this model we can only generate random handwriting styles which are being hallucinated by the model. Mimicking a specific handwriting style is not so efficient with this model. Mimicking or imitating a specific handwriting style can have an extensive variety of applications like generating personalized handwritten documents, editing a handwritten document by using the similar handwriting style and also it is extended to compare handwriting styles to identify a forgery. A web prototype is developed along with the model to test the results where the user can enter the text input and select handwriting style to be used. And the application will return the handwritten document containing input text mimicking the selected handwriting style. The application will also provide a way to fine-tune the handwriting styles by changing few parameters.
Smart Innovation, Systems and Technologies, Aug 8, 2017
In all the modern browsers, maintaining user's web history is one of the primary tasks. Browser h... more In all the modern browsers, maintaining user's web history is one of the primary tasks. Browser history will help to summarize the activity of the user during a certain period. However, current browser history is not so efficient to visualize in a user-friendly manner and also doesn't provide enough information for personalized recommendations. One of the key reason is that browsers never maintain any inter-connection between history items. Overall history is main‐ tained in a linear fashion with no information about how the user reached to a particular state. Another issue is that it is not possible to calculate how much time the user spent on any particular website using current history system. This paper provides a conceptual idea of solving these issues by providing a framework that solves this issue by introducing linked data and also describes how this can benefit in improving user experience and quality of recommendations.
Web Browsers are one of the most used client-side software in today's world and maintaining the d... more Web Browsers are one of the most used client-side software in today's world and maintaining the details of the user's search is one of the primary tasks of today's browsers. However, the browsing history management methodologies that are currently used to save and visualize the details of the user's search can be improved by a great extent to make it a lot easier for the user to browse data over the internet. The techniques used by the modern browsers in doing so are, to an extent, inefficient due to the fact that they only show a serial list of URLs the user queried for and the time at which they were queried with no details of how the user actually ended up reaching a particular page. The primary issue with such methodologies is that the browsers do not maintain the details of the relationship between various history items. This paper provides a solution to this issue with a practical implementation of a client-side browser history management extension that solves the above-mentioned problems and hence describes how the user's browsing experience can be enhanced.
This paper elucidates the energy optimization problem in routing data packets applicable to heter... more This paper elucidates the energy optimization problem in routing data packets applicable to heterogeneous wireless sensor networks using the artificial bee colony algorithm for utilizing the collective intelligence of the swarm of sensors and a mobile sink. The applications of Wireless Sensor Networks are far and wide with sensing, computing and communicating capabilities embedded but are restricted by their battery lifetime. To overcome this we are using the shortest path with nodes containing the most energy in the cluster to route the data packets from sensors to elected cluster heads. This way the hops taken by packets from other nodes to reach the cluster head would cost the least loss in the lifetime for the network. This algorithm proves to be especially effective in heterogeneous networks and gives a robust performance. The proposed algorithm is compared to the results from existing techniques to show superior performance.
2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Oct 18, 2018
Handwriting is a skill developed by humans from the very early stage in the order to represent hi... more Handwriting is a skill developed by humans from the very early stage in the order to represent his/her thoughts visually using letters and making meaningful words and sentences. Every person improves this skill by practicing and develops his/her own style of writing. Because of the distinctiveness of handwriting style, it is frequently used as a measure to identify a forgery. Even though the applications of synthesizing of handwriting is less, this problem can be generalized and can be functionally applied to other more practical problems. Synthesizing the handwriting is a quite complicated task to achieve. Deep recurrent neural networks specifically Deep LSTM cells can be used along with a Mixture Density Network to generate artificial handwriting data. But using this model we can only generate random handwriting styles which are being hallucinated by the model. Mimicking a specific handwriting style is not so efficient with this model. Mimicking or imitating a specific handwriting style can have an extensive variety of applications like generating personalized handwritten documents, editing a handwritten document by using the similar handwriting style and also it is extended to compare handwriting styles to identify a forgery. A web prototype is developed along with the model to test the results where the user can enter the text input and select handwriting style to be used. And the application will return the handwritten document containing input text mimicking the selected handwriting style. The application will also provide a way to fine-tune the handwriting styles by changing few parameters.
Smart Innovation, Systems and Technologies, Aug 8, 2017
In all the modern browsers, maintaining user's web history is one of the primary tasks. Browser h... more In all the modern browsers, maintaining user's web history is one of the primary tasks. Browser history will help to summarize the activity of the user during a certain period. However, current browser history is not so efficient to visualize in a user-friendly manner and also doesn't provide enough information for personalized recommendations. One of the key reason is that browsers never maintain any inter-connection between history items. Overall history is main‐ tained in a linear fashion with no information about how the user reached to a particular state. Another issue is that it is not possible to calculate how much time the user spent on any particular website using current history system. This paper provides a conceptual idea of solving these issues by providing a framework that solves this issue by introducing linked data and also describes how this can benefit in improving user experience and quality of recommendations.