Rajesh Prasad | Bharati Vidyapeeth Deemed University Pune (original) (raw)

Papers by Rajesh Prasad

Journal of Advanced Research in Dynamic and Control Systems, 2019

Auerbach Publications eBooks, May 2, 2023

IGI Global eBooks, 2020

InInternetofthingsanditsrelevanttechnologiestheroutingofdataplaysoneofthemajorroles.In thispaper,... more InInternetofthingsanditsrelevanttechnologiestheroutingofdataplaysoneofthemajorroles.In thispaper,aroutingalgorithmispresentedforthenetworksconsistingofsmartobjects,sothatthe InternetofThingsanditsenablingtechnologiescanprovidehighreliabilitywhilethetransmitting thedata.Theproposedtechniqueexecutesintwostages.Infirststage,thesensornodesareclustered and an optimal cluster head is selected by using k-means clustering algorithm. The clustering is performedbasedonenergyofsensornodes.Thentheenergycostoftheclusterheadandthetrust levelofthesensornodesaredetermined.Atsecondstage,anoptimalpathwillbeselectedbyusing theGeneticAlgorithm(GA).Thegeneticalgorithmisbasedontheenergycostatclusterhead,trust levelatsensornodesandpathlength.Theresultantoptimalpathprovideshighreliability,better speedandmorelifetimes.

Evolutionary Intelligence, May 28, 2019

Due to the advancement of a variety of photo editing and image processing software, image forensi... more Due to the advancement of a variety of photo editing and image processing software, image forensics analysis has become an important research topic in recent years. Numbers of research works are presented for image forensic analysis. Accordingly, this paper proposes a method named as Dragonfly Bayes Fusion System (DBFS) by integrating the Naive Bayes (NB) classifier and the Dragonfly optimization for detecting the tampered Joint Photographic Experts Group image. Initially, the input image is applied to the existing six forensic tools separately, and the classified binary map is generated. Then, the proposed DBFS fuses these decisions for generating the optimal decision. Here, the NB classifier creates the model by finding the mean and variance of every feature and this model is given as input to the Dragonfly optimization for optimally generating the probabilistic measures. Finally, the posterior probability of each feature is determined with respect to the tampered class, and the original class and the tampered image block is determined. The performance of the proposed system is evaluated with the existing methods, such as fuzzy theory based classification, rule-based classification, average method, and weighted average method for the evaluation metrics accuracy, False Positive Rate (FPR), and True Positive Rate (TPR). The experimental results show that the proposed system outperforms the existing methods by obtaining the maximum accuracy of 0.9519, minimum FPR of 0.0490, and maximum TPR of 0.8720 when compared to the existing methods.

International journal of rough sets and data analysis, Apr 1, 2017

Over past few years, we are the spectators of the evolution in the field of information technolog... more Over past few years, we are the spectators of the evolution in the field of information technology, telecommunication and networking. Due to the advancement of smart phones, easy and inexpensive access to the internet and popularity of social networking, capture and use of digital images has increased drastically. Image processing techniques are getting developed at rapidly and at the same time easy to use image tampering soft-wares are also getting readily available. If tampered images are misused, big troubles having deep moral, ethical and lawful allegations may arise. Due to high potential of visual media and the ease in their capture, distribution and storage, we rarely find a field where digital visual data is not used. The value of image as evidence of event must be carefully assessed and it is a call for from different fields of applications. Therefore, in this age of fantasy, image authentication has become an issue of utmost importance.

International Journal of Image and Graphics

Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmla... more Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmland, and infrastructure. To address this, it is necessary to devise and employ an effective flood management system that can immediately identify flood areas to initiate relief measures as soon as possible. Therefore, this research work develops an effective flood detection method, named Anti- Corona-Shuffled Shepherd Optimization Algorithm-based Deep Quantum Neural Network (ACSSOA-based Deep QNN) for identifying the flooded areas. Here, the segmentation process is performed using Fuzzy C-Means with Spatial Constraint Multi-Kernel Distance (MKFCM_S) wherein the Fuzzy C-Means (FCM) is modified with Spatial Constraints Based on Kernel-Induced Distance (KFCM_S). For flood detection, Deep QNN has been used wherein the training progression of Deep QNN is done using designed optimization algorithm, called ACSSOA. Besides, the designed ACSSOA is newly formed by the hybridization of Anti Corona V...

International Journal of Business Analytics, 2016

Document retrieval plays a crucial role in retrieving relevant documents. Relevancy depends upon ... more Document retrieval plays a crucial role in retrieving relevant documents. Relevancy depends upon the occurrences of query keywords in a document. Several documents include a similar key terms and hence they need to be indexed. Most of the indexing techniques are either based on inverted index or full-text index. Inverted index create lists and support word-based pattern queries. While full-text index handle queries comprise of any sequence of characters rather than just words. Problems arise when text cannot be separated as words in some western languages. Also, there are difficulties in space used by compressed versions of full-text indexes. Recently, one of the unique data structure called wavelet tree has been popular in the text compression and indexing. It indexes words or characters of the text documents and help in retrieving top ranked documents more efficiently. This paper presents a review on most recent efficient indexing techniques used in document retrieval.

2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), 2019

In this World of Words the rate of arriving new born worlds are tremendously increase with respec... more In this World of Words the rate of arriving new born worlds are tremendously increase with respect to time zone, as it is obvious that it will create a lack of much better and reliable word management with us. Now to survive we possess good clusters of similar bunch of worlds and their making process which called clustering are available. In this paper will see various clustering methods, qualities of good clusters with various Algorithms used on ground of Data mining. This will help to refill the lacks in future development in this area.

Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmla... more Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmland, and infrastructure. To address this, it is necessary to devise and employ an e®ective°o od management system that can immediately identify°ood areas to initiate relief measures as soon as possible. Therefore, this research work develops an e®ective°ood detection method, named Anti-Corona-Shu®led Shepherd Optimization Algorithm-based Deep Quantum Neural Network (ACSSOA-based Deep QNN) for identifying the°ooded areas. Here, the segmentation process is performed using Fuzzy C-Means with Spatial Constraint Multi-Kernel Distance (MKFCM S) wherein the Fuzzy C-Means (FCM) is modi¯ed with Spatial Constraints Based on Kernel-Induced Distance (KFCM S). For°ood detection, Deep QNN has been used wherein the training progression of Deep QNN is done using designed optimization algorithm, called ACSSOA. Besides, the designed ACSSOA is newly formed by the hybridization of Anti Corona Virus Optimization (ACVO) and Shu®led Shepherd Optimization Algorithm (SSOA). The devised method was evaluated using the Kerala Floods database, and it acquires the * Corresponding author.

Prostate cancer (PCa) represents the general type of cancer and is considered the third leading r... more Prostate cancer (PCa) represents the general type of cancer and is considered the third leading reason of death worldwide. As a combined part of computer-aided detection (CAD) applications, magnetic resonance imaging (MRI) is extensively studied for the precise detection of PCa. However, various issues rely on MRI, which includes the complexity of interpretation and increased time. Thus, deep learning-based tumor detection and segmentation methods attempt to be imperative techniques for radiologists to execute their tasks more precisely. The objective is to present Gradient Bald vulture optimization (GBVO)-based Deep Convolution Neural Networks (DCNN) with U-Net++ for segmenting and detecting prostate cancer. Initially, image pre-processing is done using Non-Local Means (NLM) filter. After pre-processing, image segmentation is carried out using the proposed optimized multi-objective Unet++, where the objective function in Unet++ is modified using pixel-wise cross entropy and the Jaccard coefficient. In addition, the training of Unet++ is done using the newly designed Gradient Bald Eagle Optimization (GBEO), which is a combination of Stochastic Gradient Descent (SGD) and Bald Eagle optimization (BEO). Finally, cancer detection is done using DCNN. DCNN is trained using GBVO, which is the integration of the African Vultures Optimization Algorithm (AVOA) and GBEO. The proposed method outperformed state-of-the-art techniques. The developed method achieved the highest accuracy of 0.916, a false negative ratio (FNR) of 0.104, a false positive ratio (FPR) of 0.100, and a negative predictive value (NPV) of 0.903.

Semantic IoT: Theory and Applications, 2021

In the coming few years, there is going to be rapid advancement in terms of technology like 5G, 6... more In the coming few years, there is going to be rapid advancement in terms of technology like 5G, 6G, etc. When we think about 5G, the performance of the internet is going to increase multifold. The 5G i.e. fifth-generation network is going to be very heterogeneous. There is a need for a standardized solution to the issues in this technology. In this work, we are trying to understand the problems specifically in IoT (Internet of Things) area of 5G. In the literature survey, we found out that various solutions have been proposed in the area of the Internet of Things, but there is a lack of some generic solutions for all IoT projects. Every project works excellent in its closed and specified environment. When we try to connect multiple IoT projects, there is a big problem of interoperability. Some ICT standardization organizations have proposed some solutions to interoperability to overcome this scenario. Few solutions have been proposed by some authors to provide interoperability using semantic technologies. The solution for this problem of heterogeneous IoT can be provided using the semantic technologies in combination with that of SDN (Software Defined Network), NFV (Network Function Virtualization), and Cloud infrastructure.

International Journal of Engineering Research and, 2015

Author identification of a document can be implemented using statistical or computational method.... more Author identification of a document can be implemented using statistical or computational method. In author identification, an author can be distinguished by his unique writing style. The basic idea behind author identification using statistical or computational method authorship is to measure different textual features for determining the author. The statistical method allows us to analyse and explore aspects of a text that wouldn't be easy for us to identify. In this paper we have focused on CUSUM technique which is a statistical method. CUSUM technique is based on calculation of average sentence length and set of words used by the author frequently.

2019 IEEE Pune Section International Conference (PuneCon)

Day by day use of internet is increasing rapidly, all the world is nowadays likely moving towards... more Day by day use of internet is increasing rapidly, all the world is nowadays likely moving towards to Internet of Things or IoT. Many industries, organizations now using IoT applications because of that its use is increased rapidly. Usability of IoT is growing so fast, therefore the network became more vulnerable to attacks. Security aspects become very essential to Internet of Things applications. There are various security approaches used for securing IoT applications but recently Machine Learning (ML) is used by most of the researcher for security purpose. A machine learning method monitors IoT applications intelligently and provides a significant solution to attacks. This paper gives a brief survey about IoT security and overview of machine learning methods used for securing some IoT security issues.

Journal of Data Mining and Management

About 80% organizational data are present in the unstructured (Text) format. E-mails, Social medi... more About 80% organizational data are present in the unstructured (Text) format. E-mails, Social media, notes, and wide variety of different types of documents in text formats are present, but all these data are not got importance and analyzed in meaningful ways. It has been observed that information workers spend their significant time (up to one third) to locating this information and trying to make sense of it. Text analytics (TA) is the process which analyzed all these available unstructured text information and converts it into useful information which helps the organization significantly in their business processes. In this paper we have discussed the business values, methods of text analytics, and business application of text analytics.

Journal of Data Mining and Management

About 80% organizational data are present in the unstructured (Text) format. E-mails, social medi... more About 80% organizational data are present in the unstructured (Text) format. E-mails, social media, notes, and wide variety of different types of documents in text formats are present, but all these data are not get importance and analyzed in meaningful ways. It has been observed that information workers spend their significant time (up to one third) to locating this information and trying to make sense of it. Text analytics is the process which analyzed all these available unstructured text information and converts it into useful information which helps the organization significantly in their business processes. In this paper, we have highlighted the business values, some of the methods, and business application of text analytics.

2018 International Conference On Advances in Communication and Computing Technology (ICACCT), 2018

Author Identification (AI) is one of the applications of text mining. It is a technique to identi... more Author Identification (AI) is one of the applications of text mining. It is a technique to identify anonymous author of electronic - text. This paper presents a survey on present techniques for identifying author of anonymous text document. We outline this survey based on AI techniques on literature wrote in various Languages like English, Japanese, Mongolian, Persian, Albanian, Indian, Brazilian and Russian. This paper also presents Language translation issues and effect on author identity of anonymous text document i.e. from English to German and/or Japanese and then back to English and also Arabic to English. We have also studied feature independent method. An evaluation of AI techniques under different Languages is analyzed based on accuracy of the AI and data set applied as a training data. At the end we conclude this paper with observations and future scope in this area.

2018 International Conference On Advances in Communication and Computing Technology (ICACCT), 2018

Authorship Identification is task to identify author of an article or document whose author is no... more Authorship Identification is task to identify author of an article or document whose author is not known. This can be possible by comparing set of articles or documents whose authorship is known to this unknown article. This paper presents comparative approach based on similarity of unknown documents against the known by use of various features. The main focus of the paper is to show the difference in articles which were written in different time frames. And also observe, how the feature gets addressed in this different time frame of the same author. All method shows the comparison over several features.

Authorship analysis process in which finding the author of unknown text when the history of the w... more Authorship analysis process in which finding the author of unknown text when the history of the writing style of the author known. It can be viewed as a multi-class, single-mark content classification assignment. A lot of author identification problems had been created and solved with the different methods. Character and word n-gram are most commonly used methods for feature construction and participated in authorship identification task. In this paper, we point out the methodology of formation of word n-gram. The approach described in the paper does not depend on constant value n, the value of n changes according to the occurrence of word sequences. The methodology applied to the collection of text which is from the varied time domain. We used a dataset of 13 authors, whose text generation time is big. Dynamic value of n chosen to generate word sequence. In terms of accuracy, the result shows improvement as compared to the fixed value of n in word n-gram. We also explore the signif...

Advances in Intelligent Systems and Computing, 2020

Author identification (AI) is a process of investigating author of an anonymous text document. AI... more Author identification (AI) is a process of investigating author of an anonymous text document. AI has a great help in digital forensic, copyright issues, plagiarism detection, etc. for making the law process quick and efficient. This paper presents AI on Indian regional language Marathi. Insted of it kindly replce it by this scentence: In this research paper, we proposed 21 language-specific lexical features. Validation of these proposed features is done on “Author wise Marathi Language Typewritten Text Corpus” published by us at Indian Language Technology Proliferation and Deployment Center. Experimentation is performed with proposed 21 features. Performance is compared through various machine learning algorithms like Naive Bayes, k-Nearest Neighbor and Sequential Minimal Optimization. k-Nearest Neighbor performs well over Naive Bayes and Sequential Minimal Optimization with average accuracy achieved as 82.06 on comedy articles and 85.44 on mixed articles. Proposed language-specific features provide significant improvement in result of accuracy over traditional features.

Journal of Advanced Research in Dynamic and Control Systems, 2019

Auerbach Publications eBooks, May 2, 2023

IGI Global eBooks, 2020

InInternetofthingsanditsrelevanttechnologiestheroutingofdataplaysoneofthemajorroles.In thispaper,... more InInternetofthingsanditsrelevanttechnologiestheroutingofdataplaysoneofthemajorroles.In thispaper,aroutingalgorithmispresentedforthenetworksconsistingofsmartobjects,sothatthe InternetofThingsanditsenablingtechnologiescanprovidehighreliabilitywhilethetransmitting thedata.Theproposedtechniqueexecutesintwostages.Infirststage,thesensornodesareclustered and an optimal cluster head is selected by using k-means clustering algorithm. The clustering is performedbasedonenergyofsensornodes.Thentheenergycostoftheclusterheadandthetrust levelofthesensornodesaredetermined.Atsecondstage,anoptimalpathwillbeselectedbyusing theGeneticAlgorithm(GA).Thegeneticalgorithmisbasedontheenergycostatclusterhead,trust levelatsensornodesandpathlength.Theresultantoptimalpathprovideshighreliability,better speedandmorelifetimes.

Evolutionary Intelligence, May 28, 2019

Due to the advancement of a variety of photo editing and image processing software, image forensi... more Due to the advancement of a variety of photo editing and image processing software, image forensics analysis has become an important research topic in recent years. Numbers of research works are presented for image forensic analysis. Accordingly, this paper proposes a method named as Dragonfly Bayes Fusion System (DBFS) by integrating the Naive Bayes (NB) classifier and the Dragonfly optimization for detecting the tampered Joint Photographic Experts Group image. Initially, the input image is applied to the existing six forensic tools separately, and the classified binary map is generated. Then, the proposed DBFS fuses these decisions for generating the optimal decision. Here, the NB classifier creates the model by finding the mean and variance of every feature and this model is given as input to the Dragonfly optimization for optimally generating the probabilistic measures. Finally, the posterior probability of each feature is determined with respect to the tampered class, and the original class and the tampered image block is determined. The performance of the proposed system is evaluated with the existing methods, such as fuzzy theory based classification, rule-based classification, average method, and weighted average method for the evaluation metrics accuracy, False Positive Rate (FPR), and True Positive Rate (TPR). The experimental results show that the proposed system outperforms the existing methods by obtaining the maximum accuracy of 0.9519, minimum FPR of 0.0490, and maximum TPR of 0.8720 when compared to the existing methods.

International journal of rough sets and data analysis, Apr 1, 2017

Over past few years, we are the spectators of the evolution in the field of information technolog... more Over past few years, we are the spectators of the evolution in the field of information technology, telecommunication and networking. Due to the advancement of smart phones, easy and inexpensive access to the internet and popularity of social networking, capture and use of digital images has increased drastically. Image processing techniques are getting developed at rapidly and at the same time easy to use image tampering soft-wares are also getting readily available. If tampered images are misused, big troubles having deep moral, ethical and lawful allegations may arise. Due to high potential of visual media and the ease in their capture, distribution and storage, we rarely find a field where digital visual data is not used. The value of image as evidence of event must be carefully assessed and it is a call for from different fields of applications. Therefore, in this age of fantasy, image authentication has become an issue of utmost importance.

International Journal of Image and Graphics

Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmla... more Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmland, and infrastructure. To address this, it is necessary to devise and employ an effective flood management system that can immediately identify flood areas to initiate relief measures as soon as possible. Therefore, this research work develops an effective flood detection method, named Anti- Corona-Shuffled Shepherd Optimization Algorithm-based Deep Quantum Neural Network (ACSSOA-based Deep QNN) for identifying the flooded areas. Here, the segmentation process is performed using Fuzzy C-Means with Spatial Constraint Multi-Kernel Distance (MKFCM_S) wherein the Fuzzy C-Means (FCM) is modified with Spatial Constraints Based on Kernel-Induced Distance (KFCM_S). For flood detection, Deep QNN has been used wherein the training progression of Deep QNN is done using designed optimization algorithm, called ACSSOA. Besides, the designed ACSSOA is newly formed by the hybridization of Anti Corona V...

International Journal of Business Analytics, 2016

Document retrieval plays a crucial role in retrieving relevant documents. Relevancy depends upon ... more Document retrieval plays a crucial role in retrieving relevant documents. Relevancy depends upon the occurrences of query keywords in a document. Several documents include a similar key terms and hence they need to be indexed. Most of the indexing techniques are either based on inverted index or full-text index. Inverted index create lists and support word-based pattern queries. While full-text index handle queries comprise of any sequence of characters rather than just words. Problems arise when text cannot be separated as words in some western languages. Also, there are difficulties in space used by compressed versions of full-text indexes. Recently, one of the unique data structure called wavelet tree has been popular in the text compression and indexing. It indexes words or characters of the text documents and help in retrieving top ranked documents more efficiently. This paper presents a review on most recent efficient indexing techniques used in document retrieval.

2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), 2019

In this World of Words the rate of arriving new born worlds are tremendously increase with respec... more In this World of Words the rate of arriving new born worlds are tremendously increase with respect to time zone, as it is obvious that it will create a lack of much better and reliable word management with us. Now to survive we possess good clusters of similar bunch of worlds and their making process which called clustering are available. In this paper will see various clustering methods, qualities of good clusters with various Algorithms used on ground of Data mining. This will help to refill the lacks in future development in this area.

Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmla... more Floods are the deadly and catastrophic disasters, causing loss of life and harm to assets, farmland, and infrastructure. To address this, it is necessary to devise and employ an e®ective°o od management system that can immediately identify°ood areas to initiate relief measures as soon as possible. Therefore, this research work develops an e®ective°ood detection method, named Anti-Corona-Shu®led Shepherd Optimization Algorithm-based Deep Quantum Neural Network (ACSSOA-based Deep QNN) for identifying the°ooded areas. Here, the segmentation process is performed using Fuzzy C-Means with Spatial Constraint Multi-Kernel Distance (MKFCM S) wherein the Fuzzy C-Means (FCM) is modi¯ed with Spatial Constraints Based on Kernel-Induced Distance (KFCM S). For°ood detection, Deep QNN has been used wherein the training progression of Deep QNN is done using designed optimization algorithm, called ACSSOA. Besides, the designed ACSSOA is newly formed by the hybridization of Anti Corona Virus Optimization (ACVO) and Shu®led Shepherd Optimization Algorithm (SSOA). The devised method was evaluated using the Kerala Floods database, and it acquires the * Corresponding author.

Prostate cancer (PCa) represents the general type of cancer and is considered the third leading r... more Prostate cancer (PCa) represents the general type of cancer and is considered the third leading reason of death worldwide. As a combined part of computer-aided detection (CAD) applications, magnetic resonance imaging (MRI) is extensively studied for the precise detection of PCa. However, various issues rely on MRI, which includes the complexity of interpretation and increased time. Thus, deep learning-based tumor detection and segmentation methods attempt to be imperative techniques for radiologists to execute their tasks more precisely. The objective is to present Gradient Bald vulture optimization (GBVO)-based Deep Convolution Neural Networks (DCNN) with U-Net++ for segmenting and detecting prostate cancer. Initially, image pre-processing is done using Non-Local Means (NLM) filter. After pre-processing, image segmentation is carried out using the proposed optimized multi-objective Unet++, where the objective function in Unet++ is modified using pixel-wise cross entropy and the Jaccard coefficient. In addition, the training of Unet++ is done using the newly designed Gradient Bald Eagle Optimization (GBEO), which is a combination of Stochastic Gradient Descent (SGD) and Bald Eagle optimization (BEO). Finally, cancer detection is done using DCNN. DCNN is trained using GBVO, which is the integration of the African Vultures Optimization Algorithm (AVOA) and GBEO. The proposed method outperformed state-of-the-art techniques. The developed method achieved the highest accuracy of 0.916, a false negative ratio (FNR) of 0.104, a false positive ratio (FPR) of 0.100, and a negative predictive value (NPV) of 0.903.

Semantic IoT: Theory and Applications, 2021

In the coming few years, there is going to be rapid advancement in terms of technology like 5G, 6... more In the coming few years, there is going to be rapid advancement in terms of technology like 5G, 6G, etc. When we think about 5G, the performance of the internet is going to increase multifold. The 5G i.e. fifth-generation network is going to be very heterogeneous. There is a need for a standardized solution to the issues in this technology. In this work, we are trying to understand the problems specifically in IoT (Internet of Things) area of 5G. In the literature survey, we found out that various solutions have been proposed in the area of the Internet of Things, but there is a lack of some generic solutions for all IoT projects. Every project works excellent in its closed and specified environment. When we try to connect multiple IoT projects, there is a big problem of interoperability. Some ICT standardization organizations have proposed some solutions to interoperability to overcome this scenario. Few solutions have been proposed by some authors to provide interoperability using semantic technologies. The solution for this problem of heterogeneous IoT can be provided using the semantic technologies in combination with that of SDN (Software Defined Network), NFV (Network Function Virtualization), and Cloud infrastructure.

International Journal of Engineering Research and, 2015

Author identification of a document can be implemented using statistical or computational method.... more Author identification of a document can be implemented using statistical or computational method. In author identification, an author can be distinguished by his unique writing style. The basic idea behind author identification using statistical or computational method authorship is to measure different textual features for determining the author. The statistical method allows us to analyse and explore aspects of a text that wouldn't be easy for us to identify. In this paper we have focused on CUSUM technique which is a statistical method. CUSUM technique is based on calculation of average sentence length and set of words used by the author frequently.

2019 IEEE Pune Section International Conference (PuneCon)

Day by day use of internet is increasing rapidly, all the world is nowadays likely moving towards... more Day by day use of internet is increasing rapidly, all the world is nowadays likely moving towards to Internet of Things or IoT. Many industries, organizations now using IoT applications because of that its use is increased rapidly. Usability of IoT is growing so fast, therefore the network became more vulnerable to attacks. Security aspects become very essential to Internet of Things applications. There are various security approaches used for securing IoT applications but recently Machine Learning (ML) is used by most of the researcher for security purpose. A machine learning method monitors IoT applications intelligently and provides a significant solution to attacks. This paper gives a brief survey about IoT security and overview of machine learning methods used for securing some IoT security issues.

Journal of Data Mining and Management

About 80% organizational data are present in the unstructured (Text) format. E-mails, Social medi... more About 80% organizational data are present in the unstructured (Text) format. E-mails, Social media, notes, and wide variety of different types of documents in text formats are present, but all these data are not got importance and analyzed in meaningful ways. It has been observed that information workers spend their significant time (up to one third) to locating this information and trying to make sense of it. Text analytics (TA) is the process which analyzed all these available unstructured text information and converts it into useful information which helps the organization significantly in their business processes. In this paper we have discussed the business values, methods of text analytics, and business application of text analytics.

Journal of Data Mining and Management

About 80% organizational data are present in the unstructured (Text) format. E-mails, social medi... more About 80% organizational data are present in the unstructured (Text) format. E-mails, social media, notes, and wide variety of different types of documents in text formats are present, but all these data are not get importance and analyzed in meaningful ways. It has been observed that information workers spend their significant time (up to one third) to locating this information and trying to make sense of it. Text analytics is the process which analyzed all these available unstructured text information and converts it into useful information which helps the organization significantly in their business processes. In this paper, we have highlighted the business values, some of the methods, and business application of text analytics.

2018 International Conference On Advances in Communication and Computing Technology (ICACCT), 2018

Author Identification (AI) is one of the applications of text mining. It is a technique to identi... more Author Identification (AI) is one of the applications of text mining. It is a technique to identify anonymous author of electronic - text. This paper presents a survey on present techniques for identifying author of anonymous text document. We outline this survey based on AI techniques on literature wrote in various Languages like English, Japanese, Mongolian, Persian, Albanian, Indian, Brazilian and Russian. This paper also presents Language translation issues and effect on author identity of anonymous text document i.e. from English to German and/or Japanese and then back to English and also Arabic to English. We have also studied feature independent method. An evaluation of AI techniques under different Languages is analyzed based on accuracy of the AI and data set applied as a training data. At the end we conclude this paper with observations and future scope in this area.

2018 International Conference On Advances in Communication and Computing Technology (ICACCT), 2018

Authorship Identification is task to identify author of an article or document whose author is no... more Authorship Identification is task to identify author of an article or document whose author is not known. This can be possible by comparing set of articles or documents whose authorship is known to this unknown article. This paper presents comparative approach based on similarity of unknown documents against the known by use of various features. The main focus of the paper is to show the difference in articles which were written in different time frames. And also observe, how the feature gets addressed in this different time frame of the same author. All method shows the comparison over several features.

Authorship analysis process in which finding the author of unknown text when the history of the w... more Authorship analysis process in which finding the author of unknown text when the history of the writing style of the author known. It can be viewed as a multi-class, single-mark content classification assignment. A lot of author identification problems had been created and solved with the different methods. Character and word n-gram are most commonly used methods for feature construction and participated in authorship identification task. In this paper, we point out the methodology of formation of word n-gram. The approach described in the paper does not depend on constant value n, the value of n changes according to the occurrence of word sequences. The methodology applied to the collection of text which is from the varied time domain. We used a dataset of 13 authors, whose text generation time is big. Dynamic value of n chosen to generate word sequence. In terms of accuracy, the result shows improvement as compared to the fixed value of n in word n-gram. We also explore the signif...

Advances in Intelligent Systems and Computing, 2020

Author identification (AI) is a process of investigating author of an anonymous text document. AI... more Author identification (AI) is a process of investigating author of an anonymous text document. AI has a great help in digital forensic, copyright issues, plagiarism detection, etc. for making the law process quick and efficient. This paper presents AI on Indian regional language Marathi. Insted of it kindly replce it by this scentence: In this research paper, we proposed 21 language-specific lexical features. Validation of these proposed features is done on “Author wise Marathi Language Typewritten Text Corpus” published by us at Indian Language Technology Proliferation and Deployment Center. Experimentation is performed with proposed 21 features. Performance is compared through various machine learning algorithms like Naive Bayes, k-Nearest Neighbor and Sequential Minimal Optimization. k-Nearest Neighbor performs well over Naive Bayes and Sequential Minimal Optimization with average accuracy achieved as 82.06 on comedy articles and 85.44 on mixed articles. Proposed language-specific features provide significant improvement in result of accuracy over traditional features.