Prafulla Ajmire | SANT GADGEBABA AMRAVATI UNIVERSITY (original) (raw)

Papers by Prafulla Ajmire

Web Mining: An Application of Data Mining, 2020

The World Wide Web is the largest, popular and most widely used information source, which is incr... more The World Wide Web is the largest, popular and most widely used information source, which is increasing day by day. The information over the web is available in the form of web pages, the content of web pages may include texts, images, audios, videos, lists, charts, tables, hyperlinks etc. Web page structure, users' navigation on the web sites and server logs also provides useful information. To extract meaningful information from the web and discover knowledge, web mining techniques are used. Web mining uses data mining techniques to extract knowledge from web. This paper presents the study of web mining and its types.

Aegaeum Journal, 2020

Pattern Recognition has power of attraction that attract researcher as a machine learning approac... more Pattern Recognition has power of attraction that attract researcher as a machine learning approach due to it's quickly spread application areas. In the last few years, the applications related to pattern recognition are quickly increasing in a number of areas. The application areas to which disciplines have been applied include communication, business, medicine, automation, biometric authentication, military intelligence, data mining, web searching, retrieval of multimedia data, cursive handwriting recognition, document classification, speech recognition, agriculture and many others. This paper presents very brief survey of methods used for pattern recognition. On the basis of survey, pattern recognition methods can be classified in six ways. These six ways are Template matching, Statistical method, Structural method, Neural Network, Fuzzy sets and Hybrid method.

International Journal of Scientific Research and Engineering Development, 2020

Now a day's everything is in an era of Information Technology where each one must become IT incum... more Now a day's everything is in an era of Information Technology where each one must become IT incumbent and resource oriented. Our day to day life activities revolve around technology, from last few decades it was observed that technology is providing the generation with at most benefit and ease. Therefore, Internet of Things has emerged in the latest trends of technology. The future of computing and communications is depend on this new technological revolution where it contains some distinguishing features and also the features of both the Internet and the Telecommunications Network in such a specified and wide domain which helps people to understand the real world applications, where each object can perform multiple tasks while communicating with other different objects using IoT which makes human life far better and easier than ever with full of devices, sensors and other objects which allows each other to communicate in a network environment. This paper explores the current research work on IoT as Three-layer traditional architecture, and how it relates with architecture of Internet and Telecommunications Management Network. After review it was observed that there is a requirement to reform a technical framework of the Internet and the Logical Layered Architecture of the Telecommunication Management Network because three-layer architecture doesn't provides all features and significance of the Internet of Things, for this purpose only a new five-layer architecture of IoT was established. Finally, at the end a new improved architecture to the internet of things (IoT) was proposed that takes into consideration the basic concept of IoT and its working.

AEGAEUM JOURNAL

Blockchain is an immutable and distributed ledger. In simple terms we describe it as, a chain of ... more Blockchain is an immutable and distributed ledger. In simple terms we describe it as, a chain of blocks containing data or information in a secure and genuine way that is grouped together in a network. Each block in a blockchain network stores some information with the hash value of its previous block which helps to maintain the integrity of data publicly. This network is interconnected with different nodes which are also known as miners (who analyse a block and have a local copy of public ledger), helps to have access for a requested block of user from anywhere. Blockchain based systems can provide interoperability, data integrity and save a lot of time, money and human resources to the problems of a low-trust country such as India, since blockchain provide decentralized approaches to the data management and creation of a value. This paper studies various blockchain applications in different areas such as healthcare, education, medicine and law. The aim of this paper is to analyse methods currently used in blockchain applications and proposing different methods which uses blockchain technology that can greatly benefit in terms of integrity, transparency and enhanced security of their data.

Aegaeum Journal, 2020

Internet of Things (IoT) consists of various technologies, which supports advanced services in va... more Internet of Things (IoT) consists of various technologies, which supports advanced services in various application domains. The idea behind is to provide interconnection of internet enabled things or devices to each other and to humans, to achieve some common goals. It is expected that IoT to be seamlessly integrated into our environment and human will be wholly solely dependent on this technology for comfort and easy life style. Many central features of the modern world, such as hospitals, organizations, cities, grids, and buildings etc. all are to be facilitated by intelligence feature of IoT. This also facilitates the machines and objects to communicate, compute and coordinate with each other. Machine Learning helps number of machines connected together to understand what the user requires from the database. Machine learning plays a key role in IoT aspect to handle the huge amount of data generated by those machines. It gives IoT and those machines a brain to think, which is called as "Embedded Intelligence". This paper will mainly focus on IoT Technology, Elements and Applications, Challenges in IOT,Machine-Learning algorithms and Machine Learning in IoT Applications.

Journal of Emerging Technologies and Innovative Research, 2019

Recognition of Devanagari CAPTCHA script characters is yet a challenging problem. Many lingual ch... more Recognition of Devanagari CAPTCHA script characters is yet a challenging problem. Many lingual character recognition systems have been developed since last few years. There are several techniques that are proposed to deal with problem of character recognition. This paper presents an efficient Devanagari character recognition scheme that implements effective feature extraction methods and use classifiers like SVM (Support Vector Machine) and PNN (Probabilistic Neural Network) for recognizing printed Devanagari characters. To prepare a database, 5 samples of each Devanagari character from 5 different Kruti Dev fonts have been considered. There are 34 consonants and 13 vowels in Devanagari script. These characters are classified based on their structural properties. The presence or absence of vertical bar plays vital role in the structure of Devanagari characters. The vertical bar is used in the middle of some characters. It is also used as a terminator of many characters. There are 2 consonants that have middle-bar, 9 consonants and 3 vowels that have no-bar. There are 9 consonants out of 34 and 3 vowels out of 13, which have no end-bar. Such specific characters and 10 numeric characters are chosen for experiments. The experiments are performed on a dataset having 14 alphabetic characters (which have middle-bar & no-bar) and 10 numeric characters together, using SVM and PNN classifiers respectively. So, in all 24 characters are used to prepare a dataset of 6000 (24 x 250) character images. The proposed scheme has given average character recognition rates of 96.47% using SVM and 97.54%using PNN which are comparatively higher than other techniques.

Compound character recognition of Handwritten Devanagari is one of the challenging tasks due to i... more Compound character recognition of Handwritten Devanagari is one of the challenging tasks due to its complexity as compare to many other scripts. Compound characters itself complex in structure. It is written with combination of two or more characters. The character may be formed with different sequence of combinations of basic characters, such as vowels and consonants. The recognition of compound characters makes this task more challenging to the researchers. The frequency of occurrence of compound characters in Marathi language is more as compared to other languages derived from devanagari script. The various researchers used different classification techniques such as Neural Network, Soft Computing, Seventh Central Moment, Multiclass SVM Classifier with orthogonal moment, wavelet transformation etc. This paper deals with the study of different classification techniques used for compound character recognition of handwritten Devanagari compound character.

The Indian Government has recognized Hindi and English both as official languages, under the VIII... more The Indian Government has recognized Hindi and English both as official languages, under the VIII scheduled, along with 22 languages. Most of the optical character recognition research work has been done on Devanagari, Telgu, Arabic, and Bangla script. The selection of feature extraction and classification technique is the important to achieve the best accuracy of any recognition system. Features collect the data about the character and accordingly classifier classify the character uniquely. This paper, deals with the studied of the Feature Extraction and Classification techniques for the handwritten Devanagari script.

Now a day cloud computing plays an important role in internet era due to the a successive mobile ... more Now a day cloud computing plays an important role in internet era due to the a successive mobile applications cloud computing becomes more important it is the ultimate solutions for this mobile application cloud computing opens a new era for computing technology presently there are various web services through the different clouds some notable services are, Amazon web services, elastic compute cloud, Google cloud (dope box). The cloud computing offers huge opportunities of various web services to the internet users and mobile users; though there are many issues still to be covered in this paper represent survey of various cloud computing models.

Image classification is the most important process in pattern recognition. In general, this is a ... more Image classification is the most important process in pattern recognition. In general, this is a final stage of pattern matching. The classification process described the percentage of accuracy in pattern recognition. Feature extraction is another vital stage in pattern matching. These extracted feature are used for classification of the image database, that is pattern matching. The various researchers used different classification techniques for different application,support vector machine used for character recognition. Neural Network Techniques are used for Artificial Intelligent application and soft computing. These paper deals with the study of different classification techniques used for image classification.

P.E.Ajmire1, R V Dharaskar2 , V M Thakare 3 1Dept. Of Computer Science, G S Sci., Arts & Commerce... more P.E.Ajmire1, R V Dharaskar2 , V M Thakare 3
1Dept. Of Computer Science,
G S Sci., Arts & Commerce College, Khamgaon(M.S), India
2Former Director, Disha Education Society,
Raipur.(C.G), India
3 Professor and Head,P.G.T.D. Of Comp. Sci.,
S G B Amravati University, Amravati

Abstract
This research work deals with the feature extraction and
recognition of Modifiers in Marathi Text (Devanagari). Many
researchers are working on the handwritten Marathi
character recognition. As compare to English and other
languages Marathi is little bit complex language. Marathi
language contains 12 common vowels and 36 consonants. In
addition to this there are compound characters. In this
research work, the handwritten text is split in three regions
namely region above Shirorekha upper region i.e. upper
modifier, main character and lower region i.e. lower modifier
below the character. Shape features are extracted for upper
and lower modifiers. Support vector machine is used as
classifier and the average recognition rate is compatible.
Keywords: Modifier, Shape Feature Extraction.

This research work deals with the feature extraction and recognition of Modifiers in Marathi Text... more This research work deals with the feature extraction and
recognition of Modifiers in Marathi Text (Devanagari). Many
researchers are working on the handwritten Marathi
character recognition. As compare to English and other
languages Marathi is little bit complex language. Marathi
language contains 12 common vowels and 36 consonants. In
addition to this there are compound characters. In this
research work, the handwritten text is split in three regions
namely region above Shirorekha upper region i.e. upper
modifier, main character and lower region i.e. lower modifier
below the character. Shape features are extracted for upper
and lower modifiers. Support vector machine is used as
classifier and the average recognition rate is compatible.

Compound character recognition of Devanagari Script (Marathi language) is one of the challenging ... more Compound character recognition of Devanagari Script (Marathi language) is one of the challenging tasks
since the compound character is combination of one or more characters. These characters can be treated as fusion of
two or more characters and hence these are complex in structure. Marathi, Hindi, Sanskrit and Nepali are written with
Devanagari script. All these languages have compound characters. The characters may be formed with different
sequence of combinations of basic characters such as vowels and consonants. Thus the recognition of compound
characters makes this task more challenging to the researcher. So, as compared to English like Roman script, one of the
major obstacles in handwritten Marathi character recognition is the large number of complex shaped compound
characters. Considering the complexity of the problem, the present algorithm makes an attempt to identify the
compound character. This paper discuss the recognition of compound character using combination of 7 Invariant
Moment (Rotational Moment) and 7th order Central Moment(Translation Moment). SVM is used as classifier. The
overall performance of the proposed system is 93.87%.

The work in this paper is deals with the recognition of handwritten Marathi vowels. Marathi is an... more The work in this paper is deals with the recognition of handwritten Marathi vowels. Marathi is an
Indo-Aryan language spoken by about 71 million people mainly in the Indian state of Maharashtra and
neighbouring states. Marathi is also spoken in Israel and Mauritius. Marathi is thought to be a descendent of
Maharashtri, one of the Prakrit languages which developed from Sanskrit. This work is based on invariant
moments for recognition of isolated Marathi Handwritten Characters and their divisions. The proposed
technique is independent of size, slant, orientation, translation and other variations in handwritten
characters. Handwritten Marathi Characters/Numerals are more complex for recognition than corresponding
English characters due to many possible variations in order, number, direction and shape of the constituent
strokes. The work treats isolated Characters as an image of 40X40 pixel size. Seven invariant central
moments of the image and two additional feature sets are evaluated. 10 samples of each number from 20
different writers have been sampled and prepared a database has been made. Seven central invariant
moments are evaluated for each character and its parts by dividing it by two different ways. In all, there are
14 features corresponding to each character. The Gaussian Distribution Function has been adopted for
classification. The average success rate of some vowels is compatible.

The work in this paper deals with the recognition of fossil leaves. The objective of this researc... more The work in this paper deals with the recognition of
fossil leaves. The objective of this research is to use
pattern rejection algorithm in paleobotany. As there is
no standardized database available, it was developed
first and the fossil leaves recognition system design
using pattern-matching technique based on the actual
scanning or available images. The result of this
research will present either recognition or rejection of
fossil leaves. The result shows better performance if it is
applied on a specific pattern.

The feature extraction is important step in pattern recognition. The application of pattern recog... more The feature extraction is important step in pattern recognition. The application of pattern recognition to extract proper features of leaf can lead to through study of botanical characteristics of leaf. The methodological contents of this paper are to describe a novel approach for pattern recognition method for feature extraction from natural image such as plant leaf. This novel method proposed for automated living plant species recognition. This recognition of plant species will be useful for botanical students in their research for plant species identification. A leaf is an aerial and lateral outgrowth of the stem of a usually flat and dorsiventral anatomy. Their pattern, also called leaf venation, is a feature of characterization. The blade margin and the leaf arrangement at the stem are further features of characterization.

The content work in this paper is to describe the statistical techniques used for feature extract... more The content work in this paper is to describe the
statistical techniques used for feature extraction
for handwritten character recognition. Many
researchers are working for recognition of
handwritten characters. There are many script
and languages in the world. The researchers
have done work on some of them like English,
Chinese, Latin, Arabic, Japanese, Thai, Urdu,
Bangala, Telgu, Gurumukhi and Devnagari. The
character set of Indian languages is large and
consists of more complex characters when
compared to the Latin script. Handwritten
character recognition being a challenging
problem in pattern matching area. There are
various techniques used for this task like
structural, neural and template matching. Since
every electronic image of a character consist of
pixel values that are represented by spatial
configuration of O’s and 1’s. A statistical
technique for character recognition is searching
of statistical characteristics of various
characters. The object of this study is to verify the
applicability of these statistical techniques such as PCA, LDA,
ICA, SVM to handwritten character recognition.

This paper presents a review of structural features for character recognition. Structural feature... more This paper presents a review of structural features for character recognition. Structural features are the features that are physically a part of the structure of the character, such as straight lines, arcs, circles, intersections etc. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters) or gray-level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstruction ability, expected distortions and variability of the characters. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application. In this paper, we discuss the selection of appropriate standard structural features for character recognition

The different pattern recognition models have been proposed in recent years and the different res... more The different pattern recognition models have been proposed in recent years and the different research groups are working on for the recognition result.Handwritten character recognition for any Indian writing system is rendered complex because of the presence of composite characters. Hence the selection of a feature extraction method is probably the most important factor in achieving high recognition performance for Marathi character recognition.The goal of this paper is to present comparative study of various character recognition techniques used for feature extraction and recognition of handwritten Marathi character.

Web Mining: An Application of Data Mining, 2020

Aegaeum Journal, 2020

International Journal of Scientific Research and Engineering Development, 2020

AEGAEUM JOURNAL

Aegaeum Journal, 2020

Journal of Emerging Technologies and Innovative Research, 2019

K C College, Mumbai, 2019

The use of the Internet is growing rapidly, so another area has developed to use the Internet, ca... more The use of the Internet is growing rapidly, so another area has developed to use the Internet, called Internet of Things (IoT). It facilitates the machines and objects to communicate, compute and coordinate with each other. It is an empower for the intelligence related to several essential features of the modern world, such as homes, hospitals, buildings, transports and cities. The security and privacy are some of the key issues related to the wide application of IoT. Therefore, these issues prevent the wide usage of the IoT Applications. This paper represents an overview about different layered architectures of IoT and attacks regarding security from the perspective of layers. Also, a review of mechanisms that provide solutions to these issues. Furthermore, a new secure layered architecture of IoT is suggested to overcome these issues.