Archives
-
A Partial Feature Adaptive SIFT model for Morphed Image Recognition
Priyanka ; Dr. Yashpal Singh
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 145 - 150
Facial Recognition is having various challenges associated in it. One of critical challenge is the morphed image recognition. Morphed images can be the composed picture form generated from two or more persons. In this paper, a partial feature analysis approach is defined to recognize all persons composed in morphed image. In this work, the separation of facial physical features of person is done. Now each physical feature is represented under SIFT model to represent featured image. Finally, distance adaptive mapping is performed to recognize the image. The experimentation is here applied on real time morphed images. The adaptive results show that the high accuracy for individuals is obtained from the work.
Citation
IJIRST Priyanka and Dr. Yashpal Singh. "A Partial Feature Adaptive SIFT model for Morphed Image Recognition" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 145-150 MLA Priyanka and Dr. Yashpal Singh. "A Partial Feature Adaptive SIFT model for Morphed Image Recognition." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 145-150. APA Priyanka and Dr. Yashpal Singh. (2015). A Partial Feature Adaptive SIFT model for Morphed Image Recognition. International Journal for Innovative Research in Science & Technology, 2(1), 145-150. Chicago Priyanka and Dr. Yashpal Singh. "A Partial Feature Adaptive SIFT model for Morphed Image Recognition." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 145-150. 
-
A Segmentation Improved Statistical Model for Retinal Disease Identification
Parul ; Mrs. Neetu Sharma
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 151 - 157
Retinal images are analyzed to identify the glaucoma or the diabetic disease. The accuracy of disease detection depends on the extracted features. In this paper, segmentation and mathematical filters based statistical approach is presented to identify the retinal disease. At first stage of this statistical model, the features from retinal image are extracted using segmentation method. This segmentation model is able to separate the disc and cup features. Later on the ratio analysis between cup and disc is considered to identify the chances of retinal disease. The experimentation is applied on real time images. The results shows that the work has provided effective identification of retinal disease.
Citation
IJIRST Parul and Mrs. Neetu Sharma. "A Segmentation Improved Statistical Model for Retinal Disease Identification" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 151-157 MLA Parul and Mrs. Neetu Sharma. "A Segmentation Improved Statistical Model for Retinal Disease Identification." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 151-157. APA Parul and Mrs. Neetu Sharma. (2015). A Segmentation Improved Statistical Model for Retinal Disease Identification. International Journal for Innovative Research in Science & Technology, 2(1), 151-157. Chicago Parul and Mrs. Neetu Sharma. "A Segmentation Improved Statistical Model for Retinal Disease Identification." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 151-157.
-
Stabilization Analysis of Black Cotton Soil by using Groundnut Shell Ash
N. V. Gajera ; K. R. Thanki
Civil Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 158 - 162
Black Cotton soil is fertile and very good for agriculture, horticulture, sericulture and aquaculture. Though black cotton soils are very good for agricultural purposes, they are not so good for laying durable roads.The study is a potential stabilization of black cotton soils in Gujarat state using Groundnut Shell ash. Index properties of the natural soil showed that, the soil is a poor for engineering use. Liquid limit and Plasticity index values of 83.36 % and 89.32 % respectively for the natural soil suggest that the soil is highly plastic. There was gradual decrease in the free swell to a minimum value of 2.91% at 10% GSA (Groundnut Shell Ash) as compared to the natural value of 15.25%. The soaked CBR for the natural soil is 1.67% which increased to 2.17% at 10% GSA. This value fell short of specification requirement of the CBR value to be used as sub-base or base material. However, there was increase in strength for UCS of 21 days curing period from a value of 134kN/m2 as compared to 313kN/m2 for the unstabilized soil. This research is aimed at evaluating the possibility of utilizing groundnut shell ash (GSA) in the stabilization of black cotton soils.
Citation
IJIRST N. V. Gajera and K. R. Thanki. "Stabilization Analysis of Black Cotton Soil by using Groundnut Shell Ash" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 158-162 MLA N. V. Gajera and K. R. Thanki. "Stabilization Analysis of Black Cotton Soil by using Groundnut Shell Ash." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 158-162. APA N. V. Gajera and K. R. Thanki. (2015). Stabilization Analysis of Black Cotton Soil by using Groundnut Shell Ash. International Journal for Innovative Research in Science & Technology, 2(1), 158-162. Chicago N. V. Gajera and K. R. Thanki. "Stabilization Analysis of Black Cotton Soil by using Groundnut Shell Ash." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 158-162.
-
Optimized Incremental SVM based Classifier for Spam Filtering using Internet Acronyms
Indrajeet Singh Jhala ; Dr. Pankaj Dalal
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 163 - 176
The word Spam as applied to email means Unsolicited Bulk Email. Unsolicited means that the Recipient has not granted verifiable permission for the message to be sent. Bulk means that the message is sent as part of a larger collection of messages, all having substantively identical content. A message is Spam only if it is both Unsolicited and Bulk. Spam is a key problem in electronic communication, including large-scale email systems and the growing number of blogs. The anti-spam community has been divided on the choice of the best machine learning method for content-based spam detection. In many traditional machine learning applications, SVMs are applied in batch mode. That is, an SVM is trained on an entire set of training data, and is then tested on a separate set of testing data. Spam filtering is typically tested and deployed in an online setting, which proceeds incrementally. In this paper, an online incremental SVM is proposed which classifies emails as spam or ham (normal mail). The traditional textual features are augmented with character level Features, thus, extending the feature set used to train the SVM. This approach exploits the fact that most of the user written text on internet in the form of mails, tweets etc. consists of shorthand notations. The proposed model maps the popular internet shorthand notations to the corresponding words, thereby making a much more accurate classification as compared to traditional approaches. The proposed model is tested on real benchmark data set and performance is evaluated. The empirical results reveal that the proposed SVM, although is computationally heavier, nevertheless provides an improvement in classification accuracy as compared to those based only on textual features.
Citation
IJIRST Indrajeet Singh Jhala and Dr. Pankaj Dalal. "Optimized Incremental SVM based Classifier for Spam Filtering using Internet Acronyms" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 163-176 MLA Indrajeet Singh Jhala and Dr. Pankaj Dalal. "Optimized Incremental SVM based Classifier for Spam Filtering using Internet Acronyms." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 163-176. APA Indrajeet Singh Jhala and Dr. Pankaj Dalal. (2015). Optimized Incremental SVM based Classifier for Spam Filtering using Internet Acronyms. International Journal for Innovative Research in Science & Technology, 2(1), 163-176. Chicago Indrajeet Singh Jhala and Dr. Pankaj Dalal. "Optimized Incremental SVM based Classifier for Spam Filtering using Internet Acronyms." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 163-176.
-
Selective Video Encryption using Bit XOR Technique
Mrinal Paliwal ; Saddam Hussain
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 177 - 183
Selective video encryption has advanced in recent years on the grounds that they require less time and guarantees security of video substance as well. There has been numerous selective Video Encryption Techniques, which are mind boggling and reliant on different elements like key sharing and bury and intra frame contrast and so on. In this paper we propose a selective video encryption calculation, which is quick, more minimal and free of key sharing component. Here we propose another plan for computerized video encryption. In this strategy we produce an encoded video by scrambled Video-frame. In light of a safe video conspire, a successful and summed up plan of video encryption. We have proposed another plan for video encryption which taking into account encryption of I-frame (video frame).Here we have taken a thought from grid estimation for creating the encoded I-frame. In this strategy, we gather the all video frame then take frame one by one structure it and select a key Image as key frame for encryption and unscrambling procedure, so this key picture is send through secure channel.
Citation
IJIRST Mrinal Paliwal and Saddam Hussain. "Selective Video Encryption using Bit XOR Technique" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 177-183 MLA Mrinal Paliwal and Saddam Hussain. "Selective Video Encryption using Bit XOR Technique." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 177-183. APA Mrinal Paliwal and Saddam Hussain. (2015). Selective Video Encryption using Bit XOR Technique. International Journal for Innovative Research in Science & Technology, 2(1), 177-183. Chicago Mrinal Paliwal and Saddam Hussain. "Selective Video Encryption using Bit XOR Technique." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 177-183.
-
A Framework for Secure VOIP
Mandeep Singh ; Neetu Sharma
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 184 - 188
VoIP stands for Voice over Internet Protocol and is a way to carry voice traffic over computer networks like the Internet. Over the last decade VoIP has become increasingly popular, gaining millions of subscribers every year (e.g. LINE and WECHAT provide voicecall facilities) and has certainly caught the eye of telecommunication service providers all over the world. The driving factor for the success of VoIP is cost reduction, both for users and providers. But VoIP doesn’t only bring reduced costs it also brings threats and vulnerabilities since it is IP based it’s susceptible to large number of threats. The threats include spoofing or identity theft and call redirection, making data integrity a major risk. Therefore authentication and encryption techniques can be used to design a framework which can survive the possible threats. In this security framework authentication is implemented first to authenticate the true user and then cryptography techniques is used to safely transmit the information stream over the network. The authentication part will be implemented using biometrics because it is not possible to theft anyone’s physical features.
Citation
IJIRST Mandeep Singh and Neetu Sharma. "A Framework for Secure VOIP" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 184-188 MLA Mandeep Singh and Neetu Sharma. "A Framework for Secure VOIP." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 184-188. APA Mandeep Singh and Neetu Sharma. (2015). A Framework for Secure VOIP. International Journal for Innovative Research in Science & Technology, 2(1), 184-188. Chicago Mandeep Singh and Neetu Sharma. "A Framework for Secure VOIP." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 184-188.
-
Quality Evaluation of Ground Waters nearby an Urban Sewage by Physicochemical Characterization and Microbial Assessment
K. Hemalatha ; P.Satyanarayana
Department of chemistry
Year: 2015, Volume:2, Issue : 1
Pages: 189 - 196
The present research study is focused on the characterization of ground waters collected nearby an urban sewage source for physicochemical characterization and microbial assessment for quality evaluation. Twelve ground water samples were collected at distances of 0.5, 1.0, 2.0, 3.0, 4.0 and 5.0 km on both sides of the sewage source and were characterized for physicochemical parameters viz., pH, Electrical Conductivity (EC),Total Dissolved Solids (TDS), Total Alkalinity (TA), Total Hardness (TH), Ca2+, Mg2+, Na+, K+, Chloride, Sulphate, Nitrate and Phosphate. Higher levels of parameters EC, TDS, TH, TA, Mg2+, Chloride, Nitrate and Phosphate indicate the chemical contamination of waters and hence the waters are unsuitable for drinking and domestic purposes, The ground waters were further analyzed for bacterial species and in majority samples MPN count was observed. In addition, the presence of pathogenic bacterial spps like E. Coli, klebsiella, Proteus, Enterobacter and pseudomonas in ground waters indicate the bacterial contamination of the ground waters. These waters can cause waterborne diseases and hence are highly unsuitable for drinking purposes. The waters are to be treated properly by the available treatment methodologies for the protection of their quality.
Citation
IJIRST K. Hemalatha and P.Satyanarayana. "Quality Evaluation of Ground Waters nearby an Urban Sewage by Physicochemical Characterization and Microbial Assessment" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 189-196 MLA K. Hemalatha and P.Satyanarayana. "Quality Evaluation of Ground Waters nearby an Urban Sewage by Physicochemical Characterization and Microbial Assessment." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 189-196. APA K. Hemalatha and P.Satyanarayana. (2015). Quality Evaluation of Ground Waters nearby an Urban Sewage by Physicochemical Characterization and Microbial Assessment. International Journal for Innovative Research in Science & Technology, 2(1), 189-196. Chicago K. Hemalatha and P.Satyanarayana. "Quality Evaluation of Ground Waters nearby an Urban Sewage by Physicochemical Characterization and Microbial Assessment." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 189-196.
-
Online SVM based Optimized Bug Report Triaging using Feature Extraction
Neetika Sharma ; Dr. Vijay Kumar
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 197 - 209
Triage is medical term referring to the process of prioritizing patients based on the severity of their condition so as to maximize benefit (help as many as possible) when resources are limited. Bug Report triaging is a process where tracker issues are screened and prioritized. Triage should help ensure that all reported issues are properly managed - bugs as well as improvements and feature requests. The large number of new bug reports received in bug repositories of software systems makes their management a challenging task. Handling these reports manually is time consuming, and often results in delaying the resolution of important bugs. The most critical issue related with bug reports is that their number is vast and most of these are duplicates of some previously sent bug report. The solution to this problem requires that bug reports are to be categorized in groups where each group consist of all the bug reports which belongs to the same bug, and the number of groups is equal to the number of unique bugs addressed so far. Bug report corresponding to some new bug is to be placed in a separate group followed by its duplicates, if any. Classifying weather a bug report that arrived through a user, written in a natural language, is a duplicate or unique report is a time consuming task, especially when the number of bug reports that are received is large. Thus, this process needs to be automated. Bug reports have textual, contextual and categorical features and these features needs to be extracted for checking of duplicates and non duplicates. Moreover, in the group of reports, a particular report can be specified as master and all the reports that corresponds to the same bug are to be linked to it. Thus, duplicates need not be discarded so as to provide later, a complete description of the bug. In this paper, a much more extended set of textual features is considered for bug report duplicacy checking. Support Vector Machine classifier is used for classification of the incoming bug report as duplicate of non-duplicates. The simulation of the prescribed model is done using R Statistical Package. A sample of bug reports from Mozilla repository is considered, Results of the simulation model establishes the fact that Proposed classifier has higher efficiency as compared to existing technique BM25F which employs 25 feature sets.
Citation
IJIRST Neetika Sharma and Dr. Vijay Kumar. "Online SVM based Optimized Bug Report Triaging using Feature Extraction" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 197-209 MLA Neetika Sharma and Dr. Vijay Kumar. "Online SVM based Optimized Bug Report Triaging using Feature Extraction." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 197-209. APA Neetika Sharma and Dr. Vijay Kumar. (2015). Online SVM based Optimized Bug Report Triaging using Feature Extraction. International Journal for Innovative Research in Science & Technology, 2(1), 197-209. Chicago Neetika Sharma and Dr. Vijay Kumar. "Online SVM based Optimized Bug Report Triaging using Feature Extraction." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 197-209.
-
Optimized Cross Domain Sentiment Classification through N-Gram Features and Machine Learning
Chetan Sharma ; Dr. Bhavna Sharma
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 210 - 219
World Wide Web is full of blogs and forums in which provides the users a platform to share their views or remarks about diversified topics. Sentiment analysis refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information in source materials. It aims to determine the attitude of a speaker or a writer with respect to some topic or the overall contextual polarity of a document. The attitude may be his or her judgment or evaluation, affective state or the emotional state of the author when writing, or the intended emotional communication the author wishes to have on the reader. Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of users publishing sentiment data (e.g., reviews, blogs). Although traditional classification algorithms can be used to train sentiment classifiers from manually labeled text data, the labeling work can be time-consuming and expensive. Meanwhile, users often use different words when they express sentiment in different domains. Words in different domain can be treated as positive or negative and vice-versa, e.g. hard knife and hard pillow. Cross-domain sentiment classification can be done by using a spectral feature alignment (SFA) algorithm to align domain-specific words from different domains into unified clusters, with the help of domain independent words as a bridge. The proposed work extends the technique proposed by S J Pan et.al. by including character level N gram features and shorthand internet notations, usually used in the web, into sentiment classification. An SVM based classifier is proposed to classify the polarity of the reviews. Domain Independence is achieved using cross domain words. Compared to previous approaches, this technique can classify the documents with much more accuracy as the shorthand notations are increasingly popular among the internet users. Extensive experiments are performed on real world datasets of twitter and it is demonstrate that inculcation of N gram features and shorthand notations can provide much better results for polarity classification within smaller false positive and false negative rates.
Citation
IJIRST Chetan Sharma and Dr. Bhavna Sharma. "Optimized Cross Domain Sentiment Classification through N-Gram Features and Machine Learning" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 210-219 MLA Chetan Sharma and Dr. Bhavna Sharma. "Optimized Cross Domain Sentiment Classification through N-Gram Features and Machine Learning." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 210-219. APA Chetan Sharma and Dr. Bhavna Sharma. (2015). Optimized Cross Domain Sentiment Classification through N-Gram Features and Machine Learning. International Journal for Innovative Research in Science & Technology, 2(1), 210-219. Chicago Chetan Sharma and Dr. Bhavna Sharma. "Optimized Cross Domain Sentiment Classification through N-Gram Features and Machine Learning." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 210-219.
-
Clustered based Mobility Prediction in MANET
Manisha ; Dr. Yashpal Singh
Computer Engineering
Year: 2015, Volume:2, Issue : 1
Pages: 220 - 229
Mobile ad hoc networks are self-organizing and self-configuring multi-hop wireless networks capable of adaptive re-configuration when they are affected by node mobility. A mobile ad hoc network is composed of peer nodes with equal networking capabilities which are able to function as mobile routers i.e., to forward packets and maintain routes. Packets can be forwarded in multi-hops from the source nodes to the destination nodes with no need for underlying fixed network infrastructure (e.g. routers and base stations). Therefore, mobile ad hoc networks are not constrained in their deployment by any need for underlying infrastructure and they can be deployed rapidly in situations where wireless access to a backbone is impossible and an infrastructure is difficult to install (e.g., disaster recovery). In mobile ad hoc networks (MANETs), the network topology is autonomously formed and continuously changes, due to the mobility of the nodes. Clustering allows us to organize the topology in a structured manner. The association and dissociation of nodes to and from clusters perturb the stability of the network topology, and hence reconfiguration of the system is often unavoidable. Several existing on-demand clustering algorithms update that topology if needed. In this paper, an improvement to the existing clustering algorithm is done under the energy parameter specification. The effective route is here defined for clustered communication. An inter cluster and intra cluster communication is here performed under mobility vector. In this work, distance and energy adaptive algorithm is suggested to generate the effective communication route and analyze the work under different parameters which enhances the stability of the network in a more efficient way.
Citation
IJIRST Manisha and Dr. Yashpal Singh. "Clustered based Mobility Prediction in MANET" International Journal for Innovative Research in Science & Technology Volume 2 Issue 1 2015 Page 220-229 MLA Manisha and Dr. Yashpal Singh. "Clustered based Mobility Prediction in MANET." International Journal for Innovative Research in Science & Technology 2.1 (2015) : 220-229. APA Manisha and Dr. Yashpal Singh. (2015). Clustered based Mobility Prediction in MANET. International Journal for Innovative Research in Science & Technology, 2(1), 220-229. Chicago Manisha and Dr. Yashpal Singh. "Clustered based Mobility Prediction in MANET." International Journal for Innovative Research in Science & Technology 2, no. 1 (2015) : 220-229.
Abstract
| PREV | 1 2 3 4 5 | NEXT |
