2016 Second International Conference on Computational Intelligence & Communication Technology (CICT), 2016
Image processing is one of most popular research area. Image processing consists of a number of p... more Image processing is one of most popular research area. Image processing consists of a number of phases to be carried out, among which classification is one. Classification of an object is a vital job in computer vision area. Classification reflects the final results accuracies. So everyone has to pay attention at this phase. Lots of work is done on comparative learning of classification methods. This survey paper demonstrates study of parametric and non-parametric classification techniques. Study isolates parametric and nonparametric classification techniques which are employed in classification phase and offers tree depictions of such methods. For comparative study 9 classifiers are utilized among which 6 belongs to parametric category and remaining 3 belongs to non-parametric category.9 classifiers considered here are super simple, their interpretation is nice probabilistic, used mostly and well known. Assessment parameters considered are Kappa Statistic, Mean Absolute Error (MAE), Receiver Operating Characteristics Area (ROC Area) and Root Mean Square Error (RMSE). For validation test 10 cross fold method is considered. Results show that overall Decision Tree classifier or subtypes of decision tree classifier performs well. It gives better output to high values of Kappa Statistic and ROC Area measures. Also, it produces better results with less value of MAE and RMSE measures. The results produced by Bayesian Net, Naive Bayes techniques are similar.
The security of bigger data is the bottleneck in the encryption and decryption because of the big... more The security of bigger data is the bottleneck in the encryption and decryption because of the big data size. The single encryption technique using one source is not adequate to accomplish the big data cloud computing security. This paper elaborates the working of cloud computing and the collaborating source security system for the Big Data security. A collaborating encryption technique framework is proposed in this paper to meet the futures' faster encryption requirements. The traditional information security system is not capable to provide the complete security during the cloud computing. The method described in this research comprises the parallel and distributed encryption system which gets the benefits the homomorphic encryption technique. The encryption facility during the mobile communication of object is tedious. Every cloud has its own security features and can be working in collaboration with the other cloud servers. Therefore, the parallel and distributed encryption facilities can be possible at every next door of other cloud without breaking the sequence of encryption process. The essential resources become the remote resources and the allocation of these resources can be managed at every cloud. Most of the time while working with the cloud computing is the availability of network and other resources. Providing the information security in the unavailability of resources during encryption and decryption is a difficult task. The collaboration encryption technique is a framework where, different clouds can work in parallel with the distributed processing. The security mechanism is improved by the homomorphic encryption.
2015 International Conference on Computing, Communication and Security (ICCCS), 2015
Enormous applications and the future necessities of image processing area open new paths for rese... more Enormous applications and the future necessities of image processing area open new paths for researchers. The analysis and recognition of numerous documents in the form of images are the challenging task. The classification is one of the vital phases in the image processing. The methods of classification must possess the consistency and accuracy. This research analyzes the different classification techniques and the performance analysis is carried out with the help of testing the image classification principles. In this research paper few classification techniques for Devanagari script are considered and evaluated in MATLAB R2014a.
Mobile IPv6 has been developed to enable mobility in IP network for mobile terminals. MIPv6 have ... more Mobile IPv6 has been developed to enable mobility in IP network for mobile terminals. MIPv6 have a lot of feature in comparison to previous Mobile IP protocol. From the data security perspective, the basic objective during the development of Mobile IPv6 has been that it must be at least as secure as previous Mobile IP protocol and it should not introduce any new security threats. But it suffers from various security threats like Eavesdropping, Secure route optimization, connection hijacking and denial of services. and security issues are one of the primary considerations that need to be address. In this paper we proposed a mechanism which includes all security components like Authentication, confidentiality and integrity, secretes key management. It will reduce all security threats and enhance security of Mobile IPv6.
Communications in Computer and Information Science, 2017
At present, digital image processing is elevated vicinity. Image possession, a broadcast may corr... more At present, digital image processing is elevated vicinity. Image possession, a broadcast may corrupt an image with impulse noise. Several realistic appliances necessitate a superior, squat complex de-noising practice as a pre-processing maneuver. While impulse noise filtering, the need is to conserve edges and image features. The merely damaged pixel should be filtered, to evade image smoothing. Analyses of few impulse noise cutback procedures are discussed in the study, their outcomes are inspected as well as competences are estimated in MATLAB R2014a. An appraisal affords inclusive acquaintance of noise diminution methods and also assists pollsters in paramount impulse noise reduction technique selection.
Digital watermarking is the process of hiding the important digital information into another one.... more Digital watermarking is the process of hiding the important digital information into another one. There are three main watermarking techniques, Digital image watermarking, digital audio watermarking and digital video watermarking. Watermarking can be done majorly in two domains, Spatial Domain and Frequency Domain. This paper is analysis of Digital image watermarking and different techniques used for digital image watermarking in Spatial Domain based on LSB-Based, Statistical-Based, Feature-Based and Block-Based.
Classification and Rule extraction is an important application of Artificial Neural Network. To e... more Classification and Rule extraction is an important application of Artificial Neural Network. To extract fewer rules from multilayer feed forward neural network has been a research area. The internal representation of the network is augmented by a distance term to extract fewer rules from the feed forward neural network and experimented on five datasets. Understanding affect of different factors of the dataset and network on extraction of a number of rules from the network can reveal important pieces of information which may help researchers to enhance the rule extraction process. This work investigates the internal behavior of neural network in rule extraction process on five different dataset. Keywords: Rule extraction, Feed Forward Neural Network, Hidden units, Activation value, Hidden neurons.
Gender identification is a significant task which is very useful in many computer applications li... more Gender identification is a significant task which is very useful in many computer applications like human–computer interaction, surveillance, demographic studies, and forensic studies. Being one of the most popular soft biometrics, gender information plays a vital role in improvement of the accuracy of biometric systems. In this paper, we have presented an approach based on multiresolution statistical descriptors derived from histogram of Discrete Wavelet Transform. First, the input facial image was enhanced by applying contrast limited adaptive histogram equalization. During feature extraction, multiresolution statistical descriptors were computed and fed into the Nearest Neighbor, Support Vector Machine, and Linear Discriminant Analysis classifiers respectively. We have achieved encouraging accuracy for gender identification on complex dataset of frontal facial images.
Recognition of multi-script documents, both printed and handwritten, is still a challenge due to ... more Recognition of multi-script documents, both printed and handwritten, is still a challenge due to the script dependence of OCR. Identification of script is a significant process in design of multi-script OCR system for processing of multi-script documents. In this paper, we focus on wordwise script identification, as without surprise we can see many scripts mixed in single line. We present a method, which mainly comprises three steps—word extraction, feature computation, and classification. Using morphological dilation, words are extracted. Radon and wavelet transforms are employed to extract the features based on directional and multi-resolution analysis. In classification, performance of LDA, SVM, and KNN classifiers is studied separately. Experiments with our dataset of Kannada and Roman words show that the presented method is robust for wordwise handwritten script identification.
Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies, 2016
Digital Watermarking is generally classified in two domains 'Spatial' and 'Frequency&... more Digital Watermarking is generally classified in two domains 'Spatial' and 'Frequency'. This paper specially focused on analysis of various methods proposed for Digital watermarking on "images" in the frequency domain. The survey is based on parameters like transforms or combination of transforms, enhancement methods, type of cover image and watermark, human perception, detection and robustness.
Term segmentation is about splitting the whole image into segments. In case of image analysis, im... more Term segmentation is about splitting the whole image into segments. In case of image analysis, image processing one of the crucial steps is segmentation of image. Segmentation of image concern about dividing entire image in sub parts that may be similar or dissimilar with respect to features. Output of image segmentation has consequence on analysis of image, further processing of image. Analysis of image comprises depiction of object and object representation, measurement of feature. Therefore characterization, area of interest’s visualization in the image, description have crucial job in segmentation of image. This survey explains some methods of image segmentation.
According to characteristics of complex high-value deposit,the reconstructed environment and cavi... more According to characteristics of complex high-value deposit,the reconstructed environment and caving-successive were tested with backfilling delayed mining method.Using the displacement and plastic zone as the criterion,the stability of artificial roof was analyzed by FLAC3 Dsoftware.The three different types of net-degree cable shoring,i.e.,typeⅠ4 m×6 m,typeⅡ6 m×8 m and typeⅢ8 m×10 m were simulated.These subsidence,disturbance band,plastic zone and axial force were analyzed.The results show that the maximum subsidence decreases to 4.24 cm,the height of plastic zones is less than 7 m,the maximal axial force is 16.59 MN and fluctuates smoothly in type Ⅰ.All these accord with mine security rules and economical requests,so typeⅠis adopted.
Diabetic Sensorimotor polyneuropathy (DSPN) is one of the major indelible complications in diabet... more Diabetic Sensorimotor polyneuropathy (DSPN) is one of the major indelible complications in diabetic patients. Michigan neuropathy screening instrumentation (MNSI) is one of the most common screening techniques used for DSPN, however, it does not provide any direct severity grading system. For designing and modeling the DSPN severity grading systems for MNSI, 19 years of data from Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials were used. Different Machine learning-based feature ranking techniques were investigated to identify the important MNSI features associated with DSPN diagnosis. A multivariable logistic regression-based nomogram was generated and validated for DSPN severity grading using the best performing top-ranked MNSI features. Top-10 ranked features from MNSI features: Appearance of Feet (R), Ankle Reflexes (R), Vibration perception (L), Vibration perception (R), Appearance of Feet (L), 10-gm filament (L), Ankle Reflexes (L), 10-gm filament (R), Bed Cover Touch, and Ulceration (R) were identified as important features for identifying DSPN by Multi-Tree Extreme Gradient Boost model. The nomogram-based prediction model exhibited an accuracy of 97.95% and 98.84% for the EDIC test set and an independent test set, respectively. A DSPN severity score technique was generated for MNSI from the DSPN severity prediction model. DSPN patients were stratified into four severity levels: absent, mild, moderate, and severe using the cut-off values of 17.6, 19.1, 20.5 for the DSPN probability less than 50%, 75%-90%, and above 90%, respectively. The findings of this work provide a machine learning-based MNSI severity grading system which has the potential to be used as a secondary decision support system by health professionals in clinical applications and large clinical trials to identify high-risk DSPN patients.
2016 Second International Conference on Computational Intelligence & Communication Technology (CICT), 2016
Image processing is one of most popular research area. Image processing consists of a number of p... more Image processing is one of most popular research area. Image processing consists of a number of phases to be carried out, among which classification is one. Classification of an object is a vital job in computer vision area. Classification reflects the final results accuracies. So everyone has to pay attention at this phase. Lots of work is done on comparative learning of classification methods. This survey paper demonstrates study of parametric and non-parametric classification techniques. Study isolates parametric and nonparametric classification techniques which are employed in classification phase and offers tree depictions of such methods. For comparative study 9 classifiers are utilized among which 6 belongs to parametric category and remaining 3 belongs to non-parametric category.9 classifiers considered here are super simple, their interpretation is nice probabilistic, used mostly and well known. Assessment parameters considered are Kappa Statistic, Mean Absolute Error (MAE), Receiver Operating Characteristics Area (ROC Area) and Root Mean Square Error (RMSE). For validation test 10 cross fold method is considered. Results show that overall Decision Tree classifier or subtypes of decision tree classifier performs well. It gives better output to high values of Kappa Statistic and ROC Area measures. Also, it produces better results with less value of MAE and RMSE measures. The results produced by Bayesian Net, Naive Bayes techniques are similar.
The security of bigger data is the bottleneck in the encryption and decryption because of the big... more The security of bigger data is the bottleneck in the encryption and decryption because of the big data size. The single encryption technique using one source is not adequate to accomplish the big data cloud computing security. This paper elaborates the working of cloud computing and the collaborating source security system for the Big Data security. A collaborating encryption technique framework is proposed in this paper to meet the futures' faster encryption requirements. The traditional information security system is not capable to provide the complete security during the cloud computing. The method described in this research comprises the parallel and distributed encryption system which gets the benefits the homomorphic encryption technique. The encryption facility during the mobile communication of object is tedious. Every cloud has its own security features and can be working in collaboration with the other cloud servers. Therefore, the parallel and distributed encryption facilities can be possible at every next door of other cloud without breaking the sequence of encryption process. The essential resources become the remote resources and the allocation of these resources can be managed at every cloud. Most of the time while working with the cloud computing is the availability of network and other resources. Providing the information security in the unavailability of resources during encryption and decryption is a difficult task. The collaboration encryption technique is a framework where, different clouds can work in parallel with the distributed processing. The security mechanism is improved by the homomorphic encryption.
2015 International Conference on Computing, Communication and Security (ICCCS), 2015
Enormous applications and the future necessities of image processing area open new paths for rese... more Enormous applications and the future necessities of image processing area open new paths for researchers. The analysis and recognition of numerous documents in the form of images are the challenging task. The classification is one of the vital phases in the image processing. The methods of classification must possess the consistency and accuracy. This research analyzes the different classification techniques and the performance analysis is carried out with the help of testing the image classification principles. In this research paper few classification techniques for Devanagari script are considered and evaluated in MATLAB R2014a.
Mobile IPv6 has been developed to enable mobility in IP network for mobile terminals. MIPv6 have ... more Mobile IPv6 has been developed to enable mobility in IP network for mobile terminals. MIPv6 have a lot of feature in comparison to previous Mobile IP protocol. From the data security perspective, the basic objective during the development of Mobile IPv6 has been that it must be at least as secure as previous Mobile IP protocol and it should not introduce any new security threats. But it suffers from various security threats like Eavesdropping, Secure route optimization, connection hijacking and denial of services. and security issues are one of the primary considerations that need to be address. In this paper we proposed a mechanism which includes all security components like Authentication, confidentiality and integrity, secretes key management. It will reduce all security threats and enhance security of Mobile IPv6.
Communications in Computer and Information Science, 2017
At present, digital image processing is elevated vicinity. Image possession, a broadcast may corr... more At present, digital image processing is elevated vicinity. Image possession, a broadcast may corrupt an image with impulse noise. Several realistic appliances necessitate a superior, squat complex de-noising practice as a pre-processing maneuver. While impulse noise filtering, the need is to conserve edges and image features. The merely damaged pixel should be filtered, to evade image smoothing. Analyses of few impulse noise cutback procedures are discussed in the study, their outcomes are inspected as well as competences are estimated in MATLAB R2014a. An appraisal affords inclusive acquaintance of noise diminution methods and also assists pollsters in paramount impulse noise reduction technique selection.
Digital watermarking is the process of hiding the important digital information into another one.... more Digital watermarking is the process of hiding the important digital information into another one. There are three main watermarking techniques, Digital image watermarking, digital audio watermarking and digital video watermarking. Watermarking can be done majorly in two domains, Spatial Domain and Frequency Domain. This paper is analysis of Digital image watermarking and different techniques used for digital image watermarking in Spatial Domain based on LSB-Based, Statistical-Based, Feature-Based and Block-Based.
Classification and Rule extraction is an important application of Artificial Neural Network. To e... more Classification and Rule extraction is an important application of Artificial Neural Network. To extract fewer rules from multilayer feed forward neural network has been a research area. The internal representation of the network is augmented by a distance term to extract fewer rules from the feed forward neural network and experimented on five datasets. Understanding affect of different factors of the dataset and network on extraction of a number of rules from the network can reveal important pieces of information which may help researchers to enhance the rule extraction process. This work investigates the internal behavior of neural network in rule extraction process on five different dataset. Keywords: Rule extraction, Feed Forward Neural Network, Hidden units, Activation value, Hidden neurons.
Gender identification is a significant task which is very useful in many computer applications li... more Gender identification is a significant task which is very useful in many computer applications like human–computer interaction, surveillance, demographic studies, and forensic studies. Being one of the most popular soft biometrics, gender information plays a vital role in improvement of the accuracy of biometric systems. In this paper, we have presented an approach based on multiresolution statistical descriptors derived from histogram of Discrete Wavelet Transform. First, the input facial image was enhanced by applying contrast limited adaptive histogram equalization. During feature extraction, multiresolution statistical descriptors were computed and fed into the Nearest Neighbor, Support Vector Machine, and Linear Discriminant Analysis classifiers respectively. We have achieved encouraging accuracy for gender identification on complex dataset of frontal facial images.
Recognition of multi-script documents, both printed and handwritten, is still a challenge due to ... more Recognition of multi-script documents, both printed and handwritten, is still a challenge due to the script dependence of OCR. Identification of script is a significant process in design of multi-script OCR system for processing of multi-script documents. In this paper, we focus on wordwise script identification, as without surprise we can see many scripts mixed in single line. We present a method, which mainly comprises three steps—word extraction, feature computation, and classification. Using morphological dilation, words are extracted. Radon and wavelet transforms are employed to extract the features based on directional and multi-resolution analysis. In classification, performance of LDA, SVM, and KNN classifiers is studied separately. Experiments with our dataset of Kannada and Roman words show that the presented method is robust for wordwise handwritten script identification.
Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies, 2016
Digital Watermarking is generally classified in two domains 'Spatial' and 'Frequency&... more Digital Watermarking is generally classified in two domains 'Spatial' and 'Frequency'. This paper specially focused on analysis of various methods proposed for Digital watermarking on "images" in the frequency domain. The survey is based on parameters like transforms or combination of transforms, enhancement methods, type of cover image and watermark, human perception, detection and robustness.
Term segmentation is about splitting the whole image into segments. In case of image analysis, im... more Term segmentation is about splitting the whole image into segments. In case of image analysis, image processing one of the crucial steps is segmentation of image. Segmentation of image concern about dividing entire image in sub parts that may be similar or dissimilar with respect to features. Output of image segmentation has consequence on analysis of image, further processing of image. Analysis of image comprises depiction of object and object representation, measurement of feature. Therefore characterization, area of interest’s visualization in the image, description have crucial job in segmentation of image. This survey explains some methods of image segmentation.
According to characteristics of complex high-value deposit,the reconstructed environment and cavi... more According to characteristics of complex high-value deposit,the reconstructed environment and caving-successive were tested with backfilling delayed mining method.Using the displacement and plastic zone as the criterion,the stability of artificial roof was analyzed by FLAC3 Dsoftware.The three different types of net-degree cable shoring,i.e.,typeⅠ4 m×6 m,typeⅡ6 m×8 m and typeⅢ8 m×10 m were simulated.These subsidence,disturbance band,plastic zone and axial force were analyzed.The results show that the maximum subsidence decreases to 4.24 cm,the height of plastic zones is less than 7 m,the maximal axial force is 16.59 MN and fluctuates smoothly in type Ⅰ.All these accord with mine security rules and economical requests,so typeⅠis adopted.
Diabetic Sensorimotor polyneuropathy (DSPN) is one of the major indelible complications in diabet... more Diabetic Sensorimotor polyneuropathy (DSPN) is one of the major indelible complications in diabetic patients. Michigan neuropathy screening instrumentation (MNSI) is one of the most common screening techniques used for DSPN, however, it does not provide any direct severity grading system. For designing and modeling the DSPN severity grading systems for MNSI, 19 years of data from Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials were used. Different Machine learning-based feature ranking techniques were investigated to identify the important MNSI features associated with DSPN diagnosis. A multivariable logistic regression-based nomogram was generated and validated for DSPN severity grading using the best performing top-ranked MNSI features. Top-10 ranked features from MNSI features: Appearance of Feet (R), Ankle Reflexes (R), Vibration perception (L), Vibration perception (R), Appearance of Feet (L), 10-gm filament (L), Ankle Reflexes (L), 10-gm filament (R), Bed Cover Touch, and Ulceration (R) were identified as important features for identifying DSPN by Multi-Tree Extreme Gradient Boost model. The nomogram-based prediction model exhibited an accuracy of 97.95% and 98.84% for the EDIC test set and an independent test set, respectively. A DSPN severity score technique was generated for MNSI from the DSPN severity prediction model. DSPN patients were stratified into four severity levels: absent, mild, moderate, and severe using the cut-off values of 17.6, 19.1, 20.5 for the DSPN probability less than 50%, 75%-90%, and above 90%, respectively. The findings of this work provide a machine learning-based MNSI severity grading system which has the potential to be used as a secondary decision support system by health professionals in clinical applications and large clinical trials to identify high-risk DSPN patients.
Uploads
Papers by Chitra Dhawale