Papers by priyadarshan dhabe
International Journal of System Assurance Engineering and Management, 2017
In this paper, we propose a Modified Implicit Bernstein Form (MIBF) for computing the Bernstein c... more In this paper, we propose a Modified Implicit Bernstein Form (MIBF) for computing the Bernstein coefficients of a polynomial. The MIBF avoids several redundant computations in Smith's Implicit Bernstein Form (IBF) (Smith in J Glob Optim 43:445-458, 2009). Based on the MIBF, we then propose a serial (or CPU based) Bernstein Algorithm for polynomial global optimization. On a set of test problems, the proposed Bernstein Algorithm is about 1.8 times faster than the one based on IBF in Dhabe and Nataraj (Int J Syst Assur Eng Manag, 2017). To obtain further speedups, we next propose a GPU parallel optimization algorithm based on the MIBF, and obtain speedups of up to 44 times with 97% reductions in computations over the serial version. Thus, we recommend the GPU parallel Bernstein algorithm based on the proposed MIBF form for solving polynomial global optimization problems. Keywords Bernstein algorithm Á Bernstein polynomials Á Global optimization Á GPU computing Á Parallel computing Á Polynomial optimization Let pðxÞ be a l-variate polynomial defined using x ¼ ðx 1 ; x 2 ;. . .; x l Þ variables on a box like domain X ¼ ½x 1 ; x x 1 Â Á Á Á Â ½x 1 ; x x 1 of degree N ¼ ðn 1 ; n 2 ;. . .; n l Þ. Let S ¼ ð0; 0;. . .; 0Þ;. . .; ðn 1 ; n 2 ;. . .; n l Þ be the set of multiindices I ¼ ði 1 ; i 2 ;. . .; i l Þ, that describes powers of l variables in a given polynomial term. Finding the minimum and maximum values of such polynomials has several applications in scientific and engineering fields (Nataraj and Arounassalame 2009). The Bernstein polynomial approach is proven successful for this task. Bernstein polynomials (Nataraj and Arounassalame 2009; Nataraj and Arounassalame 2011) are linear combinations of Bernstein bases. Their ''range enclosing property'' (Nataraj and Arounassalame 2009) allows to find global extremes without actual function evaluation. The Bernstein Algorithm (BA) to global optimization uses a branch and bound strategy (Nataraj and Kotecha 2002); for the different variants of the algorithm and its applications, see, for instance, Nataraj and Kotecha (2004), Nickolls et al.
Video Call-Based Real-Time Crime Reporting System
Advances in Systems Analysis, Software Engineering, and High Performance Computing, 2022
Most of the crimes that happen these days don't reach the police either because nobody report... more Most of the crimes that happen these days don't reach the police either because nobody reports them or there is no real time proof. The citizens don't have the real-time images, videos related to the crime, and hence, it goes unreported. This chapter presents a real-time video call-based crime reporting system, where the crime victim or an eye witness can start an end-to-end encrypted video call with the police present in the nearest police station. A data science approach is used to find the nearest police station. Once the police officer picks up the call, he will get the location of the crime and nearest route to reach the crime spot. Police can even catch the criminals or handle the crime while it is happening. After the video call ends, a recording of that call will also be available to the police.
Data Set Reduction to Improve Computing Efficiency and Energy Consumption in Healthcare Domain
Improved UFHLSNN (IUFHLSNN) for Generalized Representation of Knowledge and Its CPU Parallel Implementation Using OpenMP
EAI International Conference on Big Data Innovation for Sustainable Cognitive Computing, 2019
Fuzzy Hyper Line Segment Neural Network (FHLSNN) (Kullarni et al., International Joint conference... more Fuzzy Hyper Line Segment Neural Network (FHLSNN) (Kullarni et al., International Joint conference on 4:2918–2933, 2001) is a hybrid system that combines fuzzy logic (Zadeeh, IEEE Trans. Fuzzy Syst. 4:103, 1996) and neural networks (Zurada, Fundamental Concepts and Models of Artificial Neural Systems, 1992, pp. 30–36). It is used extensively for real-world pattern classification (Zurada, Fundamental Concepts and Models of Artificial Neural Systems, 1992, pp. 30–36). It learns patterns in terms of n-dimensional Hyper Line Segment (HLS). Modified Fuzzy Hyper Line Segment Neural Network (MFHLSNN) (Patil et al., The 12 IEEE International Conference, vol. 2, 2003) is a modified version of FHLSNN (Kullarni et al., International Joint conference on 4:2918–2933, 2001) that improves the quality of reasoning and recall time per pattern using modified fuzzy membership function. Updated Fuzzy Hyper Line Segment Neural Network (UFHLSNN) (Dhabe, 2016 International Conference on Computing, Analytic...
A New Data Structure for Representation of Relational Databases for Application in the Normalization Process
In this paper, a new data structure named relational tree is proposed for the representation of t... more In this paper, a new data structure named relational tree is proposed for the representation of the relational database in computer memory. Relational database schema represented using relational tree(s) appears to be more promising for semiautomating the process of normalization in a very efficient manner, which is prime motive of this paper. This paper provides all the fundamental concepts required for the understanding of the representation of relational schema using relational tree so that efficient algorithms of various normal forms can be designed by using this representation. This automation will considerably reduce manual efforts and errors in the process of normalization in software industries. Space requirements also improved, compared to previously proposed approaches. It is expected that application of various normalization algorithms on this way of representation is very efficient since the relational tree can be easily manipulated.
Drowsy Detection and Alarming System (DroDeASys)
— The paper discusses the Drowsy Detection & Alarming System that has been developed, using a non... more — The paper discusses the Drowsy Detection & Alarming System that has been developed, using a non-intrusive approach. The system is basically developed to detect drivers dozing at the wheel at night time driving. The system uses a small infra-red night vision camera that points directly towards the driver’s face and monitors the driver’s eyes in order to detect fatigue. In such a case when fatigue is detected, a warning signal is issued to alert the driver. This paper discusses the algorithms that have been used to detect drowsiness. The decision whether the driver is dozing or not is taken depending on whether the eyes are open for a specific number of frames. If the eyes are found to be closed for a certain number of consecutive frames then the driver is alerted with an alarm.
Modified K-Nearest Neighbor Fuzzy Classifier Using Group Prototypes and Its Application to Skin Segmentation
EAI International Conference on Big Data Innovation for Sustainable Cognitive Computing, 2019
This paper describes proposed modifications to the K-NN classifier, i.e., Modified Fuzzy KNN (MFK... more This paper describes proposed modifications to the K-NN classifier, i.e., Modified Fuzzy KNN (MFKNN) to address some complexity drawbacks of KNN. MFKNN calculates group prototypes from several patterns belonging to the same class and uses these prototypes for the recognition of patterns. Number of prototypes created by MFKNN classifier is dependent on the distance factor d. More prototypes are created for smaller value of d and vice versa.
Analysis and design of ICU Knowledge Management System (IKMS) for Indian environment with usability perspective
… (ICCAE), 2010
... Priyadarshan Dhabe Manikrao Dhore, Balaji Barbadekar Department of Computer Engineering Vishw... more ... Priyadarshan Dhabe Manikrao Dhore, Balaji Barbadekar Department of Computer Engineering Vishwakarma Institute of Technology, Pune, India ... 26-32. [8] G. Bhutkar, S. Mail, M. Dhore and M. Kadam, Need of customer orientation in IT domain, Proceedings of IMECS, 2007 ...
Recognition of handwritten characters using modified fuzzy hyperline segment neural network
In this paper membership function of fuzzy hyperline segment neural network (FHLSNN) proposed by ... more In this paper membership function of fuzzy hyperline segment neural network (FHLSNN) proposed by U.V. Kulkarni and T.R. Sontakke is modified to maintain convexity. The modified membership function is found superior than the function defined by them, which gives relatively lower values to the patterns which are falling close to the hyperline segment (HLS) but far from two end points
International Journal
AER (Articulated Entity Relationship) diagrams proposed by us, are the extension of Entity Relati... more AER (Articulated Entity Relationship) diagrams proposed by us, are the extension of Entity Relationship (ER) diagrams to accommodate functional dependencies (FDs) as their integral part. Accommodation of FDs in ER diagram helps to achieve total and unconditional automation of relational database normalization. In this paper we have implemented a software Integrated Development Environment (IDE), called AER IDE, designed by extending the Graphical Editing Framework (GEF) and Draw2d plug-in functionality of Eclipse. The AER IDE helps to draw, validate, store and normalize AER diagrams. An AER IDE has five modules. AER Editor allows creation and edition of AER diagrams using Model View controller (MVC) approach. AER diagrams are translated and stored as an xml file. AER Validator provides the facility of AER diagram validation based on a set of proposed rules. AER Normalizer allows normalization of an AER diagram, in one go, with the help of the proposed AER normalization rules and algorithms. Thus, it allows the total and unconditional automation of relational database normalization up to a given normal form; as an integral part of AER IDE. It also serves as a visual aid for the normalization process which is always easy to understand and interpret rather than theoretical approach. AER-XML Bidirectional Translator provides the import and export functionality of AER diagram, to and from an XML template making it compatible with the other toolset. AER-SQL Generator generates DDL scripts in the SQL schema format. The AER IDE is tested with ten distinct AER diagrams with all possible combinations of AER features and validation rules.
A GPU parallel Bernstein algorithm for polynomial global optimization
International Journal of System Assurance Engineering and Management
Pattern classification using updated fuzzy hyper-line segment neural network and it's GPU parallel implementation for large datasets using CUDA
2016 International Conference on Computing, Analytics and Security Trends (CAST), 2016
Fourier fuzzy neural network for clustering of visual objects based on their gross shape and its application to handwritten character recognition
2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), 2004
In this paper, an unsupervised feedforward Fourier fuzzy neural network (FFNN) is proposed which ... more In this paper, an unsupervised feedforward Fourier fuzzy neural network (FFNN) is proposed which is suitable for clustering of object images based on their gross shapes. This 3-layer feedforward neural network is described along with its training. Its performance is tested for synthetic image database containing objects of various shapes and with realistic image database of handwritten Devanagari digits. FFNN
A new clustering method based on geometrical moment of patterns
The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03., 2003
In this paper a new approach of moment based clustering is proposed, in which cluster centroids a... more In this paper a new approach of moment based clustering is proposed, in which cluster centroids are calculated using regular geometrical moments of patterns. For this purpose zeroth order and first order moments are used. This approach is compared with fuzzy min-max neural network (FMN) clustering algorithm. The performance of the proposed algorithm is found equiporable with FMN clustering, when tested for Fisher Iris data. The performance comparison is done at equal number of clusters created by both the algorithms by adjusting the network parameters. The recall of the proposed approach is found around three times faster than the FMN clustering algorithm.
Proposed novel schemes based on IPV4 for data steganography and transmitting over Internet
National Conference on Signal and Image Processing Applications, 2009
GPU Paralleliza+ on of Bernstein Algorithm (BA) using Implicit Bernstein Form (IBF)
Modified Fuzzy Hyper-Line Segment Neural Network and it‟ s Application to Heart Disease Detection
Heart Diseases Detection Using Fuzzy Hyper Sphere Neural Network Classifier
International Journal of Database Management Systems, 2011
In this paper a tool called RDBNorma is proposed, that uses a novel approach to represent a relat... more In this paper a tool called RDBNorma is proposed, that uses a novel approach to represent a relational database schema and its functional dependencies in computer memory using only one linked list and used for semi-automating the process of relational database schema normalization up to third normal form. This paper addresses all the issues of representing a relational schema along with its functional dependencies using one linked list along with the algorithms to convert a relation into second and third normal form by using above representation. We have compared performance of RDBNorma with existing tool called Micro using standard relational schemas collected from various resources. It is observed that proposed tool is at least 2.89 times faster than the Micro and requires around half of the space than Micro to represent a relation. Comparison is done by entering all the attributes and functional dependencies holds on a relation in the same order and implementing both the tools in same language and on same machine.
Fingerprint verification using haar wavelet
2010 2nd International Conference on Computer Engineering and Technology, 2010
This paper deals with a new image based approach for fingerprint verification using Haar Wavelet ... more This paper deals with a new image based approach for fingerprint verification using Haar Wavelet Transform. Haar wavelet is used for decomposition of the fingerprint image. Haar wavelet transformation is carried out directly on the gray-scaled fingerprint image without any preprocessing steps. Decomposition of the fingerprint image is carried out up to three levels. Then wavelet statistical features are extracted
Uploads
Papers by priyadarshan dhabe