Manohar Pandit | Dr.Babasaheb Ambedkar Marathwada University (original) (raw)

Papers by Manohar Pandit

Medial Axis Transform (MAT) is one of the promising tools used for the shape recognition and it p... more Medial Axis Transform (MAT) is one of the promising tools used for the shape recognition and it poses the advantages like space and complexity reduction, ease of processing for shape recognition. MAT representation of shapes uses object centred co-ordinate system that represents bending, elongation and thickness. But MAT of the objects is very much sensitive to small perturbations of its boundary. To overcome this problem, we prune the particular portion. In our approach, we use local or global pruning for branch significance computation. For this we use group-wise approach in which we develop a group-wise skeletonization framework that gives fuzzy significance for each branch. This is called as Groupwise Medial Axis Transform (G-MAT). This approach has several applications like shape analysis and shape recognition. This approach has been tested on various geometries of the shapes and gives good recognition results.

This paper describes and demonstrates a graphical method of Skeletal Shock Graph, which is based ... more This paper describes and demonstrates a graphical method of Skeletal Shock Graph, which is based on the shape or geometry of the object. Shock Graph is an abstraction of the skeleton of a shape onto a Directed Acyclic Graph (DAG) in which the skeleton points are labeled according to the local variation of the radius function at each point. A large image data base is created by using suitable image acquisition technique, which is converted into binary images. Skeleton and its labeling of the binary image is obtained by applying Skeletonization Algorithm. Then next steps adopted are formation of Shock Graph and labeled tree, indexing the data base and generation of attribute vectors, pruning the data base and lastly matching the tree of query image with that of database images for recognition. This paper discusses and demonstrates the existing challenges and prospective research areas in Skeletal Shock Graph based object recognition and also presents some comparative results against t...

Proteomics, 2011

Identification and analysis of types of biological protein-protein interactions and their interfa... more Identification and analysis of types of biological protein-protein interactions and their interfaces to predict obligate and non-obligate complexes is a problem that has drawn the attention of the research community in the past few years. In this paper, we propose a prediction approach to predict these two types of complexes. We use desolvation energies - amino acid and atom type - of the residues present in the interface. The prediction is performed via two state-of-the-art classification techniques, namely linear dimensionality reduction (LDR) and support vector machines (SVM). The results on a newly compiled data set, namely BPPI, which is a joint and modified version of two well-known data sets consisting of 213 obligate and 303 non-obligate complexes, show that the best prediction is achieved with SVM (76.94% accuracy) when using desolvation energies of atom-type features. Also, the proposed approach outperforms the previous solvent accessible area-based approaches using SVM (75% accuracy) and LDR (73.06% accuracy). Moreover, a visual analysis of desolvation energies in obligate and non-obligate complexes shows that a few atom-type pairs are good descriptors for these types of complexes.

English and empowerment in the …, 2009

Explorations in Applied Linguistics: MV Nadkarni …, 1995

... Article Outline. 1. Introduction 2. Geological setting 3. Analytical methods 4. Samples: petr... more ... Article Outline. 1. Introduction 2. Geological setting 3. Analytical methods 4. Samples: petrography and zircon CL imagery 4.1. Raj25 (recrystallised charno-enderbite, Sandmata Complex) 4.2. ... 4.1. Raj25 (recrystallised charno-enderbite, Sandmata Complex). ...

Obstetrics and …, 2000

From the Departments of Obstetrics and Gynecology, Mechanical Engineering, and Pathology, Univers... more From the Departments of Obstetrics and Gynecology, Mechanical Engineering, and Pathology, University of Michigan Medical Center, Ann Arbor, Michigan. ... See other articles in PMC that cite the published article. ... To analyze the quantity and distribution of ...

... Additional Information. How to Cite. Collins, S., Ellaway, P., Harrington, D., Pandit, M. and... more ... Additional Information. How to Cite. Collins, S., Ellaway, P., Harrington, D., Pandit, M. and Impey, L. (2007), Short communication: The complications of external cephalic version: results from 805 consecutive attempts. ... Author Information. 1 John Radcliffe Hospital, Oxford, UK. 2 ...

International Journal of Electrical Power & Energy Systems, 2001

On-line monitoring of the power system voltage security has become a vital factor for electric ut... more On-line monitoring of the power system voltage security has become a vital factor for electric utilities. This paper proposes a voltage contingency ranking approach based on parallel self-organizing hierarchical neural network (PSHNN). Loadability margin to voltage collapse following a contingency has been used to rank the contingencies. PSHNN is a multi-stage neural network where the stages operate in parallel rather

The paper presents the design of three types of neural networks with different features, includin... more The paper presents the design of three types of neural networks with different features, including traditional backpropagation networks, radial basis function networks and counterpropagation networks. Traditional backpropagation networks require very complex training process before being applied for classification or approximation. Radial basis function networks simplify the training process by the specially organized 3-layer architecture. Counterpropagation networks do not need training process at all and can be designed directly by extracting all the parameters from input data. Both design complexity and generalization ability of the three types of neural network architectures are compared, based on a digit image recognition problem.

Page 1. 1 ON THE ECONOMICS OF CHOICE OF INVASIVE SPECIES CONTROL OPTIONS Krishna P. Paudel, Louis... more Page 1. 1 ON THE ECONOMICS OF CHOICE OF INVASIVE SPECIES CONTROL OPTIONS Krishna P. Paudel, Louisiana State University Agricultural Center Mahesh Pandit, Louisiana State University Agricultural Center Michael ...

and Virginia). The purpose of this survey was to obtain information about the cotton producers' a... more and Virginia). The purpose of this survey was to obtain information about the cotton producers' attitude towards the adoption of precision agricultural technology. Data consists of 7456 observation for 681 cotton farmers who adopted technologies between 1966 and 2007. Considering, year as a unit of duration for technologies adoption, we observed whether the cotton producer adopt the technologies or not in a particular year. Each cotton producer can adopt one or more than one technology as a case of multiple technologies adoption. There are total of 474 events with each farm experiencing an average of 0.70 events. The events in this data set range from 1 to 11 for 11 technologies. Figures 1 and 2 give summary representation of adoption behavior of these cotton producers. We found that 255 farmers adopted only one technology; 97 farmers adopted exactly two technology; 55 farmers adopted exactly 3 technology; 24 farmers adopted only four technology, 9 farmers adopted exactly 5 technology, 4 farmers adopted exactly 6 technology. Further there is exactly one farmer who adopts 7 to 10 technology. Finally, no farmer adopted all 11 technologies.

We tested for club convergence in U.S. agricultural total factory productivity using a sigma conv... more We tested for club convergence in U.S. agricultural total factory productivity using a sigma convergence test. We used the same club of states as used by McCunn and Huffman as well as different states within 10 clubs identified by the cluster analysis. Results showed convergence was evident only in a few club groups. Clusters group identified using a statistical method identified only converging clubs. Variables affecting total factor productivity among states were identified using parametric, semiparametric and nonparametric methods. Semiparametric and nonparametric methods gave a better fit than a parametric method as indicated by the specification test. Our results indicated that health care expenditure, public research and extension investment, and private expenditure are important variables impacting total factor productivity differences across states.

Market channel alternatives that include garden centers, landscapers, mass merchandisers and re-w... more Market channel alternatives that include garden centers, landscapers, mass merchandisers and re-wholesalers have contributed to the growth of ornamental crops sales in the United States (U. S.). The homogenous subpopulation of the U.S. nursery producer was clustered using mixture of export method and found that there exist four homogenous group of Nursery Producer. The impact of growers’ business characteristics on shares of sales to these channels by firm size was estimated using multivariate fractional regression and nonparametric model. Important explanatory variables were regions of the U.S., sales of plant groups, kinds of contract sales, and promotional expenses, and their effect varies by cluster. We also found that in some cases nonparametric estimation procedure is better than parametric estimates.

… , IEEE Transactions on, 2004

This paper introduces a novel parameter automation strategy for the particle swarm algorithm and ... more This paper introduces a novel parameter automation strategy for the particle swarm algorithm and two further extensions to improve its performance after a predefined number of generations. Initially, to efficiently control the local search and convergence to the global optimum solution, time-varying acceleration coefficients (TVAC) are introduced in addition to the time-varying inertia weight factor in particle swarm optimization (PSO). From the basis of TVAC, two new strategies are discussed to improve the performance of the PSO. First, the concept of "mutation" is introduced to the particle swarm optimization along with TVAC (MPSO-TVAC), by adding a small perturbation to a randomly selected modulus of the velocity vector of a random particle by predefined probability. Second, we introduce a novel particle swarm concept "self-organizing hierarchical particle swarm optimizer with TVAC (HPSO-TVAC)." Under this method, only the "social" part and the "cognitive" part of the particle swarm strategy are considered to estimate the new velocity of each particle and particles are reinitialized whenever they are stagnated in the search space. In addition, to overcome the difficulties of selecting an appropriate mutation step size for different problems, a time-varying mutation step size was introduced. Further, for most of the benchmarks, mutation probability is found to be insensitive to the performance of MPSO-TVAC method. On the other hand, the effect of reinitialization velocity on the performance of HPSO-TVAC method is also observed. Time-varying reinitialization step size is found to be an efficient parameter optimization strategy for HPSO-TVAC method. The HPSO-TVAC strategy outperformed all the methods considered in this investigation for most of the functions. Furthermore, it has also been observed that both the MPSO and HPSO strategies perform poorly when the acceleration coefficients are fixed at two.

Medial Axis Transform (MAT) is one of the promising tools used for the shape recognition and it p... more Medial Axis Transform (MAT) is one of the promising tools used for the shape recognition and it poses the advantages like space and complexity reduction, ease of processing for shape recognition. MAT representation of shapes uses object centred co-ordinate system that represents bending, elongation and thickness. But MAT of the objects is very much sensitive to small perturbations of its boundary. To overcome this problem, we prune the particular portion. In our approach, we use local or global pruning for branch significance computation. For this we use group-wise approach in which we develop a group-wise skeletonization framework that gives fuzzy significance for each branch. This is called as Groupwise Medial Axis Transform (G-MAT). This approach has several applications like shape analysis and shape recognition. This approach has been tested on various geometries of the shapes and gives good recognition results.

This paper describes and demonstrates a graphical method of Skeletal Shock Graph, which is based ... more This paper describes and demonstrates a graphical method of Skeletal Shock Graph, which is based on the shape or geometry of the object. Shock Graph is an abstraction of the skeleton of a shape onto a Directed Acyclic Graph (DAG) in which the skeleton points are labeled according to the local variation of the radius function at each point. A large image data base is created by using suitable image acquisition technique, which is converted into binary images. Skeleton and its labeling of the binary image is obtained by applying Skeletonization Algorithm. Then next steps adopted are formation of Shock Graph and labeled tree, indexing the data base and generation of attribute vectors, pruning the data base and lastly matching the tree of query image with that of database images for recognition. This paper discusses and demonstrates the existing challenges and prospective research areas in Skeletal Shock Graph based object recognition and also presents some comparative results against t...

Proteomics, 2011

Identification and analysis of types of biological protein-protein interactions and their interfa... more Identification and analysis of types of biological protein-protein interactions and their interfaces to predict obligate and non-obligate complexes is a problem that has drawn the attention of the research community in the past few years. In this paper, we propose a prediction approach to predict these two types of complexes. We use desolvation energies - amino acid and atom type - of the residues present in the interface. The prediction is performed via two state-of-the-art classification techniques, namely linear dimensionality reduction (LDR) and support vector machines (SVM). The results on a newly compiled data set, namely BPPI, which is a joint and modified version of two well-known data sets consisting of 213 obligate and 303 non-obligate complexes, show that the best prediction is achieved with SVM (76.94% accuracy) when using desolvation energies of atom-type features. Also, the proposed approach outperforms the previous solvent accessible area-based approaches using SVM (75% accuracy) and LDR (73.06% accuracy). Moreover, a visual analysis of desolvation energies in obligate and non-obligate complexes shows that a few atom-type pairs are good descriptors for these types of complexes.

English and empowerment in the …, 2009

Explorations in Applied Linguistics: MV Nadkarni …, 1995

... Article Outline. 1. Introduction 2. Geological setting 3. Analytical methods 4. Samples: petr... more ... Article Outline. 1. Introduction 2. Geological setting 3. Analytical methods 4. Samples: petrography and zircon CL imagery 4.1. Raj25 (recrystallised charno-enderbite, Sandmata Complex) 4.2. ... 4.1. Raj25 (recrystallised charno-enderbite, Sandmata Complex). ...

Obstetrics and …, 2000

From the Departments of Obstetrics and Gynecology, Mechanical Engineering, and Pathology, Univers... more From the Departments of Obstetrics and Gynecology, Mechanical Engineering, and Pathology, University of Michigan Medical Center, Ann Arbor, Michigan. ... See other articles in PMC that cite the published article. ... To analyze the quantity and distribution of ...

... Additional Information. How to Cite. Collins, S., Ellaway, P., Harrington, D., Pandit, M. and... more ... Additional Information. How to Cite. Collins, S., Ellaway, P., Harrington, D., Pandit, M. and Impey, L. (2007), Short communication: The complications of external cephalic version: results from 805 consecutive attempts. ... Author Information. 1 John Radcliffe Hospital, Oxford, UK. 2 ...

International Journal of Electrical Power & Energy Systems, 2001

On-line monitoring of the power system voltage security has become a vital factor for electric ut... more On-line monitoring of the power system voltage security has become a vital factor for electric utilities. This paper proposes a voltage contingency ranking approach based on parallel self-organizing hierarchical neural network (PSHNN). Loadability margin to voltage collapse following a contingency has been used to rank the contingencies. PSHNN is a multi-stage neural network where the stages operate in parallel rather

The paper presents the design of three types of neural networks with different features, includin... more The paper presents the design of three types of neural networks with different features, including traditional backpropagation networks, radial basis function networks and counterpropagation networks. Traditional backpropagation networks require very complex training process before being applied for classification or approximation. Radial basis function networks simplify the training process by the specially organized 3-layer architecture. Counterpropagation networks do not need training process at all and can be designed directly by extracting all the parameters from input data. Both design complexity and generalization ability of the three types of neural network architectures are compared, based on a digit image recognition problem.

Page 1. 1 ON THE ECONOMICS OF CHOICE OF INVASIVE SPECIES CONTROL OPTIONS Krishna P. Paudel, Louis... more Page 1. 1 ON THE ECONOMICS OF CHOICE OF INVASIVE SPECIES CONTROL OPTIONS Krishna P. Paudel, Louisiana State University Agricultural Center Mahesh Pandit, Louisiana State University Agricultural Center Michael ...

and Virginia). The purpose of this survey was to obtain information about the cotton producers' a... more and Virginia). The purpose of this survey was to obtain information about the cotton producers' attitude towards the adoption of precision agricultural technology. Data consists of 7456 observation for 681 cotton farmers who adopted technologies between 1966 and 2007. Considering, year as a unit of duration for technologies adoption, we observed whether the cotton producer adopt the technologies or not in a particular year. Each cotton producer can adopt one or more than one technology as a case of multiple technologies adoption. There are total of 474 events with each farm experiencing an average of 0.70 events. The events in this data set range from 1 to 11 for 11 technologies. Figures 1 and 2 give summary representation of adoption behavior of these cotton producers. We found that 255 farmers adopted only one technology; 97 farmers adopted exactly two technology; 55 farmers adopted exactly 3 technology; 24 farmers adopted only four technology, 9 farmers adopted exactly 5 technology, 4 farmers adopted exactly 6 technology. Further there is exactly one farmer who adopts 7 to 10 technology. Finally, no farmer adopted all 11 technologies.

We tested for club convergence in U.S. agricultural total factory productivity using a sigma conv... more We tested for club convergence in U.S. agricultural total factory productivity using a sigma convergence test. We used the same club of states as used by McCunn and Huffman as well as different states within 10 clubs identified by the cluster analysis. Results showed convergence was evident only in a few club groups. Clusters group identified using a statistical method identified only converging clubs. Variables affecting total factor productivity among states were identified using parametric, semiparametric and nonparametric methods. Semiparametric and nonparametric methods gave a better fit than a parametric method as indicated by the specification test. Our results indicated that health care expenditure, public research and extension investment, and private expenditure are important variables impacting total factor productivity differences across states.

Market channel alternatives that include garden centers, landscapers, mass merchandisers and re-w... more Market channel alternatives that include garden centers, landscapers, mass merchandisers and re-wholesalers have contributed to the growth of ornamental crops sales in the United States (U. S.). The homogenous subpopulation of the U.S. nursery producer was clustered using mixture of export method and found that there exist four homogenous group of Nursery Producer. The impact of growers’ business characteristics on shares of sales to these channels by firm size was estimated using multivariate fractional regression and nonparametric model. Important explanatory variables were regions of the U.S., sales of plant groups, kinds of contract sales, and promotional expenses, and their effect varies by cluster. We also found that in some cases nonparametric estimation procedure is better than parametric estimates.

… , IEEE Transactions on, 2004

This paper introduces a novel parameter automation strategy for the particle swarm algorithm and ... more This paper introduces a novel parameter automation strategy for the particle swarm algorithm and two further extensions to improve its performance after a predefined number of generations. Initially, to efficiently control the local search and convergence to the global optimum solution, time-varying acceleration coefficients (TVAC) are introduced in addition to the time-varying inertia weight factor in particle swarm optimization (PSO). From the basis of TVAC, two new strategies are discussed to improve the performance of the PSO. First, the concept of "mutation" is introduced to the particle swarm optimization along with TVAC (MPSO-TVAC), by adding a small perturbation to a randomly selected modulus of the velocity vector of a random particle by predefined probability. Second, we introduce a novel particle swarm concept "self-organizing hierarchical particle swarm optimizer with TVAC (HPSO-TVAC)." Under this method, only the "social" part and the "cognitive" part of the particle swarm strategy are considered to estimate the new velocity of each particle and particles are reinitialized whenever they are stagnated in the search space. In addition, to overcome the difficulties of selecting an appropriate mutation step size for different problems, a time-varying mutation step size was introduced. Further, for most of the benchmarks, mutation probability is found to be insensitive to the performance of MPSO-TVAC method. On the other hand, the effect of reinitialization velocity on the performance of HPSO-TVAC method is also observed. Time-varying reinitialization step size is found to be an efficient parameter optimization strategy for HPSO-TVAC method. The HPSO-TVAC strategy outperformed all the methods considered in this investigation for most of the functions. Furthermore, it has also been observed that both the MPSO and HPSO strategies perform poorly when the acceleration coefficients are fixed at two.