Loading...
![Thumbnail Image](assets/images/Collection.png)
Theses
Browse
25 results
Search Results
ThesisItem Open Access Reliability indices and signature analysis of complex networks(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-08) Bisht, Soni; Singh, S.B.The present research is based on the development of reliability models with the application of UGF, Supplementary variable technique, ANN, and Signature. In this study, six different reliability models have been developed. Model 1 generates an efficient algorithm to compute the reliability indices of complex bridge networks having i.i.d. lifetime components (nodes, edges), with the help of UGF and Owen’s method. Applying reliability structure function, proposed algorithms are used to find the signature and the MTTF. Model 2 assess the reliability characteristics of bridge network and square ladder network on the basis of the flow of information/signals from a source node to a sink node using the universal generating function. The main focus of this model is to estimate the reliability indices, namely, reliability, MTTF, sensitivity assuming failure to be exponentially distributed. Furthermore, for computing the signature of networks with the help of Owens method we have assumed that all components are independent and have identically distributed. Model 3 deals with the reliability and signature analysis of one of the most common multistage interconnection networks, namely, Shuffle exchange networks (SENs).An efficient algorithm has been established to compute the signature and Mean-time-to-failure of shuffle exchange networks with the help of Owen’s method incorporating independent and identically distributed lifetime component. All perspectives of the reliability, viz. terminal, broadcast and network reliability have been analyzed with the help of universal generating function. Model 4 estimates the reliability of Benes network having both independent and identically and non-identically distributed components in three contexts, viz. terminal, broadcast, and network with the help of universal generating function. Subsequently, the signature is computed with the help of Owen’s method using different algorithms. At last, we have computed the mean time to failure with the help of minimal signature. Model 5 focuses on the reliability indices and signature evaluation of all-digital protection system. In this model, firstly, we have computed the reliability of all-digital protection systems using a universal generating function having both independent and identically and non-identically distributed components. Afterwards, the signature is evaluated with the help of Owen’s method using different algorithms where all the system components are coherent. Lastly, we have calculated the mean time to failure with the help of minimal signature. Model 6 [Section 1] introduces the concept of the acyclic transmission network in which numbers of nodes are capable of receiving or sending a signal to the target nodes. The model combined the concepts of Markov processes and minimal cuts incorporating copula to find the various reliability measures. Various reliability characteristics such as transition state probabilities, reliability, MTTF and sensitivity of the proposed network has been evaluated with the help of minimal cuts coupling with Markov processes using Gumbel-Hougaard copula, supplementary variable techniques and Laplace transforms. [Section 2] studies the reliability and profit function of acyclic transmission network with the application of Markov process and artificial neural network. After determining the reliability by Markov process, it is improved with the help of the artificial neural network. All the presented models are demonstrated by appropriate illustrative examples.ThesisItem Open Access A study of some micro-polar fluid flow problems(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-12) Singh, Khilap; Manoj KumarIn the recent decades, the importance of non-Newtonian fluids has significantly increased because of their relation with applied sciences. The flow of these fluids takes vital role not only in hypothesis but also in several industrial processes. Among the various non-Newtonian fluids, the micro-polar fluids have achieve the special attention in recent years due to their applications in biotechnology, chemical engineering, geophysics, materials processing and polymeric fabrication and so on. Micro-polar fluids correspond to the many industrial important fluids for example, bio-fluids, body fluids, colloidal suspensions, human and animal blood, lubricants, polymers, liquid crystals, paints etc. Because of wide range of utilizations of these fluids present work is done to examine the impact of different parameters on the flow behaviors of micro-polar fluid. In the present work, author has studied different problems of micro-polar fluid flow in various shaped bodies. The governing equations of flows of micro-polar fluid are non-linear in nature and solved by using both analytical and numerical methods. Different numerical methods for example Finite element method, Finite difference method, Quasilinearization, Keller-box method, Runge-Kutta-Fehlberg fourth fifth order method and Shooting method etc. can be applied for handling these problems. In the present thesis author has used Keller-box method, Runge-Kutta-Fehlberg fourth fifth order method, shooting method together with an analytic method known as differential transformation method. The work incorporated in the present research is divided into five chapters. Author has formulated eight problems out of which seven are for steady flow and one is for unsteady flow. One problem is solved by applying differential transformation method, two problems are solved by applying Keller box method, while six problems are solved by applying shooting technique along with Runge-Kutta-Fehlberg fourth fifth order method. To approve of results obtained from all these problems with particular conditions, author compare results with results of previously published literature. Excellent agreement between the results is obtained. The impact of various pertinent parameters on velocity, micro-rotation, temperature and concentration profiles is studied comprehensively and is portrayed graphically. The skin-friction coefficient, the couple stress coefficient, the Nusselt and Sherwood numbers have also been computed and depicted using graphs and tables. It is hoped that the results obtained from the present study will give important data to group of audience.ThesisItem Open Access Intuitionistic fuzzy rule based modelling to study few psychological parameters(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-08) Gupta, Virendra; Sanjay KumarUnlike fuzzy set, Intuitionistic fuzzy set (IFS) uses separate functions for membership and non-membership grade. Hence, IFS is considered more ideal tool than fuzzy set to handle non-determinism along with uncertainty. In the present study, we have developed an intuitionistic fuzzy rule based model for predicting anxiety level of students using extraversion and motivation. Participants in the present study are 22 students from the department of physics, chemistry and mathematics. In this study, we also compare performance of IFS rule based model with the performance of earlier fuzzy rule based model, ANFIS model and hybrid models. The chapter 1 describes the basic preliminaries of fuzzy sets, IFS and basic terminology of psychology. It also contains the description of problem undertaken. A brief review of past research work in the area of fuzzy logic, intuitionistic fuzzy sets, psychology and cognitive science have been presented in chapter 2. The chapter 3 comprehensively describes the various material (collection of data through Maudsley Personality Inventory questionnaire) and method that is being used in the duration of course of investigation. The results obtained have been placed in chapter 4 and this chapter also includes comparison with the results obtained output by fuzzy method, ANFIS and Genetic Algorithm method. The works have been summarized in chapter 5. The literature used in the course of study has been referred under section literature cited.ThesisItem Open Access A study of boundary layer flow and heat transfer of nanofluid over an inclined cylinder with suction/injection(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-06) Shikha; Manoj KumarAn analysisis done with the problem related to flow and heat transfer of nanofluid flow over an inclined stretching porous cylinder due to various parameters such as heat generation/absorption, suction/injection and viscous dissipation etc. There are many medical branches, mechanical engineering, hydrodynamic and chemical engineering etc., in which the flow of immersed bodies in Newtonian and non-Newtonian fluid flow are studied. The other parameters which are affecting the flow have been analyzed and with the help of graphs, we discussed its impact on velocity and thermal boundary layer. Further their effects on skin friction coefficient and Nusselt number are studied and discussed in details. This thesis contains five chapters which are further divided on the basis of their aim. Chapter 1 introduces the basic requirements of various fundamental concepts needed to study the presented problem of dynamic fluid mechanics. In chapter 2, it is broadly discussed the relation of past research work with the presented work. Mathematical formulation of the problem, detailed description of used methodology and its numerical solution is discussed in chapter 3.Results and discussion of the considered problems revealed in chapter 3 are discussed in chapter 4 and the summery of the work is done in chapter 5. During the course of analysis, the literature used in the course of the study has been referred under the section of literature cited. The presented analysis helps in nano field of applied science such as miniaturized technology, mechanical engineering and medical science etc.ThesisItem Open Access Investigation of reliability characteristics of different networks incorporating copula(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-06) Nautiyal, Nisha; Singh, S.B.In this thesis, authoress has studied the following two different models: 1. Evaluation of reliability of a k-out-of-n network with the help of Gumbel-Hougaard family of Copula. 2. Reliability assessment of a mobile ad-hoc network (MANET) applying Gumbel-Hougaard family of Copula. Both models involve the comprehensive study of the networks having different failure rates which are studied by copula methodology. In the first model, a k-out-of-n network having the property that atleast k node must be there which can have flow from source to terminal, out of the total n nodes, is considered. The nodes which got failed are being repaired by coupling the two repair rates, i.e., exponential and general repair. By using the supplementary variable technique probabilities for different transition has been obtained. Reliability, M.T.T.F and sensitivity of the network have been analyzed using the Gumbel-Hougaard family of Copula. In the second model, a mobile ad-hoc network (MANET) has been studied. The network taken is an environment of a battlefield which has been modeled as a MANET. It includes headquarters (source), three Indian forces (Sub-MANETs) and the base camp of terrorist (sink). The main aim is to destroy the base camp (or to reach the sink). The reliability, M.T.T.F and sensitivity of the MANET have been evaluated by the same method as used in the above model.ThesisItem Open Access Expert system for portfolio management based on technical indicators using ANN(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-06) Pandey, Ankita; Pal, A.K.Present work entitled “EXPERT SYSTEM FOR PORTFOLIO MANAGEMENT BASED ON TECHNICAL INDICATORS USING ANN” treated the issue of developing an ANN model which generates future values and portfolio system based on technical indicators. Artificial neural networks are very good in the stock market prediction as they non linear and complex models. In this work, we have used the artificial neural network to predict the stock prices and on the bases of their prediction we generate a portfolio system. The presented study comprises five chapters. The first chapter is aimed to fulfil the basic need of introducing artificial neural network, time series, portfolio and the use of neural network in portfolio management. Chapter two accomplished majority of passed research work related with present work. Chapter three covers the material and methods used for the present study. We have presented the neural network for the prediction and simulated it in MATLAB software. Chapter four describes the result and discussion of the encountered taken in chapter three. The work has been summarized in chapter five. Along with the finding of the study, the literature used in the course of the study has been referred under the section of literature cited. The related study may be helpful for the investors of stock market to make wise decisions so that they can have maximum profit.ThesisItem Open Access Interval-valued intuitionistic hesitant fuzzy and uncertain linguistic based multi-criteria group decision making methods(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-01) Joshi, Dheeraj Kumar; Sanjay KumarMulti-criteria group decision making (MCGDM) has various applications in many real life problems of banking, data mining, water resource location, human resource development, resource allocation and portfolio selection. The present research work mainly focus on development and implementation of MCGDM/MCDM models in the environment of uncertainty and hesitation. In this study, 6 different models of MCGDM methods are developed in interval-valued intuitionistic hesitant fuzzy (IVIHF), probabilistic hesitant fuzzy (PHF) and interval-valued intuitionistic hesitant fuzzy linguistic and uncertain linguistic environment. These models are based on entropy measure, distance and similarity measures. Cloud model based TOPSIS method and Choquet integral based TOPSIS methods are also developed to consider both randomness, fuzziness and interaction phenomenon in MCGDM problems. Model [1] is IVIHF entropy based MCGDM method. In this model criterion weights are determined using IVIHF entropy. Model [2] is probabilistic intuitionistic fuzzy information based TOPSIS method. In Model [3], a series of distance and similarity measures for probabilistic hesitant fuzzy set is defined and used in MCDM problem. In Model [4], a new class of fuzzy set called probabilistic hesitant fuzzy linguistic set is defined and used in MCGDM problem. In Model [2], Model [3] and Model [4] a real case study of stock selection problem has been taken for MCGDM methods. Model [5] is trapezium cloud based TOPSIS method for MCGDM and is used to rank different stocks on the basis of some financial criteria. Model [6] is Choquet integral based TOPSIS method in interval-valued intuitionistic hesitant fuzzy uncertain linguistic environment and deals with the situations where decision makers have hesitation in providing their preferences over objects in decision making. All developed models (Model [1-6]) are implemented on real life problems of stock selection problem, candidate selection problem and ranking of the organizations. To examine the validity of ranking results validity test of all models (Model [1-6]) under certain test criteria are also done along with comparative analysis. Simulation study of Model [2], Model [3] and Model [4] with similar real data set of seven organizations provides their different ranking. To further compare rankings of the organizations: Model [2-4] are implemented in portfolio selection problems to analyze portfolio risk and return.ThesisItem Open Access Interval-valued intuitionistic hesitant fuzzy and uncertain linguistic based multi-criteria group decision making methods(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-01) Joshi, Dheeraj; Sanjay KumarMulti-criteria group decision making (MCGDM) has various applications in many real life problems of banking, data mining, water resource location, human resource development, resource allocation and portfolio selection. The present research work mainly focus on development and implementation of MCGDM/MCDM models in the environment of uncertainty and hesitation. In this study, 6 different models of MCGDM methods are developed in interval-valued intuitionistic hesitant fuzzy (IVIHF), probabilistic hesitant fuzzy (PHF) and interval-valued intuitionistic hesitant fuzzy linguistic and uncertain linguistic environment. These models are based on entropy measure, distance and similarity measures. Cloud model based TOPSIS method and Choquet integral based TOPSIS methods are also developed to consider both randomness, fuzziness and interaction phenomenon in MCGDM problems. Model [1] is IVIHF entropy based MCGDM method. In this model criterion weights are determined using IVIHF entropy. Model [2] is probabilistic intuitionistic fuzzy information based TOPSIS method. In Model [3], a series of distance and similarity measures for probabilistic hesitant fuzzy set is defined and used in MCDM problem. In Model [4], a new class of fuzzy set called probabilistic hesitant fuzzy linguistic set is defined and used in MCGDM problem. In Model [2], Model [3] and Model [4] a real case study of stock selection problem has been taken for MCGDM methods. Model [5] is trapezium cloud based TOPSIS method for MCGDM and is used to rank different stocks on the basis of some financial criteria. Model [6] is Choquet integral based TOPSIS method in interval-valued intuitionistic hesitant fuzzy uncertain linguistic environment and deals with the situations where decision makers have hesitation in providing their preferences over objects in decision making. All developed models (Model [1-6]) are implemented on real life problems of stock selection problem, candidate selection problem and ranking of the organizations. To examine the validity of ranking results validity test of all models (Model [1-6]) under certain test criteria are also done along with comparative analysis. Simulation study of Model [2], Model [3] and Model [4] with similar real data set of seven organizations provides their different ranking. To further compare rankings of the organizations: Model [2-4] are implemented in portfolio selection problems to analyze portfolio risk and return.ThesisItem Open Access Intuitionistic fuzzy and hesitant fuzzy sets based time series forecasting methods(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2017-12) Bisht, Kamlesh; Sanjay KumarIn the present research work, various time series forecasting methods using intuitionistic fuzzy, hesitant fuzzy and dual hesitant fuzzy sets are developed to address issue of non stochastic uncertainty and non-stochastic hesitation. These methods are presented in form of various models. Model [1] and Model [4] are computational algorithm based higher order fuzzy time series forecasting models which are based on intuitionistic fuzzy and hesitant fuzzy respectively. Model [2] and Model [3] use hesitant fuzzy set to handle hesitancy in fuzzy time series forecasting. In the present research work, methodology of hesitant fuzzy time series forecasting method is also developed and presented in Model [5]. Model [6] is intuitionistic fuzzy time series forecasting model which is based on dual hesitant fuzzy set. Model [2], Model [3], Model [5] and Model [6] use max-min composition operation. Performance of these developed models over existing fuzzy time series and intuitionistic fuzzy time series forecasting methods is verified by implementing them on two time series data of University of Alabama and SBI share price. The outperformance of all models is tested using RMSE and AFER error measures. Validity of the developed models id tested using correlation coefficients, tracking signal, evaluation parameter and performance parameters. Superiority of developed models is also tested using two tailed t-test at the confidence level 1% and 5%. In forecasting enrollments of University of Alabama, the performance of Model [4] in terms of both RMSE and AFER is found better than model [1], Model [2], Model [3], Model [5] and Model [6]. In forecasting share prices of SBI, the performance of Model [6] in terms of both RMSE and AFER is found better than Model [1], Model [2], Model [3], Model [4] and Model [5]. In forecasting enrollments of University of Alabama, Model [1] outperforms over Model [2] but its performance is equally good as of Model [3], Model [4], Model [5] and Model [6]. Model [2] outperforms over Model [4] and Model [5] but its performance is good as Model [3] and Model [6]. Model [3] performs equally good as Model [4], Model [5] and Model [6]. Model [4] outperforms over Model [6] but its performance is good as Model [5]. Model [5] is equally good in performance as the Model [6]. In forecasting SBI share prices, Model [1] outperforms over Model [2], Model [3] but its performance is good as Model [4], Model [5]. Model [2] outperforms over Model [4], Model [5] and Model [6] but its performance is good as Model [3]. Model [3] outperforms over Model [4], Model [5] and Model [6]. Model [4] performed equally good as Model [5] and Model [6]. Model [5] outperforms over Model [6]. All developed models not only handle the non-stochastic uncertainty and hesitation but also enhance the accuracy in forecasted enrollments and financial time series data of SBI share price.
- «
- 1 (current)
- 2
- 3
- »