Loading...
Govind Ballabh Pant University of Agriculture and Technology, Pantnagar
After independence, development of the rural sector was considered the primary concern of the Government of India. In 1949, with the appointment of the Radhakrishnan University Education Commission, imparting of agricultural education through the setting up of rural universities became the focal point. Later, in 1954 an Indo-American team led by Dr. K.R. Damle, the Vice-President of ICAR, was constituted that arrived at the idea of establishing a Rural University on the land-grant pattern of USA. As a consequence a contract between the Government of India, the Technical Cooperation Mission and some land-grant universities of USA, was signed to promote agricultural education in the country. The US universities included the universities of Tennessee, the Ohio State University, the Kansas State University, The University of Illinois, the Pennsylvania State University and the University of Missouri. The task of assisting Uttar Pradesh in establishing an agricultural university was assigned to the University of Illinois which signed a contract in 1959 to establish an agricultural University in the State. Dean, H.W. Hannah, of the University of Illinois prepared a blueprint for a Rural University to be set up at the Tarai State Farm in the district Nainital, UP. In the initial stage the University of Illinois also offered the services of its scientists and teachers. Thus, in 1960, the first agricultural university of India, UP Agricultural University, came into being by an Act of legislation, UP Act XI-V of 1958. The Act was later amended under UP Universities Re-enactment and Amendment Act 1972 and the University was rechristened as Govind Ballabh Pant University of Agriculture and Technology keeping in view the contributions of Pt. Govind Ballabh Pant, the then Chief Minister of UP. The University was dedicated to the Nation by the first Prime Minister of India Pt Jawaharlal Nehru on 17 November 1960.
The G.B. Pant University is a symbol of successful partnership between India and the United States. The establishment of this university brought about a revolution in agricultural education, research and extension. It paved the way for setting up of 31 other agricultural universities in the country.
Browse
50 results
Search Results
ThesisItem Open Access A COMPREHENSIVE APPLICATION OF ARTIFICIAL INTELLIGENCE BASED HYBRID DEEP LEARNING IN IMAGE CLASSIFICATION(G. B. Pant University of Agriculture & Technology, Pantnagar-263145, 2023-02) Pandey, Ankita; Kumar, ArunArtificial intelligence refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term may also be applied to any machine that exhibits traits associated with a human mind such as learning and problem-solving. Deep learning drives many artificial intelligence applications and services that improve automation, performing analytical and physical tasks without human intervention. Real-world deep learning applications are a part of our daily lives, but in most cases, they are so well-integrated into products and services that users are unaware of the complex data processing that is taking place in the background. The applications for artificial intelligence are endless. In light of the foregoing facts, the present research is centered to propose a comprehensive application of hybrid deep learning models based on artificial intelligence techniques which include transfer learning, deep learning, machine learning, and fuzzy inference system. In this study, six models are introduced. Model [1] presents an effective facial emotion intensity classifier by fusion of the pre-trained deep architecture and fuzzy inference system. The pre-trained architecture VGG16 is used for basic emotion classification and it predicts emotion class with the class index value. By class index value, images are sent to the corresponding Fuzzy inference system for estimating the intensity level of detected emotion. This fusion model effectively identifies the facial emotions (happy, sad, surprise, and angry) and also predict the 13 categories of emotion intensity. Model [2] proposes a casting fault detector to automate the inspection process in casting production. two transfer learning-based convolution neural networks and one lightly structured convolution neural network are created and verified for detecting manufacturing flaws in submersible pump impellers. Model [3] investigate various fusion of deep learning-based feature extractors and machine learningbased classifiers for differentiating two subtypes Adenocarcinoma and Squamous cell carcinoma of nonsmall cell lung cancer. This research generates seven automated integrated models by using five deep feature extractors: InceptionResNetV2, InceptionV3, Xception, VGG16 and, VGG19 and three classifiers: Support vector machine, XGBoost, and Fully connected neural network. Then the most effective optimal model is selected via comparative study and performance. Model [4] construct three transfer learning-based classifiers Binary, Benign, and Malignant. The Binary classifier classifies breast cancer as benign and malignant, the Benign classifier classifies four sub-classes of benign cancer and the Malignant classifier classifies four sub-classes of malignant cancer. All three classifiers are individually trained for their corresponding classification task and then integrated to give the outcome of the combined proposed system. As a result, the proposed system automatically classifies cancer into its major class and then sub-class with greater accuracy. The proposed breast cancer classification is performed on BreaKHis and BACH data. Model [5] develop an automated optimal novel model for knee osteoporosis classification through a comprehensive examination held on various deep learning architectures. This examination starts with the transfer learning model (ResNet50, MobileNet, ResNet50V2, and Xception) and then extended to a concatenated version of the top two models MobileNet and ResNet50V2 based on performance. Finally, on the basis of critical examination, an optimal novel CNN inspired by MobileNet and ResNet50V2 is invented. For classification, FCNN optimized by random search technique is employed. Model [6] develop the Cascade network to identify diabetic retinopathy on the most challenging data IDRiD in literature. The Cascade network extracts the multiscale dense features through the task specific novel CNN and Of-the-self CNN Xception. The proposed model first time in literature construct an architecture to perform combinedly binary and multigrading of DR and DME in a single input. The present study implements a limited data merging strategy with the most relevant DDR data images. To find the optimal network, this research also investigates the various network architectures and Cascade networks with different Of-the-self CNN.ThesisItem Open Access Forecasting and multi-criteria decision making for trading and investment in stock market using soft computing techniques(G. B. Pant University of Agriculture and Technology, Pantnagar, 2022-07) Bisht, Kiran; Arun KumarDuring the last decades the globalization of economies, intensifying competition among firms, financial institutions and organizations as well as the rapid economic, social and technological changes, have led to an increasing uncertainty and instability in the financial market. Within this context, the importance of making efficient financial decisions while handling complexities has increased. Soft computing covers a wide range of techniques offering tolerance to the presence of uncertainty and imprecision, making them ideal for modeling financial decisions. In light of the foregoing facts, the present research is centered to propose financial decision making models based on soft computing techniques which include fuzzy sets, neural networks, and evolutionary algorithms. In this study, seven models are introduced. Model [1] presents multi-objective financial trading systems based on deep reinforcement learning. The systems have been designed to give signals (buy, hold or sell) in the live market in order to get maximum return with minimum risk. Reward-based deep reinforcement learning architectures have been used to simulate the models for gaining better results. Model [2] proposes a financial time series forecasting method for stock selection. Fuzzy time series forecasting procedure using fuzzy c-means clustering and two deep learning architectures (SVM and MLP) has been developed for forecasting daily stock prices. Portfolio construction based on stock prices and ACO algorithm for portfolio optimization is derived. Model [3] considers the concept of diversification addressed by modern portfolio theory and suggests a hybrid MCDM technique for diverse stock selection. Neutrosophic base-criteria method has been devised for criteria weight assessment. The concept of correlation coefficient between assets with PROMETHEE partial ranking are merged for finding realistic relationship between the stocks to construct a diversified and profitable portfolio. PSO algorithm for optimizing Portfolio’s Sharpe ratio with rank constraint has been derived. Model [4] provides an effective portfolio construction method based on sector analysis. Dempster-Shafer theory and Granger causality test have been employed for indentifying strong and diverse sector of economy. Construction of portfolio by picking leading stocks of strong and diverse sectors and its optimization using deep recurrent neural network is presented. Model [5] offers a stock selection method integrating the concerns of a novice investor and a stock market specialist. An integrated framework unifying fuzzy delphi method, fuzzy base-criterion method and Dempster-Shafer theory has been developed for assessing important criteria, their weights and reliable ranking of stocks. Portfolio optimization is done using LSTM embedded deep recurrent neural network. Model [6] introduces fuzzy TOPSIS and evidence theory based intraday stock selection procedure. To counter the ambiguity and conflict in intraday data belief divergence measure has been employed for credible ranking of intraday stocks one day before trading. Model [7] presents an MCDM method hybridizing MEREC and CoCoSo method through some specific modifications to their main structures in context to its application in ranking stocks. The method has been developed in neutrosophic environment to cope up ambiguity and inference of decision making data. Parabolic measure has been used as performance measure in MEREC method to reduce its complexity. All the present models have been implemented on real data of Indian stock market (NSE and BSE) and detailed analysis have been done to verify their practicality.ThesisItem Open Access Performance evaluation of wireless/mobile communication systems for real-time applications(G.B. Pant University of Agriculture & Technology, Pantnagar, Distt: Udham Singh Nagar, Uttarakhand. PIN : 263145, 2022-07) Mittal, Abhinav; Pal, A.K.With the rise of smart wireless devices equipped with multi-radio interfaces, there has been increased demand for real-time video traffic. Real-time transport of live video or stored video is the predominant part of real-time multimedia. Video streaming is the main approach for delivery of stored video over wireless networks where the streaming video is partitioned into packets and played out simultaneously during video delivery. Multiple simultaneous associations with heterogenous networks can be allowed by multihoming support. In this study, we propose models based on adaptive probabilistic flow splitting multipath transmission scheme to dynamically assign the video traffic flow to different networks in response to the channel capacities available on the different networks. The essential characteristics of video traffic are taken into account, such as deterministic burst intervals, highly dynamic burst length, and batch arrivals of transmission packets. The PGF of packet delay and arbitrary moments are evaluated by probability generating function and z-transform method. QoS of video transmission delivery is analyzed on the basis of delay metrics such as average packet delay, delay jitter and delay outage probability. The numerical and simulations results demonstrate the effectiveness of our analysis framework and the performance gain of multipath transmission. Also, we have developed a queueing models for wireless communication using Aloha and OFDMA-Aloha. In this model, we have derived an adaptive algorithm for Aloha and OFDMAAloha. The performance of developed model has been evaluated in terms of mean access delay and mean packet delay of the two MAC Protocols. The present study may be helpful in applied scientific fields like performance enhancement of video streaming, multipath transmission, flow splitting and OFDMA-Aloha.ThesisItem Open Access A study of some boundary layer hybrid nanofluid flow and heat transfer(G.B. Pant University of Agriculture and Technology, Pantnagar, District Udham Singh Nagar, Uttarakhand. PIN - 263145, 2022-07) Moh Yaseen; Manoj KumarThe present study deals with the heat transfer of hybrid nanofluid and nanofluid flow. MoS2-SiO2/water hybrid nanofluid and MoS2/water nanofluid flow have been studied in the current models. This study investigates the boundary layer flow of hybrid nanofluids past the solid bodies of various geometries (parallel disks, stretching or shrinking sheet, slendering surface, and a flat plate). The steady laminar boundary layer flow of hybrid nanofluids is studied under various physical conditions and boundary conditions. The hybrid nanofluid flows are modeled with the help of the equation of mass, equation of momentum, equation of energy, and equation of species transport. Hybrid nanofluid offers a wide range of applications. The hybrid nanofluids predict better thermal efficiency and heat transfer due to the improved thermal performance. This thesis comprises of five chapters. The initial chapters consist of essential notions, definitions and literature related to boundary layer theory. The group of similarity transformation has been utilized to convert the principal equations into the non-dimensional set and the Runge-Kutta-Fehlberg method along with shooting and the built-in function "bvp4c" in MATLAB is employed to solve them. In along with the finding of the study, the literature used in the course of the study has been referred to under the section of literature cited. This study can be beneficial in learning about metal medicine, wires, glass fiber production, different fields of chemistry, engineering, and industry because all of them witness the production of heat and deal with heat transfer phenomena.ThesisItem Open Access Some fixed point theorems in intuitionistic fuzzy metric space with certain contractive conditions(G.B. Pant University of Agriculture and Technology, Pantnagar, District Udham Singh Nagar, Uttarakhand. PIN - 263145, 2022-09) Dimri, Ritikesh; Sanjay KumarIn the present research work fixed point theorems in complete fuzzy metric space due to Wairojjana et al. (2015) and Patir et al. (2018) are extended to complete intuitionistic fuzzy metric space with certain contractive conditions using altering distance functions. The work is presented in five chapters. Chapter one focuses on the basic preliminaries and definitions related to metric spaces, fuzzy metric spaces, intuitionistic fuzzy metric spaces, contractive mapping, altering distance function and fixed point. Chapter two presents a review of the literature which is studied during the proposed work. In chapter three definition of increasing and decreasing altering distance function is given.Fixed point theorems due to Wairojjana et al. (2015) and Patir et al. (2018) for complete fuzzy metric space extented to complete intuitionistic fuzzy metric spaceare proved in this chapter. In chapter four, the theorems proved are supported by few examples. Chapter five summarizes the work in brief along with the conclusions. The literature used in the course of the study has been referred under the section of literature citedThesisItem Open Access Binary classification of Pneumothorax in chest X-Ray images using deep neural network(G.B. Pant University of Agriculture and Technology, Pantnagar, District Udham Singh Nagar, Uttarakhand. PIN - 263145, 2022-08) Kaur, Manjeet; Arun KumarCurrently, lung diseases are extremely common throughout the globe and few of which include chronic obstructive pulmonary disease, pneumonia, pneumothorax, tuberculosis etc. Air in the pleural cavity is thought to be as “pneumothorax". This is a state when the lung surface or chest wall is breached, allowing air to enter the pleural space and causing the lung to collapse, it is a serious situation and might be life-threatening. Chest radiographs are the foremost significant and extensively used diagnostic techniques to detect thoracic or lung diseases among various medical imaging technologies. Pneumothorax can be diagnosed by chest X-rays, CT scans or ultrasound techniques but chest X-ray is the most often used accessible radiological method for screening and diagnosing thoracic diseases. The diagnosis from the chest X-Ray can be of great efficiency and time saving if done through automated systems instead of manual image reading. Tremendous research works are being conducted to develop reliable automatic diagnostic systems for detecting diseases within the chest radiographs. Artificial Intelligence (AI) tools have proven to be effective in optimizing the medical industry. Several framework-supported computing techniques have been proposed for the automated identification of pneumothorax from chest radiographs. Numerous models for pneumothorax automated diagnosis are certainly available. In this study, we have taken chest X-ray images and then used the Deep Transfer Learning technique along with Machine Learning to detect the presence or absence of pneumothorax in chest X-ray images. We have aggregated the unique and computational attributes of Deep Learning and Machine Learning. We have used the Deep Transfer Learning technique which is a pre-trained model that is a Residual Network for image feature extraction and the Support Vector Machine (SVM) algorithm which creates the best decision boundary known as “Hyperplane” to classify data points, is a Machine Learning model used for pneumothorax binary classification. To achieve effective outcomes, a balancing data technique with augmentation is used to create a balance between the training and validation dataset, as well as an automatic adjusting learning rate technique called "ReduceLROnPlateau" to monitor validation loss and obtain optimal learning rates. As an implementation tool, “Google Colab” is used. In our proposed method model, it outperforms in terms of metrics that include accuracy, recall (Sensitivity), f-1 score, precision, loss, and AUC(Area Under The Curve). The performance of the framework is evaluated on a dataset that is available on “Kaggle” which is chest X-ray images. This research work has set a new record with a good performance by achieving state-of-the-art results as 0.8831 in terms of AUC and 0.4375 in terms of loss. The Precision, Recall, and f-1 score is obtained as 0.78, 0.81, and 0.794 respectively.ThesisItem Open Access Markov models for reliability and cost analysis of repairable systems incorporating maintenance and inspections(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2022-01) Pant, Himani; Singh, S.B.The present research is based on the development of reliability models incorporating maintenance and inspection policies and studying them utilizing a Markov process approach. In this study, eight different models have been developed. Model 1 examines a maintained system with numerous failure modes that is subjected to periodic inspection using a calendar-based inspection strategy. The system is renewed at each of the inspection. The limiting average and point availability theorems for the model are deduced. Model 2 provides a model for a maintained k-out-of-n:G system with several failure modes that must be inspected on a periodic basis. During the inspection, the system is renewed if discovered to be operating or failed. Theorems on limiting and point availability and long-run average cost rate (LRACR) for the system are developed. Model 3 presents a three-state (normal, degraded, and entirely failed) and newly introduced k/r-out-of-n system with a repair strategy that is periodically examined. For the suggested model, theorems on LRACR and limiting and point availability are derived. Model 4 investigates a system with hidden defects that is subjected to sequential examination. When a system breakdown is detected, perfect repairs are carried out at random times. Propositions on point and limiting availability and system's LRACR are obtained. Model 5 examines a single-unit system that is susceptible to degradation and shocks. The system has three states: normal, degraded, or failed. Inspections are undertaken progressively at sequential times. When a total or partial failure is identified, perfect repairs are done. The reliability, availability (point and limiting) and the LRACR of the system are computed. Model 6 looks at broad expressions for limiting availability and LRACR of a single-unit randomly failing system with alternating phases of operation and rest. System undergoes imperfect periodic inspections. Furthermore, it is assumed that inspection and maintenance time is non-negligible, and that corrective repairs are perfect. Model 7 analyses the availability (point and limiting) and cost of a system examined on a periodic basis and incorporating numerous failure modes and a downtime limit concept. Model 8 looks into an optimal design problem for a repairable series parallel system. The system's components are prone to breakdown, with various repair teams assigned to each subsystem. Four types of interdependence are explored. The goal of the task was to identify the ideal number of system components and repair teams that minimises the system cost. The PSO technique with dynamic parameters is used to find the ideal structure. All the presented models are demonstrated by appropriate illustrative examples.ThesisItem Open Access Stochastic alternating renewal processes models for reliability analysis of multi-component systems incorporating queuing delay(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-10) Agarwal, Shweta; Singh, S.B.In the real-world scenario, most of the systems are comprised of more than one component and hence it becomes inevitable to estimate the reliability and availability of multi-component systems. Also, in most of the complex repair models the system fluctuates between up-state and down-state and the failure is revealed at the time of inspection. Keeping the aforementioned facts in view, the present research is centered to propose the reliability and availability models on the basis of derived proposition, Markov process, renewal theory. In this study, six models are introduced. Model [1] aims to propose a notion of alternating renewal process to mathematically model a multi-failure complex system to develop its availability and maintenance measures. In the study, M/E2/1 queueing model with infinite waiting space during service times of components has been worked out under FCFS discipline. The primary objective of the paper is about obtaining the system’s reliability, availability, and the optimal interval period with minimum maintenance cost. Model [2] analyzes the reliability characteristics of batch service queuing system with a single server model which envisages Poisson input process and exponential service times under First Come First Served (FCFS) queue discipline. With the help of renewal theory and stochastic processes the model has been designed to discuss the reliability and its characteristics. Model [3] considers the reliability characteristics of a multi-component system envisaged with Poisson arrivals and analyzed service in bulk. In the general bulk service rule the repair process is initialized when a threshold of “a” number of failed components is reached with the maximum capacity “b”. Considering the above facts reliability and availability expressions of the considered model has been derived. Model [4] treats a risk system in which at the occurrence of failure due to any of the mode of failures the failed component joins a M/G/1 queue. After the completion of the repair, whenever the serviceman becomes idle it starts an exponential classical vacation in which the serviceman does not serve the failed unit. Incorporating the above cited facts, expressions for estimating the reliability and its other measures are derived. Model [5] investigates the reliability and other measures related to it for a periodically inspected system. Whenever any of the components gets failed it joins the M/G/1 queue with a waiting threshold. While if the service of the failed components is commenced in the threshold amount of time, then it remains to its completion. Various reliability measures like availability, maintenance, long run maintenance cost rate have been estimated for the considered system. Model [6] analyses a periodically inspected system subject to imperfect maintenance policy. The considered system is inspected and maintained periodically and passes through a fixed number of imperfect repairs before being replaced. Incorporating the given facts, the reliability of the periodically inspected system is evaluatedThesisItem Open Access Flow and heat transfer in hybrid nanofluid flow over a vertical plate with heat absorption and viscous dispersion(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-07) Gumber, Priya; Manoj KumarPresent work intends to address the issue of flow and heat transfer in nanofluids over a vertical plate with heat absorption and viscous dispersion. The various flow regime conditions including different physical phenomenon like suction/injection effect, volume fraction, Eckert number, heat generation/ absorption and shape parameter etc. have been incorporated, to study their effects on velocity, temperature and micro- rotation profiles. The physical quantities of interest viz. skin friction coefficient, Nusselt number have also been calculated and their analysis is included in this study. The study presented in the thesis comprises of five chapters. The first chapter is aimed to fulfill the basic need of introducing the various concepts and foundation needed for fluid mechanics. Chapter two throw light on majority of passed research work related with the present work. Chapter three covers the mathematical formulation of the problem and its detailed description. A proper description of used methodology, together with the details of the numerical solution is also presented. Chapter four describes the result and discussion of the considered problem taken in chapter three. The work has been summarized in chapter five. In 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 to applied scientific fields and different branch of engineering and applied mathematics.