@upes.ac.in
Assistant Professor (Senior Scale), School of Computer Science
University of Petroleum & Energy Studies
System integration, optimization, and performance.
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Surendra Kumar Shukla, Upendra Dwivedi, and Gagan Deep Singh
AIP Publishing
Gagan Deep Singh, Vikas Tripathi, Ankur Dumka, Rajkumar Singh Rathore, Mohit Bajaj, José Escorcia-Gutierrez, Nojood O. Aljehane, Vojtech Blazek, and Lukas Prokop
Elsevier BV
Gaurica Puri, Abhiram Varanasi, Gagandeep Singh, Harshit Agarwal, Ravi Tomar, and Tanupriya Choudhury
Springer Nature Singapore
Surendra Kumar Shukla, Upendra Dwivedi, Gagan Deep Singh, Ankur Dumka, and Bhasker Pant
IEEE
COVID 19 has created chaos in the world. It has affected every individual’s life including political opinion, social life, and economic conditions. The researchers are interested in finding out the pinnacle and slow down points in every phase of covid 19. The said fact is supposed to be helpful for government and non-government organizations to make health related decisions in a better manner. Further, the government can utilize their resources effectively with less affecting the economic activity. In this research work, we are examining the Covid 19 situation in India using the data available in public domains. An exploratory data analysis has been carried out on Covid 19 data to get more understanding of pandemic. Exploratory Data Analysis (EDA) shows that Covid 19 cases are widespread in Indian states and union territories. The state’s populations and resources have a significant impact on Covid 19 status. The states having more populations are suffering with many covid cases compared to smaller states with less populations
Surendra Kumar Shukla, Kireet Joshi, Gagan Deep Singh, and Ankur Dumka
IEEE
World's economy is driven by the stock market. Investors want to gain a reasonable profit by putting their valuable wealth in suitable stocks thus residing in a secure and win-win situation. Stock market movement is a critical concern which decides the profit or loss for the customers. Fundamental behind market movement is identified as time series. Thus, time series prediction could insist investors to design a suitable strategy during the investments to overcome the risk of erroneous investments. Therefore, a LSTM based model which works with the principle of time series has been adopted in this research work to predict stock prices. Furthermore, recurrent oriented Short-Term Long Memory (LSTM) algorithm has been developed and is employed for predicting the stock price of a company based on the historical prices available. And, next 30 days stocks were predicted. The proposed algorithm is verified with the Apple stock data (AAPL). The obtained results are analyzed through training RMSE (root mean squared error) and the test RMSE. Compared to the related stock prediction approaches, the proposed LSTM based algorithm performs better than its counterparts and shows definite accuracy in predicting the stock prices.
Gagan Deep Singh, Jatender Sharma, and Tarandeep Kaur Bhatia
IEEE
The work presented in this paper is the outcome of the study that was based on the online surveys conducted at UPES for the improvement of IT related services. First, the qualitative approach has opted in which brainstorming sessions are done and questions for the survey are collected. The second approach is applied based on quantitative research in which a questionnaire is prepared and circulated to end-user of IT services at “The University of Petroleum and Energy Studies”, UPES, Dehradun. The survey is circulated to the staff and faculties of UPES for feedback. The biannual survey is done in the first month of the year 2021 and then repeated after improving the IT services, second survey was conducted in July 2021. A methodology is proposed and adopted to validate the study. The statistical techniques are applied and based on this satisfaction index SI is computed for both the surveys. The SI comparison of both surveys shows that the SI value has been improved with a 0.13 index in the second survey. This concludes that these types of survey-based studies are very important for organizations that have deployed IT-based services in their organizations. This paper also suggests that the SI value is based on the end-user and it always hinders the performance of the users in their day-to-day tasks. So, performance evaluation of end-user satisfaction plays an integral role in the development of any organization.
Gagan Deep Singh, Anil Kumar, and Ankur Dumka
Springer Nature Singapore
Gagan Deep Singh, Manish Prateek, Sunil Kumar, Madhushi Verma, Dilbag Singh, and Heung-No Lee
Institute of Electrical and Electronics Engineers (IEEE)
Vehicular Adhoc Networks (VANETs) are used for efficient communication among the vehicles to vehicle (V2V) infrastructure. Currently, VANETs are facing node management, security, and routing problems in V2V communication. Intelligent transportation systems have raised the research opportunity in routing, security, and mobility management in VANETs. One of the major challenges in VANETs is the optimization of routing for desired traffic scenarios. Traditional protocols such as Adhoc On-demand Distance Vector (AODV), Optimized Link State Routing (OLSR), and Destination Sequence Distance Vector (DSDV) are perfect for generic mobile nodes but do not fit for VANET due to the high and dynamic nature of vehicle movement. Similarly, swarm intelligence routing algorithms such as Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) routing techniques are partially successful for addressing optimized routing for sparse, dense, and realistic traffic network scenarios in VANET. Also, the majority of metaheuristics techniques suffer from premature convergence, being stuck in local optima, and poor convergence speed problems. Therefore, a Hybrid Genetic Firefly Algorithm-based Routing Protocol (HGFA) is proposed for faster communication in VANET. Features of the Genetic Algorithm (GA) are integrated with the Firefly algorithm and applied in VANET routing for both sparse and dense network scenarios. Extensive comparative analysis reveals that the proposed HGFA algorithm outperforms Firefly and PSO techniques with 0.77% and 0.55% of significance in dense network scenarios and 0.74% and 0.42% in sparse network scenarios, respectively.
Himanshi Vig, Gagan Deep Singh, Tanupriya Choudhury, and Tanmay Sarkar
IEEE
The privacy of transmitting data in the era of super-fast internet and high-volume data generation has become a tough job. To solve this problem, the combination of steganography and visual cryptography together is considered. Steganography is the process of concealing some data inside any form of digital data. The proposed method takes the original image and the secret message is encoded in its LSB (least significant bits), where genetic algorithm modifies the pixel values of encrypted image, therefore making the secret of the message tough to crack and then secretly hides the data in the original image and it is detected after undergoing visual cryptography which helps to encrypt visual information so that on decryption, data or the information appears as an image. The aim of this model is to design an efficient and secured algorithm for better reliability, security and efficiency for a secret message.
Gagan Deep Singh, Himanshi Vig, and Anuj Kumar
IEEE
India's population is currently second-highest and still growing every year. This leads to a huge concern, including the number of job opportunities, poverty, health, and economics of the nation being the significant factors to be considered. Governments in various regions have been putting in their best efforts to resolve these problems and provide a feasible solution. In this paper, the growing population in Uttarakhand and its impact on natural resources are analyzed and the trends of poverty, unemployment, and growth in the state are evaluated using a machine learning and data visualization approach. The quantitative evaluations on the association between education, income inequality, and mortality are provided by analyzing these aspects. A resource is any earth's utility that people require, and its requirement changes with time. Hence, studying the resources and their usage will enhance the economy and convert non-productivity to productivity, leading to the maintenance of a balanced and stable economy. In this paper, the Gradient Boosting Classifier Model is used that measures the highest accuracy of 85.78%, compared to the accuracy of existing works taking the census data (2011) from censusindia.gov.in/.
Gagan Deep Singh, Sunil Kumar, Hammam Alshazly, Sahar Ahmed Idris, Madhushi Verma, and Samih M. Mostafa
Hindawi Limited
The vehicular ad hoc network (VANET) has traditional routing protocols that evolved from mobile ad hoc networks (MANET). The standard routing protocols of VANET are geocast, topology, broadcast, geographic, and cluster-based routing protocols. They have their limitations and are not suitable for all types of VANET traffic scenarios. Hence, metaheuristics algorithms like evolutionary, trajectory, nature-inspired, and ancient-inspired algorithms can be integrated with standard routing algorithms of VANET to achieve optimized routing performance results in desired VANET traffic scenarios. This paper proposes integrating genetic algorithm (GA) in ant colony optimization (ACO) technique (GAACO) for an optimized routing algorithm in three different realistic VANET network traffic scenarios. The paper compares the traditional VANET routing algorithm along with the metaheuristics approaches and also discusses the VANET simulation scenario for experimental purposes. The implementation of the proposed approach is tested on the open-source network and traffic simulation tools to verify the results. The three different traffic scenarios were deployed on Simulation of Urban Mobility (SUMO) and tested using NS3.2. After comparing them, the results were satisfactory and it is found that the GAACO algorithm has performed better in all three different traffic scenarios. The realistic traffic network scenarios are taken from Dehradun City with four performance metric parameters including the average throughput, packet delivery ratio, end-to-end delay, and packet loss in a network. The experimental results conclude that the proposed GAACO algorithm outperforms particle swarm intelligence (PSO), ACO, and Ad-hoc on Demand Distance Vector Routing (AODV) routing protocols with an average significant value of 1.55%, 1.45%, and 1.23% in three different VANET network scenarios.
Today’s era is of smart technology, Computing intelligence and simulations. Many areas are now fully depended on simulation results for implementing real time workflow. Worldwide researchers and many automobile consortium are working to make intelligent Vehicular Ad hoc Network but till yet it is just a theory-based permutation. If we take VANET routing procedures then it is mainly focussing on AODV, DSDV and DSR routing protocols. Similarly, one more area of Swarm Intelligence is also attained attention of industry and researchers. Due the behavior of dynamic movement of vehicle and ants, Ant Colony Optimization is best suited for VANET performance simulations. Much of the work has already done and in progress for routing protocols in VANET but not focused on platooning techniques of vehicle nodes in VANET. In our research idea, we came up with a hypothesis that proposes efficient routing algorithm that made platooning in VANET optimized by minimizing the average delay waiting and stoppage time. In our methodology, we have used OMNET++, SUMO, Veins and Traci for testing of our hypothesis. Parameters that we took into consideration are end-to-end delay as an average, packet data delivery ratio, throughput, data packet size, number of vehicle nodes etc. Swarm Intelligence has proved a way forward in VANET scenarios and simulation for more accurate results. In this paper, we implemented Ant Colony Optimization technique in VANET simulation and proved through results that if it integrates with VANET routing scenarios then result will be at its best.
R. S. Bhowmick, A. Kumar, G. D. Singh, and S. Kumar
Copernicus GmbH
<p><strong>Abstract.</strong> Remote sensing data and satellite images are broadly used for land cover information. There are so many challenges to classify pixels on the basis of features and characteristics. Generally it is pixel classification that required the count of pixels for certain area of interest. In the proposed model, we are applying unsupervised machine learning to classify the content of the input images on the basis of pixels intensity. The study aims to compare classification accuracy of different landscape characteristics like water, forest, urban, agricultural areas, transport network and other classes adapted from CORINE (Coordination of information on the environment) nomenclature. To fulfil the aim of the model, accessing data from Google map using Google static API service which creates a map based on URL parameters sent through a standard HTTP (Hyper Text Transfer Protocol) request and returns the map as an image which can be display on any graphical user interface platform. The Google Static Maps API returns an image either in GIF, PNG or JPEG format in response to an HTTP request. To identify different land cover/use classes using k-means clustering. The model is dynamic in nature that describes the clustering as well formulate the area of the concerned class or clustered fields.</p>
Gagan Deep Singh, Ravi Tomar, Hanumat G. Sastry, and Manish Prateek
Springer Singapore
The vehicular ad hoc network (VANET) is an ad hoc network system based on the concept of mobile ad hoc network (MANET) in which nodes (vehicle) that are being connected with each other by wireless technologies. But due to the non deterministic mobility behavior and high velocity of automobiles, the topology is unpredictable. Such types of system can work independently and can also be interconnected through internet with in its infrastructure. The system characteristics such as multi-hop paths, node mobility, huge network, device heterogeneity, congestion and bandwidth are the constraints in designing the routing protocols for VANET. The present routing protocols that have been deployed for MANET are used to test the VANET accuracy and performance. Present research efforts are strongly emphasized on designing a novel routing algorithm and its implementations. Recent VANET research are majorly focused on predefined areas such as broadcasting and routing, security, quality of service (QoS) and infotainment with information dissemination during emergencies. In this paper authors present a detailed review of wireless standards used in VANET with a number of trials in VANET and its deployment in many of the developed countries. As a conclusion we conceptualized some of the issues and research challenges in VANET that had not yet addressed so that industry can opt for widespread adoption of scalable, reliable, secure and robust VANET protocols, architectures services and technologies and enable the ubiquitous deployment of it.