Sanjeev Rana

Followers

Following

Public Views

Ami Pedahzur

University of Haifa

David Seamon

Kansas State University

Armando Marques-Guedes

UNL - New University of Lisbon

Jon R Sayers

The University of Sheffield

Jeffrey Townsend

Yale University

Andrew N Liaropoulos

University of Piraeus

Rohit De

Yale University

Rui Dias

Universidade de Coimbra

Journal of Computer Science IJCSIS

Dr. Matthew Crosston

Brown University

Interests

Uploads

Papers by Sanjeev Rana

Forest Fire Detection by using MESA2DA Clustering Protocol based on Artificial Intelligence Techniques

2023 International Conference on Smart Computing and Application (ICSCA)

An Optimized System for Sentiment Analysis using Twitter Data

Challenges and Opportunities for Deep Learning Applications in Industry 4.0

Progression in technology and innovation increases internet users, who post their perspectives on... more Progression in technology and innovation increases internet users, who post their perspectives on social media platforms regarding any product or service. It brings forth significant terms, i.e.,”feedback of users,” termed as sentiments and plays a substantial role for commercial organizations to analyze and find polarity related to their respective services. In Sentiment Analysis, the feature extraction phase is a crucial one that affects the entire process's processing. In the case of high dimensional Real- Time data, it leads to a sparse feature matrix and gives rise to steady processing. In this exploration work, we have proposed an Improved Optimized Feature Sentiment Classifier for Big Data (IOFSCBD) System, which deals with advancing the classifiers by giving improved values in each sort of dataset. Results show better execution of the Improved Optimized Feature Sentiment Classifier for Big Data system System.

Performance Analysis of Off-Line Signature Verification

Advances in Intelligent Systems and Computing, 2020

To reduce fraud in financial transactions, signature verification is important for security purpo... more To reduce fraud in financial transactions, signature verification is important for security purposes. In this paper, an attempt has been made to analysis the performance of off-line handwritten signature verification using image-based features. Photocopies and scanned documents are considered as the best possible evidence in the situations when the original documents are either lost or damaged. Although the photocopies are the filtered images of original information and do not reproduce details as in the original documents. In this paper, combinations of four features, i.e., Average object area, mean, Euler number and area of signature image is used to verify the signature. Publically available database BHsig260 is used. In this database, two types of signature are available, i.e.,Bengali and Hindi. Proposed work shows that accuracy of Hindi off-line signature verification is 78.5% with sample size of 15 and accuracy of Bengali off-line signature verification is 69.1 with sample size of 20.

QoS Enabled Task Scheduling Approach in Cloud Computing as Per Service Level Agreement

Journal of Computational and Theoretical Nanoscience, 2020

Due to constraints along with profit margins in background, service provider’s sometime neglect t... more Due to constraints along with profit margins in background, service provider’s sometime neglect to feed essential services to their respective clients. Such compulsion raises the demand for efficient task scheduling that can meet multiple objectives. But without any prior agreement, again makes a casual approach. So this dispute can be addressed when competent scheduling executes right over the Service Level Agreement. It acts as hotspots to define set of rules to assure quality of service. At this time, there is a huge demand of SLA opted scheduling that can produce profitable results from provider’s and client’s as well. This article presents a fundamental approach that can be applied to existing scheduling techniques on the fly. Result shows drastic improvement in terms of average waiting time, average turnaround time without comprising provider’s cost margin at all along with fairness.

Comparative Analysis of Impact of Convolution and Optimize Features on Tweets Sentiment Classification

An Effective Integrity Verification Scheme for Ensuring Data Integrity in Cloud Computing

Innovations in Bio-Inspired Computing and Applications, 2021

Implementing a Multi-layer Job Scheduling Approach with Effective Load Balancing and Energy Saving over a Cloud

Proceedings of the 2018 10th International Conference on Information Management and Engineering, 2018

Initially the client server database is created on the cloud. The servers are hereby categorized ... more Initially the client server database is created on the cloud. The servers are hereby categorized according to their processing time, speed and RAMs. On the basis of these configurational parameters they are classified as higher, intermediate and lower priority servers. The clients are categorized on basis of job requests and are differentiated into three priority types; viz. high priority, middle priority and low priority depending upon the processing need (time) of the job requests. The client job requests of longer time duration will take more processing time and hence shall be sent to the highest priority (configuration) server. In this paper we present the multilayered job scheduling approach on basis of preferences for both the client and the server. A high priority job request is executed by higher configuration server while the lower tasks are accomplished by the lower configuration servers; that helps in energy saving. If the higher server has finished up with its assigned jobs; then job requests from lower server are migrated to the higher server; which leads to load balancing with effective resource allocation. The overall process has been best illustrated with help of example wherein all the servers will execute the jobs requests in stipulated time. This fast execution helps the servers to free themselves early and results in better energy efficiency.

Towards energy efficient multi layer job scheduling approach over a cloud network

2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017

Cloud computing is a technology that provides Information Technology as a service to its users. T... more Cloud computing is a technology that provides Information Technology as a service to its users. The clients/users can access the services from cloud environment through the internet and remote servers. Due to scarcity and large cost of cloud resources there is need for proper scheduling and allocation of cloud resources. The cloud resources must be allocated in efficient and effective way so that total cost of resources should be minimized. The cloud resources must be utilized in energy efficient methods. Scheduling algorithms are used for dispatching user tasks or jobs to a particular resource or data. This paper provides review of different cloud scheduling strategies used in cloud environment. It also provide introduction of proposed scheduling approach so that scarce resources of cloud environment are allocated in efficient, effective and economical way. The paper also provides scheduling by dividing the client requests into multi layer structure.

Feature Selection for Handwritten Signature Recognition Using Neighborhood Component Analysis

Advances in Intelligent Systems and Computing, 2020

Implementing job scheduling approach in cloud environment

2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017

Cloud Computing helps us to utilize the facilities of multiple applications such as web conferenc... more Cloud Computing helps us to utilize the facilities of multiple applications such as web conferencing, games, E-mail on the Internet. With cloud computing we can create and configure the applications online. It also helps us to customize the applications according to clients need. We can store over data online and retrieve the data anytime anywhere. Cloud provides us enormous storage and offers different types of resources such as high speed server, runtime platform, applications and software. Due to scarcity and large cost of cloud resources there is need for proper scheduling and allocation of cloud resources. The cloud resources must be allocated in efficient and effective way so that total cost of resources should be minimized. Scheduling algorithms are used for dispatching user tasks or jobs to a particular resource or data. This paper provides review of different cloud scheduling strategies used in cloud environment.

An Efficient Data Aggregation Approach for Prolonging Lifetime of Wireless Sensor Network

In today’s environment the aim of wireless sensor network is not restricted to data gathering. Bu... more In today’s environment the aim of wireless sensor network is not restricted to data gathering. But also focus on extraction of useful information. Data aggregation is the term used for extraction of useful information. Data aggregation helps in gathering and aggregating data in energy-efficient way so that network lifetime is heightened. This paper presents a data aggregation approach Mutual Exclusive Sleep Awake Distributed Data Aggregation (MESA2DA). This approach merges with our previous work Mutual Exclusive Sleep Awake Distributed Clustering (MESADC). MESA2DA approach selects cluster head on the basis of MESADC protocol. After that, data aggregation is done by cluster head on its cluster members to remove redundancy, so that the packets delivered to base station are reduced which helps in prolonging lifetime of wireless sensor network. The results obtained with MESA2DA approach are compared with HEED protocols in terms of average energy, delay, throughput, and packet delivery r...

Offline Signature Recognition Using Deep Features

Blockchain Based Business Model for Digital Assets Management in Trust less Collaborative Environment

International Journal of Computing and Digital Systems, 2020

With the advancements of digitalization, an organization can only survive by working in collabora... more With the advancements of digitalization, an organization can only survive by working in collaboration with other organization by sharing its digital assets. Due to lack of trust among the collaborative organization, the management of digital assets is challenging in todays rapidly growing competitive world. Traditional approaches of digital asset management are based on centralized access control and do not suited well in collaborative environment. Collaborative environment does not allow any single organization to take full control over entire digital assets because of different trust level among the organizations. Further, these approaches suffer from single point of failure that cost very high to the businesses. These problems of centralized approach are the roots for the need of a decentralized approach for digital assets management. In this paper, we discussed the need of decentralized access control for digital assets management and reviewed how Blockchain based business mode...

Cloud Security and Energy Efficiency

Cloud computing is the newest distributed computing paradigm and it offers tremendous opportuniti... more Cloud computing is the newest distributed computing paradigm and it offers tremendous opportunities to solve large scale scientific problems. However, it presents a range of challenges that need to be addressed in order to be efficiently utilized for workflow applications. With the rapid development of Cloud computing, more and more users deposit their data and application on the cloud. Cloud computing has many characteristics, e.g. multi-user, virtualization, scalability and so on. Because of these new characteristics, usual security technologies can’t make Cloud computing fully safe. Therefore, Cloud computing security becomes the present research focus. With the increasing popularity of the cloud computing model and quick proliferation of cloud infrastructures there are increasing concerns about energy consumption and ensuing impact of cloud computing as a contributor to total CO2 emissions. Due to the growing demand of cloud services, allocation of energy efficient resources (CP...

Download

Efficient Task Scheduling Technique under Batch Mode Heuristic for Cloud Environment

2021 6th International Conference on Signal Processing, Computing and Control (ISPCC), 2021

From solving complex computational problems to huge data intensive tasks, Cloud Computing is emer... more From solving complex computational problems to huge data intensive tasks, Cloud Computing is emerged as one the growing technology. It is not restricted to hand out gigantic problems but also gratifying day to day clients with variable requirements. To accomplish such a variety of users, Cloud always required an efficient task scheduling to cater such dynamism. So, this paper presents a scheduling technique named Efficient Task Scheduling technique under Batch Mode Heuristic for Cloud Environment (ETSBMH) that mapped cloudlets in an efficient way to reduce the makespan along with a new type of metric that depicts variation among heterogeneous virtual machines completion time. We named it Machine Makespan Aware Completion time Variation (MMACV) that considered completion time variation among machines with respect to makespan. Results reveal the effectiveness of proposed technique from on hand approaches in terms of reduced makespan, less MMACV and improved average machine utilization rate.

Performance Comparative Analysis of Heuristic based Independent Task Scheduling Techniques on Standard and Real Datasets

2021 2nd International Conference on Smart Electronics and Communication (ICOSEC), 2021

Allocating user cloudlets under heterogeneous environment like Cloud is a tiresome process. It’s ... more Allocating user cloudlets under heterogeneous environment like Cloud is a tiresome process. It’s one of core steps that efficiently hunt for capable yet diverse resources. Therefore, researchers around the world have given birth to several algorithms under heuristic and meta-heuristic categories. Such mapping techniques are proposed by keeping different performance parameters. Different metrics are used for evaluating the efficiency of scheduling algorithms like: resource utilization rate, makespan, waiting time, fitness, flow time and machines variation etc. This paper has compared eleven heuristic techniques based on the above parameters on standard, real and artificial dataset to yield their performance in heterogeneous scenarios.

Certificateless Efficient Group Key Management Scheme in Mobile Adhoc Networks

International Journal of Computer Science

Securing mobile ad hoc networks (MANETs) is a crucial task for their good deployments. One fundam... more Securing mobile ad hoc networks (MANETs) is a crucial task for their good deployments. One fundamental aspect of providing confidentiality and authentication is key management. While Public Key Infrastructure (PKI) based solutions has provided these properties historically, MANETs are resource constrained and benefit from symmetric key encryption. In this paper, we proposed a certificateless efficient group key management scheme (CE-GKMS) in MANETs for group confidentiality which uses identity based cryptography for secure multicast group communication. The scheme does not need PKI in which mobile nodes needs large storage to carry certificates and to perform public key cryptography based large computation. The scheme introduced a new idea of hiding the public keys and making them visible only to the trusted nodes which not only make it difficult for cryptanalyst to crack the private information but also permit to keep small value of encryption and decryption component causes asymmetric cryptography operation faster. For scalability and dynamic reconfigurability, we divide the network into groups. Leaders in these groups securely communicate with each other to agree on group key in response to membership change and member mobility-induced events. The performance results prove the effectiveness of our proposed key management scheme CE-GKMS.

Download

Blockchain Technology and Artificial Intelligence Based Decentralized Access Control Model to Enable Secure Interoperability for Healthcare

Sustainability

Healthcare, one of the most important industries, is data-oriented, but most of the research in t... more Healthcare, one of the most important industries, is data-oriented, but most of the research in this industry focuses on incorporating the internet of things (IoT) or connecting medical equipment. Very few researchers are looking at the data generated in the healthcare industry. Data are very important tools in this competitive world, as they can be integrated with artificial intelligence (AI) to promote sustainability. Healthcare data include the health records of patients, drug-related data, clinical trials data, data from various medical equipment, etc. Most of the data management processes are manual, time-consuming, and error-prone. Even then, different healthcare industries do not trust each other to share and collaborate on data. Distributed ledger technology is being used for innovations in different sectors including healthcare. This technology can be incorporated to maintain and exchange data between different healthcare organizations, such as hospitals, insurance companie...

Download

Blockchain-Based Model to Improve the Performance of the Next-Generation Digital Supply Chain

Sustainability

In the era of the fourth industrial revolution, all aspects of the industrial domain are being af... more In the era of the fourth industrial revolution, all aspects of the industrial domain are being affected by emerging technologies. Digitalization of every process is taking place or under process. One of the most important components common to every domain is the supply chain process. Organizations employ a digital supply chain to track the delivery of their products or materials. The digital supply chain is still suffering from a few issues such as no provenance, less transparency, and a trust issue. Blockchain technology, one of the emerging technologies, can be integrated with the supply chain to deal with the existing issues and to improve its performance. In this paper, a model is proposed to integrate blockchain technology with the supply chain to improve performance. The proposed model uses the combination of the Ethereum blockchain and the interplanetary file system to maintain the traceability, transparency, and trustworthiness of the supply chain.

Download

Intelligent Amalgamation of Blockchain Technology with Industry 4.0 to Improve Security

Internet of Things

Forest Fire Detection by using MESA2DA Clustering Protocol based on Artificial Intelligence Techniques

2023 International Conference on Smart Computing and Application (ICSCA)

An Optimized System for Sentiment Analysis using Twitter Data

Challenges and Opportunities for Deep Learning Applications in Industry 4.0