Manish Sharma
@geu.ac.in
Associate professor
Graphic era deemed to be university dehradun
RESEARCH INTERESTS
Social Networks Analysis
Internet of Things
Time Series Analysis
Recommendation System
Machine Learning
Scopus Publications
Scholar Citations
Scholar h-index
Scopus Publications
Yogendra Narayan Prajapati and Manish Sharma
Springer Nature Switzerland
Kanchan Yadav, Sagar Chirade, Malay Banerjee, Manish Sharma, N. Sri Ramya, K. Aravinda, and Adil Abbas Alwan
EDP Sciences
The design and prototyping processes have undergone significant transformation due to the emergence of E-Design and Virtual Prototyping in a time marked by remarkable technological progress. This study examines the significant influence of digital aspects on several industries, providing a comprehensive analysis of their potential for transformation. E-Design comprises a wide range of digital tools and processes that aid in the inception, development, and refining of design ideas. Through the utilisation of computer-aided design (CAD), virtual reality (VR), and augmented reality (AR), E-Design has emerged as a platform that facilitates novel opportunities for creative expression and collaborative endeavours. This technology empowers designers and engineers to surpass the limitations imposed by geographical distances, thereby promoting international collaboration and facilitating the emergence of interdisciplinary creativity. In contrast, Virtual Prototyping provides a dynamic platform that enables the iterative enhancement of prototypes, free from the restrictions imposed by physical constraints. By employing intricate simulations and digital twinning techniques, this approach expedites the cycle of product development, diminishes expenses, and mitigates the adverse effects on the environment. The rise of Virtual Prototyping has facilitated equal access to prototyping, hence enabling startups and small enterprises to engage in the process. This study examines case studies in several industries, including automotive, aerospace, architecture, and healthcare, to demonstrate the transformative impact of E-Design and Virtual Prototyping on product development and project lifecycles. This study investigates the obstacles and ethical implications linked to E-Design and Virtual Prototyping, encompassing concerns regarding data security, intellectual property rights, and the digital divide. This highlights the necessity of practising responsible innovation and implementing ethical principles in order to effectively navigate this revolutionary environment.
Yogendra Narayan Prajapati and Manish Sharma
IEEE
the COVID-19 pandemic has created a huge challenge for healthcare services around the world. Understanding the factors affecting treatment outcomes in COVID-19 is important to provide personalized and effective treatment, especially taking into account gender differences. This challenge involves using machine learning to analyze patient data, identify risk factors, and develop predictive models to predict the incidence and severity of COVID-19, including the impact of gender on the disease. This will allow doctors to create treatment plans and allocate resources efficiently based on a person's gender and other health-related factors. The aim of this article is to develop and evaluate novel machine learning algorithms to predict the clinical outcome of COVID-19 in patients, including the effect of father's gender. The goal is to develop accurate predictive models that will help doctors predict the progression and severity of COVID-19 in humans, including gender-specific factors.
Bharathi Gururaj, Prajith Prakash Nair, Harish L, Arun Kumar S, Manish Sharma, and Ramya Maranan
IEEE
The well-known neurological disorder (epilepsy) is recurrent seizures. It can profoundly affect a person's life and well-being, as well as society as a whole. Many different detection methods are employed to determine whether a person has epilepsy or not. One of the often-employed methods is the examination of electroencephalography (EEG) signals. The EEG is important in epilepsy for a variety of reasons. However, some of the EEG signal aberrations can behave as noise and reduce the predictability of the process. To find the optimal method for artifact removal, this project attempts to build supervised and unsupervised algorithms and compare their performances. For this purpose, a dataset consisting of EEG signals of both normal humans and people who are affected by epilepsy is collected This dataset is then preprocessed using two artifact removal techniques called the Independent Component Analysis (ICA) and Principal Component Analysis (PCA). The features that can be useful during the process of epilepsy detection are extracted using a feature extraction method called the Fourier Transform. The features are then classified using two different techniques. The feature classification techniques used in this study are the quadratic discriminant analysis and the Random Forest (RF) algorithm. The models are then trained and tested using the collected EEG signals. The results of the testing are then compared to find the best combination of the feature classification technique and the artifact removal technique. It is found that the combination of the RF algorithm and the ICA is the best algorithm with an accuracy of over 97%. The second-best combination is the RF algorithm and the PCA algorithm. This combination can be deployed as a backend processor of an epilepsy detection application. As it has an inbuilt, artifact removal it is expected to provide flawless predictions in the future.
Vaishali Gajendra Shende, A. Jency, K. Pavithra, T. Jayasudha, G. Venkatesan, and Manish Sharma
IEEE
The data collected by the Information Systems related to Public Health are underutilized, mainly due to their large volume and their complexity. This work was applied to the Knowledge Discovery in Databases technique based on the National Centre for Disease Control (NCDC), with the objective of tracing the epidemiological profile of viral hepatitis. Foram used the data referring to the corporation of Chennai in the year 2022, from two quais it was possible to compare the information obtained with the knowledge available in the specialized literature. Obtain a clear, simple and objective representation of the epidemiological profile of viral hepatitis through a decision tree and classification rules.
Varun Jindal, Vinay Kukreja, Shiva Mehta, Amit Gupta, and Manish Sharma
IEEE
This study combines convolutional neural networks (CNN) with federated learning to detect and categorise six disease types in red globe grape leaves. The innovative approach uses distributed machine learning among four clients while protecting data privacy, which might have ramifications for other privacy-sensitive applications besides agricultural disease detection. Each client in the research had a local dataset of red globe grapes leaf diseases, and the study deployed a federated learning model across the four clients. The clients updated the global model collectively after individually training CNN models on their local data and sharing model updates with a central server while maintaining data privacy. The model's professional capacity to recognize and categorise illness states across clients with high reliability was shown by experimental outcomes assessed through Precision, Recall, F1-Score, Support, and Accuracy, supporting the effectiveness of federated learning. The model displayed a strong performance in terms of these average metrics, despite fluctuations in individual customers' results, which were caused mainly by possible class imbalances. Between 87.34% and 94.36% were the Macro-average values, 88.39% to 94.50% were the Weighted-average values, and 88.40% to 94.49% were the Micro-average values for all customers. These excellent results show the model's ability to balance Precision and Recall, adjust to class imbalances, and successfully detect true positives worldwide. This study offers a practical, scalable, and privacy-preserving approach for crop multi-class disease identification, making a substantial contribution to precision agriculture. A significant advancement in distributed machine learning has been made due to the encouraging findings highlighting the potential of federated learning with CNNs for more extensive applications.
Devansh Goel, Divya Singh, Amit Gupta, Satya Prakash Yadav, and Manish Sharma
IEEE
Freshness attracts buyers and money for sellers. How effective will it be to automatically classify vegetables and fruits according to the freshness rate? Well, the next question comes from each one of us, is it possible or not? Yes, it is possible. This study focuses on the classification of apples based on parameters for setting their freshness. For the sake of classification, we have trained the model using CNN i.e., convolutional neural networks. Using this model apples are classified based on their appearance which is one of the most common approaches taken by humans while manually classifying apples. It is an easy, time-effective, and precise method that we prefer as the basic or most popular parameter to define the freshness of any fruit and vegetable is through their image. Using this approach, we have used CNN architectures VGG16 and Inception V3 and their accuracies were 86% and 93%. The model which is being created by us is tested on four activation functions such as read, sigmoid, tanh, and linear.
Roja Boina, Abhay Chaturvedi, Manish Sharma, Anurag Shrivastava, Indradeep Kumar, and Aln Rao
IEEE
An unexpected pandemic known as COVID-19 struck the entire world in the year 2020. Research in numerous sectors has been prompted to address it as a result of the lack of treatment. Understanding the new variety and developing a vaccination become more challenging as a virus evolves. Numerous nations are impacted by the rise of novel variations. Therefore, it is crucial to assess COVID-19's performance in addition to death forecasting. The proposal develops numerous analyses, visualizations, and predictive models that can forecast COVID 19 performance. The goal is to first track data visualization, later Covid 19 data are analyzed and predicted globally to raise awareness by applying machine learning techniques including linear regression, support vector regression, and Holt forecasting method. The objective of this study is to understand how machine learning methods and applications are used for various COVID-19-related tasks and investigations. An analysis of research published in Science Direct, Springer, Hindawi, and MDPI on this topic in 2020 using the search terms COVID-19, machine learning, supervised learning, and unsupervised learning. In total, 16,306 articles were retrieved, but 14 searches from these publications were used in this study. It has been demonstrated that machine learning can be useful for understanding, predicting, and differentiating COVID-19.
Manish Sharma and Richa Gupta
IEEE
Data is identified as the fuel of modern society for its versatility of use and effectiveness of use. In addition, modern businesses are making a decline based on analysis of historical data and patterns of the data. Such dependency on data analysis makes the process of data analysis important for data mining. Therefore the overall study has shed light on the significance of the data mining process and extraction process of data in order to make a data-driven decision. Additionally, the problems related to the process of data extraction and data mining are mentioned in the study which helps to achieve an overall concept for the data extraction and data mining process. Additionally, the significance of the process is mentioned in the study. Additionally, there are tables constructed that represent problems of the data extraction process and mining and the significance of the stems of mining. The study concludes in a way that helps in the implication of data extraction methods for business.
R. Josphineleela, M Jyothi, L. Natrayan, A. Kaviarasu, and Manish Sharma
IEEE
Health monitoring system in general is an innovation which is adopted worldwide especially in the last decade. The Patients suffering from permanent disables are much required to monitor them for their survival. Such patients are facing lot of issues because in no time their health is at risk. It is very difficult to predict them as there is a need of nursing all the time too. This paper presents a mobile phone linked health monitoring device programmed and controlled by Internet of Things (IoT). The important takeaway is to provide a handheld support for the healthcare professionals can monitor or to be notified when they are even outside the hospital environment to ensure the safety of the disable patients. The sensors collect the necessary information which is been sent to the IoT server and linked with the Internet module. The system consists of sensory devices, data acquisition system (DAQ), a controller (ESP32) and a software application. The body temperature, heat rate per minute, Heart ECG, oxygen level and Blood pressure are constantly monitored and stored as a report. The same report has been sent to the professionals, mobile phone through developed IoT application. Additionally, a text message is sent to the senior doctors' mobile phone if the sensor data exceeds the threshold value. Therefore, a mobile phone linked health monitoring system for disable patients constantly monitor and notify the concerned person on time and save precious life.
Pradosh Kumar Sharma, Ajay Rana, Smita Sharma, Manish Sharma, Mesay Mengstie, and Annam Takshitha Rao
IEEE
Bandpass filters, which only transmit frequencies that fall inside the transmission band and reject all other frequencies, are necessary for wireless communication systems. As 5G is set to be implemented, there will be a greater need for filters that operate in new frequency ranges. In 2022, the initial use is anticipated. The two key standards for filters that are used to build mobile applications are size and performance. With a repetition range of 26–28 GHz, the passband channel is designed in this proposal, simulated, and constructed. For downconversion of mmWave signals to microwave frequencies between 2 and 18 GHz, this channel can be employed as the front end of the apparatus. The size and efficiency of channels must be taken into account when planning new portable communications applications. Small, high-performance filters made by merging two components can be used in future mmWave applications like 5G. High-quality channels with minimal imprint are preferred for mmWave applications like 5G.
Manish Sharma and Rishi Sikka
IEEE
As a consequence of increased power usage, the power industry is rapidly growing, thus companies, investors, and agencies are focusing on implementing new rules to support operational performance. In distributed generation, big data analyses are being utilised to help energy firms, customers, and other parties particular provider, spot areas with delay, and allocate resources effectively to build a conducive conditions. Smart grid technology is replace outdated systems in the energy sector. This has facilitated the adoption of smart metres and enhanced the free flow of vast quantities of data and ideas. These facts once more were acquired using BDA modelling in analyse the current trend and anticipate future parameters on rising preferences and demands. As a consequence, this offers a range of options for successful expansion and efficient saving. Numerous scientists claim that the implementation of big personal information analytics aids in the improvement of any microgrid use, the asking for solar and wind power, the involvement in understanding the categories and designations of latency, the assistance in monitoring energy systems, and the forecasting of patterns for greater scalability. These elements often contribute to the overall improvement of energy administration and encourage more efficient development and growth. The goal of this study is to utilise primary sources to interview people in order to determine the overall impact of BDA on furthering the framework of energy conservation for sustainable agriculture. The researchers want to collect data using a structured questionnaire, and AMOS will be applied to analyze data and find out how the factors are related.
Pradeep Kumar Tiwari, Maya Pandey, and Manish Sharma
Springer Singapore
Preeti Mishra, Kashish Khurana, Saloni Gupta, and Manish K. Sharma
IEEE
Cloud computing is one of the most emerging field in the IT Industry which provides scalable, expandable and almost perfectly elastic software or hardware services to the users. As the scalability and elasticity of cloud computing services increases, it also increases the risk of malicious intervention into cloud. Since the number and types of malware attacks are increasing day by day, it triggers the need of an efficient, robust and scalable malware detection approach for securing virtual domains running in cloud. In this paper, we propose a dynamic analysis approach, called VMAnalyzer which applies deep learning based machine learning techniques for detecting attacks at VM-layer in cloud environment. The VMAnalyzer extracts the ordered sequence of system calls of all the monitored programs and performs the two-layer classification. In layer-1, convolutional neural network (CNN) is applied to extract and select the relevant system call sequences. A number of potentially diverse layers in CNN not only provides the architecture for important feature extraction but also take care of convolution of n-grams with full sequential modelling. The layer-1 output is fed as a input to layer-2 using pipelining. In layer-2, Bi-Directional Long Short Term Memory (LSTM) is applied for learning and detecting the behavior of malicious system call sequences. Our evaluation results demonstrate that our approach outperforms previously used methods for malware detection in cloud. The approach has been validated using University of New Maxico (UNM) dataset and results seem to be promising.
Manish Sharma, Shikha N. Khera, and Pritam B. Sharma
Springer Science and Business Media LLC
Manish Sharma, Praveen Sharma, Ashwini Saini, and Kirti Sharma
Springer Singapore