Vivank Sharma

Vivank Sharma

Bengaluru, Karnataka, India
4K followers 500+ connections

Join to view profile

About

Full Stack Software & Machine Learning Engineer with experience in building & deploying…

Activity

Join now to see all activity

Experience

  • Dell Technologies Graphic

    Dell Technologies

    Bengaluru, Karnataka, India

  • -

    Bengaluru, Karnataka, India

  • -

    Hyderabad, Telangana, India

  • -

  • -

    Vellore, Tamil Nadu

  • -

  • -

    Vellore, Tamil Nadu, India

  • -

    Vellore, Tamil Nadu, India

  • -

    Vellore Area, India

  • -

    Dharamshala

  • -

    Vellore, Tamil Nadu, India

Education

Licenses & Certifications

Join now to see all certifications

Volunteer Experience

Publications

  • Crop Analysis and Seed Marketing using Regression and Association Rules of India

    IEEE

    Agriculture plays a crucial and vital role in the country’s economy. A significant population of any country across the globe depends on agriculture for survival. Many times resources are wasted when the farmers are not able to correctly predict the crop to be grown due to lack of information. We have tried to build a model that predicts the type of product that can be cultivated in a given land-based on climatic conditions. Therefore, the crop with maximum production probability for a given…

    Agriculture plays a crucial and vital role in the country’s economy. A significant population of any country across the globe depends on agriculture for survival. Many times resources are wasted when the farmers are not able to correctly predict the crop to be grown due to lack of information. We have tried to build a model that predicts the type of product that can be cultivated in a given land-based on climatic conditions. Therefore, the crop with maximum production probability for a given area of land can be grown. Thus in this way, the resources and hard work of the farmers would be optimized and will provide better results. This model would also help in effective seed marketing as the predictive analysis of the suitable crop would help the suppliers supply the suitable crop seed in enough quantity to the farmers who would benefit the suppliers as well as the farmers.

    Other authors
    See publication

  • Performance Analysis of the Classifiers for Optical Character Recognition

    IEEE

    A brain can be easily able to recognize handwritten words in which computers are still struggling to figure out what they are. This incredible power of the mind requires to be transferred to a computer for automatic digitalization of handwritten texts and manuscripts. The work proposed in this paper tried to make a model which can recognize and predict different Hindi character, which can be further used to identify and digitalize the whole page or text. Our model uses different approaches like…

    A brain can be easily able to recognize handwritten words in which computers are still struggling to figure out what they are. This incredible power of the mind requires to be transferred to a computer for automatic digitalization of handwritten texts and manuscripts. The work proposed in this paper tried to make a model which can recognize and predict different Hindi character, which can be further used to identify and digitalize the whole page or text. Our model uses different approaches like a base-line neural network, convolutional neural network, and a simple logistic regression model.

    Other authors
    See publication

  • Design and Algorithms of the Device to predict Blood Glucose Level based on Saliva Sample using Machine Learning

    IEEE

    Regular tracking of blood glucose level is an integral part of treatment of Diabetes Mellitus, a chronic disease that occurs either when the pancreas does not produce enough insulin. Commercially available devices are involve pricking and analyzing of blood sample. Observing the pain, cost and chance of infection, non-invasive devices to measure blood sugar level are under research and development for the past decade. The paper proposes a method to develop a portable and economic device that…

    Regular tracking of blood glucose level is an integral part of treatment of Diabetes Mellitus, a chronic disease that occurs either when the pancreas does not produce enough insulin. Commercially available devices are involve pricking and analyzing of blood sample. Observing the pain, cost and chance of infection, non-invasive devices to measure blood sugar level are under research and development for the past decade. The paper proposes a method to develop a portable and economic device that can determine the blood glucose level of the patient by analyzing a saliva sample deposited by patient using spectroscopic methods. The device is constructed considering two theories as basis. The first theory is relation of glucose concentration of a solution to the attenuation observed while performing absorption spectroscopy. The second theory is the existence of relation between salivary glucose level and blood glucose level. Using the first theory, a device was constructed which uses NIR spectroscopy to find concentration of glucose in the given solution. The attenuation and concentration have been correlated using Machine Learning, $\mathrm{R}2=0.96$ . Data of salivary glucose level and blood glucose level was acquired and correlated using machine learning and $\mathrm{R}2=0.87$ . The proposed device requires patient to deposit saliva in a test tube and place it in the device. The device first predicts the glucose concentration of the solution(saliva). The device then uses the correlation between salivary glucose level and blood glucose level to find blood glucose level. The data is displayed and stored in the cloud.

    Other authors
    See publication

  • Drone Detection Mechanism using Radiocommunication Technology and Internet Protocol Address

    IEEE

    Unmanned Aerial Vehicles (UAVs) are among the real significant advances that have various significant and advantageous applications. But recently the threats imposed by Unmanned Aerial Vehicles (UAVs), especially small drones, have increased to a greater extent. Unmanned Aerial Vehicles(UAVs) are being misused nowadays for various illegal activities including terrorism and smuggling. Recently, there have been situations where they enter private or confined property. To kill such exercises, a…

    Unmanned Aerial Vehicles (UAVs) are among the real significant advances that have various significant and advantageous applications. But recently the threats imposed by Unmanned Aerial Vehicles (UAVs), especially small drones, have increased to a greater extent. Unmanned Aerial Vehicles(UAVs) are being misused nowadays for various illegal activities including terrorism and smuggling. Recently, there have been situations where they enter private or confined property. To kill such exercises, a framework has been structured which can distinguish and detect the nearness of obscure little aerial targets, for example, Unmanned Aerial Vehicles (UAVs), specifically small drones. The system is based on the concept of Radio Communication(RC) technology and Internet Protocol(IP) address. This framework is devised such that it detects Internet Protocol(IP) addresses in certain range and using the detected Internet Protocol(IP) addresses and presence or absence of radio waves, detects the presence of Unmanned Aerial Vehicles(UAVs). This system is capable of detecting the presence of unknown Unmanned Aerial Vehicles(UAVs) in certain range. This paper reports on the prototype of the same.

    Other authors
    • Manisha Kumari
    See publication

  • Machine Learning based Predictive Analysis for failure of monitored control System

    IEEE

    When an abnormality is identified in an IoT system or sub-system using change point discovery, a failure prediction dependent on predictive analytic models can distinguish an up-and-coming failure condition ahead of time. In view of this recognition, it can make proactive prescriptive move. This proactive activity in conventional applications is regularly booked support exercises. Although it is workable for us to expect and start activities using IoT sensor information, the edge layer isn't…

    When an abnormality is identified in an IoT system or sub-system using change point discovery, a failure prediction dependent on predictive analytic models can distinguish an up-and-coming failure condition ahead of time. In view of this recognition, it can make proactive prescriptive move. This proactive activity in conventional applications is regularly booked support exercises. Although it is workable for us to expect and start activities using IoT sensor information, the edge layer isn't constantly furnished with equipment that can get such guidelines and make the restorative move. We propose a failure prediction dependent on IoT sensor data analytic models that can distinguish an up-and-coming failure condition ahead of time.

    Other authors
    See publication

Projects

  • Musica - A music recomendation system

    This project is music prediction system that works on the basis of scoring of each app by each user and hence merge it to form a prediction.

    It's able to predict songs based on

    User's likes and dislikes
    Based on song and it's the genre
    User's a listening pattern
    Author's hits
    Similar songs

    See project

  • Team Fourth Dimension

    Designed and Developed a unique modern template clean and Responsive HTML5/CSS3.

    A landing page based for Team Fourth Dimension .

    With FireBase as a backend and hosted on a custom server powered by GITHUB.

    See project

  • Falsify-Fact-Engine

    Falsify, is a fact engine that looks up a given fact all over the internet, reads stories, news articles and recognizes if the given fact is a statement of truth or not, later it analyses the statement's genuinity and tells you if it's a Truth/Lie.

    See project

  • Devnagri-OCR

    -

    The brain can easily able to recognize handwritten words which computers are still struggling to figure out what they are.

    This amazing power of the brain requires to be transferred to the computer for automatic digitalization of handwritten texts and manuscript.

    The work I proposed in this project tried to make a model which is able to recognize and predict different Hindi character which can be further used to identify and digitalize the whole page or text. The model uses…

    The brain can easily able to recognize handwritten words which computers are still struggling to figure out what they are.

    This amazing power of the brain requires to be transferred to the computer for automatic digitalization of handwritten texts and manuscript.

    The work I proposed in this project tried to make a model which is able to recognize and predict different Hindi character which can be further used to identify and digitalize the whole page or text. The model uses different approaches like a base-line neural network, convolutional neural network, and a simple logistic regression model.

    See project

  • wSenti - A sentiment analyzer of slangs used in micro-blogs

    -

    So, this project which uses the power of natural language processing for and gives a score of the micro-blogs in range of 0-10, where 0 for most negative and 10 for the most positive sentiment.

    In this, I developed a model which not only focuses on keywords which also takes into consideration of every single word and try to overcome slangs by making custom dataset and using stemmers to find its original keyword and meaning. Hence, it makes our model different in the form and capability…

    So, this project which uses the power of natural language processing for and gives a score of the micro-blogs in range of 0-10, where 0 for most negative and 10 for the most positive sentiment.

    In this, I developed a model which not only focuses on keywords which also takes into consideration of every single word and try to overcome slangs by making custom dataset and using stemmers to find its original keyword and meaning. Hence, it makes our model different in the form and capability that it can also detect and analyze informal English, which is mostly used in microblogs.

    See project

  • wMeter

    -

    Recognizing and extracting display value from Electricity Meter, Gas meter and Water Meter’s 7 segment LCD display images is an immediate need to validate end to end functionalities of these devices; to check whether the value displayed is correct reading based on connected inputs. Any wrong display lead to loss of revenue for our consumers; eventually leads to recalling the devices and incur loss of business opportunity. Rework will need additional efforts which will contribute to increase R&D…

    Recognizing and extracting display value from Electricity Meter, Gas meter and Water Meter’s 7 segment LCD display images is an immediate need to validate end to end functionalities of these devices; to check whether the value displayed is correct reading based on connected inputs. Any wrong display lead to loss of revenue for our consumers; eventually leads to recalling the devices and incur loss of business opportunity. Rework will need additional efforts which will contribute to increase R&D Engineering Costs. Hence correct display in device display is paramount important.

    Developed a solution using Machine Learning techniques which can analyse the snapshots and reads the text from those images and returns the numbers/text for further processing. These images are taken with webcam/camera which is placed on top of the device.

    A web portal is created through which users can locate the meter and get the result displayed on meters. Output from the solution (Image conversion to text) is within 5 seconds.

  • Technical United Conference

    -

    A dynamic multi page website designed and developed for a conference with a great UI and responsive for every dimension of screen size.

    Which includes agendas for conference and live matrix of committees and countries and a live portal for coordinators of even for maintaining registrations live.

    See project

  • HackOff

    -

    A single page website created with dark theme keeping in mind website for coders.

    With simple and responsive UI for displaying information regarding HackOff hack-a-thon conducted by The Institution of engineering and Technology (IET) - On Campus VIT.

    See project

  • nTech-NewsReader

    -

    We all techies are always craving for a one stop destination for all the Tech news all over the world.

    nTech is search engine that looks up all over the internet, reads stories, news articles and recognises if the given fact is a statement of tech or not, later it analyses the statement and categorises it on the basis of tags and display it to users

    See project

  • PhotoBlog

    -

    Connecting to a closed circle has never been easy

    Photo blog provides a social media app kind of interface and in addition it can be also used for creating a closed network among your friends and family

    With an amazing UI used google cloud for it's backend to make it super fast.

    See project

Honors & Awards

  • Secure and Private AI scholarship challenge

    Udacity

    Selected for securing nano degree course on Udacity

  • Runner up in Startup-VIT Hack

    Vellore Institute of Technology

    Our team participated in Startup-VIT that was organized by Technology Business Incubator Vellore Institute of Technology (VITTBI) and adjudged Second Place.

    Which won us funding of Rs.1 Lakh for carrying out and completing our research on a smart hearing aid.

    And also won the cash prize of Rs.60,000.

  • Finalist of WeHack

    Honeywell Technology Solutions

    Finalist in Honeywell Automation Challenge 2019

Languages

  • English

    Full professional proficiency

  • Hindi

    Native or bilingual proficiency

  • Marathi

    Professional working proficiency

  • Spanish

    Elementary proficiency

More activity by Vivank

View Vivank’s full profile

  • See who you know in common
  • Get introduced
  • Contact Vivank directly
Join to view full profile

Other similar profiles

Explore more posts

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Vivank Sharma

2 others named Vivank Sharma are on LinkedIn

See others named Vivank Sharma

Add new skills with these courses

See all courses