Mohit Gandhi

Purpose: During COVID pandemic there were no automated solutions for automating health parameters like heart/pulse rate, mask recognition and temperature. After the pandemic most of the offices will start for on-site work and schools will start, during this time we also need to take care if any employee or student is having correct body temperature and is wearing mask. Instead of hiring someone and risk their life to check temperature and mask for so much employees and students is tough task. So to solve this problem we want to create an integrated 3D printed device which monitors their heart rate, temperature and checking are they wearing a mask using Edge Impulse model on AWS IoT Edukit and Embedded Camera.

Working: of the computer vision is done on the ESP32 Cam using the Deep Learning model. The Mask Detection model is trained with Edge Impulse and a custom dataset, and the resulting library is utilized in the ESP32 CAM. Edge computing refers to the practice of executing all calculations immediately at the source of data rather than transferring data to an external server or cloud for processing.
Flow:
1)When a user stands in front of the device, the IR Distance sensor detects it and activates the camera, heart sensor, and temperature sensor. Read the image and infer it using the Mask Model.
2)Using the Mask Classification Model trained on Edge Impulse and the MobileNet V1 Architecture, determine if an employee or a person is wearing a mask.
3)UART connectivity is used to send predictions to M5Core2.
4)Then Check the pulse rate using the Pulse Sensor and send it to the M5Core2 for display on the screen.
5)The Temperature sensor will determine the body temperature and send it to the M5Core2 for display on the screen.
6)If the findings demonstrate that the person is not healthy, the case will be transmitted to admin using AWS IoT and SMTP via SES.

Inspiration:There are 466 million persons in the world with disabling hearing loss (6.1% of the world’s population) , I have created this app for them and their family so that they can communicate easily. This will allow a person with hearing loss and person who doesn’t knows Sign language to communicate to each other easily. We were also inspired from Hana’s ASL workshop.

Goals:
1) Take Voice from User and Convert it to Sign Language in form of a GIF
2) It will Take Video from User and convert the Sign Language in Video to Voice using Machine Learning
Goals Achieved: 1) Successfully created a Multifeatured Desktop App
2) Got Accuracy of 95% in predicting Sign Language

Working:
a)VOICE/TEXT TO SIGN LANGUAGE CONVERSION:

1)Scraping Data from Giphy using Chrome Extension
2)Then filtered the gif files and added names to it and Also added gif files of single alphabets
3)Took Voice/Text input from user and split into words and checked if it is present in the GIF filenames. If it is not present then use the Alphabet GIFs for making up words.
4)Finally Displayed it onto Tkinter App

b)SIGN LANGUAGE TO VOICE/TEXT CONVERSION:

1)Used the ASL Dataset on Kaggle of Alphabets and Created a CNN algorithm in Tensorflow and trained the model for small data.
2)Used Live Webcam feed of user hand and predicted the Alphabet from a Region of Interest.
3)Finally Displayed it onto Tkinter App

Purpose: In today’s world, the computer field is proliferating in Artificial Intelligence, Machine Learning, Neural Network, Blockchain, Web Development, Software Development, etc. But to succeed in these domains, everyone has to have basic knowledge of coding and the various languages required to build their skillset, and an immense amount of practice is needed. So here we are, coming up with a platform Coding-kid that will help users to solve puzzles, develop their coding skills by practicing different types of coding puzzles and improving their skills like algorithms, data structures, etc. And get hired in renowned companies or set up their own.

Features:
1) Online Platform to solve puzzles with leaderboard
2)Responsive Web App

Nowadays Agriculture is facing lots of issues which in turn affect production yields. One of the major problems faced by farmers is plant disease which needs to be solved in an early stage otherwise it will affect the whole plant. I have a Mango Farm for about 50-60 trees at my native place, which are prone to diseases like powdery mildew, anthracnose, die back, blight, red rust, sooty mould, etc. and once it gets affected to one plant it keeps spreading.I and my team have also surveyed various deep learning algorithms are used to detect the plant disease early by using technology. To avoid this I have created a Machine Learning Model to detect if plant is unhealthy or not using images of leaves .

Purpose: today’s world, the computer field is proliferating in Artificial Intelligence, Machine Learning, Neural Network, Blockchain, Web Development, Software Development, etc. But to succeed in these domains, everyone has to have basic knowledge of coding and the various languages required to build their skillset, and an immense amount of practice is needed. So here we are, coming up with a platform Coding-kid that will help users develop their coding skills by practicing different types of coding statements and improving their skills like algorithms, data structures, etc. And get hired in renowned companies or set up their own. The idea behind this project is to enhance my problem-solving ability.

Features:
1)To make an Online Code Judge System that will allow users to code Online and get results immediately.
2)To provide Interview and Practice Coding Questions to Ace Algorithm and Data Structures Skills.
3)To provide a simple platform so that children can also participate and get knowledge of programming hence called Coding-Kid.
4)There will also be Weekly Contests on our Platform so that users can get insight into how actual Coding Interview Rounds work.

Coronavirus (COVID-19) live Dashboard with Data from API - HTML CSS JavaScript. The aim of this project is to keep people updated about the current status of the spread of the virus around the globe. We can view the total number of cases,recovered cases,deaths for the current day for any given country. Data fetched from : CORONAVIRUS COVID19 API.

Due to social distancing norms, several restrictions have been established in public settings due to the COVID-19 pandemic. In offices and schools, there are no automated systems or procedures for managing large groups of people. Some systems use camera footage of workspaces to verify whether individuals are wearing masks, and temperature checks are done manually by designated authorities and processed on massive servers. The paper contains a proposed prototype of a portable device that can manage if individuals entering the workspace are wearing masks, and have an appropriate heart pulse rate using M5Stack Core2, ESP32 Camera Module, and distance sensors. For optimization and fast Mask Detection Model which will run entirely on the device, Tensorflow Lite and Edge Computing are used. The mask detection model achieves an accuracy of 87.8%. Here the focus was on edge computing with limited RAM usage and with an optimized MobileNetV1 model.

Nowadays, running computer vision models on embedded devices like Raspberry Pi and Nvidia Jetson has become ubiquitous. But the main issue is the limited performance on these devices due to smaller CPUs and power factors. To solve this, we have proposed research on various parallel processing techniques to get complete optimal performance of computer vision models like GoogleNet, Squeezenet, and Mobilenet on a Raspberry Pi using OpenVino Toolkit. We tested and compared these models' interpretation on factors like CPU, RAM Utilization, and Inference Time using Two Neural Compute Sticks and analyzed it on different Intel Processors. The results using Two Neural Sticks were significant than typical processors and increased by a factor of 2 to 3 for all models. So using these results, we can directly use the technique for the suitable model.

The growth of medical sensors like heart rate,blood sugar, and other health monitoring sensors is huge.Along with the use of sensors in devices and healthcare systems, the use of image classification models like mask detection on edge devices is of growing demand. The survey consists of various techniques used in modern healthcare devices and various other methods like sensor fusion and wireless sensors to collect and monitor health data. And it also includes a comparison of multiple mask detection models which were deployed on embedded devices like Raspberry Pi, Nvidia Jetson and cameras like OpenMV, ESP32Cam and deep learning models like MobileNetV1, InceptionV4, and YOLO Tiny which were optimized using TensorFlow Lite.

A major problem in agriculture is plant disease that is not recognized in the early stages, due to which, the people working in this industry face resulting losses, such as lost income, loss of time and effort, etc. We have surveyed different hardware implementations of plant disease detection on embedded devices, such as the Raspberry Pi, field-programmable gate arrays (FPGAs) with very large scale integration (VLSI), and ARM processors that use frameworks such as TinyML and TFLite. And studied and analyzed major deep learning algorithms and techniques, such AlexNet, long short-term memory (LSTM), LeNet-5, and ResNet, which have been used for plant disease detection.