AI Body Language Decoder using MediaPipe and Python
Body language are visual languages produced by the movement of the hands, face and body. In this project we evaluate representations based on skeleton poses, as these are explainable, person-independent, privacy-preserving, low-Dimentional representations. Basically skeletal representations generalize over an individual’s appearance and background, allowing us to focus on the recognition of motion. We present a real-time on-device body tracking pipeline that predicts hand skeleton and the whole body notion. It is implemented via MediaPipe, a framework for building cross-platform ML solutions. We perform using pose estimation systems and analyze the applicability of the estimation systems to body language recognition by evaluating failure cases of the existing models. The proposed system and architecture demonstrates real-time inference and high prediction quality.
Published by: Sankeerthana Rajan Karem, Sai Prathyusha Kanisetti, Dr. K. Soumya, J. Sri Gayathri Seelamanthula, Madhurima kalivarapu
Author: Sankeerthana Rajan Karem
Paper ID: V7I3-2223
Paper Status: published
Published: June 30, 2021
The future of space robots
Space robots have been a significant medium for scientists to further advance their knowledge of space. These robots have enabled remarkable progress in the field of space exploration and have continuously helped in fulfilling the growing curiosity of humans. The Hubble Space Telescope, a legendary scientific instrument has taken pictures of our vast universe, bringing back to us the early moments of the creation of the universe and widening the horizons of our knowledge about the cosmos. The Giotto Spacecraft has enabled scientists to venture into interplanetary space and learn more about the comets and their true nature. Many such wonders of technology have done miracles in space and the bright future of these robots seems to be waiting for us to test our capability and hence design more advanced robots capable of withstanding harsh conditions experienced in space, being more resourceful than humans, having a brain of its own using the emerging technology of artificial intelligence which will make these robots capable of comprehending and analyzing data and sending it to us the most formulated form. This concise data can be used to derive inferences and conclusions which will lead to our better understanding of the extent of the universe and our place in it. This paper provides an overview of space robotics mentioning in detail its evolution and its future scope as well as covering its advantages.
Published by: Reva Agrawal
Author: Reva Agrawal
Paper ID: V7I3-2141
Paper Status: published
Published: June 30, 2021
Hotel management system using Raspberry Pi
In this Era, Automation plays a very important role in different fields. Automation is becoming more and more popular day by day due to its various advantages. The development in the embedded system has proved to a reliable solution in monitoring and controlling the environment monitoring system. This can be achieved by local networking or through remote control or through mobile. The Raspberry pi is a single-board computer that has recently more popular. It has powerful hardware and also upgraded power system with 4 USB ports. So we are using the Raspberry pi for controlling the environment of the Hotel. The hotel management system is a web-based application that allows the customer to order the food from its remote location which is in the hotel itself.
Published by: Jyoti Sanjay Shinde, Vaishnavi Sanjay Korape, Pooja Ramchandra Shelake, Mahesh S. Mathpati
Author: Jyoti Sanjay Shinde
Paper ID: V7I3-2059
Paper Status: published
Published: June 30, 2021
Investigation on the diffusion of chlorides into concrete
This paper discusses Rapid Chloride Permeability Test investigations on the penetration of chloride ions into the concrete. Concrete samples of M40 and M50 Grades have been tested. The concrete specimens are made using standard molds of 100mm diameter x 50mm height. After curing the concrete samples are experimented. Specimens were cast and tested for 28 days. One chamber is filled with sodium chloride (NaCl) and another sodium hydroxide solution is filled. The strength of sodium chloride solution is varied from 1000ppm-35000ppm and the strength of sodium hydroxide solution are 0.04N. For all the combinations, RCPT was carried out and the charge passed through the specimens was noted. The Rapid Chloride Permeability Test values are found, the penetration charge through the concrete decreased with an increase in the grade of concrete.
Published by: Sandesh N. S., Sudeep Y. H.
Author: Sandesh N. S.
Paper ID: V7I3-2219
Paper Status: published
Published: June 30, 2021
Malaria Parasite Detection System using Deep Learning and Image Processing
Malaria is a mosquito-borne blood disease caused by Plasmodium parasites which are deadly, infectious, and life-threatening. The conventional and standard way of diagnosing malaria is by visual examination of blood smears via microscope for parasite-infected red blood cells under the microscope by qualified technicians. The given method is inefficient, time-consuming and the diagnosis depends on the experience and the knowledge of the person doing the examination. Image processing based Automatic image recognition technologies has been applied to malaria blood smears for diagnosis before. However, the practical performance has not been up to expectation. With the early prediction results, healthcare professionals can provide better decisions for patient diagnosis and treatments. This motivates us to make malaria detection and diagnosis fast, easy and efficient. To get quick results for the malaria tests, we proposed a model that involves Deep Learning and Image Processing. In this paper, we developed a model using Convolutional Neural Networks (CNNs) classifier that predicts whether the input image is malaria parasitized or not. The CNN model has many convolution blocks that detect even the tiniest possibility of plasmodium parasite present in our input. The proposed model is also evaluated using a large amount of data to increase its accuracy and correctness while detecting the malaria parasite.
Published by: Gaddayi Pravallika, M. Sion Kumari, Dora Aasritha, Gandepalli Vandana, Gandrapu Suswitha
Author: Gaddayi Pravallika
Paper ID: V7I3-2221
Paper Status: published
Published: June 30, 2021
House rate prediction system using Machine Learning
Everyone's desire is to purchase a home. When it comes to getting the best price, some people spend more than the property is actually worth. To tackle this challenge, we devised a method for predicting the price of a property using Machine Learning's Linear Regression model. We took into account all of the factors that one considers when purchasing a home, such as the neighborhood, the number of bedrooms, and the number of restrooms. It will undoubtedly assist the buyer in obtaining the best possible price.
Published by: Pratyush Kumar Mishra, Richa Tiwary, Harshitha T., Jagbeer Poonia, Dr. Shantakumar B. Patil
Author: Pratyush Kumar Mishra
Paper ID: V7I3-2218
Paper Status: published
Published: June 30, 2021
