Autonomous Railway Track Crack Detection and Accident Prevention System
Train derailment is a predominant issue that needs to be solved, the major cause of the derailment is due to cracks and bridges on the track. To overcome this problem we have proposed an autonomous system (Robot) that uses an ultrasonic sensor with a range of 30 cm primarily based on distance measurement and density sensor to detect deeper cracks, the sensor is used to detect cracks present on the railway track by sending ultrasonic waves. As soon as the crack is detected the GPS Sensor is used to find out the latitudinal and longitudinal coordinates of the area where the crack is detected. The detected crack along with the exact location is sent to a nearby railway station using a GSM module. These data are then sent to the cloud server which is then analysed and compared with the threshold and the cracks can be rectified on the exact location of the damage. The proposed self-governing system is a robot along with wheels and motors which are controlled by a motor driver. Here we are using an Arduino Uno Microcontroller. These sensors and modules are integrated with this Arduino UNO board. The board is uploaded with a program using the Arduino IDE to carry out the crack detection function. This board takes readings from the ultrasonic sensor and these readings are continuously stored in the cloud for analysis and it accordingly communicates with the other module to effectively detect cracks beneath the surface of the tracks and on the surface.
Published by: R. Prithvik Adithya, Naren Subra M. V., Somya Gupta, K. Tamizhelakkiya
Author: R. Prithvik Adithya
Paper ID: V6I5-1159
Paper Status: published
Published: September 16, 2020
Removing the impurities chloride & alkalies from granulated blast furnace slag
The river sand and manufactured sand forms by the crushed rocks in millions of years. Nowadays, the reduction of river sand and manufactured sand is too fast in our environment because of our rapid construction world. So the GBFS (Granulated Blast Furnace Slag) is used at the place of river sand and manufactured sand but the presence of alkali and chloride in GBFS causes different problems like corrosion in reinforcement, react with external agents, high heat generated during the heat of hydration process and less durability. In this project, the foam separation method is adopted for removing the presence of alkali from GBFS (Granulated Blast Furnace Slag) and balance the pH value of crushed slag just like river sand and manufactured sand. The alkali and chloride remove from crushed slag in the form of bubbles and floats over the surface. The pH value balanced like river sand and manufactured sand. By using the foam separation method, 99% of alkali removed from GBFS (Granulated Blast Furnace Slag). The pH value of GBFS is balanced as equal to the river sand which is approx 7.00. The external effect of rainwater and chemical attacks are protected by removing the alkali from GBFS (Granulated Blast Furnace Slag). The total weight of construction also reduces because of the less value of bulk density of slag i.e. 1200kg/m³. After this method N-A-S-H OR C-A-S-H gel substituted by the C-S-H gel which is the same as well as river sand mix concrete. Also, protect our forest soil and area which places dumped by the Slag and its harmful to the soil nutrients and also for ecosystem.
Published by: Praveena Ratre
Author: Praveena Ratre
Paper ID: V6I5-1163
Paper Status: published
Published: September 16, 2020
Wireless transmission of electricity through EM waves
Modern problems require modern solutions. The most important thing in power engineering is the transmission of electricity from place to place. No.of disturbance can be produced form the wireless transmission as like the conventional transmission lines. This paper is going to present brief information about one possible way of wireless transmission of electricity which could be useful for the near future. The true potential of wireless transmission has never witnessed. The potential of wireless transmission can change the perception of what we see in the field of electricity. Transmission of power from the source to load could be easy through the air without any interconnecting wires. In this particular paper using EM waves from magnetron as transmitter and using carbon nanotubes placed in the solar panel as receiver for the conversion of EM waves into electrical energy can be explained. By this proposed constructional we can transmit electricity where the world has never seen.
Published by: Voggu Sai Teja Sagar, G. Madhu Murali Siran, Shaik Haaris Saad
Author: Voggu Sai Teja Sagar
Paper ID: V6I5-1160
Paper Status: published
Published: September 14, 2020
Towards Singularity: Implications to Intelligent UI with Explainable AI approach to HCI
This paper has the aim of incorporating and prototyping the realms and the possibilities of future UI designs. It collectively analyses recent AI techniques and signifies the need for Intelligent User Interfaces (IUIs) that might shape future inventions and act beneficially for understanding the technological impacts it can produce. The architecture of HCI is prone to undergo a drastic transformation where multimodal interaction through cyborg automation will play a major role in singularity. For solving current issues in UI designs such as gender, disability, and color issues, Explainable AI (XAI) is further improving interpretability and explainability of Machine Learning (ML) algorithms. This paper furthermore explains the convergence of Engineering and Life sciences with its association to improving the outlines of future UIs on a process of gaining collective intelligence.
Published by: Sushrut Ghimire
Author: Sushrut Ghimire
Paper ID: V6I5-1158
Paper Status: published
Published: September 14, 2020
Evolution of the Indian Telecom Industry and its impact on consumer
The purpose of this paper is to profile the Indian telecom industry (2015 – 2020) from an economic and game theoretic perspective. The Indian Telecom industry has undergone massive change over the last few years, and the paper investigates the long run impact of these changes on consumer welfare. The paper uses literature and books on different oligopoly models and pricing strategies to explain the workings of the telecom industry. These models are verified using empirical data. The first section of the paper explains the entry of new firms in an oligopoly, and the second section explains how present and future equilibrium models, pricing strategies and collusion in the telecom industry impact consumer welfare. The study uses the models discussed to predict the future of the telecom industry and identifies the role of the government in order to increase long run consumer welfare.
Published by: Sahil Koita
Author: Sahil Koita
Paper ID: V6I5-1153
Paper Status: published
Published: September 14, 2020
Predicting Diabetes using Machine Learning Technique
Diabetes is a chronic illness with the potential to induce a worldwide health care crisis. As per the International Diabetes Federation, 382 million people exist with diabetes in the world currently. By 2035, the number is expected to be doubled as 592 million. Diabetes mellitus or diabetes is a disease generally induced due to the grown level of glucose in the blood. Physical and chemical tests are different traditional methods for diagnosing diabetes. However, diabetes prediction in advance is pretty challenging for medical practitioners due to complicated interdependence on multiple factors as diabetes influences individual organs such as eye, heart, kidney, eye, nerves, foot, etc. Data science techniques have the potential to help the medical field by answering some of the general questions. One such task is to facilitate predictions on medical data. Machine learning is the most useful technology for the medical field in data science. Machine learning is helpful because of the way machines learn from experience. This project aims to propose a valuable technique for earlier detection of the diabetes disease for a patient with higher efficiency by combining the outcomes of different machine learning techniques, the supervised machine learning methods including Decision Tree, Logistic Regression, Random Forest, Neural Network, XGBoost, and Support Vector Machine
Published by: A. K. Aravind Kumar
Author: A. K. Aravind Kumar
Paper ID: V6I5-1152
Paper Status: published
Published: September 11, 2020
