Mini thermal power plant
Generating electricity is present there is a shortage of fuel, oil, gas, etc. burning of those fuels causes environmental problems like radioactivity pollution, heating, etc. so this ﴾coal, oil, gas﴿ limiting resources, therefore, ensuring new technology is required for electricity generation, by exploitation thermoelectrical generators to get power as a most promising technology is free for environmental benefits in production. Thermo electrical generator will convert directly thermal ﴾heat﴿ energy into voltage. In this TEG there are not any moving elements and it can't be turn out any waste throughout power production and hence it is considered a green technology. Thermo electrical power generation supplies a possible application within the direct exchange of waste‐heat energy into electric power wherever it's surplus to believe the value of the thermal energy input. This technique can have an associate most outcome. the appliance of this selection inexperienced technology in changing waste‐heat energy directly into electric power will too improve the efficiencies of energy conversion systems
Published by: Ramamoorthy Jyothivara Prasad, Bestha Chandrakanth, Pranav M., Purushotham Reddy P., Zabiullah S.
Author: Ramamoorthy Jyothivara Prasad
Paper ID: V7I3-2236
Paper Status: published
Published: June 30, 2021
Detection of Dyscalculia using Machine Learning
The detection of learning disabilities is still tedious and time consuming and a deep research is required for the simplification of the same. Dyscalculia is one of the Specific learning Disorders (SLD) with a specific impairment in Mathematics. Early detection of Dyscalculia is one of these tedious, time consuming tasks. Detection of Dyscalculia is carried out by conducting various tests where every individual test has to be conducted and evaluated manually as the scores of these individual tests alone are not sufficient for detection. For some cases, the scores from these tests are not sufficient. Some extra tests like Curriculum Based Test [CBT’s] and/or Wide Range Achievement Test [WRAT] are to be administered. Artificial intelligence (AI) or health care involves the use of complex algorithms to emulate human cognition in the perusal of complicated medical data. The derivatives of Woodcock Johnson Tests of Achievements are used to determine learning disabilities. These tests are conducted by the doctors.
Published by: Bonga Lavanya, Bodapati Pratima, Boya Padma Praamoda, Bhukya Sravya, Dr. Esther Sunanda Bandaru
Author: Bonga Lavanya
Paper ID: V7I3-2168
Paper Status: published
Published: June 30, 2021
Analysis and implementation of construction automation (Robotics) for glazing curtain wall
Glass panel (curtain-wall, glass ceiling etc.) is a type of building material for interior/exterior finishing. The demand for larger glass panel has increased along with the number of high-rise buildings and an increased interest in interior design. In Typical construction methods most of the construction works have been still managed by a human operator. Construction processes having number of problems cost overrun and risk factors that may cause various accidents such as falling, colliding, capsizing, and squeezing in work environments. The idea of this study to identify the new technological robots for installing large glass panels on construction sites to the reduce the time ,cost and accidents .. On evaluation, analyze and propose robotic construction methods for manipulating large glass panels in risk zones on high-rise buildings. and to identify the cost and time difference compared to human manipulate.
Published by: Praveen Kumar, Vidya
Author: Praveen Kumar
Paper ID: V7I3-2213
Paper Status: published
Published: June 30, 2021
Human heart condition prediction using Machine Learning implementation paper
Heart disease is one of the complex diseases and globally many people suffered from this disease. On time and efficient identification of heart disease plays a key role in healthcare, particularly in the field of cardiology. In this article, we proposed an efficient and accurate system to diagnosis heart disease and the system is based on machine learning techniques. The system is developed based on classification algorithms includes Support vector machine, Logistic regression, Artificial neural network, K-nearest neighbor, Naïve bays, and Decision tree while standard features selection algorithms have been used such as Relief, Minimal redundancy maximal relevance, Least absolute shrinkage selection operator and Local learning for removing irrelevant and redundant features. We also proposed novel fast conditional mutual information feature selection algorithm to solve feature selection problem. The features selection algorithms are used for features selection to increase the classification accuracy and reduce the execution time of classification system. Furthermore, the leave one subject out cross-validation method has been used for learning the best practices of model assessment and for hyper meter tuning. The performance measuring metrics are used for assessment of the performance of the classifiers. The performances of the classifiers have been checked on the selected features as selected by features selection algorithms. The experimental results show that the proposed feature selection algorithm (FCMIM)is feasible with classifier Random Forest Classifier for designing a high-level intelligent system to identify heart disease. The suggested diagnosis system achieved good accuracy as compared to previously proposed methods. Additionally, the proposed system can easily be implemented in healthcare for the identification of heart disease.
Published by: Akshay Baban Pathare, Abhijit Yuvraj Sonawane, Santosh Machhindra Punde, Akash Rajendra Shete, Santosh Waghmode
Author: Akshay Baban Pathare
Paper ID: V7I3-2222
Paper Status: published
Published: June 30, 2021
Performance of geopolymer coarse aggregate in 50% replacement with natural coarse aggregate using iron ore tailings
Concrete contributes a very important role in the construction sector. Aggregates are the basic ingredients in concrete which will contribute about 60-70% of the total composition. Due to the highest demand for aggregates, it has resulted in over-exploitation of natural resources, hence it is very important to use alternative material. As we know fly ash and IOT are the largest wastes that have been producing in all over India and these are the best suitable alternative materials. In Karnataka state, Kudremukh iron ore company (KIOCL) produce a large amount of IoT waste and was deposited in the Lakya dam. The present study in undertaken to determine the fly ash and IOT characteristics using XRD and SEM analysis and also to determine the strength and durability of concrete made up of geopolymer coarse aggregate for M40 grade of concrete. The cubes of size 75x75x75 are prepared by mixing IoT and fly ash in proportion 70:30 respectively with varying molarity of alkaline activator as 4M, 6M, 8M, 10M & 12M. These cubes are crushed to obtain Geopolymer coarse aggregates and these aggregates are used in RCC structures to check the mechanical behavior and workability of concrete.
Published by: Suchetha R. Murthy, Shiva Kumar G.
Author: Suchetha R. Murthy
Paper ID: V7I3-2233
Paper Status: published
Published: June 30, 2021
TDA layer: Impact of persistent homology on the performance of Convolutional Neural Networks
In this work, we introduce the topological data analysis layer that estimates persistent homology on attributes extracted from convolutional layers for image classification. This method shows that topological information can be utilized to upgrade network performance. This work focuses on applying persistent images on the deep convolutional layer to learn topological features and also exploring the behavior of topological data analysis on various convolutional neural network architectures like sequential architecture and extended width architecture. Based on our empirical analysis, we exhibit the significance of topological data analysis on convolutional neural networks by attaining reliable scores on classification tasks on benchmark datasets.
Published by: Kavin Kumar D., Vinuraj Koliyat, Ramasamy Seenivasagan, Sudarshan Subbaiyan, Sounder Matheshwaran
Author: Kavin Kumar D.
Paper ID: V7I3-2228
Paper Status: published
Published: June 30, 2021
