Securing cloud storage through face recognition mode
In many cases benefits given by a cloud server isn’t completely trusted by clients. Presently data are corrupted by an unauthenticated user with the help of employee’s. Generally, data are securely handled by Separate Organization but some employees sell their access specifiers to hackers for money due to single level Management and data are not made safe. To overcome this issue we move towards Advance Safe technology where data are downloaded by the user (admin or organization) with the help of face detection video mode when they accept the user request by recognizing their face among the hierarchy of employees and then the data is shared from one place to another. Here Encryption Algorithm is used for sharing data in a secure means by detecting a face in hierarchy.
Published by: Nadar Steffy Felicia Inbamani, Kumar P.
Author: Nadar Steffy Felicia Inbamani
Paper ID: V5I1-1263
Paper Status: published
Published: February 5, 2019
Improving generalization in reinforcement learning on Atari 2600 games
Deep Reinforcement Learning (DRL) is poised to revolutionize the field of artificial intelligence (AI) and represents a crucial step towards building autonomous systems with a higher-level understanding of the world around them. In particular, deep reinforcement learning has changed the landscape of autonomous agents by achieving superhuman performance on board game Go, a significant milestone in AI research. In this project, we attempt to train a Deep RL network on Demon Attack – an Atari 2600 game and test the model on different game environments to investigate the feasibility of applying Transfer Learning on environments with same action space but slightly different state space. We further extend the project to use established Reinforcement Learning techniques such as DQN, Dueling DQN, and SARSA to examine whether RL agents can be generalized on unfamiliar environments by fine-tuning the hyperparameters. Finally, we borrow classic regularization techniques like 2 regularization and dropout from the world of supervised learning and probe whether these techniques which have received very limited attention in the domain of reinforcement learning are effective in reducing overfitting of Deep RL networks. Deep Networks are expensive to train and complex models take weeks to train using expensive GPUs. We find that the use of the above techniques prevents the network from overfitting on the current environment and gives satisfactory results when tested on slightly different environments thus enabling substantial savings in training time & resources.
Published by: Abhi Savaliya, Chirag Ahuja, Chirayu Shah, Sagar Parikh
Author: Abhi Savaliya
Paper ID: V5I1-1254
Paper Status: published
Published: February 4, 2019
Experimental study on mechanical behavior of different grade M-sand concrete
In this paper were investigated in the comparison of compression strength and slump strength of M-sand and river sand. M-sand Rock crushed to the required grain size distribution is termed as manufactures sand (M-sand). The natural river sand was the cheapest resources of sand. The size of manufactured sand (M-Sand) is less than 4.75mm. A particle passing 75 microns, Sieve Size/ Granule Thickness IS Codes 150 microns - 4.75 mm and IS - 383: 1970. Then water absorption is 2.2. We are analyzed the specific gravity and moisture content of M-sand and river sand of concrete. Then we're prepared M-sand concrete moulded with help of mold die. The three grade of concrete we are prepared, they are M-sand grade M25, M-30, and M-35. After we conducted a compression test and slump test. Finally, we obtained in M25 grade of concrete; slump values and compression strength are more in comparison with M-sand till 7 days having 30.01 and 28 days we obtained 43.04. In M30 grade of concrete, slump values and compression strength are more in comparison with river sand. slump values of 170 mm > 150 mm (30 min) slump values of 140 mm > 100 mm (60 min) compressive strength 7 days 37.31N/mm2 > 32.02 N/mm compressive strength 28 days 48.5N/mm2 > 43.16 N/mm2. In M35 grade of concrete, slump values and compression strength are more in comparison with river sand. slump values of collapse is better than 170 mm (30 min) slump values of 150 mm > 110 mm (60 min) compressive strength 7 days 41.21N/mm2 > 37.41 N/mm2 compressive strength 28 days 54.32N/mm2 > 50.55 N/mm2.
Published by: R. Balasubramanian
Author: R. Balasubramanian
Paper ID: V5I1-1258
Paper Status: published
Published: February 4, 2019
Biometric methods to speed up fingerprint processing using OCT: A survey
Fingerprint recognition is a crucial security technique with a steady growing usage for the identification and verification of people. However, current fingerprint acquisition systems have bound disadvantages, that embody the necessities of physical contact with the acquisition device, and also the presence of undesirable artifacts, like scars, on the surface of the fingerprint. There are various sectors or domains where Biometric authentication plays a vital role, these areas include Internet of Things (IoT), Smartphones, Healthcare, and many more. This paper evaluates the accuracy of a whole framework for the capturing of uninjured, undistorted fingerprints from underneath the skin's surface using Optical Coherence Tomography (OCT), the extraction and conversion of the submerged knowledge into a usable fingerprint and also the matching of such fingerprints. The main objective of this paper is to provide the study of the biometric algorithms, OCT based methods, and their relative comparisons.
Published by: Soonrutha Karothu, Vineeta Tiwari, Siddhant Verma, M. Sugadev
Author: Soonrutha Karothu
Paper ID: V5I1-1257
Paper Status: published
Published: February 4, 2019
A survey on soil testing technique
Continuous cropping without the adequate measurement and provisioning of the soil nutrient may endanger the sustainability of the agriculture. Soil nutrient measurement s greatly required for proper plant growth and effective fertilization. A key in soil testing for formulated fertilization is to determine the number of soil nutrients, followed by recommendation of the nutrient needs and site-specific fertilization. Nitrogen, Phosphorus and Potassium are the three important nutrients required for plant growth.
Published by: Vaishnavi G., C. M. Manoj, Rakshitha M. P., Manu N, Nithin Kumar
Author: Vaishnavi G.
Paper ID: V5I1-1207
Paper Status: published
Published: February 1, 2019
(Re)-mythifying the popular: Are some excavations too strenuous for ordinary readers
ABSTRACT Over the last decade, rectification and reinterpretation of Historical and Mythological facts had been one of the most popular themes in Indian English Literature. The demystifications portrayed in the works of Ashwin Sanghi, Christopher Doyle and Amish Tripathy were very much successful in indulging the element of mystery and thrill amongst the readers due to their adroit defamiliarization of the familiar tales. To attain such defamiliarization, many authors tend to adopt a number of interdisciplinary methodologies to excavate the alternate interpretations. These calculative discourses from the fields of Geography, Archaeology, Chemistry, Geography or Mathematics form the twists in the tale that leads to the conclusion. But, the problem is that what fraction of the Indian myth-loving culture is subjected to these bodies of knowledge. For example, Ashwin Sanghi’s The Krishna Key has an illustration of the Cartesian equation in an aquatic plain curve to obtain The Swastika symbol. Hence, the theme primarily associated with the cultural aspects, seem to take an applied dimension. Unfortunately, such methodologies of interpretation cannot be perfectly grasped by the Indians belonging to every exposure of the society. It needs sheer knowledge and scholastic prerequisites to fully enjoy the depth of such works. This paper tries to find the gravity and the extent of relatability of such depictions with the common readers of the country, the probable problems and as such, identify the authors’ objectives and the presumable target readers.
Published by: Poumita Paul
Author: Poumita Paul
Paper ID: V5I1-1209
Paper Status: published
Published: February 1, 2019