Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
3 results
Search Results
Item A laboratory investigation on a single row of suspended porous pipes was conducted in a two-dimensional regular wave flume to study their hydraulic performance. The wave energy losses at the structure were computed and the effects of depth of submergence, incident wave steepness, water depth, pipe diameter, percentage of perforations, size of perforations and relative wave height on loss coefficient were studied. It was found that as incident wave steepness increases, loss coefficient K 1 increases. Water depth has insignificant effect on K 1. It is also observed that as percentage of perforations increases, K 1 increases. For the range of variables studied, as the relative wave height increases, K 1 decreases.(Energy dissipation at single row of suspended perforated pipe breakwaters) Rao, S.; Rao, N.B.S.; Shirlal, K.G.; Guddeti, G.R.2003Item Simplified and improved multiple attributes alternate ranking method for vertical handover decision in heterogeneous wireless networks(Elsevier, 2016) Chandavarkar, B.R.; Guddeti, G.R.Multiple Attribute Decision Making (MADM) is one of the best candidate network selection methods used for Vertical Handover Decision (VHD) in heterogeneous wireless networks (4G). Selection of the network in MADM is predominantly decided by two steps, i.e., attribute normalization and weight calculation. This dependency in MADM results in an unreliable network selection for handover, and in a rank reversal (abnormality) problem during the removal and insertion of the network in the network selection list. Hence, this paper proposes a Simplified and Improved Multiple Attributes Alternate Ranking method referred to as SI-MAAR to eliminate the attribute normalization and weight calculation methods, thereby solving the rank reversal problem. Further, the MATLAB simulation results demonstrate that the proposed SI-MAAR method outperforms MADM methods such as TOPSIS, SAW, MEW and GRA with respect to the network selection reliability and rank reversal problems. © 2015 Elsevier B.V. All rights reserved.Item Unobtrusive Behavioral Analysis of Students in Classroom Environment Using Non-Verbal Cues(Institute of Electrical and Electronics Engineers Inc., 2019) Ashwin, T.S.; Guddeti, G.R.Pervasive intelligent learning environments can be made more personalized by adapting the teaching strategies according to the students' emotional and behavioral engagements. The students' engagement analysis helps to foster those emotions and behavioral patterns that are beneficial to learning, thus improving the effectiveness of the teaching-learning process. Unobtrusive student engagement analysis is performed using the students' non-verbal cues such as facial expressions, hand gestures, and body postures. Though there exist several techniques for classifying the engagement of a single student present in a single image frame, there are limited works on the students' engagement analysis in a classroom environment. In this paper, we propose a convolutional neural network architecture for unobtrusive students' engagement analysis using non-verbal cues. The proposed architecture is trained and tested on faces, hand gestures and body postures in the wild of more than 350 students present in a classroom environment, with each test image containing multiple students in a single image frame. The data annotation is performed using the gold standard study, and the annotators reliably agree with Cohen's ? = 0.43. We obtained 71% accuracy for the students' engagement level classification. Further, a pre-test/post-test analysis was performed, and it was observed that there is a positive correlation between the students' engagement and their test performance. © 2013 IEEE.