Deep Learning based Skin Sensitization Hazard Prediction of Cosmetic Chemicals using Hybrid molecular Representations

Keerthana Jaganathan,Kil To Chong,Jung Mu Kim,Minho Song 대한전기학회 2021 대한전기학회 워크샵 Vol.2021 No.4

Deep Learning based Skin Sensitization Hazard Prediction of Cosmetic Chemicals using Hybrid molecular Representations

Keerthana Jaganathan,Kil To Chong,Jung Mu Kim,Minho Song 대한전기학회 2021 정보 및 제어 심포지엄 논문집 Vol.2021 No.4

Wind tunnel investigations on aerodynamics of a 2:1 rectangular section for various angles of wind incidence

Keerthana, M.,Harikrishna, P. Techno-Press 2017 Wind and Structures, An International Journal (WAS Vol.25 No.3

Multivariate fluctuating pressures acting on a 2:1 rectangular section (2-D) with dimensions of 9 cm by 4.5 cm has been studied using wind tunnel experiments under uniform and smooth flow condition for various angles of wind incidence. Based on the variation of mean pressure coefficient distributions along the circumference of the rectangular section with angle of wind incidence, and with the aid of skin friction coefficients, three distinct flow regimes with two transition regimes have been identified. Further, variations of mean drag and lift coefficients, Strouhal number with angles of wind incidence have been studied. The applicability of Universal Strouhal number based on vortex street similarity of wakes in bluff bodies to the 2:1 rectangular section has been studied for different angles of wind incidence. The spatio-temporal correlation features of the measured pressure data have been studied using Proper Orthogonal Decomposition (POD) technique. The contribution of individual POD modes to the aerodynamic force components, viz, drag and lift, have been studied. It has been demonstrated that individual POD modes can be associated to different physical phenomena, which contribute to the overall aerodynamic forces.

Hockey activity recognition using pre-trained deep learning model

Keerthana Rangasamy,Muhammad Amir Asari,Nur Azmina Rahmad,Nurul Fathiah Ghazali 한국통신학회 2020 ICT Express Vol.6 No.3

Activity recognition in sports is often complex task resulting from the rapid dynamic interaction within players. In this paper, pre-trained VGG-16, deep learning based hockey activity recognition model has been proposed. Own hockey dataset consisting of four main activity includes free hit, goal, penalty corner and long corner was constructed as there are no existing field hockey datasets available. Experimental results indicate that the pre-trained deep learning model generates comparative results on this challenging dataset by tweaking the hyperparameters of this pre-trained model.

Detecting Sinkhole Attack in Wireless Sensor Network using Enhanced Particle Swarm Optimization Technique

G. Keerthana,G. Padmavathi 보안공학연구지원센터 2016 International Journal of Security and Its Applicat Vol.10 No.3

Wireless Sensor Network (WSN) is a collection of tiny sensor nodes capable of sensing and processing the data. These sensors are used to collect the information from the environment and pass it on to the base station. A WSN is more vulnerable to various attacks. Among the different types of attacks, sinkhole attack is more vulnerable because it leads to a variety of attacks further in the network. Intrusion detection techniques are applied to handle sinkhole attacks. One of effective approach of intrusion detection mechanism is using Swarm Intelligence techniques (SI). Particle Swarm Optimization is one of the important swarm intelligence techniques. This research work enhances the existing Particle Swarm Optimization technique and the proposed technique is tested in a simulated environment for performance. It is observed that the proposed Enhanced Particle Swarm Optimization (EPSO) technique performs better in terms of Detection rate, False Alarm rate, Packet delivery ration, Message drop and Average delay when compared to the existing swarm intelligence techniques namely, Ant Colony Optimization and Particle Swarm Optimization.

Numerical investigations on the effect of mean incident wind on flutter onset of bridge deck sections

M. Keerthana,P. Harikrishna 국제구조공학회 2022 Structural Engineering and Mechanics, An Int'l Jou Vol.82 No.4

The effect of mean angle of wind attack on the flutter critical wind speed of two generic bridge deck cross-sections, viz, one closed box type streamlined section (deck-1) and closed box trapezoidal bluff type section with extended flanges/overhangs (deck-2) type of section have been studied using Computational Fluid Dynamics (CFD) based forced vibration simulation method. Owing to the importance of the effect of the amplitude of forcing oscillation on the flutter onset, its effect on the flutter derivatives and flutter onset have been studied, especially at non-zero mean angles of wind attack. The flutter derivatives obtained have been used to evaluate flutter critical wind speeds and flutter index of the deck sections at non-zero mean angles of wind attack studied and the same have been validated with those based on experimental results reported in literature. The value of amplitude of forcing oscillation in torsional degree of freedom for CFD based simulations is suggested to be in the range of 0.5° to 2°, especially for bluff bridge deck sections. Early onset of flutter from numerical simulations, thereby conservative estimate of occurrence of instability has been observed from numerical simulations in case of bluff bridge deck section. The study aids in gaining confidence and the extent of applicability of CFD during early stages of bridge design, especially towards carrying out studies on mean incident wind effects.

Wind tunnel investigations on aerodynamics of a 2:1 rectangular section for various angles of wind incidence

M. Keerthana,P. Harikrishna 한국풍공학회 2017 Wind and Structures, An International Journal (WAS Vol.25 No.3

Multivariate fluctuating pressures acting on a 2:1 rectangular section (2-D) with dimensions of 9 cm by 4.5 cm has been studied using wind tunnel experiments under uniform and smooth flow condition for various angles of wind incidence. Based on the variation of mean pressure coefficient distributions along the circumference of the rectangular section with angle of wind incidence, and with the aid of skin friction coefficients, three distinct flow regimes with two transition regimes have been identified. Further, variations of mean drag and lift coefficients, Strouhal number with angles of wind incidence have been studied. The applicability of Universal Strouhal number based on vortex street similarity of wakes in bluff bodies to the 2:1 rectangular section has been studied for different angles of wind incidence. The spatio-temporal correlation features of the measured pressure data have been studied using Proper Orthogonal Decomposition (POD) technique. The contribution of individual POD modes to the aerodynamic force components, viz, drag and lift, have been studied. It has been demonstrated that individual POD modes can be associated to different physical phenomena, which contribute to the overall aerodynamic forces.

모국어 말소리 대조 시 작업기억과 변별능력 간의 연관성

Usha Shastri,Keerthana Kulath Purath Raj,Mable Mathew,Mohan Kumar Kalaiah,Ajith Kumar Uppunda c 한국언어청각임상학회 2019 Communication Sciences and Disorders Vol.24 No.1

배경 및 목적: 모국어의 말소리(phone)를 변별할 때, 특히 도전적 상황에서 이를 수행할 때에는 매우 큰 개인차가 존재한다. 말소리 변별 시 유용한 단서를 활용할 수 있는 능력이 인지능력에 의해 촉진되는지, 이를 통해 개인차를 어느 정도 설명해 줄 수 있는지에 대해서는 잘 알려져 있지 않다. 본 연구는 말라얄람어(Malayalam)를 모국어로 사용하는 청자가 말라얄람어 말소리를 맥락 단서 없이 구분할때 작업기억능력과 변별능력 간에 어떤 연관성이 있는지 알아보고자 하였다. 방법: 말라얄람어를 모국어로 사용하는 18-25세 청자 40 명이 본 연구에 참여하였다. 참여자들로 하여금 무의미단어 사이에 삽입된 말라얄람어 8개 말소리를 변별하도록 하였다. 읽기폭 과제, 조작폭 과제, 숫자 바로외우기 과제, 숫자 거꾸로외우기 과제 등을 이용하여 작업기억능력을 측정하였고, 각 말소리의 변별점수, 전체 말소리 변별점수(8개 말소리로부터 얻은 평균변별점수)와 변별 시 반응시간을 함께 측정하였다. 결과: 참여자의 말소리 변별점수는 57.8%-99%의 범위를 보였다. 피어슨 적률상관분석 결과 모든 작업기억능력 측정치와 전체 말소리 변별점수 간에는 유의한 정적 상관이 나타나 작업기억능력이 말소리 변별에 중요한 역할을 하는 것으로 나타났다. 작업기억능력의 측정치는 말소리 변별점수 다양성의 24.7%를 설명할 수 있었다. 논의 및 결론: 맥락 단서가 없는 상황에서의 말소리 변별은 인지 부담을 높인다. 그러므로 높은 능력은 어려운 상황에서 모국어 말소리를 변별하는 데 도움을 준다. 이 연구는 모국어 말소리 지각에서 인지가 미치는 하향식 영향력을 제시하고 있다. Objectives: Large individual variability is documented for identification performance of native phones, especially in challenging situations. It is not known whether the ability to utilize cues available for phone identification is facilitated by cognitive abilities, thereby explaining a proportion of the individual variability. This study investigated the relationship between working memory capacity and identification of a few Malayalam phones in the absence of contextual cues among native listeners. Methods: Forty native listeners of Malayalam, aged between 18 and 25, participated in this study. Participants identified 8 Malayalam phones embedded in nonsense words. Working memory capacity was measured using tasks such as reading span, operation span, digit forward span, and digit backward span. Identification score for each phone, total phone identification score (average identification score from 8 phones), and reaction time during identification were obtained. Results: Phone identification score of participants ranged from 57.8% to 99%. Pearson product moment correlation analysis showed a significant positive correlation between all measures of working memory capacity and total phone identification score, indicating that working memory capacity play a role in the identification of phones. Reaction time showed a significant negative correlation with digit backward span and operation span. The measures of working memory capacity accounted for 24.7% of the variability in phone identification score. Conclusion: Identification of phones in the absence of contextual cues increases the cognitive load. Therefore, higher working memory capacity might aid in native phone identification in difficult situations. This study reveals the top down influence of cognition on native speech perception.

Performance of fly ash stabilized clay reinforced with human hair fiber

Rekha, L. Abi,Keerthana, B.,Ameerlal, H. Techno-Press 2016 Geomechanics & engineering Vol.10 No.5

Industrialization and urbanization are the two phenomena that are going relentless all over the world. The consequence of this economic success has been a massive increase in waste on one hand and increasing demand for suitable sites for construction on the other. Owing to the surplus raw materials and energy requirement needed for manufacturing synthetic fibers, applications of waste fibers for reinforcing soils evidenced to offer economic and environmental benefits. The main objective of the proposed work is to explore the possibilities of improving the strength of soil using fly ash waste as an admixture and Human Hair Fiber (HHF) as reinforcement such that they can be used for construction of embankments and land reclamation projects. The effect of fiber content on soil - fly ash mixture was observed through a series of laboratory tests such as compaction tests, CBR and unconfined compression tests. From the stress - strain curves, it was observed that the UCC strength for the optimised soil - flyash mixture reinforced with 0.75% human hair fibers is nearly 2.85 times higher than that of the untreated soil. Further, it has been noticed that there is about 7.73 times increase in CBR for the reinforced soil compared to untreated soil. This drastic increase in strength may be due to the fact that HHF offer more pull-out resistance which makes the fibers act like a bridge to prevent further cracking and thereby it improves the toughness which in turn prevent the brittle failure of soil-flyash specimen. Hence, the test results reveal that the inclusion of randomly distributed HHF in soil significantly improves the engineering properties of soil and can be effectively utilized in pavements. SEM analysis explained the change of microstructures and the formation of hydration products that offered increase in strength and it was found to be in accordance with strength tests.

Cr3+ doped Al2O3 nanoparticles: Effect of Cr3+ content in intensifying red emission

Lewis Prinston Melroy,N Keerthana,Hebbar N Deepak,Choudhari K.S.,Kulkarni Suresh D. 한국물리학회 2021 Current Applied Physics Vol.32 No.-

Cr3+-doped α-Al2O3 nanoparticles (Al2 xCrxO3, 0.005 ≤ x ≤ 0.05) were synthesized by co-precipitation method. X-ray diffraction (XRD) patterns of Cr3+:Al2O3 nanoparticles revealed the crystallite size of ~53 nm and electron microscopy (SEM & TEM) confirmed the spherical nanoparticle formation. Diffuse reflectance spectra (DRS) displayed peaks at 406 and 558 nm corresponding to the Cr3+ transitions which became prominent with the increase in Cr3+ concentration which was also evidenced by the gradually increasing pink coloration of the samples. Photoluminescence (PL) studies showed the sharp red emission at 694 nm (ruby line) which was observed for all samples. The Dq/B value for all samples was found to be greater than 2.3 confirming the presence of Cr3+ ions in the octahedral sites. Chromaticity diagrams displayed the maximum red appearance for the sample with x = 0.01 and a lifetime of 4 ms. The synthesized Cr3+:Al2O3 nanoparticles with smaller crystallite sizes and narrow near monochromatic emission can be used in various applications including sensing, lasing, and bioimaging applications.