Government Engineering College at Thrissur

Trichur, India

Government Engineering College at Thrissur

Trichur, India
Time filter
Source Type

Syamili S.,Government Engineering College at Thrissur | Abraham A.,Government Engineering College at Thrissur
Proceedings of the International Conference on Inventive Communication and Computational Technologies, ICICCT 2017 | Year: 2017

As the presentation slides are of vital importance in a person's career, a significant amount of time is spent for its preparation. An automatic paper-summarizer will reduce the amount of time and human effort. Presently, tools exist for formatting and designing themes for slides, but not for content generation. This paper proposes a summarization system that automatically generates presentation slides from scientific papers. The proposed system accepts scientific papers as input and prepares presentation slides, which includes text, images and graphs present in them. Papers and slides are learned and trained using Support Vector Regression model. It calculates and predicts the regression scores. Based on the regression scores, the relevant content of the paper is selected for generating summary. The generated summary is used for making slides using Integer Linear Programming along with the images present in papers. © 2017 IEEE.

Monson N.S.,Government Engineering College at Thrissur | Kumar K.V.M.,Government Engineering College at Thrissur
Proceedings of the International Conference on Inventive Communication and Computational Technologies, ICICCT 2017 | Year: 2017

The detection of manipulated images is of utmost significance nowadays, mainly due to the various technological, moral, and judicial connotations associated with image editing. In this paper, a common form of image manipulation known as image composition or splicing is examined. The forgery detection method proposed here makes use of fine inconsistencies in the colour of the lighting of images. Our approach is machine-learning based which makes use of a behaviour knowledge space. This technique can be used in photographs having two or more people. To achieve forgery detection, complementary illuminant estimators are incorporated on image regions of similar material. Colour-, texture- and edge-based features are extracted from these illuminant estimates which are then provided to a machine-learning approach for automatic decision-making. © 2017 IEEE.

Aarathi K.S.,Government Engineering College at Thrissur | Abraham A.,Government Engineering College at Thrissur
Proceedings of the International Conference on Inventive Communication and Computational Technologies, ICICCT 2017 | Year: 2017

Recent years the number of vehicles increases tremendously. Because of that to identify the vehicle is significant task. Vehicle color and number plate recognition are various ways to identify the vehicle. So Vehicle color recognition essential part of an intelligent transportation system. There are several methods for recognizing the color of the vehicle like feature extract, template matching, convolutional neural network (CNN), etc. CNN is emerging technique within the field of Deep learning. The survey concludes that compared to other techniques CNN gives more accurate results with less training time even for large dataset. The images taken from roads or hill areas aren't visible because of haze. Consequently, removing haze may improve the color recognition. The proposed system combines both techniques and it adopts the dark channel prior technique to remove the haze, followed by feature learning using CNN. After feature learning, classification can be performed by effective classification technique like SVM. © 2017 IEEE.

Jasmin E.A.,Government Engineering College at Thrissur | Jagathy Raj V.P.,Cochin University of Science and Technology
International Journal of Electrical Power and Energy Systems | Year: 2011

This paper presents Reinforcement Learning (RL) approaches to Economic Dispatch problem. In this paper, formulation of Economic Dispatch as a multi stage decision making problem is carried out, then two variants of RL algorithms are presented. A third algorithm which takes into consideration the transmission losses is also explained. Efficiency and flexibility of the proposed algorithms are demonstrated through different representative systems: a three generator system with given generation cost table, IEEE 30 bus system with quadratic cost functions, 10 generator system having piecewise quadratic cost functions and a 20 generator system considering transmission losses. A comparison of the computation times of different algorithms is also carried out. © 2011 Elsevier Ltd. All rights reserved.

Ahammed M.M.,Sardar Vallabhbhai National Institute of Technology, Surat | Meera V.,Government Engineering College at Thrissur
Journal of Hazardous Materials | Year: 2010

The present study was conducted to compare the performance of a dual-media filter consisting of manganese oxide-coated (MOCS) and iron hydroxide-coated sand (IOCS) with that of IOCS filter and uncoated sand filter in treating water contaminated by microorganisms, heavy metals and turbidity with a view to its use in simple household water purification devices in developing countries. Long-duration column tests were conducted using two natural waters namely, roof-harvested rainwater and canal water. Performance of the filters showed that dual-media filter was more efficient in removing bacteria and heavy metals compared to IOCS filter, while uncoated sand filter showed very poor performance. The average effluent levels for dual-media filter when tested with rainwater were: turbidity 1.0 ± 0.1. NTU; total coliforms 3 ± 2. MPN/100. mL; heterotrophic plate count 170 ± 20. CFU/mL; zinc 0.06 ± 0.01. mg/L, while that for IOCS filter were: turbidity 1.0 ± 0.1. NTU; total coliforms 4 ± 2. MPN/100. mL; heterotrophic plate count 181 ± 37. CFU/mL; zinc 0.20 ± 0.07. mg/L. Similar results were obtained for canal water also. Up to 900 bed volumes (BV) could be treated without affecting the efficiency in the case of rainwater, while the filter operation had to be terminated after 500. BV due to excessive headloss in the case of canal water. The study thus showed the potential of the dual-media for use in low-cost household water filters for purification of natural waters. © 2010 Elsevier B.V.

Poulose S.,Indian Institute of Technology Madras | Panda T.,Indian Institute of Technology Madras | Nair P.P.,Government Engineering College at Thrissur | Theodore T.,Institute of Chemical Technology
Journal of Nanoscience and Nanotechnology | Year: 2014

Metal nanoparticles have unique optical, electronic, and catalytic properties. There exist well-defined physical and chemical processes for their preparation. Those processes often yield small quantities of nanoparticles having undesired morphology, and involve high temperatures for the reaction and the use of hazardous chemicals. Relatively, the older technique of bioremediation of metals uses either microorganisms or their components for the production of nanoparticles. The nanoparticles obtained from bacteria, fungi, algae, plants and their components, etc. appear environment-friendly, as toxic chemicals are not used in the processes. In addition to this, the formation of nanoparticles takes place at almost normal temperature and pressure. Control of the shape and size of the nanoparticles is possible by appropriate selection of the pH and temperature. Three important steps are the bioconversion of Ag+ ions, conversion of desired crystals to nanoparticles, and nanoparticle stability. Generally, nanoparticles are characterized by the UV-visible spectroscopy and use of the electron microscope. Silver nanoparticles are used as antimicrobial agents and they possess antifungal, anti-inflammatory, and anti-angiogenic properties. This review highlights the biosynthesis of silver nanoparticles by various organisms, possible mechanisms of their synthesis, their characterization, and applications of silver nanoparticles. © 2014 American Scientific Publishers.

Vanchipura R.,Government Engineering College at Thrissur | Sridharan R.,National Institute of Technology Calicut
International Journal of Advanced Manufacturing Technology | Year: 2013

This paper focuses on the problem of determining a permutation schedule for n jobs in an m-machine flow shop that operates in a sequence-dependent setup time (SDST) environment. Two constructive heuristic algorithms are developed with the minimisation of makespan as the objective. The first heuristic algorithm termed as setup ranking algorithm obtains the sequence using the setup times of jobs only. The second heuristic algorithm, fictitious job setup ranking algorithm (FJSRA), is developed using the concept of fictitious jobs. Pairs of jobs with minimum setup time between them constitute the fictitious jobs. Both these algorithms are compared with an existing constructive algorithm. For the purpose of experimentation, Taillard benchmark problems are used to develop SDST benchmark problems at eight different levels of sequence-dependent setup times. Graphical analysis, relative performance index analysis and statistical analysis are carried out on the results obtained for all the eight sets of benchmark problems. The analysis reveals that FJSRA emerges as the better algorithm for larger problems and for smaller problems with higher level of setup time. The results of statistical analysis are used to develop setup time dominance matrix for deciding upon the algorithm to be used for a particular size of problem. © 2012 Springer-Verlag London.

Sajeena Beevi B.,Government Engineering College at Thrissur | Madhu G.,Cochin University of Science and Technology | Sahoo D.K.,Cochin University of Science and Technology
Waste Management | Year: 2015

Anaerobic digestion (AD) of the organic fraction of municipal solid waste (OFMSW) is promoted as an energy source and waste disposal. In this study semi dry anaerobic digestion of organic solid wastes was conducted for 45days in a lab-scale batch experiment for total solid concentration of 100g/L for investigating the start-up performances under thermophilic condition (50°C). The performance of the reactor was evaluated by measuring the daily biogas production and calculating the degradation of total solids and the total volatile solids. The biogas yield at the end of the digestion was 52.9L/kg VS (volatile solid) for the total solid (TS) concentration of 100g/L. About 66.7% of the volatile solid degradation was obtained during the digestion. A first order model based on the availability of substrate as the limiting factor was used to perform the kinetic studies of batch anaerobic digestion system. The value of reaction rate constant, k, obtained was 0.0249day-1. © 2014 Elsevier Ltd.

Navas K.A.,Government Engineering College at Thrissur | Sasikumar M.,Marian Engineering College
IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India) | Year: 2011

All multimedia signal processing algorithms need suitable fidelity metrics for validating the results. Audio, image, and video are the major signals associated with multimedia, and the researchers rely upon objective metrics rather than subjective metrics due to pragmatic and uneconomic aspects of the latter. This paper analyses the available human visual system (HVS)-based objective fidelity metrics for the image processing, and highlights the inadequacy of the metrics for a special set of images known as region-of-interest (ROI) images and discusses a few research directions in this area. Copyright © 2011 by the IETE.

Prasanthkumar K.P.,Government Engineering College at Thrissur | Alvarez-Idaboy J.R.,National Autonomous University of Mexico
RSC Advances | Year: 2014

Oxidation of 2-aminopyrimidine (2Apy) by hydroxyl radicals (•OH) in aqueous medium has been studied using pulse radiolysis coupled to optical absorption and M05-2X/6-311++G(d,p) level DFT calculations aimed at elucidation of the reaction mechanism. The rate constant (k) 2.76 ± 0.06 × 109 M-1 s-1 determined by the pulse radiolysis method for the title reaction at neutral pH reflects a diffusion-controlled process. The maximum absorption wavelength (λmax 330 and 550 nm) of transient(s) remains intact in the pH range 10.5-7. Radical adduct formation (RAF) reactions with N1 (N3 is an identical site), C2, C4 (C6 is an identical site) and C5 as the target atoms, hydrogen transfer (HT) reaction with amino group and single electron transfer (SET) of 2Apy with •OH were modelled theoretically. Lowest Gibbs free energy of activation (ΔG ≠) in solution, 1.72 kcal mol-1, was calculated for RAF at C5; the computed k value for this process is 2.0 × 109 M-1 s-1 using the transition state theory (TST). The relative yield (87%) of this major product predicted from the computed k value shows excellent agreement with the results of the pulse radiolysis redox titrations. Subsequently, the possibilities for other RAF reactions, HT and SET were ruled out. As an extension to the above work, we have carried out a theoretical survey of the reactivity of •OH with 4-aminopyrimidine (4Apy); wherein the RAF at C5 is proposed as the most probable mechanism with a ΔG≠ of 2.15 kcal mol-1. © 2014 The Royal Society of Chemistry.

Loading Government Engineering College at Thrissur collaborators
Loading Government Engineering College at Thrissur collaborators