June - 2019 (Volume-9 ~ Issue-6 ~ Series-4)

Paper Type :: Research Paper
Title :: Kernel Based Object Counting Using Density Estimation
Country :: India
Authors :: Parvathy Mohan G || Riya John
Page No. :: 01-07

Object counting focuses on the prediction of the number of objects in a given image of interest or a frame from a video. This can be further used for obtaining the object statistics in a given counting scenario. There are many approaches in count estimations. Here density estimation based approach is considered. But the performance of density estimation based method seems to decrease when new counting scenarios are considered which can be solved by manifold based approach. In this paper a patch based method which makes use of kernels is presented. Here importance is given to techniques that make use of less number of training samples. In this paper various object counting scenarios are discussed and apart from the kernels used for counting purpose, exponential kernel is explored in this paper.

Key words: Density estimation, density-map reconstruction, kernel-based, kernel function, object counting

[1]. Yi Wang and YuexianZou and Wenwu Wang(2018), Manifold-based Visual Object Counting, IEEE Trans.Image Processing., 27(7), 3248 - 3263
[2]. V. Lempitsky and A. Zisserman(2010), Learning to count objects in images,Advances in Neural Information Processing Systems,1324– 1332.
[3]. G. Antonini and J.-P.Thiran(2006), Counting pedestrians in video sequences using trajectory clustering,IEEE Trans. Circuits Syst. Video Technol., 16(8),1008–1020
[4]. J. L. Bentley(1975), Multidimensional binary search trees used for associative searching,Communications of the ACM, 18(9),509–517
[5]. SiyuHuang,Xi Li (2018),Body Structure Aware Deep Crowd Counting, IEEE Transactions on Image Processing,27(3), 1049-1059

Paper Type :: Research Paper
Title :: A Study on Deep Learning Networks for Detecting Alzheimer's Disease
Country :: India
Authors :: Gayathri V S || Deepa P L
Page No. :: 08-14

Alzheimer's disease (AD) is a most prevalent form of dementia which cause severe memory loss and decline in other cognitive functions. The early diagnosis of Alzheimer's disease is essential in order to avoid severity in the disease. The early stage of AD called as Mild cognitive impairment should be diagnose early for better timely treatment. The combination of neuroimaging modalities such as positron emission tomography (PET) and Magnetic resonance imaging (MRI) shows effective way for the diagnosis of Alzheimer's disease. The deep learning techniques can be effectively used for the better diagnosis of Alzheimer's as early as possible. The main objective of this study is based on the different networks that are used to detect the Alzheimer's disease and its optimization.

Key words: Deep learning, multimodal neuroimaging, transfer learning, AlexNet, CNN

[1]. Jun Shi, Xiao Zheng, Yan Li, Qi Zhang, and Shihui Ying, "Multimodal Neuroimaging Feature Learning with Multimodal Stacked Deep Polynomial Network for Diagnosis of Alzheimer's Disease", IEEE Journal of Biomedical and HealthInformatics, Vol.22, Issue 1, 2018.
[2]. Cahit Deniz Gürkaynak, Nafiz Arica, "A case study on transfer learning in convolutional neural networks," in IEEE 2018 26th Signal Processing and Communications Applications Conference(SIU)10.1109/SIU.2018.8404642
[3]. J. A. Turner, S. G. Potkin, G. G. Brown,D. B. Keator, G. McCarthy, and G. H. Glover, "Neuroimaging for the diagnosis and study of psychiatric disorders," IEEE Signal Process. Mag., vol. 24, no. 4, pp. 112-117, 2007.
[4]. J. Schmidhuber, "Deep learning in neural networks: an overview," Neural Netw, vol. 61, pp. 85-117, 2015.
[5]. G. E. Hinton, and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, 2006.

Paper Type :: Research Paper
Title :: Segmentation of Heart Sound and Classification of Murmurs Using Empirical Wavelet Transform
Country :: India
Authors :: Abhina G N || Paul Thomas
Page No. :: 15-20

Phonocardiogram (PCG) are used for the study of heart sound and heart murmur. Heart sounds are consist of prominent systole (s1) and diastole (s2) and less prominent s3 and s4. Cardiac arrhythmias can be detected and diagnosed using the heart sound and heart murmur information. In this paper, we propose an Empirical Wavelet Transform (EWT) based decomposition of PCG signal and further classification of murmurs. Shannon entropy envelope and instantaneous phase of the signal are calculated for the identification of heart sounds. After identifying s1 and s2, cardiac cycle is calculated and from the cardiac cycle, heart rate is computed. Performance analysis shows that this proposed method achieves sensitivity (Se) of 96%, specificity (Sp) of 94% and overall accuracy of (OA) 95%. Murmurs are classified according to location and time of the occurrence of the heart sound. The PCG signal used in this work are taken from standard database of PhysioNet/CinC Challenge database.

Keywords: Phonocardiogram, heart sound,heart murmur, heart rate.

[1]. V. Nivitha Varghees, and K. I. Ramachandran (2018), Effective Heart Sound Segmentation and Murmur Classification Using Empirical Wavelet Transform and Instantaneous Phase for Electronic Stethoscope IEEE Signal Process. Lett., 18(4), 255-258.
[2]. X. Wang et al (2009), Detection of the first and second heart sound using heart sound energyProc. Int. Conf. Biomed. Eng. and Informatics, 1-4.
[3]. Jerome Gilles (2013) Empirical wavelet transform IEEE Trans. Signal Process., 61(16) 3999-4010.
[4]. V. N. Varghees and K. Ramachandran (2014), A novel heart sound activity detection framework for automated heart sound analysisBiomed. Signal Process. Control, 13, 174-188.
[5]. S. Xiao et al. (2002), A relative value method for measuring and evaluating cardiac reserveBiomed. Eng. Online, 6, 1-6.

Paper Type :: Research Paper
Title :: Helmet Detection and License Plate Recognition Using CNN
Country :: India
Authors :: Emy Barnabas || AmrithaB.J
Page No. :: 21-24

Nowadays, road accidents are one of the major causes that leads to human death. Among them, motor bike accidents are common and causes critical injuries. Helmet is one of the main protection unit for a motor bicyclist. However, many fail to conform to the law of wearing helmet. Here, to detect the motorcyclists who are violating the helmet laws, a system using image processing and convolutional neural network is implemented. The system consist of motorbike detection , helmet vs no helmet classification and motorbike licence plate recognition. The motorbikes are detected using the feature vector HOG. Once the motorbike is detected, by means of convolutional neural network, it is determined whether the motorcyclist is wearing a helmet or not. If the motorcyclist is identified without helmet, then the license plate of the motorcycle is detected using tesseract OCR.

Keywords: - Helmet Detection, Convolutional Neural Network, Tesseract OCR, License Plate Extraction

[1]. .J.Chiverton, "Helmet presence classification with motorcycle detection and tracking," in IET Intelligent Transport Systems, vol. 6, no. 3, pp. 259-269, September 2012.
[2]. R. Silva, K. Aires, T. Santos, K. Abdala, R. Veras and A. Soares, "Automatic detection of motorcyclists without helmet," 2013 XXXIX Latin American Computing Conference (CLEI), Naiguata, 2013, pp. 1-7.
[3]. R. R. V. e. Silva, K. R. T. Aires and R. d. M. S. Veras, "Helmet Detection on Motorcyclists Using Image Descriptors and Classifiers," 2014 27th SIBGRAPI Conference on Graphics, Patterns and Images, Rio de Janeiro, 2014, pp. 141-148.
[4]. P. Doungmala and K. Klubsuwan, "Helmet Wearing Detection in Thailand Using Haar Like Feature and Circle Hough Transform on Image Processing," 2016 IEEE International Conference on Computer and Information Technology (CIT), Nadi, 2016, pp. 611-614.
[5]. K. Dahiya, D. Singh and C. K. Mohan, "Automatic detection of bike-riders without helmet using surveillance videos in real-time," 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, 2016, pp. 3046-3051.

Paper Type :: Research Paper
Title :: New Mathematical Approach for Economic Power Dispatch Problem with Quadratic Objective Function
Country :: India
Authors :: S. Kavitha || Nirmala P. Ratchagar
Page No. :: 25-30

A new mathematical approach is proposed for the solution of optimization problem with quadratic objective function subject to satisfying equality and inequality constraints. The convergence of the conventional lambda iteration method is improved by using superlinear bracketing method. Lambda value is updated in each iteration by the superlinear bracketing method. The practical application of the proposed method is illustrated with economic power dispatch problem. Economic power dispatch problem is one of the fundamental issues in an electrical power system operation. It is a nonlinear optimization problem and their objective is to minimize the total fuel cost of a thermal power generating units subject to satisfying various operating constraints. The proposed mathematical approach is implemented for the solution of economic power dispatch problem. The result shows that the proposed method provides the optimal solution which provides the optimal solution and it requires lesser number of iterations for convergence.

[1]. C.L.Wadhwa, Electrical Power System. New age international publisher. 2005.
[2]. Hadi Sadaat, Power system analysis. Tata McGraw-Hill. 2016.
[3]. R.M.S.Danaraj, F.Gajendran, Quadratic programming solution to emission and economic dispatch problems. Institution of Engineer Journal.2005; 86.
[4]. H.A.Taha, Operation Research: An introduction. Prentice Hall of India. 1997
[5]. R.P.Brent, Algorithms for Minimization Without Derivatives. Englewood Cliffs. NJ: Prentice-Hall. 1973

Paper Type :: Research Paper
Title :: Modeling of Sluice Gate Operational Patterns with Two Openings and Free Flow Condition in Retention Ponds as Flood Controllers
Country :: India
Authors :: Ali Mallombassi || M. Bisri || Pitojo Tri Juwono || Ratna Musa
Page No. :: 31-43

Retention ponds function as flood control stabilizers. This pond is built on river bodies equipped with release gates and spillways. The spillway is used to drain water that exceeds the water level which is planned to be used for the release gate using a sluice gate that manages the discharge. So that it does not exceed the capacity of the downstream of the pond. The sluice gate is a flow rate meter on the open channel used in the retention pool mentioned above. The amount of discharge that passes through the sluice gate is influenced by the difference in height of the water upstream and downstream of the gate, because the water passing through the gate is not equal to the discharge formula equal to the speed multiplied by the wet fender but there is a reduction in flow due to flow discharge (Cd) coefficient on the gate.........

Keywords: Sluice gate, Coefficient, Debit, High Water.

[1]. D Lozano, L. Mateos, G.P. Merkley, and A.J. Clemmens, Field calibration of submerged sluice gates in irrigation canals, Journal of Irrigation and Drainage Engineering, 135(6), 2009, 763-772.
[2]. M Bijankhan, V. Ferro, and S. Kouchakzadeh, New stage–discharge relationships for free and submerged sluice gates, Flow Measurement and Instrumentation, 28, 2012, 50–56.
[3]. M.F. Sauida, Calibration of submerged multi-sluice gates, Alexandria Engineering Journal, 53(3), 2014, 663-668.
[4]. H.K. Shayan, and J. Farhoudi, Effective parameters for calculating discharge coefficient of sluice gates, Flow Measurement and Instrumentation, 33, 2013, 96–105.
[5]. H.R. Henry, Discussion of "Diffusion of submerged jets‟ by M.L. Albertson, Y.B. Doi, R.A.Jensen ad H. Rouse. Transactions of the American Society of Civil Engineers, 115, 1950, 687-694.

Paper Type :: Research Paper
Title :: Tuning Some Optical Parameters of (PbO)1-x (ZnO)x Prepared by Spray Pyrolysis Technique
Country :: Nigeria
Authors :: Oluyemi Folasade || K. A. Aduloju || Mukolu I.A
Page No. :: 44-50

In the last few decades, the world energy requirement is ever growing owing to the growth in the world population and the techno-economic growth of the countries .This work is focused on a way of utilizing the Sun to provide sustainable energy source for the future. Different thin films of average thickness 152nm were prepared from nanoparticles of (PbO)1-x (ZnO)x precursorson borosilicate glass substrate by spray pyrolysis techniques at 2500C temperature . Investigations on some optical constants of the films investigated revealed;refractiveindices within1.28- 1.76, extinction coefficients in the range 0.28 – 3.89 , and the energy gap(Eg) in the range 1.50eV to 3.5eV i,e, a bit below PbO(2.90eV)and a little above ZnO(3.37eV) the stating materials.in all, sample F had the peak value of all the optical constants investigated. The wide band gaps displayed by the film as revealed by Spectroscopic measurements depicts their solar technology applications.

Keywords: Population, Sun, Nanoparticles, Precursors, Substrate, Optical constants,Refractive indices, Extinction coefficients.

[1]. Cotton, F.A, Wilkinson,G. Advanced Inorganic Chemistry, Fifth Edition, John Wiley & Sons, Inc., 1988.
[2]. Eya, D.D.O, Ekpunobi A.J and Okeke C.E, Optical properties and applications of lead oxide thin films prepared by chemical bath deposition technique, academic open internet journal, vol. 14 , 2005
[3]. Cruz, M. Hern´an, L Morales, J.,S´anchez, L. J. Power Sources 108 , 2002, 35
[4]. Bao.D, H. Gu, A. Kuang, Sol gel-derived C-axis oriented ZnOthin films, Thin Solid Films 312 ,1988, 37-39.
[5]. Cao.B, Cal.W, From ZnOnanorods to nanoplates: chemicalbath deposition growth and surface-related emissions, J. Phys.Chem. C ,112 , 2008, 680-685.

Paper Type :: Research Paper
Title :: A Novel Method for Ensemble of Surrogates Based on Global and Local Measures
Country :: China
Authors :: Ying Luo || Jiajia Qiu || Jian Zhang
Page No. :: 51-56

Surrogate models are widely used in the community of engineering design and optimization to substitute computationally expensive simulations for efficient approximation of system behaviors. However, since the actual system behaviors are usually not known a priori, it is very challenging to select the most appropriate surrogate model for a specific application.To deal with this issue, an ensemble model that combines different surrogate models has been presented, and many efforts are devoted to the weight factor selection for the component surrogate models based on global measure and local measure respectively. In this paper, a novel ensemble of surrogate models is developed to take advantage of both global and local measures.........

Keywords: Surrogate model, Metamodel, Ensemble, Global measure, Local measure.

[1]. Myers RH, Montgomery DC (2002) Response surface methodology: process and product optimization using designed experiments. Wiley, New York
[2]. Fang HB, Horstemeyer MF (2006) Global response approximation with radial basis functions. Engineering Optimization 38(4):407–424.
[3]. Liu GR, Zhang J, Li H, Lam KY, Kee BBT (2006) Radial point interpolation based finite difference method for mechanics problems. International Journal for Numerical Methods in Engineering 68(7):728– 754
[4]. Martin JD, Simpson TW (2005) Use of kriging models to approximate deterministic computer models. AIAA Journal 43(4):853–863.
[5]. Clarke SM, Griebsch JH, Simpson TW (2005) Analysis of support vector regression for approximation of complex engineering analyses. Journal of Mechanical Design 127(6):1077–1087.

Paper Type :: Research Paper
Title :: Performancce Analysis of PAPR Reduction in DWT-OFDM in comparsion with conventional OFDM System
Country :: India
Authors :: Rayani Sunil || M Srinivasa Rao
Page No. :: 57-62

Orthogonal frequency division multiplexing (OFDM) is an operative multicarrier wireless system for high transmission data rate and is widely used in wireless communication systems. In general, we use a conventional fast Fourier transform (FFT) OFDM for high transmission data rate. In present days, multi-carrier wireless systems suggest that the use of wavelet transforms (WT) outperforms the conventional fast Fourier transform (FFT) orthogonal frequency division multiplexing (OFDM) systems. Wavelets based systems provide better spectral efficiency because of no cyclic prefix requirement, have very narrow side lobes and also exhibit improved BER performance. However, the OFDM system suffers from a major drawback at the transmitter that is the high peak-to-average power ratio (PAPR) of the transmitted.........


[1]. Ochiai and Imai ,"Performance analysis of deliberately clipped OFDM signals" IEEE Transactions on Communications ,Volume: 50 , Issue: 1 , Jan 2002 ,pp: 89-101
[2]. X. Wang, T. Tjhung, C. Ng, and A. Kassim, "On the SER Analysis of A-Law Companded OFDM System, Global Telecommunications Conference, 2000. GLOBECOM '00. IEEE, Vol. 2, Dec. 2000, p. 756 -760.
[3]. X. Huang, J. Lu, J. Zheng, K. B. Letaief, and J. Gu, "Companding transform for reduction in peak-toaverage power of OFDM signals," IEEE Trans. Wireless Commun., vol. 3, no. 6,Nov. 2004, pp. 2030– 2039.
[4]. P. Mukunthan and P. Dananjayan, "Papr reduction based on a modified pts with interleaving and pulse shaping method for stbc mimo-ofdm system," in Third International Conference on Computing Communication & Network- ing Technologies (ICCCNT). IEEE, July 2012.
[5]. S. H. Han and J. H. Lee, \An overview of peak-to-average power ratio reduction techniques for multicarrier transmission," Wireless Communications, IEEE, vol. 12, no. 2, 2005, pp. 56-65.

Paper Type :: Research Paper
Title :: Pilot based Channel Estimation of OFDM aided with KGMO Algorithm
Country :: India
Authors :: P.Sreesudha || Dr.B.L.Malleswari
Page No. :: 63-67

Now a days there is a huge demand for wireless communications. To accommodate huge number of users new methods are required. Orthogonal Frequency Division Multiplexing (OFDM) is one of the promising technology for modern wireless communications. In this paper OFDM system performance is investigated by estimating the channel with the help of Kinetic Gas Molecule Optimization (KGMO) algorithm. Comb type pilot arrangement is used for estimating the channel with Least Square (LS) estimation method. Results are simulated with Matlab and shown at the end of the paper.

Keywords: OFDM; Channel Estimation; Least Square Estimation; Optimization Algorithm.

[1]. N. LaSorte, W. J. Barnes and H. H. Refai (2008). The History of Orthogonal Frequency Division Multiplexing. IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference, New Orleans, LO, Jan, 1-5.
[2]. Surinder Singh, Hari Ram, Sandeep Singh Gill (2011). Performance Evaluation of Channel Estimation in OFDM System for Different QAM and PSK Modulations. International Journal of Electrical and Computer Engineering (IJECE), 1(2), 140-150.
[3]. Nahar, Ali &Ezzaldean, Mohammed Moanes, & Gitaffa, Sabah & K. Khleaf, Hussain (2016).OFDM channel estimation based on novel local search particle swarm optimization algorithm. Review of Information Engineering and Applications, 3(2), 11-21.
[4]. Moein S, Logeswaran R. (2014). KGMO: A swarm optimization algorithm based on the kinetic energy of gas molecules. Inf Sci 275, 127–144.