Journal Vol – 14 No -3, June 2019
Face Recognition using Machine Learning Algorithms
Authors:
Amirhosein Dastgiri, Pouria Jafarinamin, Sami Kamarbaste, Mahdi GholizadeDOI NO:
https://doi.org/10.26782/jmcms.2019.06.00017Abstract:
Face recognition is one of the most challenging issues in analyzing images. Face recognition technology is one of the fastest technologies that do the identification process without having the slightest disturbance to the person. Face recognition today has found many applications that can be used for faces recognition, military issues, legal issues, image retrieval, identification of protagonists, video images, and so on. Face recognition is considered as one of the smart computer analysis scenarios. There are always improvements in this area that make these improvements accurate in identifying facial expressions. Accordingly, the present paper seeks to study facial recognition using machine learning algorithms. Time information has useful features for recognizing facial expressions. However, a lot of effort is needed to manually design features. In this paper, to reduce these factors, a machine learning technique is selected, which is an automated tool that extracts useful features from raw data. Using machine learning methods can be considered as a more effective way. In this paper, a method based on machine learning algorithms for face recognition is presented. The proposed algorithms perform the unknown image by comparing it with known and stored images in databases and also obtaining information from a person familiar with the process of face recognition. The results show that the proposed method has high accuracy compared to other previous methods.Keywords:
face recognition, machine learning al gorithms,image process,Refference:
Human Gait Recognition using Neural Network Multi-Layer Perceptron
Authors:
Faisel Ghazi Mohammed, Waleed khaled EeseeDOI NO:
https://doi.org/10.26782/jmcms.2019.06.00018Abstract:
The wide separation of using camera video surveillance and increasing the depending on these video to identify human identity. One of trending method to achieve this task is human gait recognition. In this paper, human gait recognized using three features include gait energy image (GEI) human body height and width. Features are easy to extract and archived high correlation to target class. Neural network Multi-Layer Perceptron used to build a recognition model to achieve 90 % accuracy.Keywords:
human gait recognition,gait energy image,Neural network Multi-Layer Perceptron,Refference:
Control System Based Modeling and Simulation of Cardiac Muscle With Optimization Using Performance Index
Authors:
Soumyendu Bhattacharjee, Aishwarya Banerjee, Biswarup NeogiDOI NO:
https://doi.org/10.26782/jmcms.2019.06.00019Abstract:
Because of the prolong use of the system, the performance (Output parameters of the system) can change and output of the system may start deteriorating from the desired value. If the performance of a system, based on control theory is not up to the expectations as per the desired specification, then some changes in the system are required to obtain the desired performance. The control system can be represented with a set of mathematical equations called system model which are used to answer questions via analysis and simulation. A model is a precise representation of a system dynamics which are the arrangement of physical elements and that physical elements are analyzed to make governing equations. Cardiovascular muscle senses the force generated due to the contraction and expansion of muscle wall .This can be well understood by the analytical approach of the transfer function generated by using a mechanical model of force displacement analogy. The efficiency of the work also lies in the measure of the movement of cardiovascular factors in the system. The mass of heart muscle varies with different age groups both for male and female. This work is based on the glimpses of changing transfer function with different age groups due to the variation of mass of heart muscle. Viscous drag has also been calculated considering different values of damping coefficient for a particular value of mass. For attending the optimality in the performance of the system one designed controller is used along with the derived transfer function in cascade arrangement. To get more stability of the system, damping coefficient is chosen for the system model considering less settling time and steady state error. The open loop transfer function in the forward path is simply the product of derived transfer function and designed transfer function of controller. The design emphasizes on the optimality in operation of the control process which has been determined by the performance index (PI) of the total process using integral square method.Keywords:
Transfer Function, Steady State Error, Performance Index,Integral Square Error,Refference:
Hydrological Modeling of Upper Indus Basin Using HEC -HMS.
Authors:
Muhammad Ismail Khan, Saqib Shah, Jowhar Hayat, Faisal Hayat Khan, Mehre MunirDOI NO:
https://doi.org/10.26782/jmcms.2019.06.00020Abstract:
One of the most frequently used mechanism to estimate the basin’s hydrological response due to precipitation is Hydrological modeling. In the paper to pretend the rainfall-runoff processing Upper Indus Basin, Pakistan the HEC-HMS model is used. The development of most of hydrological methodologies is done before 1990. But the advancement in GIS technologies and the management of spatial data has assisted repetitious processing tasks for high resolution datasets improving efficiency and spatial variations. Although large amount of data are often required but the preprocessors in GIS helps hydrological modeling through the semi-automated spatial analysis. We used HEC-HMS for hydrological modeling of Upper Indus Basin. To estimate the watershed discharge over time, the HEC-HMS routes a runoff hydrograph through the stream network. It produces the event based storm hydrograph which can be used in urban drainage design, water management, reservoir design, land use impact studies, flood forecasting and floodplain mapping To cover seven years (2005-2011) data Rainfall-runoff simulation is done using random rainstorm measures of these years. Selected events are used for model calibration and the remaining are used for model validation. The statistical tests of error function like root mean square error (RMSE), Nash Sutcliffe efficiency (NASH), mean biased efficiency (MBE), R-square between the observed and simulated data are conducted for calibration of the model. The results show values of R-square of 0.855, and the values of RMSE between the observed and simulated data were indicated as 7.83 and the value of NASH is 0.91 similarly, the value of MBE is 1.5 between the observed and simulated discharge for calibration of the model, respectively. The results indicate values of R-Square is 0.856 and value of RMSE is 9.54 and value of NASH is 1.5 and, the value of MBE is 1.5 among the experimental and simulated discharge for validation of the model, respectively. For validation and calibration of model select sub-basin of Upper Indus Basin, precipitation and discharge data from 2005 to 2011 is used in modeling.Keywords:
Hydrological m.odeli.ng,Rainfall-runoff simulation,Upper Indus Basin,model calibration,model validation,Refference:
I. Ateeq-ur Rauf and Abdul Razzaq Ghumman (June 2018) Impact Assessment of Rainfall-Runoff Simulations on the Flow Duration Curve of the Upper Indus River-A comparison of Data-Driven and Hydrologic Models.
II. Abushandi, Eyad & Merkel, Broder (2014). Modelling Rainfall Runoff Relations Using HEC-HMS and IHACRES for a Single Rain Event in an Arid Region of Jordan.
III. Brooks, K.N., N.B., 2003. Hydrology and the Management of Watersheds. 3rd Edition, Wiley-Blackwell, Ames, ISBN-10: 0813829852 pp: 574.
IV. Cunderlik, Juraj & Simonovic, Slobodan. (2004). Inverse Modeling of Water Resources Risk and Vulnerability to Changing Climatic Conditions.
V. D.R Archer, H.J.Fowler(August 2004) Hydrology and Earth System Sciences
VI. France, R.L., 2002. Handbook of Water Sensitive Planning and Design. 1st Edition, Lewis Publishers, Boca Raton, ISBN-10: 1566705622, pp: 699.
VII. Hassan A.K.M Bhuivan, Heather McNairn, Jarett Powers and Amine Merzouki (September 2017)Application of HEC-HMS in a Cold Region Watershed and Use of RADARSAT-2 SoilMoisture in Initializing the Model.
VIII. KimhuySok and Chantha OeurngApplication of HEC-HMS Model to Assess Streamflow and water Resources Availability in Stung Sangker Catchment of Mekong’ Tonle Sap Lake Basin in Cambodia.
IX. MeilingWang, LeiZhang, Thelma D Baddoo(September 2016) Hydrological Modeling in a Semi-Arid Region Using HEC-HMS.
X. Mahmood, R.; Jia, S.; Babel, M.S. Potential Impacts of Climate Change on Water Resources in the Kunhar River Basin, Pakistan. Water 2016, 8, 23
XI. Mukhopadhyay, Biswajit & Khan, Asif. (2014). A quantitative assessment of the genetic sources of the hydrologic flow regimes in Upper Indus Basin and its significance in a changing climate. Journal of Hydrology. 509. 549–572