Asian Journal of Convergence in Technology
Not a member yet
868 research outputs found
Sort by
Healthcare Data Management and Analysis
Get PDFThe Electronic Medical Records (EMRs) are the primary sources to study the enhancement of health and medical care. The rapid development in science and medical technology has produced various methods to detect, verify, prevent, and treat diseases. This has led to the generation of big health-care data and difficulties in processing and managing data. To capture all the information about a patient and to get a more detailed and complete view for insight into care coordination and management decisions big data technologies can be used. A more detailed and complete picture about patients and populations can be identified along with patients at risk before any health issue arises. Optimal strategies to commercialize treatments and the next generation of health care treatments can be identified and developed by it
Face Recognition Using Combined DRLBP & SIFT Features Using Arduino Uno 328
No full textIn this paper, face recognition is proposed using combined DRLBP and SIFT features with the help of ARDUINO UNO 328 for high efficient signal transfer system applications. The aim of this research is to develop a nonreal-life application of a security lock system employing a face recognition methodology. DRLBP is chosen for the face recognition algorithmic program. Arduino microcontroller is employed to represent the response to face identification. USB serial communication is employed to interface between the MATLAB and Arduino UNO Microcontroller. First, the image of the individual is captured then the captured image is then transferred to the information developed in MATLAB during this stage, the captured image compares to the training image within the database to see the individual standing. If the system acknowledges the individual as an authentication person or un-authentication person, the result is sent to the Arduino UNO microcontroller
Artificial Intelligence based Personal Assistant
No full textMany people like business men, executives andmanagement persons need personal assistant to help themwith their day to day tasks. Personal assistant perform manytasks including replying to emails, managing appointments,scheduling different events etc. Now a days concept ofvirtual intelligent personal assistant’s concept is quitepopular. Virtual intelligent personal assistant performs taskslike playing music, dialling phone numbers, searchinginformation on Internet etc. Concept of smart equipmentslike switching on and off lights and fans etc is also popular.The need of a reliable low cost system has remained an everdesired requirement. This paper combines both concept ofpersonal assistant and control of home appliances. Thispaper is based on interactive personal assistant capable ofprocessing voice commands given by the user to execute thedesired operations like search anything from the internet,fetching stock market information, weather report, basiccalculations, opening mailbox, etc. With the help of IOT,proposed system will be able to control home appliances(Smart home concept), thereby making our lives easier andwill prove to be a boon for the disabled
Operation Methods for Grid-connected PV system for Voltage Control in Distribution System – A Review
Get PDFAbstract—PV solar systems employ inverters to transform dcpower from solar panels into ac power for injecting into thepower grids. Inverters that perform multiple functions inaddition to real power production are known as “smartinverters”. This paper presents a novel control of PV inverter as adynamic reactive power compensator – STATCOM. This “smartPV inverter” control enables a PV solar inverter to operate inthree modes – i) Full PV, ii) Partial STATCOM, and iii) FullSTATCOM, depending upon system needs
Parametric study and CFD Analysis of Air Filter
Get PDFThe objective of work is to analyze the fluid flow through the air filter with porous medium offour cylinder spark ignition engine by performing experimental and computational fluiddynamics analysis(CFD) for reducing pressure drop in air filters. CFD analysis will be performedusing Ansys Fluent V14.5 using 2-D incompressible Reynolds Averaged Navier Stokes equations.A standard round air filter (Mahle KFA0247496) is used for performing experimental analysiswith all laboratory equipment’s for calculating pressure drop(using differential pressure gauge)and studying velocity profile(using Dantec anemometer) and boundary conditions for 2-Dimensional simulation air filter element are set with some approximations based onexperimental values. Thus in order to improve air filtration efficiency parametric optimization ofair filters is done by varying parameters like width of filter element, eccentricity of air flow infilter, and thickness of filter element using ANSYS Workbench after model validation withexperimental results. Moreover a comparison is being made between triangular and rectangularair filter element to find out their effects in pressure drop. Thus an optimized value ofparameters is be found which further reduces pressure drop in air filter to improve air filtrationefficiency and engine performance of a vehicle
Survey on Image Fusion: Hand Designed to Deep Learning Algorithms
Get PDFAbstract—Image fusion is the process ofcombining/integrating multiple images to generate the singleimage having all meaningful information. The input/sourceimages are captured through various sensing devices underdifferent parameter setting. It is impossible to focus on allinformation or all small objects in single image. Hence, Imagefusion methods provide the composite image known as fusedimage with complementary information. Fused image should bemore suitable for human as well as machine perception.Therefore, several methods have been developing to improve thequality of images. Traditional methods include spatial andtransform domain based image fusion in which spatial domainincludes the fusion methods with pixel, blocks or segmentationbased processing. Whereas, transform domain utilizes thetransform theories to transform the image in another domainrather than same domain of the input and performs fusion ruleon transformed image. Spatial domain methods produce spatialand spectral distortion in the fused image whereas transformmethods often perform inadequately when images obtained fromdifferent sensor modalities. Recently the concept of deep learninghas enlarged to enhance the development in image processingand computer vision problems such as segmentation,classification, super-resolution, etc. Deep learning algorithmssuch as convolutional neural network (CNN), deep autoencoder(DAE), and deep belief networks (DBN) with different categoryof images such as multi-modal, multi-resolution, multi-temporaland multi-focus have been proposed for image fusion. Itsapplications include disease analysis, disaster assessment,providing a complete information for diagnosis, detection ofchange, etc
MULTI FUSION PATH PLANNING ALGORITHM FOR UGV
Get PDFThis research paper presents the work on the multifusion path planning algorithm for Unmanned Ground Vehicle(UGV), which includes, tasks such as studying various existingalgorithms, combing algorithms for better results,implementing multi fusion path planning algorithm to producean optimal path for UGV in a simulated environment. Todetermine collision free path for a robot from start to goalposition in a workspace comprising of obstacles, is the mainchallenge in the design of an autonomous UGV. The Multifusion Path planning algorithm subsequently attempts tocreate free paths for the UGV to travel in the workspacewithout colliding with obstacles. Probabilistic roadmap (PRM)algorithm along with Dijkstra algorithm is used for the UGVnavigation in an environment. Python is used for simulation ofthe results
Deep learning based heart disease prediction
Get PDFData mining is the process of data analyzing fromvarious perspectives and combining it into useful information.This technique is used for finding heart disease. Based on riskfactor the heart diseases can be defined very easily. The main aimof this work is to evaluate different classification techniques inheart diagnosis. First, the ECG numeric dataset is extracted andpreprocess them. After that using extract the features that iscondition to be find to be classified by Convolution NeuralNetwork (NN).Compared to existing; Convolution NeuralNetwork provides better performance. After classification,performance criteria including accuracy, precision, F-measure isto be calculated. Compared to KNN, Convolution NeuralNetwork provides better performance. The comparison measureexpose that Convolution Neural Network is the best classifier forthe diagnosis of heart disease on the existing dataset
ANTI RIGGING VOTING MACHINE
Get PDFNow a days elections are notconducted by the usual fair processes through which people choose their Democratic Leader instead it becomes a war ground in most of the places in India. We can see that most parts which are affected with these problems are where the ruling political parties are unfairlycast fake votes and create violence using muscle power and influence. So we came up with a smart voting machine which helps us to conduct a proper and fair voting process and passively decreases the scope of violation taking place due to unfair Election process. Now a days every organisation has the biometric security or identification system. So we implement the biometric identification system along with the traditional EVM to make an advanced and highly secured voting system. It basically helps us to stop the fake voting and conduct a peaceful voting process
Analysis of Air Quality Estimation based on Air Pollutants Parameters
Get PDFAir quality is the degree that tells us how pure orpolluted the air is. It is important to know air quality inour surrounding as it negatively impacts human healthand environment. Modernization and industrializationhave given birth to air pollution which has becomehidden killer. Making cities more respirable starts byanalyzing and seizing the air pollution data. Longestablishedair quality prediction model gave lessaccurate and unsatisfactory result. There is a need ofreliable data-analytics based solutions which willoptimally predict air quality thereby enhancing ourquality life. We evaluated various studies in this domainand summated the important researches done. This workwill give future directions to the upcoming researchers