Volume-8 Issue-5S, February 2020 – International Journal of Recent Technology and Engineering (IJRTE)

E10180285S20

IJRTE Journal — Fri, 17 Mar 2023 06:41:39 +0000

A Novel T-C-T Solar Photovoltaic Array Configurations using Rearrangement of PV Modules with Shade Dispersion Technique for Enhancing the Array Power
V. Bala Raju¹, Ch. Chengaiah²
¹V. Bala Raju, Research Scholar, Department of EEE, SVU College of Engineering, SV University, Tirupati (Andhra Pradesh), India.
²Dr. Ch. Chengaiah, Professor, Department of EEE, SVU College of Engineering, SV University, Tirupati (Andhra Pradesh), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 68-78 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10180285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1018.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Total-Cross-Tied (TCT) solar array configuration has more output power under uniform irradiance condition (un-shade case) among all conventional solar photovoltaic (SPV) array configurations but reduced array power under non-uniform irradiance cases (shading cases). To improve the performance of TCT array configuration under shading cases by using rearrangement or repositioning of existing photovoltaic (PV) modules in TCT configuration to new optimal locations within a TCT array configuration with shade dispersion technique. In this rearranged method, repositioning the modules based on puzzle pattern without altering the electrical connections among modules in an SPV array. The shading on PV modules are dispersed by changing the position of PV modules to optimal locations within SPV array so the performance of conventional TCT configuration will be improved. In this paper proposed an optimal TCT configurations, it requires a minimum number of electrical connections or ties between array modules and it depends on the shaded modules location in SPV array and also the proposed method reduces the wiring losses, mismatch losses. For this analysis, MATLAB/Simulink software is used for modeling and simulation of 6×6 size different rearrangement based TCT and proposed optimal SPV array configurations under one un-shaded case and fourteen different shading cases.
Keywords: PV Modules, Array Power, Optimal Interconnections, Wiring Losses, Partial Shading Cases, Shaded Modules.
Scope of the Article: Low-power design

Download PDF

The post E10180285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10150285S20

IJRTE Journal — Fri, 17 Mar 2023 06:33:41 +0000

VMS Mean and Minimum Utilization VM Selection Algorithm for Cloud Datacenter
Sreenivasa B.L¹, S Sathyanarayana²
¹Sreenivasa B.L, Research Scholar, Assistant Professor, Bharathiar University, Coimbatore AIMIT, St Aloysius College, (Karnataka), India.
²Dr. S Sathyanarayana, First Grade Womens College, Mysore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 63-67 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10150285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1015.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Cloud datacenter provides the various resources on-demand for the end consumers on pay-per-use through internet connection. The request for computing resources has increased which leads to the growth of power consumption inside datacenters. The major challenge is how to balance the profits by decreasing the consumption of energy and violation of SLA. VM Consolidation techniques helps VMs to migrate between the host machines in reducing energy consumption, but again which VM to select for migration between the host machine is again the challenging task. In this paper VMs Mean and Minimum Utilization VM Selection Algorithm is proposed.To select the suitable VM’s in host machine for the migration, VMs Mean method is used which finds the lowest CPU utilizing VM. To test this algorithm CloudSim Toolkit is been used. The parameter such as EC, SLAV, PDM, ESV, VM migration and SLATAH is used as a metric to evaluate the Algorithm efficiency.
Keywords: Energy Consumption (EC), SLA Violation (SLAV), Performance Degradation Due To Migration (PDM), Energy SLA Violation (ESV), VM Migration and SLA Violation Time Per Active Host (SLATAH), Minimum Utilization (MU), Virtual Machine (VM).
Scope of the Article: Cloud Resources Utilization in IoT

Download PDF

The post E10150285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10140285S20

IJRTE Journal — Fri, 17 Mar 2023 06:21:05 +0000

VMS Mean and FFD VM Allocation Algorithm for Cloud Data Center
Sreenivasa B.L¹, S Sathyanarayana²
¹Sreenivasa B.L, Research Scholar, Assistant Professor, Bharathiar University, Coimbatore AIMIT, St Aloysius College, Mangalore (Karnataka), India.
²Dr. S Sathyanarayana, First Grade Womens College Mysore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 58-62 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10140285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1014.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The datacenter power consumption is increasing speedily, because of the scalable and dynamic provisioning of resources to the remote consumers. Not efficiently utilizing the resource of host machine is the main reason for increase in power consumption. By efficiently placing the number of virtual machine in fewer active host and shutdown the inactive host could reduce the consumption of power in datacenter. In this paper VMs Mean and FFD Bin Packing Virtual Machine Placement Algorithm is proposed.FFD preprocess VM’s and Host’s by sorting all the VM’s by MIPS and Host’s by their power. To place the VM’s in host machine VMs Mean method is used which finds the lowest CPU utilizing VM. The main objective is to increase the host machine utilization by efficiently placing the VM’s into few active Host’s and also reduced the power consumption. To test this algorithm CloudSim Toolkit is been used. The parameter such as EC, SLAV, PDM, ESV, VM migration and SLATAH is used as a metric to evaluate the Algorithm efficiency
Keywords: Energy Consumption (EC), SLA Violation (SLAV), Performance Degradation Due To Migration (PDM), Energy SLA Violation (ESV), VM Migration And SLA Violation Time Per Active Host (SLATAH), First Fit Decreasing (FFD), Virtual Machine (VM).
Scope of the Article: Cloud Computing

Download PDF

The post E10140285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10130285S20

IJRTE Journal — Fri, 17 Mar 2023 06:07:07 +0000

Heart Disease Prediction using Machine Learning Models
Ruban¹, Vivek², Krithi³
¹Dr. Ruban S, Assistant Professor HOD, Department of Software Technology, St Aloysius College, Mangalore (Karnataka), India.
²Vivek, Student, Department of Software Technology, St Aloysius College, Mangalore (Karnataka), India.
³Krithi, Student, Department of Software Technology, St Aloysius College, Mangalore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 53-57 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10120285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1013.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Healthcare has become one of the most important concerns in the world. The cases of heart disease are increasing on a rapid scale among the people especially among the young generation. We can save the lives of the people if we could detect the heart disease on/before time, by getting them treated. In this matter artificial intelligence can be of a great help. Here we have collected a data set and then we have built a prediction model to detect heart disease based on the various algorithms that are available for machine learning.we have used Logistic regression, K-NN, SVM, Decision Tree, Random Forest with the accuracy values of K-Neighbors Classifier (0.956194%), Support Vector Machine (0.9561945%), Decision Tree (0.91050%), Random Forest Classifier (0.95404%) and Logistic Regression (0.95592%). The best value given by the Machine Learning model is by Logistic regression followed by K-NN.
Keywords: Heart Disease, Predictive Model, Machine Learning, Artificial Intelligence.
Scope of the Article: Machine Learning

Download PDF

The post E10130285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10120285S20

IJRTE Journal — Fri, 17 Mar 2023 06:00:04 +0000

Non-Invasive Prediction Model to Detect Sepsis using Supervised Machine Learning Algorithms
Ruban S¹, Elreena Maria Pinto², Valerie Roselyn Cardozo³, Kavya S⁴
¹Ruban S, Faculty Member PG, Department of IT, AIMIT, St Aloysius College, Mangaluru (Karnataka), India.
²Elreena Maria Pinto, PG Student, Department of IT, AIMIT, St Aloysius College, Mangaluru (Karnataka), India.
³Valerie Roselyn Cardozo, PG Student, Department of IT, AIMIT, St Aloysius College, Mangaluru (Karnataka), India.
⁴Kavya S, PG Student, Department of IT, AIMIT, St Aloysius College, Mangaluru (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 50-52 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10120285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1012.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Sepsis is a life-threatening disease that causes tissue damage, organ failure and results in the death of millions of people. Sepsis is one of the highest risky diseases identified globally. A large proportion of these deaths occur in developing countries due to inaccessibility of hospitals or lack of resources. Blood samples are taken to confirm sepsis, but it requires the presence of laboratory and is time-consuming. The aim and objective of this study is to develop a practical, non-invasive sepsis prediction model that can be used to detect sepsis using supervised machine Learning algorithms. For this retrospective analysis, we used the data available from Physio-Net database.
Keywords: Sepsis, Prediction Model, Physio-Net Dataset, Non-Invasive.
Scope of the Article: Machine Learning

Download PDF

The post E10120285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10110285S20

IJRTE Journal — Fri, 17 Mar 2023 05:50:51 +0000

Broken Character Recognition using Connected Components and Convolutional Neural Network
Roshan D Suvaris¹, S Sathyanarayana²
¹Roshan D Suvaris, Research Scholar, Assistant Professor, Bharathiar University, Coimbatore AIMIT St Aloysius College Mangalore (Karnataka), India.
²Dr. S Sathyanarayana, First Grade Womens College Mysore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 46-49 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10110285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1011.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Recognizing broken characters in scanned and ancient scanned text document is not easy because the characters may be broken and unclear. Many researches have been carried to recognize these broken characters. In this research paper we have described a new broken characters recognition method for English text documents only. The proposed method uses a hybrid approach which uses connected component concepts and convolutional neural network to identify the broken characters. The input to the approach is scanned or ancient text document which contains unclear text that is difficult to recognize and hence our new proposed methodology will recognize these characters with greater accuracy and it will give the recognized characters to the user. The projected technique has attained a precision up to 92% in recognition.
Keywords: Connected Components, Convolutional Neural Network, Image Processing.
Scope of the Article: Pattern Recognition

Download PDF

The post E10110285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10100285S20

IJRTE Journal — Fri, 17 Mar 2023 05:44:37 +0000

Predicting True Value of Used Car using Multiple Linear Regression Model
Laveena D’Costa¹, Ashoka Wilson D’Souza², Abhijith K³, Deepthi Maria Varghese⁴
¹Laveena D’Costa, Department of Big Data Analytics, AIMIT, St. Aloysius College, Mangalore (Karnataka), India.
²Ashoka Wilson D’Souza, Department of Statistics, Mangalore University, Mangalore (Karnataka), India.
³Abhijith K, Department of Big Data Analytics, AIMIT, St. Aloysius College, Mangalore (Karnataka), India.
⁴Deepthi Maria Varghese, Department of Big Data Analytics, AIMIT, St. Aloysius College, Mangalore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 42-45 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10100285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1010.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Predicting the true value of used cars requires lot of analysis. This prediction takes into account variables such as car model, fuel type, number of owner and so on. In this paper we are applying machine learning algorithms to determine the true value of cars when selling them to the dealers. We have used multiple linear regression model by dividing the data into training and test. Vehicle price forecast is both a critical and significant job, particularly when the car is used and does not come directly from the factory.
Keywords: Multiple Linear Regression, True Value.
Scope of the Article: Artificial Intelligent Methods, Models, Techniques

Download PDF

The post E10100285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10090285S20

IJRTE Journal — Fri, 17 Mar 2023 05:36:17 +0000

Digital Voting System as Internet of Things Application
Rajashree S¹, Sheetal V A², Soman K S³, Bhuvankumar P⁴
¹S Rajashree, Assistant Professor, Departmant of Computer Science, PES University, Bangalore (Karnataka), India.
²Sheetal V A, Assistant Professor, Department of Computer Science, BMS College of Engineering, Bangalore (Karnataka), India.
³Soman K S, Software Consultant, Bangalore (Karnataka), India.
⁴Bhuvankumar P, Student, Department of Electronics and Electrical, KSSEM, Bangalore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 38-41 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10090285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1009.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The objective for the efficient functioning of the Indian democracy is purely dependent on the decisions made by the citizens of our country. To avoid duplicate or illegal votes we need a secure system which uniquely identifies our citizen. In India AADHAR uniquely identifies the citizens of INDIA by their thumb impression and also provides the other details like Date of birth, address, gender, father’s name, Spouse details etc. The election process is carried out in 3 steps Creation of voter list, actual voting process, and counting of votes. Creation of voter list can be done by database which is efficient to store big data with the person’s name and his AADHAR number. In actual voting process verification can be done by using fingerprint recognition and votes should be stored depending on ward numbers. Counting is the last process which can be done very easily if previous steps are digitized. In the world of Internet of things a voter should be able to cast his vote from anywhere by validating his credentials. This paper describes a voting system with 3 possible ways for voter to cast his vote.
Keywords: Digital Election System, Aadhar Card, Voter List, IoT Application.
Scope of the Article: Internet of Things

Download PDF

The post E10090285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10080285S20

IJRTE Journal — Fri, 17 Mar 2023 05:23:58 +0000

Detection of Face Spoofing using Color Texture and Edge Features
Neenu Daniel¹, A. Anitha²
¹Neenu Daniel, Department of CSE, Noorul Islam Centre for Higher Education, Nagercoil (Tamil Nadu), India.
²A.Anitha, Department of CSE, Noorul Islam Centre for Higher Education, Nagercoil (Tamil Nadu), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 33-37 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10080285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1008.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The wide scale use of facial recognition systems has caused concerns about spoofing attacks. Security is essential requirement for a face recognition system to provide reliable protection against spoofing attacks. Spoofing happens in situations where someone tries to behave as an authorized user to obtain illicitly access the protected system to gain advantage over it. In order to identify spoofing attacks, face spoofing detection approaches have been used. Traditional face spoofing detection techniques are not good enough as most of them focus only on the gray scale information and discarding the color information. Here a face spoofing detection approach with color texture and edge analysis is presented. The approach for investigating the texture of input images, Local binary pattern and Edge Histogram descriptor are proposed. Experiments on a publicly available dataset, Replay attack, showed excellent results compared to existing works.
Keywords: Face Recognition, Color Texture Analysis, Spoofing Attacks, Spoofing Detection
Scope of the Article: Pattern Recognition

Download PDF

The post E10080285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

E10070285S20

IJRTE Journal — Fri, 17 Mar 2023 05:16:52 +0000

PyTorch YOLOv3 Object Detection for Vehicle Identification
Mohith Rajendra¹, Susobhit Panigrahi², Rashmi Joyappa Kand³, Shreya Sridhar⁴
¹Mohith Rajendra, Department of Software Developer, Bangalore (Karnataka), India.
²Susobhit Panigrahi, Department of Software Developer, Bangalore (Karnataka), India.
³Rashmi Joyappa, Department of Software Developer, Bangalore (Karnataka), India.
⁴Shreya Shridhar, Senior Business Analyst, Bangalore (Karnataka), India.
Manuscript received on 13 February 2020 | Revised Manuscript received on 20 February 2020 | Manuscript Published on 28 February 2020 | PP: 30-32 | Volume-8 Issue-5S February 2020 | Retrieval Number: E10070285S20/2020©BEIESP | DOI: 10.35940/ijrte.E1007.0285S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Detecting real-world vehicle objects captured from car-mounted cameras requires manual labelling of video images. Previous vehicle object detection papers such as the winners of the 2018 AI City Challenge [1] used a training set of over 4,500 hand labelled images. In this paper, we attempt to automate this task by applying transfer learning to a YOLOv3 model trained on Imagenet and then re-trained on a set of stock car images and a small subset of hand labelled images taken from front-mounted dashboard camera videos. The mean Average Precision (mAP) of the validation set is used to determine the effectiveness of model vehicle classification. There is a significant variance issue between the validation and training set because the video images are taken in 1) various weather and lighting conditions and 2) the stock images have different image perspectives. The experimental results demonstrate that the YOLOv3 model can reach an overall 16.07% mAP after 60 epochs of training and can identify classes of vehicles that had few training examples in the dataset.
Keywords: Object Detection, Image Processing, Pytorch, Yolov3, R-CNN, Fast R-CNN, Faster R-CNN, Deep Learning, Map, IOU.
Scope of the Article: Image Processing and Pattern Recognition

Download PDF

The post E10070285S20 appeared first on International Journal of Recent Technology and Engineering (IJRTE).