Vol. 7 No. 05 (2018) | International Journal of Engineering and Computer Science

Home
Archives
Vol. 7 No. 05 (2018)

Published: 2018-05-01

Articles

The Video Analytics Based Data Warehousing Using IoT

T. Swetha, S.Neethu Shaji, J. Vanishree, A.R. Sunita, V. Swetha

Pages No. 23883-23886

The Video Analytics Based Data Warehousing Using IoT

T. Swetha, S.Neethu Shaji, J. Vanishree, A.R. Sunita, V. Swetha

Video accumulations fundamentally have vast information volume. Video investigation attempts to normally discover illustrations and connections present in the substantial volume of video information, which can assist the end-customer with taking educated and savvy decisions and anticipate the future in light of the cases discovered transversely finished space and time. Video investigation help recognize protests in distribution centers. The measure of information is well rich in videos. To decipher and break down the video is troublesome Video examination expect a fundamental part for find cases and partner the recordings which can help end customers to get information and savvy decisions. Video examination perceives inquiries in warehousing. At the center of the item is a propelled question following motor that constantly tracks moving and stationary targets. A lightweight scattered video coding design is shown for video observation applications. Foundation casings and forefront maps are created utilizing a video examination module on the decoder side. A decoded outline is incorporated with the reproduced sub-outlines and the foundation outline. Through a reproduction, the proposed plot is seemed to accomplish better than anything cutting edge coding profitability while diminishing coding multifaceted nature enormously both at the encoder and the decoder. Every tracking method requires an object detection mechanism either in every frame or when the object first appears in the video. Object tracking is the process of locating an object or multiple objects over time using a camera. Once the object is tracked all the collected data’s are maintained in a database which is known as data warehousing. Then the collected data’s a placed in IoT.

More.. PDF

Abstract PDF Full text

Abstract 317 | PDF

A A Review on E-Ball Technology

Mrs. Abhilasha Khare

Pages No. 23887-23890

A A Review on E-Ball Technology

Mrs. Abhilasha Khare

We all are familiar with the word computer, and we all know that earlier computer was huge in size. Day by day the size of computer reduces and now a new concept of PC is introduced that is E-Ball Concept pc. The E-Ball concept PC is the smallest design among all the laptops and desktops. E-ball is design by “Apostol Tnokovski”, a 31 year old Macedonian product designer. He has replaced the old PC from the squares and rectangular shape with his newly designed wonder in a spherical shape. According to Apostol it is the best shape in nature and it draws everybody’s attention. It is the smallest PC ever made. The size of E-ball is just like a ball, we can keep in our pocket and move from one place to another. This PC contain everything in-built like keyboard, mouse etc. This PC concept features all the traditional elements like mouse, keyboard, large screen display, DVD recorder; speaker etc. It is yet to be launched in market. The research in this field is still going on.

More.. PDF

Abstract PDF Full text

Abstract 177 | PDF

Analysis of Machine Learning Techniques for Breast Cancer Prediction

Priyanka Gupta, Prof. Shalini L

Pages No. 23891-23895

Analysis of Machine Learning Techniques for Breast Cancer Prediction

Priyanka Gupta, Prof. Shalini L

Of all the deaths worldwide, the second most common cause of death is breast cancer. In 2011, the number of deaths was estimated to be 5.8 millions because of breast cancer. So, early diagnosis of cancer is very important. In this paper, machine learning techniques are explored in order to increase the accuracy of diagnosis. Methods such as CART, Random Forest, K-Nearest Neighbors are compared. The dataset used is obtained from UC Irvine Machine Learning Repository. The obtained accuracy prediction performances are proportionate to existing methods. However it is found that KNN algorithm has much better performance than the other techniques used in comparison.

More.. PDF

Abstract PDF Full text

Abstract 199 | PDF

Message Validation in Wireless Sensor Network

Shruti Amburle, Vaishali Khairnar

Pages No. 23896-23900

Message Validation in Wireless Sensor Network

Shruti Amburle, Vaishali Khairnar

Message authentication is one of the most efficient way to keep the data safe from unauthorized access and corrupted messages which is being forwarded in wireless sensor networks (WSNs). For this reason, many message authentication schemes have been developed, based on either symmetric-key cryptosystems or public-key cryptosystems. Many schemes have the restrictions of high computational and communication transparency and deficient in the scalability to node compromise attacks. To address these issues, a polynomial-based scheme was recently introduced. However, this scheme and its extensions all have the weakness of higher processing time determined by the degree of the polynomial when the number of messages transmitted is larger, the adversary can fully recover the polynomial.

This system allows the intermediate nodes authentication to transmit a larger number of messages without suffering with the time complexity problem. It is basically design to authenticate the message in network while transferring. Here we will utilize the elliptic curve polynomial y2 = (x3 + ax + b) mod p and comparison will be done between transmission with and without security mechanism of signatures. To prove that our approach is better than Polynomial based scheme we compare result between Elgamal signature analyses with ECC polynomial signature analysis.

More.. PDF

Abstract PDF Full text

Abstract 158 | PDF

Survey on Intrusion Detection System using Machine – Learning approaches

Blessing Solomon B.C, Jesu Jayarin. P

Pages No. 23901-23907

Survey on Intrusion Detection System using Machine – Learning approaches

Blessing Solomon B.C, Jesu Jayarin. P

Intrusion Detection Systems (IDSs) are a noteworthy line of guard for shielding system assets from illicit infiltrations. A lot of research is being done on the development of effective Network Intrusion Detection Systems. Anomaly based Network Intrusion Detection Systems are preferred over Signature based Network Intrusion Detection Systems because of their better significance in detecting novel attacks. The research on the datasets being used for training and testing purpose in the detection model is equally concerned as better dataset quality can advance offline Intrusion Detection. Recently, Machine Learning (ML) approaches have been implemented in the Network Intrusion Detection Systems (NIDS) to protect computer networks and to overcome network security issues. This survey paper aims at disclosing different strategies followed in Intrusion Detection Systems (IDSs) using machine learning over the years and because of the headway in advancements, our lucid view is just on the most recent patterns.

More.. PDF XML

Abstract PDF XML Full text

Abstract 142 | PDF

Quality assessment of mangoes using computer vision and machine learning

Sidharth Jail, Mosami Chinawalkar, Rahul Khedkar, Yash Rathi, Pujashree Vidap

Pages No. 23908-23913

Quality assessment of mangoes using computer vision and machine learning

Sidharth Jail, Mosami Chinawalkar, Rahul Khedkar, Yash Rathi, Pujashree Vidap

Food processing industry requires precise and accurate quality assessment of products. This assessment effects the price of product and also the storage and transport decisions. This paper intends to address the automation of quality assessment in mangoes using computer vision. The paper addresses two issues, namely the number of surface injuries and the time-to-maturity of the fruit. A visible spectrum image of the fruits is considered to extract the Region of Interest(RoI), which contain the fruit with minimal background. Each RoI is further subjected to segmentation techniques so as to identify the injured patches as well as the portion of immature(green) area on the fruit surface. The percentage of these areas is used to determine the grade and the time-to-maturity respectively for each product.

More.. PDF XML

Abstract PDF XML Full text

Abstract 468 | PDF

Driver Drowsiness Detection Based On Novel Eye Openness Recognition Method Using Image Processing

M.Valan Rajkumar, R.Sasi kala, S. Suresh, J.Chandra mohan

Pages No. 23914-23925

Driver Drowsiness Detection Based On Novel Eye Openness Recognition Method Using Image Processing

M.Valan Rajkumar, R.Sasi kala, S. Suresh, J.Chandra mohan

In this paper, we proposed a driver drowsiness detection method for which only eyelid movement information was required. The proposed method consists of two major parts. 1) In order to obtain accurate eye openness estimation, a vision based eye openness recognition method was proposed to obtain an regression model that directly gave degree of eye openness from a low-resolution eye image without complex geometry modeling, which is efficient and robust to degraded image quality. 2) A novel feature extraction method based on unsupervised learning was also proposed to reveal hidden pattern from eyelid movements as well as reduce the feature dimension. To develop such a system we need to install some hardware components like camera inside the vehicle, which can capture the image of the driver at a fixed interval, and an alarm system, which will alert the driver after detecting his/her level of drowsiness and in the next level it will stop the vehicle automatically. Now apart from these hardware components, we need a software part also, which can detect the level of drowsiness of the driver and is the main concern of our paper. In this paper, we develop a drowsiness detection system that will accurately monitor the open or closed state of the driver’s eyes in real-time. The proposed method was evaluated and shown good performance.

More.. PDF XML

Abstract PDF XML Full text

Abstract 398 | PDF

Bot Net of Things – A Survey

M. Shanmughapriya, G. Sumathi, K.C. Aarthi

Pages No. 23926-23930

Bot Net of Things – A Survey

M. Shanmughapriya, G. Sumathi, K.C. Aarthi

Internet of things is talk of the town now a days but the potential threat IoT has over the cyber safety is less emphasized. The possibility for attackers with all systems interconnected with no or less security measures installed in them, makes them vulnerable to all kinds of security attacks. Botnet consists of collection of private computers interconnected together and affected by malicious software, which can be controlled as a group without the owner’s knowledge. BotNet is roBot and Network combination, the bot here is the compromised device. Denial of service, spyware, email spam, click fraud, bit coin etc., and are some of the well-known attacks by botnet. Botnet control itself has become a community, which focuses on prevention, control and repair services. This paper focuses on detailed survey of botnet and it’s regarding features.

More.. PDF XML

Abstract PDF XML Full text

Abstract 126 | PDF

Identification and Detection of Missing RFID Tags using RUN Protocol

Parth Sagar, Ankita Jade, Nikita Bhirud, Gauri Patwari, Ankita Vaste

Pages No. 23931-23938

Identification and Detection of Missing RFID Tags using RUN Protocol

Parth Sagar, Ankita Jade, Nikita Bhirud, Gauri Patwari, Ankita Vaste

As human race or human society is growing, the wildlife/domestic animals are in danger. But as per natures rule, every living creature on this earth is important and has important role in ecosystem. The animals get misplaced sometimes and finding them is a tedious task. RFID and sensors have been deployed to detect and identify missing animals by affixing them with cheap passive RFID tag and monitoring them with RFID readers. In our project, system will help us to detect and find the missing animals using RUN protocol, using this the missing animals will get detected and the location will get generated automatically through google maps. RUN protocol uses slotted aloha for communication between tags and readers. It executes multiple frames for different seeds to reduce the effect of unexpected tags and also it reduces the time of missing tag detection and identification. RUN identifies 100% missing tags in the presence of unexpected tags where as other protocol only identifies 60% of missing tags.

More.. PDF XML

Abstract PDF XML Full text

Abstract 139 | PDF

Surveillance Robot for Military Application

S. A Joshi, Aparna Tondarkar, Krishna Solanke, Rohit Jagtap

Pages No. 23939-23944

Surveillance Robot for Military Application

S. A Joshi, Aparna Tondarkar, Krishna Solanke, Rohit Jagtap

This project presents a modern approach for surveillance at remote and border areas using multifunctional robot based on current IOT used in defense and military applications. This robotic vehicle has ability to substitute the solider at border area t provide surveillance. The robotic vehicle works both as autonomous and manually controlled vehicle using internet communication medium.This multisensory robot used to detect presence of enemy capture it in camera and give the live streaming to the authorized person Surveillance is major role while we workin on border area for this there is robot for surveillance purpose.This paper presents a smart surveillance robot for military application by using Raspberry Pi for security purpose. An field Raspberr pi sends a wireless command which is received by Authorized person on web Page and accordingly robot moves. The Video Streaming is done using Raspberry pi camera. The Raspberry pi programming is done in python language. The experimental result shows that the video streamed up to 15 frames per second.

More.. PDF XML

Abstract PDF XML Full text

Abstract 2174 | PDF

Estimation of age groups using facial recognition features

suman mann, bhuvnesh mehra, anshul mangla, shubham runwal, prateek singhal

Pages No. 23945-23951

Estimation of age groups using facial recognition features

suman mann, bhuvnesh mehra, anshul mangla, shubham runwal, prateek singhal

Facial recognition has been used to detect emotions, gender, expressions and identity. These topics have been extensively studied. But, automatic Age Estimation is a topic that has not been researched much. The basis of our topic is that there are features on the human face that change as our age increases and in our research we utilize these features for age group classification. We classify the images into 6 age groups- (0-6, 8-12, 15-20, 25-32, 38-53, 60-100). The process involves 3 stages: -Pre-processing, Feature Extraction, Classification. Preprocessing includes commotion decreasing, standardization and change of the crude information into structure that is suitable for the pattern recognition. A small set of good features is selected from the available features, in order to provide best matching information. This process discovers important features to obtain an effective and improved answer for a given problem which is the next step. At last the classification or clustering stage is performed. Classification comprises of allotting a class mark to a given pattern while clustering discoveries homogeneous small groups in information. We also deal with comparison study of various feature extraction techniques (Haar feature extraction, HOG feature extraction) and classification techniques (Naïve Bayes, SVM, KNN, Neural Network-Back propagation algorithm) and finally try to determine the best possible combination for age group classification. Convolutional Neural Networks is also applied to estimate the age groups.

More.. PDF XML

Abstract PDF XML Full text

Abstract 128 | PDF