22 Articles Published

1. INTROSPECTION OF VARIOUS K-NEAREST NEIGHBOR TECHNIQUES

Authors: M.VINYA BABU , SUHAS G. KULKARNI

Abstract: K-Nearest Neighbor (kNN) technique is used in different application areas, as it is very simple, highly efficient and effective. Its main advantage is simplicity but the disadvantages can’t be ignored. Hence many researchers proposed different forms of kNN technique under various situations. Broadly kNN techniques are categorized into structure based and non-structure based (structure less) techniques. The objective of this paper is to introspect the key idea, pros and cons and target data or application area behind every kNN technique. Principal Axix Tree (PAT), Orthogonal Structure Tree(OST) , Nearest Feature Line(NFL), Center Line (CL) ,k-d Tree, Ball Tree, Tunable NN etc. are structure based techniques whereas weighted kNN, Model based kNN, Ranked NN (RNN),Condensed NN, Reduced NN, Pseudo/Generalized NN, Clustered kNN (CkNN) , Mutual kNN ( MkNN), constrained RkNN etc. are structure less techniques developed on the basis of kNN. Structure based techniques reduces the computational c

Keywords: nearest neighbor, kNN, Data Mining

Pages: 89 - 92 | DOI: 10.15224/978-981-07-6260-5-65

2. A SURVEY ON INTERNET TRAFFIC CLASSIFICATION

Authors: AFZAL HUSSAIN SHAHID , M. P SINGH , PRABHAT KUMAR

Abstract: Internet traffic classification is remained to be important issue for years due to three major reasons. First, the fact that we cannot limit the number of users connected and obviously there would be continual increase in the number of users connected to the Internet with time. Second, increase in user access speed (due to the development of highly efficient hardware and software technology). Third, there are applications that require more network resources. This survey is done to find out the main problems in the field of Internet traffic classification and to acquire the knowledge about different classification techniques that have significant Impact on the scientific and research community.

Keywords: Application Identification, Traffic Measurement, Classification

Pages: 84 - 88 | DOI: 10.15224/978-981-07-6260-5-64

3. TCP-RP: A NEW VERSION OF TCP BASED ON FUZZY LOGIC

Authors: ARCHANA B. PATANKAR , RAHUL S. PATIL

Abstract: TCP is the most popular end to end communication protocol in wired as well as wireless communication networks. At any point of time during the communication using TCP it is the size of the congestion window (cwnd) which determines the performance of the TCP. In this paper, we propose a new version of TCP: TCP-RP. TCP-RP uses fuzzy logic to determine optimum cwnd size during the Slow Start and Congestion Avoidance phase of TCP and improves network performance.

Keywords: TCP-RP, congestion window(cwnd), acknowledgement (ACK) Sender Maximum Segment Size (SMSS), Bandwidth(BW), A, N.

Pages: 80 - 83 | DOI: 10.15224/978-981-07-6260-5-63

4. FACE DETECTION BASED ON VIDEO

Authors: BHAVIN PANDYA , NIRAJ ACHARI , SIDDHARTH BHAVSAR

Abstract: Face detection is a very important system used by a variety of applications like face recognition systems, automatic lens adjustment, video surveillance systems etc. These systems need to primarily identify frontal face images and use them for further processing. Thus, face detection forms a primary basis for many systems. In our system, we propose an algorithm that detects faces by four modules. In the first module, we simple will detect moving objects by frame differencing technique of motion detection. In the next module, we will crop the image based on color. We will find a specific range of color of human skin and accordingly crop the image. In the third module, we will verify the symmetry of the cropped parts. A symmetry algorithm will be applied to verify the symmetry of the given part. Finally, we will detect the eye of the face by comparing the image with various eye templates. If during any of the four modules, a part of the image does not meet the threshold of the algorithm

Keywords: motion detection, skin, face geometry, flood fill, HSV

Pages: 1 - 3 | DOI: 10.15224/978-981-07-6260-5-46

5. USING DECISION TREE CLASSIFIERS FOR EFFICIENT INTRUSION DETECTION SYSTEM

Authors: SACHIN P. GAVHANE , VARUNAKSHI BHOJANE

Abstract: Maximum Processing computation and more time consuming task has always been a limit in processing huge network intrusion data. This problem can be minimized through feature selection to condense the size of the network data involved. In this paper, we first preprocess dataset KDD 99 cup. Then we study and analysis of two decision tree algorithms (C4.5 and standard ID3) of data mining for the task of detecting intrusions and compare their relative performances. Based on this study, it can be concluded that C4.5 decision tree is the most suitable with high true positive rate (TPR) and low false positive rate (FTR) and low computation time with high accuracy.

Keywords: Intrusion Detection, KDD 99 Cup Dataset, C4.5, ID3

Pages: 4 - 9 | DOI: 10.15224/978-981-07-6260-5-47

6. AUTOMATION SYSTEM USING SPEECH RECOGNITION FOR SPEAKER DEPENDENCY THROUGH MFCC

Authors: AMOL C.WANI , PRABHAKAR V. MHADSE

Abstract: This paper discusses the methodology for project named “Automation System Using Speech Recognition for Speaker Dependency through MFCC”. Automation system is growing to improve the quality; the goal of design of speaker dependent automation is to provide an efficient integration and higher security among appliances. Such automation systems must comply with the household equipments. This paper discusses the overall design of Automation System Using Speech Recognition for Speaker Dependency through MFCC which is to be implemented. This system will have hardware for appliance interface using Zigbee wireless modules and speech processor. Software section includes development of Mel Frequency cepstral coefficient (MFCC) algorithm using MATLAB. The system focus on recognition of speech commands stored in data base of MATLAB and it is matched with incoming speech command of speaker. Using MFCC system will be speaker dependent, for speaker independent systems speech processor of will be used.

Keywords: automation system, MFCC, speaker identification, Speech processing, ZigBee module

Pages: 75 - 79 | DOI: 10.15224/978-981-07-6260-5-62

7. STUDY OF GRAPHICAL PASSWORD SCHEMES AND “TWO LEVEL” AUTHENTICATION TECHNIQUE FOR SOFTWARE APPLICATIONS

Authors: HEMANGI KULKARNI , SONAL AHUJA

Abstract: Login is the basic and primary stage of authentication to any system. For Login users create memorable passwords, so that they remember those passwords when they next need access to the system Users create their own passwords as system generated passwords are difficult to remember. Going with same fact such text based factors are vulnerable to many well known attacks. So an alternative method was designed that used Graphical Passwords that use images or representation of Images as passwords. There are various graphical password schemes and software’s in market. Text based passwords are mercilessly broken down so to mitigate the issues with the old methods advanced techniques have been proposed using Graphical Passwords. This paper aims at providing a comparative study of the various advance graphical password techniques available and I have also proposed a system using Cued Click Point Based Authentication for tightening the authentication process of any Online Application.

Keywords: Graphical Passwords, Recognition-Based Graphical User authentication, Recall-Based Graphical User Authentication, Pure Recall-Based Authentication, Cued Recall-Based Authentication, Usability, Security, Cued ClickPoint(CCP)

Pages: 10 - 14 | DOI: 10.15224/978-981-07-6260-5-48

8. SOLUTION OF PERIODIC BURGERS’ EQUATION USING MODIFIED IMPLICIT SCHEME WITH MULTIGRID METHOD

Authors: ABHIJIT KUMAR SINHA , DEBASISH PRADHAN , MURARI SHARAN

Abstract: In this article we discussed numerical solution of periodic Burgers’ equation using the implicit scheme with multigrid method and the solutions obtained here are compared with analytical solution. We constructed the exact solution using Cole- Hopf transformation and separation of variables.

Keywords: Multigrid method, V cycle, Burgers’ equation, Implicit scheme, Cole- Hopf Transformation, Sepration of Variable.

Pages: 15 - 19 | DOI: 10.15224/978-981-07-6260-5-49

9. CLUSTER HEAD SELECTION IN MOBILE WIRELESS SENSOR NETWORKS: A SURVEY

Authors: M. P SINGH , PRITI KUMARI , PRABHAT KUMAR

Abstract: Wireless sensor networks have made the task of surveillance and detection easy up to greater extent. And mobile wireless sensor network is an advancement of wireless sensor network in a way to fulfil requirements of current surveillance techniques more appropriately. In this survey paper, we have considered an important part of mobile wireless sensor network i.e. clustering. So far proposed and implemented algorithms for clustering in mobile wireless sensor network is discussed here with the consideration of LEACH as a basic algorithm for clustering in wireless sensor network.

Keywords: Mobile wireless sensor network, clustering, cluster head, LEACH

Pages: 20 - 24 | DOI: 10.15224/978-981-07-6260-5-50

10. BACKGROUND ESTIMATION USING 3 PARAMETER BASED RUNNING AVERAGE METHOD

Authors: DEBASISH PRADHAN , RADHE SHYAM SHARMA

Abstract: In this paper, we have discussed the background estimation using “3 parameter based running average method”, and then used background subtraction followed by an appropriate thresholding operation to detect the moving object. Our main aim is to do the background modeling to get moving object. In this process, detection of moving object directly depends on background model. Numerical experiments confirm our theoretical results.

Keywords: Background estimation, motion detection, running average and temporal difference

Pages: 25 - 25 | DOI: 10.15224/978-981-07-6260-5-51

11. GRAPH EMBEDDING FRAMEWORK ON RELEVANCE FEEDBACK: A SURVEY

Authors: BELAJOGLEKAR , TEJASWINIYADAV

Abstract: To improve the performance of the content based image retrieval (CBIR), relevance feedback (RF) plays an important role as it allows interactive image retrieval. Different RF techniques have been proposed, such as density estimation RF algorithm, subspace learning algorithm, classification based algorithm etc. The existing density estimation algorithm considers only positive samples and classification based algorithms considers positive and negative samples in different groups . Subspace learning algorithm assumes that positive and negative samples are linearly distributed .But existing algorithms are having the main drawback of semantic gap as well as ‘small sample size’ problem. In this paper, we discuss various RF techniques proposed earlier in the literature. The advantages of using a graph embedding framework for RF are also discussed. In addition this paper also provides a comparative study of various methods proposed by researchers in RF.

Keywords: Image retrieval, content based image retrieval (CBIR), relevance feedback (RF).

Pages: 29 - 32 | DOI: 10.15224/978-981-07-6260-5-52

12. SMART HOME SYSTEM CONTROLLING ELECTRICAL APPLIANCES VIA BLUETOOTH AD HOC NETWORK COMMUNICATION ON ANDROID PLATFORM

Authors: MONICA DESWAL , SUDHIR KUMAR

Abstract: Technology is endless process and it is being developed continuously. Bluetooth Based Home Automation System[1] is one of the recent technology came in existence. Each technology has several limitations. This paper emphasizes on the limitation of this technology and some advancement in technology to overcome those limitations. This design is presented to overcome the limited range limitation of Bluetooth devices and routing problem. This also focuses on decreasing operational and maintenance cost of the network established. The main idea of paper is to establish wireless ad hoc network for communication between several devices

Keywords: Home, Automation, System

Pages: 33 - 37 | DOI: 10.15224/978-981-07-6260-5-53

13. EMERGENCY INDICATION AND WARNING SYSTEM FOR FISHERMEN

Authors: DHARANI.S , FATHIMA NIHAR.C , HARIPRIYA.G

Abstract: This paper is done in the intention of saving and protecting our fishermen from natural disasters and boundary crossing. The device will consist of a tracker and a travel logger that will help locate the position of the fishermen by the coast guard. It will give a warning when the fishermen cross the boundary to themselves and to the coast guard. It will also consist of a sensor that will detect storm, and warn the fishermen and the coast guard in case of danger such as heavy storm, etc. In case of such danger or of any kind, the coast guard, nearby police station and hospital will be intimated automatically. The fisherman can also manually intimate the coast guard, nearby police station and hospital. If in case of tsunami alerts, the coast guard or the nearby police station can intimate the fishermen. This device also enables the alerts to reach the fishermen. Also the device will be made using a material such that it will float on water and will not be affected due to contact with wa

Keywords: Lightning sensor, GPS tracker, GSM, energy efficient system, floatation device.

Pages: 66 - 69 | DOI: 10.15224/978-981-07-6260-5-60

14. IMAGE RETRIEVAL USING NAVIGATION PATTERN FOR RELEVANCE FEEDBACK: A SURVEY

Authors: BELAJOGLEKAR , KARISHMAMUTHA

Abstract: This paper addresses survey of work done on relevance feedback in the past few years. Till date, various techniques have been proposed for relevance feedback. Some techniques used Bayesian classifier, while others are log based and Neuro-fuzzy based. Some of them use human computer interaction for providing feedback. However, existing methods require a large number of iterations and also it is difficult to converge the query towards user intention. Hence, in this paper we present some of the recent techniques that overcome the above disadvantages and their comparative analysis.

Keywords: Navigation Pattern, Relevance Feedback

Pages: 38 - 42 | DOI: 10.15224/978-981-07-6260-5-54

15. QUANTITATIVE BEHAVIOR BASED INTRUSION DETECTION SYSTEM FOR MANETS

Authors: A DAMODARAM , S.MAMATHA

Abstract: The use of wireless links makes a Mobile Ad hoc Network(MANET) susceptible to malicious attacks, ranging from passive eavesdropping to active interference. In wired networks an attacker has to pass through a set of firewalls and gateways to access the network. Whereas MANETS does not have firewalls or gateways so attacks can take place from all directions. Every node in a MANET is an autonomous unit in itself and free to move independently. So any node without adequate protection is very much prone to be captured or compromised. Intrusion prevention techniques like encryption and authentication can reduce the risk of intrusion but cannot completely eliminate them so a second level of defense is needed. We propose a new quantitative method of intrusion detection system to detect intrusion in MANETS with mobile nodes. The proposed method is a behavioral anomaly based system which is dynamic, scalable, configurable and robust. For simulating the proposed system we use AODV routing protoco

Keywords: AODV routing protocol, Intrusion Detection System, Mobile Ad hoc Network (MANET)

Pages: 61 - 65 | DOI: 10.15224/978-981-07-6260-5-59

16. PASSWORD AUTHENTICATION THROUGH LIP READING USING HUMAN MACHINE INTERFACE

Authors: SHARMILA SENGUPTA , VIBHANSHU GUPTA

Abstract: This paper is about a lip reading technique for speech recognition by using motion estimation analysis. It presents a user authentication system based on password lip reading. Motion estimation is done for lip movement image sequences representing speech. In this methodology, the motion estimation is computed without extracting the speaker’s lip contours and location. This leads to obtaining robust visual features for lip movements representing utterances. The proposed methodology comprises of two phases, a training phase and a recognition phase. In both the phases an n x n video frame of the image sequence for an utterance (password) is divided into m x m blocks. This method calculates and fits eight curves for each frame. Each curve represents motion estimation of this frame in a specific direction. These eight curves are representing set of features of a specific frame and are extracted in an unsupervised manner. The feature set consists of the integral values of the motion estimati

Keywords: component, formatting, style, styling, insert

Pages: 43 - 47 | DOI: 10.15224/978-981-07-6260-5-55

17. CARNITINE TRANSLOCASE IN CARDIAC CELL: STRUCTURAL, FUNCTIONAL AND FLUX BALANCE ANALYSIS IN PRE-ß-OXIDATION PATHWAY OF HOMO SAPIENS

Authors: SOMNATH TAGORE , TARIKA VIJAYARAGHAVAN

Abstract: Fats are stored in the body in the form of fatty acids and reused whenever the body is unable to consume essential fats (at the time of exercise, fasting etc). In the human heart cell, the transport of certain fatty acids into the mitochondria is required to produce energy. This is done via a certain enzyme called Carnitine Translocase. This work deals with the detection and manipulation of carnitine translocase in order to analyze its importance in avoiding certain cardiovascular disorders like hyperglycemia, arrhythmia etc.

Keywords: carnitine translocase, flux balance analysis, transcription factor

Pages: 48 - 51 | DOI: 10.15224/978-981-07-6260-5-56

18. A NOVEL APPROACH TO UNIFORMLY DISTRIBUTE THE LOAD IN WIRELESS SENSOR ROUTING PROTOCOL LEACH

Authors: G. RAM MOHANA REDDY , NITISH SABOO , PRAJNA PANDURANG BHAT , RAHUL YADAV , SURESH PANWAR

Abstract: A wireless sensor network (WSN) consists of spatially distributed autonomous sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. and to cooperatively pass their data through the network to a main location. Energy efficiency is the important key for WSN. To lower the energy consumption, the network is divided into several clusters in cluster routing algorithm LEACH (Low Energy Adaptive Clustering Hierarchy). Even though clustering provides energy efficiency, but uneven load distribution still occurs in general. In this paper an approach is presented which divides the deployment region into sub-regions and thereby uniformly distributing the load among the sensor nodes. Different shapes are considered for dividing the deployment region into equal sub-regions.

Keywords: wireless sensor network, energy efficiency, LEACH, load distribution

Pages: 52 - 56 | DOI: 10.15224/978-981-07-6260-5-57

19. AUTOMATED RAILWAYS COLLISION AVOIDANCE SYSTEM USING WIRELESS NETWORKS

Authors: MEENAKSHI SOOD , ABHISHEK GOYAL , AMIT BIR SINGH CHADHA , DAVISHA VERMA

Abstract: This paper concentrates on predicting and removing the major cause of railway accidents, that is, head-on collisions on the same track. For this purpose we are using advanced technology to identify train positions, detect collision as well as the points where collisions may occur. The primary goal of this paper is to provide an anti-collision safety device for vehicles travelling on tracks, even without any driving personnel, that is to say, a device which itself can estimate risks and react in consequence. This ensures that if any collision is likely to occur, then this system will help to avoid collisions by giving an alarm in time and actuating emergency brakes if required. The goal of this work is to design and implement a cost effective and intelligent full-fledged microcontroller and wireless based Train Anti Collision System to successfully prevent the train collisions. It aims at efficiently integrating into the existing signaling system implemented in Indian Railways and avoid

Keywords: GSM (Global System for Mobile Communication), GPRS (General Packet Radio Services), GPS (Global Positioning System), ZigBee, CAS (Collision Avoidance System).

Pages: 57 - 60 | DOI: 10.15224/978-981-07-6260-5-58

20. QUANTITATIVE BEHAVIOR BASED INTRUSION DETECTION SYSTEM FOR MANETS

Authors: A DAMODARAM , S.MAMATHA

Abstract: The use of wireless links makes a Mobile Ad hoc Network(MANET) susceptible to malicious attacks, ranging from passive eavesdropping to active interference. In wired networks an attacker has to pass through a set of firewalls and gateways to access the network. Whereas MANETS does not have firewalls or gateways so attacks can take place from all directions. Every node in a MANET is an autonomous unit in itself and free to move independently. So any node without adequate protection is very much prone to be captured or compromised. Intrusion prevention techniques like encryption and authentication can reduce the risk of intrusion but cannot completely eliminate them so a second level of defense is needed. We propose a new quantitative method of intrusion detection system to detect intrusion in MANETS with mobile nodes. The proposed method is a behavioral anomaly based system which is dynamic, scalable, configurable and robust. For simulating the proposed system we use AODV routing protoco

Keywords: AODV routing protocol, Intrusion Detection System, Mobile Ad hoc Network (MANET)

Pages: 61 - 65 | DOI: 10.15224/978-981-07-6260-5-59

21. E-LEARNING IMPLEMENTATION: BENEFITS AND CHALLENGES IN DEVELOPING COUNTRIES

Authors: AYMAN A. ALTAMEEM

Abstract: E-learning (electronic learning) is emerging as the new paradigm of modern education. Educational institutions, either willingly or reluctantly, are increasingly embracing e-learning in order to remain competitive and improve their services. Advances in e-learning technologies have initiated significant opportunities and threats to institutions within the education sector. With particular reference to e-learning, the absence of accurate information on the key challenges which influence the implementation of e-learning in developing countries could mislead an institution into implementation failure. The extant research tends to specifically focus on developed countries, with little undertaken in developing countries, especially with regards to the implementation process. Therefore, this study investigates the challenges that hinder the implementation of e-learning in developing countries. It also presents the benefits that have emerged with the implementation of e-learning. The positive

Keywords: e-learning, developing countries, challenges

Pages: 70 - 74 | DOI: 10.15224/978-981-07-6260-5-61

22. AN FPGA EMBEDDED ACCA ARCHITECTURE FOR HIGH RESOLUTION TARGET DETECTION

Authors: RIDHA DJEMAL

Abstract: This paper presents an efficient FPGA-based architecture of CFAR target detector for radar system based on the automatic censored cell averaging (ACCA) detector based on ordered data variability (ODV). The ACCA–ODV detector estimates the unknown background level by dynamically selecting a suitable set of ranked cells and applying successive hypothesis tests. The proposed detector does not require any prior information about the non homogenous background environment. It uses the variability index statistic as a shape parameter to accept or reject the ordered cells under investigation. The detection process is achieved on the fly in real-time where the processing time must be lower than 0.5 µs for high resolution detection. The proposed architecture is based on the embedded software solution which consists on execution an the ANSI-C code of the detector over the Nios-II soft-core processor downloaded in the FPGA with the requires hardware components, such as on-chip memories, UART and JT

Keywords: Constant False Alarm Rate (CFAR), Target Detection, Embedded System, Programmable device FPGA, Ordered Data Variability (ODV)

Pages: 10 - 14 | DOI: 10.15224/978-981-07-6261-2-47