Accepted Papers

PERFORMANCE ANALYSIS OF CONGESTION CONTROL TECHNIQUES ADTCP AND IMPROVED-ADTCP: FOR IMPROVING TCP PERFORMANCE OVER AD-HOC NETWORKS.

Sreenivasa B.C¹ and G.C. Bhanu Prakash² ,

¹Associate Professor Department of Computer Science and Engineering Research Scholar, SAHE Uni-versity ,Tumkur

²Professor Department of Computer Science and Engineering, SirMVisvesvarayaInstituteofTechnology-Bangalore,INDIA

ABSTRACT

Identifying the occurrence of congestion in a Mo-bile Ad-hoc Network (MANET) is a major task. The inbuilt congestion control techniques of existing Transmission Control Protocol (TCP) designed for wired networks do not handle the unique properties of shared wireless multi-hop link. There are several approaches proposed for detecting and overcoming the congestion in the mobile ad-hoc network. In this paper we present a Modified AD-hoc Transmission Control Protocol (IMPROVED-ADTCP) method where the receiver detects the probable current network status and transmits this information to the sender as feedback. The sender behavior is altered appropriately. The proposed technique is also compatible with standard TCP.

KEYWORDS

Congestion, TCP, Ad-hoc.

UNSW-NB15 DATASET FEATURE SELECTION AND DATA VISUALIZATION

V. Kanimozhi,School of Computing,Sathyabama Institute of Science & Technology, Chennai, India

ABSTRACT

Anomaly detection system in network, monitors and detects intrusions in the networking area, which forms the Network Intrusion Detection System (NIDS). The various network datasets are available in networking communications with relevant and irrelevant features, which drastically decreases the rate of intrusion detection and increases False Alarm Rate. The recently available network dataset is UNSW-NB15 dataset was created in 2015. The top significant features are proposed as feature selection for dimensionality reduction in order to obtain more accuracy in attack detection and to decrease False Alarm Rate. We apply a combination fusion of Random Forest Algorithm with Decision Tree Classifier using Anaconda3 (a free and open-source distribution of Python3) and package management system Miniconda (package manager) in which 45 features have been decreased to the strongest four features.

KEYWORDS

Data visualization; feature selection; intrusion detection; UNSW-NB15 Dataset

FEATURE EXTRACTION AND AUTHENTICATION OF THE IRIS OF A HUMAN EYE

Barsha Deka, Sharmistha Sarkar and Jyotismita Sarma Department of Electronics and Telecommunication, Royal School of Engineering and Technology, Assam

ABSTRACT

With the need for security systems going up, Iris recognition is emerging as one of the most important methods of biometrics-based identification systems. This paper discusses about iris recognition which is used to overcome some of the problem like to automate the recognition of the iris by reducing complexity and increasing algorithm speed. To derive a unique mapping, Iris recognition systems make use of the uniqueness of the iris patterns. Iris recognition system outperforms others because of its high accuracy. Three stages are followed while working with this iris system i.e. preprocessing, feature extraction and recognition stage. This paper presents an automated iris recognition system where overall computational match speed is reduced. The proposed method is tested with the CASIA database iris images, which consists of left and right eye set for the different human. The proposed method reduces the FAR to 15.6 percent and FRR to 14 percent.

KEYWORDS

Iris recognition, FAR, FRR.

SEGMENTATION AND DETECT MOVING RGB OBJECT BASED ON KINECT

Ahmed Mustafa Taha Alzbier, Han Cheng,Mohamed Tahir, Jiang Shan, Umer Syed Changchun University of Science and Technology, Changchun, China

ABSTRACT

As the present field of computer vision technology is growing up fast, the Image processing is most important in this field used to produce digital maps and satellite photos, which yields more accurate results. Kinect Capture the video frames using the video input function in MATLAB and Set the properties of the video object. Moving RGB object detection and segmentation is an important and fundamental topic in computer vision. Its applications can be found in a large number of engineering fields .However, object detection is defined as extracting the motion part of a video stream. Now in this paper to detection and segmentation RGB colour objects in real time we have to subtract the colour component of the gray scale image to extract the components in the frame image. And use a median filter to filter out noise. A median filter is more effective than convolution when the goal is to simultaneously reduce noise. However, the adaptive median filtering can handle impulse noise with probabilities even larger than these, and Convert the resulting gray scale image into a binary image. Remove all those pixels less than what you want, Label all the connected components in the image. And we do the image blob analysis get a set of properties for each labelled region. Generally, this paper is organized as follows. We describe our proposed algorithm for object colour detection and segmentation .The concept of the motion detection, background subtraction, segmentation. How to make the colour and segmentation followed by some experimental results and conclusions.

KEYWORDS

Computer Vision, Color Model, Median filter, Blob Analysis, Median filter, Kinect, Segmentation, Background Subtraction

INTRINSIC AND EXTRINSIC VARYING EFFECTS ON PHOTOVOLTAIC SOLAR PANEL PARAMETERS FOR I-V AND P- V CURVES CHARACTERISTICS BY MATLAB/SIMULINK

Burak Akin and Idriss Dagal Yildiz Technical University Istanbul, Turkey

ABSTRACT

The characteristics of PV solar panel for standalone system use will be studied based on manufacturer specifications in order to assure the adequate power required for the system normal operation. We examine in this paper different I-V and P-V curves based on the variation of environment and panel internal parameters effects. These studies are carrying further in order to give a success results to standalone maximum power point tracking to battery charge controller for the suburb or rural areas applications.

KEYWORDS

Photovoltaic solar panel, extrinsic-intrinsic effects, current-voltage, power-voltage curves behaviors and Matlab/Simulink

IMPROVEMENT OF THE RECOGNITION OF RELATIONSHIPS IN SOCIAL NETWORKS USING COMPLEMENTARY GRAPH COLORING BASED ON CELLULAR AUTOMATA

Mostafa Kashani, Saeid Gorgin1, SeyedVahab Shojaedini Department of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology (IROST), Tehran, Iran

ABSTRACT

Each social network can be modeled as a graph G = [V, E] in which V is a vertex representing a person in this social network, and E is an edge representing the existence of a relationship between two individuals. The social infrastructure with size m is known as the Km group in the social network G with m individual. In other words, in aKm, each person knows other individuals and is in touch with them. The present study aims at developing a method for optimizing interpersonal communication in the social network using a simple cellular automaton algorithm. The experimental resultsobtained from both simulated social network and two real social networks were analyzed.The findings revealed that the proposed method has the potential to considerably reduce not onlythe number of colorsassignedbut also the running time of the program.

KEYWORDS

Social networks, Graph coloring, Cellular automata

Improving Lifetime of Wireless Sensor Network through Energy Efficient Target Coverage under QoS Constraints

Ankur Tripathi, A.K. Daniel, Pooja Chaturvedi

ABSTRACT

Wireless sensor networks (WSNs) are gaining considerable importance in recent times due to its application in remote and hazardous environmental conditions. The battery-driven sensing devices are used to sense the region of interest and transmitting the sensed data to a central node (sink), so extending the network lifetime is crucial task. These tasks are energy consuming so effective power management schemes such as scheduling the nodes can extend the lifetime. The sensor nodes are often deployed randomly in the vicinity of the targets where deterministic deployment of sensors is not feasible to monitoring the given set of targets. The loss of exact sensor placement due to random deployment is compensated by increasing the density of sensors. The paper proposes an energy efficient mechanism to increase the lifetime of WSN. One of the methods to increase lifetime is organizing the sensor nodes into a number of several set covers. Sensors in the active set monitor the targets, while sensors from remaining sets are kept in sleep mode which is a low energy state. This optimization problem can be defined as the maximum set covers (MSC) problem and is NP-Complete and no solution exists for this problem in polynomial time. Hence a greedy based heuristic for energy efficient sensor scheduling is proposed to achieve near optimal solution. We have also incorporated a Quality of Service (QoS) parameter which considers the unutilized sensors remained after the network operation time. The simulation results show that as the number of sensors, number of targets and the sensing range is increased, the network lifetime is also increased.

KEYWORDS

Congestion, TCP, Ad-hoc.

Order Preserving Stream Processing in Fog Computing Architectures

K. Vidyasankar

Department of Computer Science,Memorial University of Newfoundland,St. John's, Newfoundland, Canada

ABSTRACT

A Fog Computing architecture consists of edge nodes that generate and possibly pre-process (sensor) data, fog nodes that do some processing quickly and do any actuations that may be needed, and cloud nodes that may perform further detailed analysis for long-term and archival purposes. Processing of a batch of input data is distributed into sub-computations which are executed at the different nodes of the architecture. In many applications, the computations are expected to preserve the order in which the batches arrive at the sources. In this paper, we discuss mechanisms for performing the computations at a node in correct order, by storing some batches temporarily and/or dropping some batches. The former option causes a delay in processing and the latter option affects Quality of Service (QoS). We bring out the trade-offs between processing delay and storage capabilities of the nodes, and also between QoS and the storage capabilities.

KEYWORDS

Fog computing, Order preserving computations, Quality of Service

Job Matching Application Using Profile Matching Model

Leah G. Rodriguez and Enrico P. Chavez

Graduate Programs, Technological Institute of the Philippines, Manila,Philippines

ABSTRACT

The advancement of technology has created big changes to speed up the job hiring process nowadays. With more tools developed, companies have embraced tools that help them recruits talents. This is a research-in-progress of developing a job matching application system for Job Recruitment Agency specifically in the province of Pangasinan, Philippines. This paper proposes an approach for the agency to extract the relevant information from resumes and analyze it based on the different attributes. With the identificication of the attributes, the proposed system is directed to adopt a clusterring algorithm to match the profile of the job seekers against the requirements of the job posted by the prospect employers. This helps the agency to find suitable candidates for a particular job in different companies and make more informed decisions.

KEYWORDS

Data mining, job matching application, profile matching model.

VARIABLE SELECTION FOR CREDIT RISK SCORING ON LOAN PERFORMANCE USING REGRESSION ANALYSIS

Dawn Iris Calibo and Melvin A. Ballera

Graduate Programs, Technological Institute of the Philippines, Manila, Philippines

ABSTRACT

The advancement of information technology has accelerated developments in the field of credit management. This is reciprocated by the introduction of data analytics to process relevant information that could be useful in financial granting decisions. With this, the researcher presents a research-inprogress of designing a risk analysis and recommendation system for the Department of Science and Technology VII Small & Medium Enterprise Technology Upgrading Program. Prior to system development selected variables to be used for credit scoring was identified through data mining using tableau software based on the project guidelines and 9-year historical data on granted loan projects. This was executed utilizing linear regression and trend model visualization for analysis. After validation, a proposed decision matrix on credit scoring was made. This becomes the basis for the development of the credit risk analysis and recommendation system by computing the center of gravity of each score through the fuzzy logic algorithm.

KEYWORDS

Credit Risk Analysis, Credit Risk Scoring, Linear Regression, Loan Performance, Variable Selection

INTER-APPLICATION COMMUNICATION: A PROTOTYPE IMPLEMENTATION

Kalaiselvi Arunachalam¹, Gopinath Ganapathy²

¹ School of Computer Science, Engineering and Applications, Bharathidasan University, India

² Registrar, Bharathidasan University, India

ABSTRACT

A growing popularity of smart devices of various type, shape and form factor with multitude of applications from diverse categories and data are used to meet the demands of users in their digitally enriched living environment. The data sharing between these applications would be beneficial to the users when these heterogeneous devices are used together by them in their home network. The inter-application communication enables an application to discover, connect and share data with other applications across heterogeneous devices in a home network. This paper provides a prototype implementation of the inter-application communication in a home network along with a brief summary about its demand in near future.

KEYWORDS

Inter-application Communication, Prototype Implementation, Home Network, App-to-App Communication, Heterogeneous Devices

Magnetic Anomalies Due To 2-D Cylinrical Structures - An Artifical Neural Network Based Inversion

Bhagwan Das Mamidala¹ and Sundararajan Narasimman²

¹ Department of Mathematics, Osmania University, Hyderabad-500 007, India

² Department of Earth Science, Sultan Qaboos University, Muscat, Oman

ABSTRACT

Application of Artificial Neural Network Committee Machine (ANNCM) for the inversion of magnetic anomalies caused by a long-2D horizontal circular cylinder is presented. Although, the subsurface targets are of arbitrary shape, they are assumed to be regular geometrical shape for convenience of mathematical analysis. ANNCM inversion extract the parameters of the causative subsurface targets include depth to the centre of the cylinder (Z), the inclination of magnetic vector(O) and the constant term (A) comprising the radius(R) and the intensity of the magnetic field (I). The method of inversion is demonstrated over a theoretical model with and without random noise in order to study the effect of noise on the technique and then extended to real field data. It is noted that the method under discussion ensures fairly accurate results even in the presence of noise. ANNCM analysis of vertical magnetic anomaly near Karimnagar, Telangana, India, has shown satisfactory results in comparison with other inversion techniques that are in vogue

KEYWORDS

Magnetic anomaly, Artificial Neural Network, Committee machine, Levenberg - Marquardt algorithm, Hilbert transform, modified Hilbert transform

A Survey On The Different Implemented Captchas

Shadi Khawandi, Firas Abdallah,Anis Ismail

Faulty of Technology, Lebanese University, Lebanon

ABSTRACT

CAPTCHA is almost a standard security technology, and has found widespread application in commercial websites. There are two types: labeling and image based CAPTCHAs. To date, almost all CAPTCHA designs are labeling based. Labeling based CAPTCHAs refer to those that make judgment based on whether the question ''what is it?'' has been correctly answered. Essentially in Artificial Intelligence (AI), this means judgment depends on whether the new label provided by the user side matches the label already known to the server. Labeling based CAPTCHA designs have some common weaknesses that can be taken advantage of attackers. First, the label set, i.e., the number of classes, is small and fixed. Due to deformation and noise in CAPTCHAs, the classes have to be further reduced to avoid confusion. Second, clean segmentation in current design, in particular character labeling based CAPTCHAs, is feasible. The state of the art of CAPTCHA design suggests that the robustness of character labeling schemes should rely on the difficulty of finding where the character is (segmentation), rather than which character it is (recognition). However, the shapes of alphabet letters and numbers have very limited geometry characteristics that can be used by humans to tell them yet are also easy to be indistinct. Image recognition CAPTCHAs faces many potential problems which have not been fully studied. It is difficult for a small site to acquire a large dictionary of images which an attacker does not have access to and without a means of automatically acquiring new labeled images, an image based challenge does not usually meet the definition of a CAPTCHA. They are either unusable or prone to attacks. In this paper, we present the different types of CAPTCHAs trying to defeat advanced computer programs or bots, discussing the limitations and drawbacks of each.

KEYWORDS

CAPTCHAs, Labeling,Segmentation, Image recognition

A Survey On Image Spam Detection Techniques Model

Shadi Khawandi, Firas Abdallah,Anis Ismail

Faulty of Technology, Lebanese University, Lebanon

ABSTRACT

Today very important means of communication is the e-mail that allows people all over the world to communicate, share data, and perform business. Yet there is nothing worse than an inbox full of spam; i.e., information crafted to be delivered to a large number of recipients against their wishes. In this paper, we present a numerous anti-spam methods and solutions that have been proposed and deployed, but they are not effective because most mail servers rely on blacklists and rules engine leaving a big part on the user to identify the spam, while others rely on filters that might carry high false positive rate.

KEYWORDS

E-mail, Spam, anti-spam, mail server, filter.