VOLUME 6, ISSUE 8, AUGUST 2017
Assessing Emerging Innovative Applications used in County Governments of Kenya
Esau Mneria Mengich, Samuel Liyala, Anthony Rodrigues
Information hiding by using Developed M8PAM Technique
Mustafa B. Mahmood, Ban N. Dhannoon
Sentiment Analysis from Opinion Mining to Human-Agent Interaction
S. Venkatesan, M. Muthuraman
Security Enhancement through Third Party Auditing for Data Storage in Cloud Computing using RC5 Algorithm
T. Kalaiselvi, Dr. S. Ravichandran Ph.D.,
Comparative Study of Scheduling Algorithms to Enhance the Performance of Virtual Machines in Cloud Computing
S. Uma Maheswari, Dr. S. Ravichandran Ph.D
An Analysis of Load Balancing Algorithms in Cloud Computing
M. Nagalakshmi, M.Sc., M. Phil., Dr. K. David, M.Sc., M. Phil, M.Tech., Ph.D
Behavioral Model for Banking Customer based on Neural Network with Time Series
V. Anbalagan, A. Malarvizhi
A Neural Network Based Kidney Segmentation from MRI Images
C. Kubendran, R. Malathi
BAN: ACLs and Route-Redistribution
Vishesh S, Nidhi AJ, Manaswini S, Preethi R, Pratiksha D Bhandarkar, Murugheshgouda VH
Advanced Communication Network using Markov Chain Technique in MIMO-OFDM
Gauri B. Maske, Prof. S. B. Mule
A Review: AODV & DYMO Protocols Effects of Black Hole Attack in MANET
Manju, Mr. Kapil Kaswan
Pre Neighbour Node Route Discovery Technique for Energy Efficient Routing in WSN
Paramjit Singh, Tejinderdeep Singh
Content-Based Picture Retrieval through Color, Texture and Shape Factors
Rashmi Police Patil, Anita Dixit
An Effective Intrusion Detection System using CRF based Cuttlefish Feature Selection Algorithm and MSVM
A. Baby, Dr. S. Ravichandran Ph.D.,
BAN- Implementation
Vishesh S, Ragavi P Ashok, Sachin MC Reddy, Meghana C, Sukruth L Babu, Parth Sharma
Kidney Abscess Segmentation and Detection on Computed Tomography Data
M. Dharani Devi, R. Malathi
A Case Study on Text Classification using Classification Algorithms and Latent Semantic Analysis
Shekhar Tanwar, Shalini L
Security Analysis on Software Defined Mobile Network
Mr. A. Venugopal M.Sc, M.Phil, Anila. N. V
Investigation of Intrusion and Denial of Service Attacks in Cloud Computing
Ayman A.A. Ali, Prof. Saif Eldin Fattoh Osman
Asymmetric Stereoscopic Video Super-Resolution and Depth Estimation
Ashwini Mahadik, Prof. R. P. Patil, Prof. Dr. S. K. Shah
Determining of Public Grievances- A Smart Way of City Management
Pratik Jayant Deshpande, Prof. Geeta Navalyal
School Students’ Performance Predication Using Data Mining Classification
Hafez Mousa, Ashraf Maghari
Web-Based Portal for Online Shopping
Vishesh S, Suhas S, Srivatsa S Murthy, Suraj Nagaraj, Amartejas M, Namratha Raj
Key Aggregate Cryptosystem for Scalable Data Distribution in Cloud Storage
D. Suguna Kumari, B. Rajesh, P. Vamshi Krishna, Y. Ramakrishna
Overview on Microarray using Advanced Regression for Lost Data
K. Lakshmipriya, Dr. R. Manickachezian
An Overview of Opinion Mining in Spatial Database for Web Based Application
Janani. S, Dr. R. Manickachezian
Overview of Sentimental Trend Analysis and Text Pattern Fetching
S. Maguda Gowreeswari, Dr. R. Manickachezian
Research Paper on Image Stegnography
Priyanka Sharma, Astha Gautam, Ruchi Singh
Generating Recommendations using an Association Rule Mining and Genetic Algorithm Combination
L.M.R.J Lobo, R. S. Bichkar
Churn Analysis with Machine Learning Algorithms
Buket Onal, Metin Zontul
Data Mining Techniques for Business Intelligence and Its Applications – A Survey
Mr. A. Venugopal, Jisha. P
An optimization based Power-Efficient Gathering in Sensor Information Systems (PRGASIS) for Wireless Sensor Network
Chandan Verma, Ashish Sharma
Using Shuffle Frog Leaping in Partitioning Graph
Somaye Amiri, Ali Hanani
Strategies in Traffic Controlling Operations in India
Anuja R. Taywade, Pooja Lapkale, Sneha V. Ramteke, Vaibhavi A Vairagade, Dr. Prakash S. Prasad
Understanding User’s Navigation Behavior using Web Mining Algorithm
Sana M. Deshmukh, Krishnakant P. Adhiya
Use of Data Mining Techniques to Determine Customer Loyalty by Performing Market Basket Analysis on E-commerce Database
Ms. Pratik Kiran Sayanak, Prof. Keerti Naregal
An Secure Information Self-Destructing Plan for Cloud Registering
Mr. Rakesh Patil, Mr. Bere S. S
Removal of Flicker noise from ECG Signal Using Wavelet
Devendra Kumar Verma, Vikash Sahu
Prediction of age-specific cancer mortality by using multinomial time series model
Seongyong Kim, Saebom Jeon
Study of µCOS RTOS on Low Cost Microcontroller
Pundaraja, Lavanya K.J, Priyanka D.L, Priyanka B.V
Comparative Study of Different Classification Algorithms for Early Prediction of Cancer
Shekhar Tanwar, Shalini L.
Review on Strategies for Visually Impaired People
Prakash S. Prasad, Akansha Ghate, Rashi Chouksey, Kshitij Shrivatsava, Lokesh Karangale
Smart Crawler for Hidden Web Interfaces
Sunita Sundarde, Pravin Rathod
Prediction Thalassemia Based on Artificial Intelligence Techniques: A Survey
Fatemeh Yousefian, Touraj Banirostam, Azita Azarkeivan
Enhancing Efficiency of Prediction based Authentication for Vehicle to Vehicle Communication
Jayshri A. Marathe, Satpalsing D. Rajput
Josephus Cube: A Novel Interconnection
Rayees Ahmad, Zahoor Ahmad Shah
WBAN- An Experimental Approach
Vishesh S, Arjuna C Reddy, Nagapragathi SV, Pooja Manjunath, Kavya P Hathwar, Anusha U
Money Transaction during Online Shopping
Payal D. Satokar, Hirendra H. Hajare, Rashmi H. Varma
Study and Analysis on Image Edge finding, Noises with Histogram Model
Pundaraja, Tejaswini.D, Priyadarshini A. Das, Leema.M, Megha.M
Low Power FinFET Based Full Adder Design
M. Vamsi Prasad, K. Naresh Kumar
Eventó – Local Events Android Application
Prof. Parag Naik, Akshay Kumar, Deepak Talan, Hemant Diwate
Cryptographic Methods to Securing Big-Data Analytics in Cloud using Parallel Computing
Adi Maheswara Reddy G, Dr K Venkata Rao, Dr JVR Murthy
Web-Based Portal for Food and Breweries
Vishesh S, Parth Sharma, Supriya Yadati Narasimhulu, Nandan AS, Kavya P Hathwar, Nikhil RS
To Study the Impact of Black Hole Attack in MANET using AODV & DYMO Protocols
Manju, Mr. Kapil Kaswan
Survey of Router Link Failure Detection in Wireless Mesh Network
Ms. Divya Jose, Mr. I. Gobi
An Enhanced Wavelet Based Neural Network Algorithm for Diabetic Retinopathy Image
R. Divya, Mrs. M. Kirthika Devi
Efficient System for Load Balancing in Cloud using Artificial Neural Network
Ashwini Y. Gudadhe, Mukul Pande
Android Based Student Information System
Chandrakala G C, Geeta Kalshety, Suma Paddki, Anuradha T
Intelligent Washing Machine Using Soft Computing
Sayali N. Patil, Dinkar L. Bhombe, Dr. Devesh D. Nawgaje
A Survey on Energy Aware Resource Allocation in a Cloud
J. Divyabharathi, Dr. M. Punithavalli
Agents Based Countermeasures to DDoS Attacks
Upinder Kaur, Dr. Payal Jain
Unified Investigation of Spectrum Sensing Schemes for Cognitive Radio Networks
Dipak P. Patil, Priyanka V. Ahire, Bharat D. Deore, Vijay M. Wadhai
Abstract
Assessing Emerging Innovative Applications used in County Governments of Kenya
Esau Mneria Mengich, Samuel Liyala, Anthony Rodrigues
DOI: 10.17148/IJARCCE.2017.6801
Abstract: In this modern age, the world has witnessed rapid growth and ever-increasing importance of e-government and governments are under pressure from citizens to quick and efficient services. Despite the Kenyan government efforts to embrace modern Information Communication Technology (ICT) applications, it seems some obsolete ICTs of yesterday are still operational. The objective of this research paper is to identify sophisticated innovative applications of ICT used in Kisumu county government that improves service delivery through use of innovative applications. Interviews and Document reviews are the data collection methods. Constructivist paradigm approach is employed and Purposive sampling technique is used targeting seven participants. Thematic Analysis�s procedures and processes are adopted during data analysis. Structuration theory is used to frame this study. The results show that the county government has adopted various modern Information Systems propelling service delivery to citizens and government stakeholders. The contribution of this paper is that despite the infancy stage of Kisumu county government of Kenya, there is evidence of use of innovative applications to enhance service delivery. This paper also recommends the way forward for the county and national governments, employees and the citizens who interact with ICT during service delivery. This paper recommends that quick interventions are required in establishing ICT infrastructure and embracing ICT training and capacity building to all employees and citizens in general.
Keywords: Innovative Applications, Information Systems (IS), Information Communication Technology (ICT), E-governance, E-government, Service delivery.
Abstract
Information hiding by using Developed M8PAM Technique
Mustafa B. Mahmood, Ban N. Dhannoon
DOI: 10.17148/IJARCCE.2017.6802
Abstract: As the result of increasing demand for the use of the Internet and applications that require storage and data transmission via the Internet, this data is being attacked by hackers. So appeared the need for data security. Researchers focused on devising different ways to keep this data from falling into the hands of intruders. There were encryption-decryption techniques and that are prone to doubt if it falls into the hands of hackers, so there was a need to use other techniques, one of these techniques is information hiding. The advantage of this technique it is not to keep intruders from knowing the hidden information, but it is to keep intruders from thinking that the information even exists. This paper is directed toward the task of steganography by using the developed method to hide every three bits from the secret message in one sample from the cover file and then adding a number to the product sample that represents the amount of central change, a proposed algorithm hides the secret message inside the popular images format which are frequently used in the Internet, this image format is known as a WebP format, also Known as the stickers for the chatting applications. Mod 8 Plus Average Method (M8PAM) is designed to hide the secret message inside a WebP image as a cover file. In this technique, the process of data hiding does not occur sequentially. So no distortion occurs in the carrier file which represents the cover file after the hiding process.
Keywords: Steganography, Mod 8 Plus Average Method (M8PAM), Central change.
Abstract
Sentiment Analysis from Opinion Mining to Human-Agent Interaction
S. Venkatesan, M. Muthuraman
DOI: 10.17148/IJARCCE.2017.6803
Abstract: The opinion mining and human-agent interaction communities are currently addressing sentiment analysis from different perspectives that comprise, on the one hand, disparate sentiment-related phenomena and computational representations, and on the other hand, different detection and dialog management methods. Sentiment/opinion detection methods used in human-agent interaction are indeed rare and, when they are employed, they are not different from the ones used in opinion mining and consequently not designed for socio-affective interactions to support our claims, we present a comparative state of the art which analyzes the sentiment-related phenomena and the sentiment detection methods used in both communities and makes an overview of the goals of socio-affective human-agent strategies. Sentiment analysis for human-agent interactions in two different use cases: job interviews and dialogs with museum visitors.
Keywords: Opinion mining, sentiment analysis, Human-agent interaction.
Abstract
Prediction of Chances Diabetic Retinopathy using Data Mining Classification Techniques
A. Ramalaniya
DOI: 10.17148/IJARCCE.2017.6804
Abstract: Diabetic retinopathy the most common diabetic eye disease, is caused by complications that occurs when blood vessels in the retina weakens or distracted. The correct diagnosis of proliferative diabetic retinopathy is essential; because it is a treatable disease and missing the diagnosis can lead to the patient becoming blind. We examined the ability of internists and ophthalmologists to diagnose proliferative retinopathy under optimal conditions. Several data mining technique serves different purposes depending on the modeling objective. I have used various data mining techniques to predict the early detection of eye disease diabetic retinopathy. Image enhancement, mass screening and monitoring of disease are the main methodologies of this work.
Keywords: Na�ve bayes, Support Vector Machine, Daibetic Retinopathy.
Abstract
Security Enhancement through Third Party Auditing for Data Storage in Cloud Computing using RC5 Algorithm
T. Kalaiselvi, Dr. S. Ravichandran Ph.D.,
DOI: 10.17148/IJARCCE.2017.6805
Abstract: Cloud computing is an internet based computing which enables sharing of services. Cloud computing allows users to use applications without installation any application and access their personal files and application at any computer with internet or intranet access. Many users place their data in the cloud, so correctness of data and security is a prime concern. Cloud Computing is technology for next generation Information and Software enabled work that is capable of changing the software working environment. It is interconnecting the large-scale computing resources to effectively integrate, and to computing resources as a service to users. To ensure the correctness of data, we consider the task of allowing a third party auditor (TPA), on behalf of the cloud client, to verify the integrity of the data stored in the cloud., the auditing process should bring in no new vulnerabilities towards user data privacy, and introduce no additional online burden to user. In this paper, we propose a secure cloud storage system supporting privacy-preserving public auditing. We further extend our result to enable the TPA to perform audits for multiple users simultaneously and efficiently with RC5 Encryption Algorithm. This shows the proposed scheme is highly efficient and data modification attack, and even server colluding attacks. Here Work is focuses on RC5 Encryption Algorithm for stored data in cloud. Resulted encrypted method is secure and easy to use.
Keywords: Cloud computing, Encryption, Data integrity, Third Party Auditor (TPA), RC5 Algorithm, privacy-preserving, public auditability.
Abstract
Comparative Study of Scheduling Algorithms to Enhance the Performance of Virtual Machines in Cloud Computing
S. Uma Maheswari, Dr. S. Ravichandran Ph.D
DOI: 10.17148/IJARCCE.2017.6806
Abstract: Nowadays, Cloud computing has become buzzword in the Information Technology and is a next stage in the evolution of Internet, It provides very large amount of computing and storage services to users through the internet. The primary aim of Cloud Computing is to provide efficient access to remote and geographically distributed resources with the help of Virtualization in Infrastructure as a Service (IaaS). We need different kind of virtual machines (VM) as per the requirement and cloud provider provides these services as per the Service Level Agreement (SLA) to ensure QoS.
Keywords: Cloud Computing, Cloud Environment, Load Balancing, Virtual Machines, Resource allocation.
Abstract
An Analysis of Load Balancing Algorithms in Cloud Computing
M. Nagalakshmi, M.Sc., M. Phil., Dr. K. David, M.Sc., M. Phil, M.Tech., Ph.D
DOI: 10.17148/IJARCCE.2017.6807
Abstract: Cloud computing is a term, which involves virtualization, distributed computing, networking, and software and web services. A cloud consists of several elements such as clients, datacenter and distributed servers. It includes fault tolerance, high availability, scalability, flexibility, reduced overhead for users, reduced cost of ownership, on demand services etc. Central to these issues the establishment of an effective load balancing algorithm. The load can be CPU load, memory capacity, delay or network load. Load balancing is the process of distributing the load among various nodes of a distributed system to improve both resource utilization and job response time while also avoiding a situation where some of the nodes are heavily loaded while other nodes are idle or doing very little work. Load balancing ensures that all the processor in the system or every node in the network does approximately the equal amount of work at any instant of time. This technique can be sender initiated, receiver initiated or symmetric type. This objective is to develop an effective load balancing algorithm using maximize or minimize different performance parameters throughput, latency for example for the clouds of different sizes virtual topology depending on the application requirement.
Keywords: cloud computing, load balancing algorithms, Virtual Machine.
Abstract
Behavioral Model for Banking Customer based on Neural Network with Time Series
V. Anbalagan, A. Malarvizhi
DOI: 10.17148/IJARCCE.2017.6808
Abstract: Data mining is an essential tool for any banking CRM strategy to be successful. It not only recognizes patterns to make predictions, but can also highlight available opportunities. With the many advantages and new avenues that it offers, this is one tool that no bank can ignore if it wants to retain its customers and stand out on a highly competitive industry. This study presents a new stage frame work of customer behavior analysis that integrated a neural network with the help of time series algorithm. The time series mining function provides algorithms that are based on different underlying model assumptions with several parameters. The learning algorithms try to find the best model and the best parameter values for the given data. In time series algorithm which roles a main part o calculate a detailed forecast including seasonal behavior of the original tije series. The autoregressive part of the algorithm uses weighed previous values while the moving average part weights the previously assumed errors of the time series. The objective of my project of to identify the most value customer in the banking databases using decomposing the data, and their loyalty. Time series data is helpful characteristics of customer and facilitates marketing strategy development.
Keywords: Data Mining, Neural Network.
Abstract
A Neural Network Based Kidney Segmentation from MRI Images
C. Kubendran, R. Malathi
DOI: 10.17148/IJARCCE.2017.6809
Abstract: Automated and robust kidney segmentation from medical image sequences is very difficult task particularly because of the gray level similarities of adjacent organs, partial volume effects and injections of contrast media. In addition to these difficulties, variations in kidney shapes, positions and gray levels make automated identification and segmentation of the kidney harder. Also, different image characteristics with different scanners much more increase the difficulty of the segmentation task. Therefore, in this work, we present an automated kidney segmentation method by using a multi-layers perception based approach that adapts all parameters according to images to handle all these challenging problems. The efficiency in terms of the segmentation performance is achieved by using the information from the previously segmented kidney image. The proposed approach is also efficient in terms of required processing time since it does not include pre-processing and training stages, which are very time consuming. Moreover, the unsupervised segmentation approach eliminates the common problem of most neural network based approaches that is dependency of results to the chosen data in the training stages.
Keywords: Image processing, segmentation, neural network.
Abstract
BAN: ACLs and Route-Redistribution
Vishesh S, Nidhi AJ, Manaswini S, Preethi R, Pratiksha D Bhandarkar, Murugheshgouda VH
DOI: 10.17148/IJARCCE.2017.6810
Abstract: Intra-body communication or intra-BAN and inter-body communication or inter-BAN are the two classifications under Body Area Networks (BAN). Body Area Network or BAN is a field of networking in which communication takes place between different sensors or network elements or other electronic components at the nodes within the body called intra-BAN and between two or more bodies called inter�BAN. In our previous paper [1] titled �BAN: intra-BAN and inter-BAN� with D01 10.17148/1JARCCE.2017.6756 we have successfully established communication between different routers /sensors at the node with the help of wireless communication protocols. Each node forwards packets to the destined location by selecting the optimal route for the packet to be transferred from the source to the destination. In this paper we configure Access Control Lists (ACL) or simply Access-list on routers placed at different nodes of the human body. The main purpose behind this configuration is for router packet filtering and traffic control. ACL or simply Access-list are a set of permit and deny commands to provide a powerful way to control traffic in and out of a network forwarding packets. It also provides additional security by denying host or IP addresses. In case of inter-BAN or inter-body communication, the two human bodies handshaking with each other may be running different routing protocols. In this case, route �redistribution needs to be done at the boundary routers which acts as a translator between the two routing protocols and the IPs advertised in one body can also be seen in the other human body running different routing protocols. In this paper the above configuration will be done and the results will be presented in a systematic manner.
Keywords: Access Control Lists (ACL), denying host or IP addresses, handshaking, router packet filtering and traffic control.
Abstract
Advanced Communication Network using Markov Chain Technique in MIMO-OFDM
Gauri B. Maske, Prof. S. B. Mule
DOI: 10.17148/IJARCCE.2017.6811
Abstract: To implement a realistic channel, markov chain is applied. Markov chain helps to achieve better BER performance. Channels like AWGN, Rayleigh and Rician is studied for Line-Of-Sight and Non Line-Of-Sight propagation. Comparison between these channels is implemented for selection of better communication channel. MIMO-OFDM transmit multiple data signals parallel. Since markov chain is irreducible, it is possible to to travel from one state to another. This will result into error free communication.
Keywords: MIMO, OFDM, Markov Chain, BER.
Abstract
A Review: AODV & DYMO Protocols Effects of Black Hole Attack in MANET
Manju, Mr. Kapil Kaswan
DOI: 10.17148/IJARCCE.2017.6812
Abstract: Wireless mobile ad hoc networks (MANETs) are self configuring, dynamic networks in which nodes are free to move. A major performance constraint comes from path loss and multipath fading Many MANET routing protocols exploit multi paths to route packets. The probability of successful packet transmission on a path is dependent on the reliability of the wireless channel on each hop. Rapid node movements also affect link stability, introducing a large Doppler spread, resulting in rapid channel variations. However, due to their inherent characteristics of dynamic topology and lack of centralized management security, MANET is vulnerable to various kinds of attacks. Black hole attack is one of many possible attacks in MANET. Black hole attack can occur when the malicious node on the path directly attacks the data traffic and intentionally drops, delay or alter the data traffic passing through it. This attack can be easily lessen by setting the promiscuous mode of each node and to see if the next node on the path forward the data traffic as expected. The implementation of AODV, OLSR and DYMO routing protocol and their comparison based on the performance metrics will be detailed in the Research Paper. The Proposal has been explained in this paper.
Keywords: AODV (Ad hoc On-Demand Distance Vector); OLSR (Optimized Link State Routing); Dynamic Manet on demand (DYMO), MANET (Mobile Ad Hoc Networks).
Abstract
Solving Prioritized Multi-Objective TSP Using Genetic Algorithm
Ammar Al-Dallal
DOI: 10.17148/IJARCCE.2017.6813
Abstract: Genetic algorithm has been successfully adopted to solve combinatorial problems. One of which is the Travelling Salesman Problem (TSP). One of the applications of TSP is when there is a trade off between delivering goods to customers using shortest path so that it is beneficial for the service provider, and delivering it based on customer�s priority so it is beneficial for the service receiver. In this paper, a multi-objective TSP is proposed to balance between shortest path and high priority using genetic algorithm. This work is featured by proposing a new fitness function to evaluate different solutions during the process of selection and crossover. The experiment is conducted by altering the factors associated with both path length and priority. The results show that better solution is achieved when more weight is assigned to the priority than when assigned to the path length.
Keywords: Genetic algorithm, Travelling Salesman Problem, mutli-objective TSP, crossover, fitness function.
Abstract
Pre Neighbour Node Route Discovery Technique for Energy Efficient Routing in WSN
Paramjit Singh, Tejinderdeep Singh
DOI: 10.17148/IJARCCE.2017.6814
Abstract: The Wireless Sensor Network (WSN) network is group of sensor nodes. Wireless Sensor Network (WSN) is suitable for places where connection through wireless is not possible. The network establish from cables is costly and difficult to implement as compares to Wireless Sensor Network (WSN). The Wireless Sensor Network (WSN) is Auto configured Network means if WSN goes down it will start automatically with its configuration so Wireless Sensor Network (WSN) is more suitable then network with wires and cables. While building infrastructure the energy consumption is main constrain while setting route the increase in distance in distance in Wireless Sensor Network (WSN) leads to problem for network .the multi-hop transmission routing consumes less energy as compared to direct link. The significant topology management should be done for less energy consumption network in Wireless Sensor Network (WSN) Sensor network is formed by sensor nodes and they are proficient for transmission. energy consumption is major issue in Wireless Sensor Network (WSN)the routing technique are formed for better energy efficient routing and to increase the life of network for efficient data transmission in Wireless Sensor Network (WSN) The various data dissemination protocol are used for better transmission and less energy consumption environment is maintained by different protocol in Wireless Sensor Network (WSN) The performance of existing technique PSO with v-leach is less as compared to proposed PNRD (Pre Neighbor Node Route Discover technique )provide efficient result and performance to minimizing the energy Loss and increase the network life of WSN. The comparative performance of other parameters like End-to End delay, Energy consumption and data transmitted is better as compared to existing PSO v-leach technique.
Keywords: Wireless Sensor Network (WSN), PNRD (Pre Neighbor Node Route Discover technique), End-to End delay, PSO v-leach technique.
Abstract
Content-Based Picture Retrieval through Color, Texture and Shape Factors
Rashmi Police Patil, Anita Dixit
DOI: 10.17148/IJARCCE.2017.6815
Abstract: The objective of this paper is to depict the retrieval of pictures from a database using texture, shape and color factors of a picture. The size of an output picture is reduced to (64x64) from the input size is of (256x256) through minimum and maximum quantifier. Color Co-occurrence Feature (CCF) is used to extract the color factors. Error Diffusion Block Truncation Coding (EDBTC) and Bit Pattern Feature (BPF) are used to extract the shape of the picture. Gabor wavelet is used to extract the texture of the picture. Pictures are retrieved using similarity measures through Euclidean distances. The accuracy 97% is achieved through the above methods.
Keywords: Color Histogram Feature, Color Co-Occurrence Feature, Error Diffusion Block Truncation Coding, Bit Pattern Feature, Gabor Wavelet, Euclidean Distance.
Abstract
An Effective Intrusion Detection System using CRF based Cuttlefish Feature Selection Algorithm and MSVM
A. Baby, Dr. S. Ravichandran Ph.D.,
DOI: 10.17148/IJARCCE.2017.6816
Abstract: In this we propose an effective intrusion detection system for improving the detection accuracy. In this proposed system, we propose a new feature selection algorithm called enhanced cuttlefish feature selection algorithm (ECFSA) for effective feature selection and Intelligent Agent based Enhanced Multiclass Support Vector Machine (IAEMSVM) classification algorithm is used for classification. The experimental results of the proposed system show that this system produced high-detection rate when tested with KDD cup 99 dataset.
Keywords: CRF � Conditional Random Field, CuttleFish Feature Selection, Multiclass Support Vector Machine.
Abstract
BAN- Implementation
Vishesh S, Ragavi P Ashok, Sachin MC Reddy, Meghana C, Sukruth L Babu, Parth Sharma
DOI: 10.17148/IJARCCE.2017.6817
Abstract: With the ever decreasing size/miniaturization of electronic devices, lower power consumption and these electronic devices becoming less expensive, the idea (once a prophecy) of a full-fledged Body Area Network (BAN) is becoming a reality. The basic idea behind Body Area Networking or BAN [1] is that electronic devices like sensors, processors; Networking devices like switches, routers and connectivity devices like Bluetooth module, Wi-Fi module etc� are placed at the nodes of the human body. Certain wireless protocols and routing protocols are used to wirelessly inter connect these nodes and choose the optimum route for packet data transfer between them respectively. The ability to share data increases the usefulness of intra-body embedded personal information devices [2], providing features not possible with independent isolated devices. In this paper we are using 3 sensors- Heartbeat sensors, body temperature sensor and pressure sensors. These sensors actively measure the real time biological parameters of a human body and the information is exchanged between these sensors at the node using wireless connectivity like Bluetooth. The information flow or traffic flow is regulated and proper route selection process is carried out using dynamic routing protocol like OSPF. The output of these devices is monitored using smartphone installed with third party android application.
Keywords: decreasing size/miniaturization of electronic devices, lower power consumption and these electronic devices becoming less expensive, wireless protocols, routing protocols, Heartbeat sensors, body temperature sensor and pressure sensors, Bluetooth, OSPF, third party android application.
Abstract
Kidney Abscess Segmentation and Detection on Computed Tomography Data
M. Dharani Devi, R. Malathi
DOI: 10.17148/IJARCCE.2017.6818
Abstract: In this paper, a novel kidney segmentation method for Computed Tomography patient data with kidney cancer is proposed. The segmentation process is based on Hybrid Level Set method with elliptical shape constraints. Using segmentation results, a fully automated technique of kidney region classification is introduced. Identification of the kidney, tumor and vascular tree is based on RUSBoost and the decision trees technique. This approach enables to resolve main problems connected with region classification: class imbalance and the number of voxels to classify. The classification is based on 64-element feature vectors calculated for the kidney region that consist of 3D edge region, orientation and spatial neighbourhood information. The proposed methodology was evaluated on clinical kidney cancer CT data set. Segmentation effectiveness in Dice coefficient meaning was equal to 0.85?0.04. Overall accuracy of the proposed classification model amount to 92.1% presented results confirm usefulness of the solution. We believe that this is the first solution which allow to segment (divide) kidney region into separable compartments, i.e. kidney, tumor and vascular trees.
Keywords: Segmentation, Computed Tomography, Neural Network, SVM, Decision Tree.
Abstract
A Case Study on Text Classification using Classification Algorithms and Latent Semantic Analysis
Shekhar Tanwar, Shalini L
DOI: 10.17148/IJARCCE.2017.6819
Abstract: Data Mining techniques are helpful in finding out patterns between data attributes and results in probalistic prediction of the label attributes. Keeping Predictive Modeling as center of attention, this paper focuses on application of analytics on dataset comprising of real world text messages. The Classification techniques i.e. Decision Tree and Random Forest combined with Bag Of Words Model, Latent Semantic Analysis, Singular Value Decomposition and Feature Engineering helps in meticulously predicting and classifying the dataset into two distinct parts i.e.legitimate text messages HAM and SPAM. The paper presents a thorough study and analysis of the techniques applied for classification and prediction, and also discusses the application of Vector Space Modelin making the dataset feasible for the application of the prediction and classification algorithms.
Keywords: Bag of Words Model, Document Frequency Matrix, Stop Words, Stemming, Cross Validation, Decision Tree, Random Forest, TF-IDF, Documents, Terms, Corpus, Vector Space Model, Latent Semantic Analysis,Singular Value Decomposition, n-gram, Feature Engineering.
Abstract
Security Analysis on Software Defined Mobile Network
Mr. A. Venugopal M.Sc, M.Phil, Anila. N. V
DOI: 10.17148/IJARCCE.2017.6820
Abstract: Software Defined Mobile Networking (SDMN) has emerged as new network architecture for dealing with network dynamics through software-enabled control. The SDMN is endorsing several new network applications; however the security has become an important concern in every application. This paper provides an extensive analysis on SDMN with several security considerations. This paper provides the introduction of SDMN and the security threats on it. The most common vulnerabilities in SDMN is Denial of Service attacks, Spoofing, Tampering, Repudiation, Information disclosure and access misuse. In this paper, a review on a wide range of SDMN security mechanisms is discussed; this includes Intrusion Detection systems, Intrusion prevention systems, firewalls, access control, deep packet inspection, and policy management. Finally the problem has been identified in the previous works on SDMN security.
Keywords: Software Defined Network, NFV, Security, Mobile Networks, Monitoring, DOS attacks, Spoofing, Wireless Network.
Abstract
Investigation of Intrusion and Denial of Service Attacks in Cloud Computing
Ayman A.A. Ali, Prof. Saif Eldin Fattoh Osman
DOI: 10.17148/IJARCCE.2017.6821
Abstract: The most threatening security issues in cloud computing are discussed in this paper. These include cloud intrusion and denial of service attacks. There are numerous intrusion attacks that threaten the cloud. We discuss the main types of them as well as the deployed intrusion detection and prevention techniques. In addition, the denial of service attack that may render the cloud system inoperable are addressed, and the remedy approaches are highlighted.
Keywords: Denial of Service Attacks, Cloud Intrusion, Cloud Computing.
Abstract
Asymmetric Stereoscopic Video Super-Resolution and Depth Estimation
Ashwini Mahadik, Prof. R. P. Patil, Prof. Dr. S. K. Shah
DOI: 10.17148/IJARCCE.2017.6822
Abstract: Recreation of full-resolution stereoscopic video from a asymmetric stereoscopic video is a challenging assignment. The existing techniques accept that the depth information is available, which forces an additional challenge in data acquisition. In this paper, we propose a novel plan that is fit for acquiring super-resolution and depth estimation at the same time from an asymmetric stereoscopic video. The proposed plot models the video super-resolution and stereo matching with a unified energy function. At that point, we apply alternating optimization technique to minimize this energy function, which can be implemented with a two-step algorithm. In the initial step, initial depth map is calculated using region based co-operative optimization technique to minimize this energy function, which can be implemented with two step function. In the second step, the super-resolution issue under the direction of the depth information is resolved. It is powerful on the grounds that each step provides extra benefit over the past step. These two steps are iteratively updated until stable depth and super-resolution results are acquired. Series of experiments are conducted on open stereoscopic video arrangements to assess the performance of the proposed technique. Based on comparison of objective indices and subjective visual results, it confirms that proposed scheme can achieve satisfactory super-resolution results and high-quality depth map simultaneously. Specifically, the subjective assessment experiment on 3D screen shows that this technique outperforms others and accomplishes the best visual sharpness.
Keywords: Asymmetric Stereoscopic Video, Super Resolution, Depth Estimation, Stereo Matching.
Abstract
Determining of Public Grievances- A Smart Way of City Management
Pratik Jayant Deshpande, Prof. Geeta Navalyal
DOI: 10.17148/IJARCCE.2017.6823
Abstract: �Data Mining� is a method of exploring huge databases with a view to develop distinct knowledge or information. �Smart city�, it's a city that technologically advances and improves the quality of residents daily lives through analyzing real time data. The above mentioned terms describes an efficient process for determining public grievances based on the data set to analyze and predict the similar grievance nature for a city. The grievance consists of grievance category such as garbage, sewage drains, water supply etc., and is also composed of attributes like �latitude and longitude� of the grievance registered. Utilizing the above mentioned attributes and data, analysis is performed on real data collected for various cities using �Bounding Box� concept and clustering algorithm �K-means Algorithm�. Results of cluster analysis show the comparison between cities and help the city planners to satisfy and fulfil the needs of citizens and make city sustainable.
Keywords: Data Mining, Smart City project, Google Map API, K-means clustering.
Abstract
School Students’ Performance Predication Using Data Mining Classification
Hafez Mousa, Ashraf Maghari
DOI: 10.17148/IJARCCE.2017.6824
Abstract: Educational management information systems generate huge amounts of data which hide a very useful knowledge. The techniques and methods used to discover the knowledge from students data are known as Educational Data Mining (EDM). The main objective of EDM is to improve students and teachers performance. Many researchers analysed students' behaviour to obtain useful knowledge that can help educators in planning for improving students' performance. There are two approaches which can be used to discover knowledge; by statistical methods and by DM techniques such as classification. This paper proposes a students' performance prediction model based on DM classification algorithms (Na�ve Bayes, Decision Tree and K-NN). The dataset was collected from a preparatory male schoolin Gaza strip, includes over 1100 records. Obtained results show that Decision Tree gives the best results. Moreover, the results indicates that social case has little impact on the students' performance, while the academic features such as previous year and first term results have more impacts on the performance. These results can be used in improving students' performance by predication their retention early to minimize students' failure.
Keywords: Data Mining DM, Classification, Educational Data Mining EDM, Students' Performance, Na�ve Bayes, Decision Tree and K-NN.
Abstract
Web-Based Portal for Online Shopping
Vishesh S, Suhas S, Srivatsa S Murthy, Suraj Nagaraj, Amartejas M, Namratha Raj
DOI: 10.17148/IJARCCE.2017.6825
Abstract: Apparel is just another word for clothing. There are many reasons to dress up- protection from cold, to cover the body, physical attraction etc��Fashion is a popular style or practise in clothing, footwear, accessories etc�In this paper we are building a web-based portal to view, buy and sell clothing, footwear, accessories etc�We have provided means to register and later login with unique user name and password to the web portal for both admin called admin login and for the client/customer called user login. The main objective of this application is to bring all items-clothing, footwear, watches and other accessories of different vendors under one roof and make it available to the public through World Wide Web hosting. All the operations are automated �billing, registration and acknowledgement, proper report generation, mail and tweets. In this paper we practically explain both server side scripting and client side scripting and the languages used in the above. We also present to you the ER diagram of the project or design both for the user and the admin. SQLs are used to communicate with the data base update or retrieve data from database.
Keywords: web-based portal, view, buy and sell clothing, footwear, accessories etc.,register and later login with unique user name and password, server side scripting, client side scripting, report generation, ER diagram, SQL, database.
Abstract
Key Aggregate Cryptosystem for Scalable Data Distribution in Cloud Storage
D. Suguna Kumari, B. Rajesh, P. Vamshi Krishna, Y. Ramakrishna
DOI: 10.17148/IJARCCE.2017.6826
Abstract: Data sharing being important functionality in cloud storage implements how to securely, efficiently, and flexibly share data with others. The public-key cryptosystems produce constant size cipher texts that efficiently delegate the decryption rights for any set of cipher texts. The significance is that one can total any arrangement of mystery keys and make them as conservative as a solitary key, yet including the energy of all the keys being accumulated. The mystery key holder can discharge a consistent size total key for adaptable decisions of figure content set in distributed storage; however the other encoded documents outside the set stay secret. The total key can be advantageously sent to others or be put away in a brilliant card with exceptionally restricted secure stockpiling.
Keywords: Cloud storage, public key encryption, cryptosystem, key aggregate encryption, and key aggregate cryptosystem.
Abstract
Overview on Microarray using Advanced Regression for Lost Data
K. Lakshmipriya, Dr. R. Manickachezian
DOI: 10.17148/IJARCCE.2017.6827
Abstract: This overview is based on dealing with lost data and Missing data during the time of data transaction and bulk data transmission. Missing data are characterized as a portion of the qualities in the data set are either lost or not watched or not accessible because of natural or non natural reasons. Data with missing qualities confuses both the data examination and the accommodation of an answer for new data. Numerous specialists are working on this issue to present more modern techniques. Despite the fact that numerous strategies are available, investigators are confronting trouble in seeking an appropriate technique because of absence of information about the strategies and their applicability. This research paper additionally directs a formal review of the missing data strategy. It talks about the strategies that are analyzed in the written works and perceptions that the authors have made. This survey is based on microarray data processing with regression method.
Keywords: Missing data, Data transmission, Micro array, Regression method, Data fixing.
Abstract
An Overview of Opinion Mining in Spatial Database for Web Based Application
Janani. S, Dr. R. Manickachezian
DOI: 10.17148/IJARCCE.2017.6828
Abstract: The Opinion mining is an ongoing field of research and development in web text mining and Data Engineering domain. It is the computational treatment of opinions and subjectivity of text. This survey paper mainly focus on a comprehensive overview of the Opinion mining algorithms and the different classification with their field of applications. Day to day proliferation of the current digital based economy a large amount of information is available in the form of textual data and user behaviours model which can often be used more easily if it is categorized or classified into some predefined classes. In case of social Networks, Ecommerce Architecture or a people hub, there are numerous varieties of people will be involved for their purchase, suggestions, posts, reviews, blogs and etc. The primary impression on the network is people suggestion. In Most of the networks, fake users revolving for two major purposes. 1) For increasing the rating of their own company. 2) To Decrease the rating of their competitor company. This survey is about how the opinion mining is used to find out fake users in spatial database.
Keywords: Opinion Mining, Spatial Database, Data engineering, User behaviour model, Fake users.
Abstract
Overview of Sentimental Trend Analysis and Text Pattern Fetching
S. Maguda Gowreeswari, Dr. R. Manickachezian
DOI: 10.17148/IJARCCE.2017.6829
Abstract: The advent of internet and World Wide Web the field of Sentiment Analysis is growing rapidly. There are numerous websites available on internet which provides analysis to users to give reviews about specific product. However the reviews expressed are mostly disorganized. An accurate method for sentiments could help us, to extract suggestions from the internet and predict customer�s preferences which could prove valuable for Social Networks, Bulk suggestions and marketing research. There are various algorithms available for Sentimental analysis. Generally Sentimental analysis has three levels of granularities: Document level, Sentence level and Aspect level. In this paper, we study and analyze different issues, data sources, classification methods and evaluation metrics for Sentiment Analysis and text pattern fetching methods.
Keywords: Sentiment Analysis, Text classification, Machine Learning, Dataset, Lexicon Approach.
Abstract
Research Paper on Image Stegnography
Priyanka Sharma, Astha Gautam, Ruchi Singh
DOI: 10.17148/IJARCCE.2017.6830
Abstract: The steganography is a powerful security method with which we can hide a secret message inside an object. Steganography is a technique used to protect the data by just hiding the data into data or information behind information. Currently, many types of steganography techniques are being used such as text, image, audio/video and protocol but digital images are the most widely used. There are many steganography procedures in which everyone has its own strength and weakness in terms of security and complexity. Some of which provides hiddenness of information while some provides a huge secret message to be hidden. This dissertation provides an overview of steganography specially image steganography and its uses. It attempts to design and develop the good steganography algorithm and briefly describes about the Least Significant Bit image steganography algorithm. In this dissertation, two parameters are used in order to measure the quality of image. First is PSNR and second is MSE.
Keywords: Steganography, Visual Cryptography, Steganography Techniques, Stego Image, PSNR, MSE.
Abstract
Generating Recommendations using an Association Rule Mining and Genetic Algorithm Combination
L.M.R.J Lobo, R. S. Bichkar
DOI: 10.17148/IJARCCE.2017.6831
Abstract: A Recommender system is a subclass that seeks to find out the rating or preference that a user would give to an object of interest. The set of available recommender systems generate a recommendation based on historical information available. The information is based on a user`s taste, but not intend. Genetic recommendation offer real-time recommendations in a specific order, thereby overcoming drawbacks of existing systems. In this paper, an Association Rule Mining technique combining features of Eclat algorithm and Genetic Algorithm is proposed. The idea is to apply association rule mining technique Eclat for generating rules and further use genetic algorithm to optimize these rules. A performance comparison is done between results achieved by another popular Association Rule Algorithm, The Apriori algorithm and the results of Eclat-Genetic algorithm. It is observed experimentally that the Eclat-Genetic model gives 28.31 % better result than the existing Apriori algorithm in terms of accuracy.
Keywords: Recommender, agriculture, Eclat-Genetic, Association Rule Mining, rules.
Abstract
Churn Analysis with Machine Learning Algorithms
Buket Onal, Metin Zontul
DOI: 10.17148/IJARCCE.2017.6832
Abstract: Competition conditions are increasing rapidly in almost every sector today. Along with the developments in the e-commerce sector, it has been seen that most of the developed countries are integrated and the development of logistics sector increases rapidly. Considering this increase in almost every sector, customer loyalty is of great importance for companies. By taking advantage of the data mining technology and taking into consideration the behavior exhibited by customers, the data obtained can???????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????? be modeled to determine the customers who have a tendency to leave the company. In this study, it was tried to reveal the lost customer behaviors by examining the shipping information of the customers working with a logistics company operating in Turkey. Data about 2.000 customers from the data received from the company were used in our application. Based on the customer shipment information, the input data were created by dividing into 5 classes. In the output data, the acquired and lost customers were taken into consideration. The information obtained by the data mining has been tested on the support vector machine algorithm. The data of these customers pertaining to past two years were divided into 3-month periods. Customer loss analysis was conducted for a total of 8 quarters including 7 sets of input data and 1 set of output data, and it is tried to make loss analysis estimation for the customers who have a tendency to leave the company in the next three months.
Keywords: Churn Analysis, Data Mining, Classification, Support Vector Machine.
Abstract
Data Mining Techniques for Business Intelligence and Its Applications – A Survey
Mr. A. Venugopal, Jisha. P
DOI: 10.17148/IJARCCE.2017.6833
Abstract: This paper deals with the data mining approaches and tools used for the business intelligence and inventory analysis. It describes the use of data mining approaches in business intelligence (BI), which coupled with data warehouse to employ data mining technology to provide accurate and up-to-date information for effective decision support system in business. The list of methodologies used in the literature is analyzed. This will help to provide out-of-stock forecasts at the store/product level. The inventory management and supply chain management using data mining techniques will improve the business by providing effective demand analysis, demand forecasting and appropriate decision support for the business. This survey concludes the further improvements which can improve the accuracy in demand analysis and forecasting in the inventory and supply chain management system. This also provides the challenges of those processes in terms of data size and uncertain business environments.
Keywords: Inventory Management, Data Mining, Big Data, Neural Networks, Hybrid Intelligent Systems, Demand Forecasting.
Abstract
An optimization based Power-Efficient Gathering in Sensor Information Systems (PRGASIS) for Wireless Sensor Network
Chandan Verma, Ashish Sharma
DOI: 10.17148/IJARCCE.2017.6834
Abstract: Routing is the major challenge for sensor networks. It presents the trade- off between efficiency as well as responsiveness. There are various protocols exist in this category. In this work, we have analysed Power Efficient Gathering in Sensor Information System (PEGASIS) hierarchical protocol for routing with the protocols on the basis of total energy consumed, sensors lifetime and provides a comparison with traditional methods. The optimization method used in the proposed work is ABC (Artificial Bee Colony). Utilization of PEGASS is done as it is considered as a redirecting method and allows good routing. This method employs some sort of greedy approach beginning from the actual furthermost node and each of the sensor nodes form some sort of string just like composition. The proposed work has been designed and implemented in WSN by using PEGASIS routing protocol. In this work, the performance analysis of the network with the scenarios consisting 50 nodes moving with the speed of the 5-10m/s within the area (1000X1000) m2 has been done in regards to the parameters packet delivery ratio, Throughput, End-to-End Delay, and Energy consumption.
Keywords: WSN (wireless sensor network), PEGASIS (Power Efficient Gathering in Sensor Information System), ABC (artificial Bee colony) and MATLAB.
Abstract
Using Shuffle Frog Leaping in Partitioning Graph
Somaye Amiri, Ali Hanani
DOI: 10.17148/IJARCCE.2017.6835
Abstract: Graph partitioning is one of the most important problem in optimization and graph theory. This problem falls into NP-problems and does not have an exact solution. In this paper, we intend to propose a new solution to optimize balanced undirected graph partitioning problem. The solution is an evolutionary algorithm, so called Shuffle Frog Leaping. A fitness function will be used to evaluate the suitability of each frog in each iteration. In order to measure the performance of our method, we partitioned a random graph with 10000 nodes into arbitrary numbers. Furthermore, we compare our result with two well-known algorithms called Genetic algorithm and Artificial intelligent.
Keywords: Balanced Graph partitioning, Shuffle Frog Leaping, Optimization algorithms.
Abstract
Strategies in Traffic Controlling Operations in India
Anuja R. Taywade, Pooja Lapkale, Sneha V. Ramteke, Vaibhavi A Vairagade, Dr. Prakash S. Prasad
DOI: 10.17148/IJARCCE.2017.6836
Abstract: Recently it has been observed that the traffic signals are operating at every square. The Roads shows zebra crossing for the pedestrians to use. While traffic signals are used to regulate the traffic but it is also seen that there are many accidents occurring because of traffic violations. This paper illustrates how the traffic can be watched by using the sensors so that the traffic can be restricted and will be followed properly without violation. Also would make work easier of RTO by directly sending email and message of ticket.
Keywords: Motion Sensors, Camera, Traffic Lights.
Abstract
Understanding User’s Navigation Behavior using Web Mining Algorithm
Sana M. Deshmukh, Krishnakant P. Adhiya
DOI: 10.17148/IJARCCE.2017.6837
Abstract: Web mining is application of data mining which is useful to extract the knowledge. So, wecan use web mining algorithm in understanding users� navigation behavior. In the proposed architecture first step is the preprocessing of web log data. In pre-processing step, modified data cleaning algorithm removes all irrelevant entries from weblog file. After data cleaning step user identification is performed depends on user's domain name or IP addresses. After preprocessing step, web mining algorithms of proposed architecture are applied to study the user navigation behavior. In the proposed architecture three algorithms are proposed. Those algorithms are, Modified Data Cleaning Algorithm, Proposed Modified Clustering Algorithm-I and Proposed Algorithm-II based on preferred path mining. Modified data cleaning algorithm is uses to remove all irrelevant entries and all multimedia files from weblog file. Proposed modified clustering algorithm-I is adapts to cluster users based on their similarity. Proposed algorithm-II based on preferred path mining accomplishes path mining on the clusters of different users found in clustering step. The results of proposed algorithms show improvement in memory usage and execution time.
Keywords: Web Usage Mining, Pre-Processing, Weblog File.
Abstract
Use of Data Mining Techniques to Determine Customer Loyalty by Performing Market Basket Analysis on E-commerce Database
Ms. Pratik Kiran Sayanak, Prof. Keerti Naregal
DOI: 10.17148/IJARCCE.2017.6838
Abstract: Lately with the quick development of e-commerce, a lot of information is gathered through operational transactions, data mining techniques are used to find and comprehend unknown customer purchase patterns. Earlier, data mining has been utilized to discover which products are connected as far as having high deals and furthermore discover which customers merit credit services. There has not been much work done in the utilization of data mining to guarantee customer loyalty in the e-commerce industry and furthermore have methodologies of expanding retail organizations to use e-commerce as a beneficial method of doing business. Customer-Product relationship has consistently been the most essential relationship for development of business. The better this relationship better is income generation and better is the development of organization .Results obtained in the piece of work are based on the concept of classification and association rule mining to provide better understanding of customer and product relationship and thus encourage organizations to develop the use e-commerce for conducting profitable business.
Keywords: Data Mining, E-Commerce, Classification using decision trees, Association rule mining.
Abstract
An Secure Information Self-Destructing Plan for Cloud Registering
Mr. Rakesh Patil, Mr. Bere S. S
DOI: 10.17148/IJARCCE.2017.6839
Abstract: With the fast advancement of adaptable cloud administrations, it turns out to be progressively vulnerable to utilize cloud administrations to share information in a companion hover in the distributed computing environment. Since it is not practical to actualize full lifecycle protection security, get to control turns into a testing undertaking, particularly when we share touchy information on cloud servers. Keeping in mind the end goal to handle this issue, we propose a key-arrangement quality based encryption with time-determined properties (KP-TSABE), a novel secure information self destructing plan in distributed computing. In the KP-TSABE conspire, each cipher text is marked with a period interim while private key is connected with a period moment. The cipher text can just be decoded if both the time moment is in the permitted time interim and the characteristics connected with the ciphertext fulfill the key's get to structure. The KP-TSABE can take care of some essential security issues by supporting user defined approval period and by giving fine-grained get to control amid the period. The touchy information will be safely self-destructed after a client determined lapse time. The KP-TSABE plan is ended up being secure under the choice l-bilinear Diffie-Hellman reversal (l-Expanded BDHI) suspicion. Far reaching correlations of the security properties show that the KP-TSABE conspire proposed by us fulfills the security necessities and is better than other existing plans.
Keywords: Sensitive data, secure self-destructing, fine-grained access control, privacy-preserving, cloud computing.
Abstract
Removal of Flicker noise from ECG Signal Using Wavelet
Devendra Kumar Verma, Vikash Sahu
DOI: 10.17148/IJARCCE.2017.6840
Abstract: An electrocardiogram ECG signal of the human heart shows the reflection the cardiac health by any of the disorder in heart rhythm, change in the morphological pattern of ECG signal. Accurate analysis of ECG signals becomes difficult if it is corrupted by noise during acquisition. Some primary source of noise are power line interference, external electromagnetic field interference, noise due to random body movements and respiration movements, electrode contact noise, electromyography (EMG) noise, and instrumentation noise. In this paper, 20 ECG signal is taken from standard MIT-BIH Arrhythmia database and Flicker noise is generated and added with original ECG signals which corrupt the signal. Noisy ECG signals is Filtered using different Wavelet function and different thresholding methods. Quantitative measurement has been done based on Signal to Noise Ratio (SNR).
Keywords: ECG, Flicker, SNR, Wavelet.
Abstract
Review on the boundary solutions in the analysis of an incomplete contingency table
Seongyong Kim
DOI: 10.17148/IJARCCE.2017.6841
Abstract: In the analysis of an incomplete contingency table, nonresponse models incorporating the missing mechanism are used to estimate nonresponses. There are three missing mechanisms, missing at random (MAR), not missing at random (NMAR) and missing completely at random (MCAR). The estimation results differ depending on the embedded missing mechanism in the nonresponse model. When the NMAR mechanism is assumed, it has been known that the nonresponse model has boundary solution problems. Boundary solutions are defined as the cell probabilities of certain columns are estimated to be zero, leading to distort estimation results. In this paper, boundary solution problems are reviewed with the reason, the identification of occurrence, and the method to overcome. The introduction of the analysis of an incomplete contingency table is also provided with the real data analysis.
Keywords: incomplete contingency table, boundary solutions, ML estimation, Bayesian method, NMAR model.
Abstract
Prediction of age-specific cancer mortality by using multinomial time series model
Seongyong Kim, Saebom Jeon
DOI: 10.17148/IJARCCE.2017.6842
Abstract: Cancer is the largest cause of death in Korea, and its proportion is increasing. Meanwhile, the cancer mortality rates vary over time as well as age. With the increased life expectancy in Korea, the proportion of the elderly age among cancer deaths has increased over time, while that of the young age has decreased. To reflect the proportions of the categories with such dynamic structures of age and time, a multinomial time series model can be used as a prediction model. However, there is a difficulty in estimating the parameters through the Markov Chain Monte Carlo (MCMC) method when some cell counts are very small relative to others, such as the number of deaths from cancer of young age group. In order to predict the age-specific cancer mortality by reflecting its dynamic structure and by overcoming estimation problems in MCMC, a power transformation is adopted as a link function of multinomial time series model instead of a logit link function, and forecasts the age-specific cancer mortality of male in Korea by 2040 using the proposed method.
Keywords: multinomial time series model, MCMC, link function, power transformation.
Abstract
Study of µCOS RTOS on Low Cost Microcontroller
Pundaraja, Lavanya K.J, Priyanka D.L, Priyanka B.V
DOI: 10.17148/IJARCCE.2017.6843
Abstract: Numbers of RTOS products from various vendors are available in the market, �C/OS-II a freeware with minimum facility is more popular among the hobbyist, researchers and small embedded system developers. In this project LCD is interfaced with the microcontroller using Serial interface. Four tasks are created using �C/OS-II RTOS. Task1 is for manage all other tasks from task create to delete. Task2 for reading characters from key board.Task3 for Displaying the entered characters on Hyper Terminal when ENTER key is pressed. Task4 for Displaying message on LCD when SPACE key is pressed. The software tools SDCC Compiler and ATMEL FLIP tool are used for implementation of tasks using �C/OS-II RTOS on AT89C51ED2 embedded development board. The result obtained indicates that best suitable for small scale industrial automation.
Keywords: SDCC, Keil IDE, �C/OS-II RTOS, Flash Magic and Embedded Development Board.
Abstract
Comparative Study of Different Classification Algorithms for Early Prediction of Cancer
Shekhar Tanwar, Shalini L.
DOI: 10.17148/IJARCCE.2017.6844
Abstract: Breast Cancer, one of the most common diseases which has impacted the female population is a result of two genes BRCA1 and BRCA2. The geneses result in the formation of cysts or lumps in the female breast which can later develop into a fully developed tumor. The tumor can either be malignant (cancerous) or benign(harmless), depending on the composition of the nuclei which forms it. This case study focuses on the several characteristics of the lumps and using classification algorithms makes an attempt for early prediction of cancer symptoms depending on the various characteristics of the lump.
Keywords: Re-index, Correlation Analysis, Relativity Analysis, 10-fold Cross Validation, Logistic Regression, Na�ve Bayes, Gradient Boosted Trees, Random Forest Trees, ROC Curves, Precision Recall Curves.
Abstract
Review on Strategies for Visually Impaired People
Prakash S. Prasad, Akansha Ghate, Rashi Chouksey, Kshitij Shrivatsava, Lokesh Karangale
DOI: 10.17148/IJARCCE.2017.6845
Abstract: Vision is the most important part of human life. The proposed paper refers to a systems that are capable to assist or guide people with vision loss, ranging from partially sighted to totally blind, by means of sound commands. Many technologies are working on implementation of smart eye for visually impaired people in different ways like voice based assistance, ultrasonic based assistance ,camera assistance and some researchers are trying to give transplantation of real eyes with robotic eyes which can capable enough to plot the real image over patient retina using some biomedical technologies. Creating a combined system of sensing technology and voice based guidance system which could give better result than individual technology by the use of microcontroller. There are some limitation in system like obstacle detection which could not see the object but detection the object and camera based system can�t work properly in different light level so the proposed system is a fusion of colour sensing sensor and the Obstacle sensor(ultrasonic sensor)as well as GPS Navigation along with the voice based assistance system. . These system does not requires a huge device to be hold for a long distance and it also does not requires any special training. This system also gives time timing through voice feedback. The main idea of the proposed system to make person aware of path he is walking and also the obstacle in the path.
Keywords: Navigation system; visually impaired; obstacle detection; microcontroller.
Abstract
Smart Crawler for Hidden Web Interfaces
Sunita Sundarde, Pravin Rathod
DOI: 10.17148/IJARCCE.2017.6846
Abstract: Deep web is growing day by day. There has been increase in the techniques to locate deep web interfaces efficiently with the help of deep web interfaces. To locate deep web resources is being very difficult due to large volume of web resources and dynamic nature of deep web. The biggest challenge is to achieve wide coverage and high efficiency. We propose a two stage framework such as smart crawler for hidden web interfaces to efficiently gather deep web. There are two stages namely Site locating and Insite exploring. In Site locating the centre pages are located with the help of search engine. In second stage Insite exploration, the wide coverage of the sites is obtained and the relevant links are formed. The page is fetched to obtain form. The representative set of domain shows accuracy, and efficiency than other crawlers.
Keywords: selection, Deep web interfaces, Two stage crawler, Page ranking.
Abstract
Prediction Thalassemia Based on Artificial Intelligence Techniques: A Survey
Fatemeh Yousefian, Touraj Banirostam, Azita Azarkeivan
DOI: 10.17148/IJARCCE.2017.6847
Abstract: Thalassemia is a type of genetic disease that can be observed in many areas of the world. The first step is a CBC test to diagnose a person with thalassemia. In this paper, the used data mining methods to diagnose thalassemia are studied and evaluated. The effective parameters in thalassemia diagnosis are the available variables in the CBC test in people that among these parameters, RBC, HGB, MCV and HTC have a significant effect on the disease diagnosis. Based on the available values in the CBC test and using artificial intelligence algorithms, the patient with thalassemia is diagnosed. Artificial intelligence algorithms are used to analysis laboratory data properly, which leads to increase accuracy in the diseases diagnosis, which has a significant impact on the treatment process and improvement of patient health.
Keywords: Thalassemia, Data mining, Classification, Artificial Intelligence Techniques.
Abstract
Dual-Link Failure Resiliency through FIPP and FDPP
Anand Kiran
DOI: 10.17148/IJARCCE.2017.6848
Abstract: Networks employ link protection to achieve fast recovery from link failures. While the first link failure can be protected using link protection, there are several alternatives for protecting against the second failure. This paper formally classifies the approaches to dual-link failure resiliency. One of the strategies to recover from dual-link failures is to employ link protection for the two failed links independently, which requires that two links may not use each other in their backup paths if they may fail simultaneously. Such a requirement is referred to as backup link mutual exclusion (BLME) constraint and the problem of identifying a backup path for every link that satisfies the above requirement is referred to as the BLME problem. This paper develops the necessary theory to establish the sufficient conditions for existence of a solution to the BLME problem. Solution methodologies for the BLME problem is developed using two approaches by: 1) formulating the backup path selection as an integer linear program; 2) developing a polynomial time heuristic based on minimum cost path routing. The ILP formulation and heuristic are applied to six networks and their performance is compared with approaches that assume precise knowledge of dual- link failure. It is observed that a solution exists for all of the six networks considered. The heuristic approach is shown to obtain feasible solutions that are resilient to most dual-link failures, although the backup path lengths may be significantly higher than optimal. In addition, the paper illustrates the significance of the knowledge of failure location by illustrating that network with higher connectivity may require lesser capacity than one with a lower connectivity to recover from dual-link failures.
Keywords: FIPP, FDPP, WDM, SRLG, BLME, ARPANET, NSFNET, NJ-LATA, ILP.
Abstract
Enhancing Efficiency of Prediction based Authentication for Vehicle to Vehicle Communication
Jayshri A. Marathe, Satpalsing D. Rajput
DOI: 10.17148/IJARCCE.2017.6849
Abstract: VANET uses vehicles as mobile nodes to create mobility in a network. A challenging problem is to design a broadcast authentication scheme for secure vehicle-to-vehicle communications. When an oversized variety of beacons arrive in a very short time, vehicles are at risk of computation-based Denial of Service attacks that excessive signature verification exhausts their procedure resources. An economical broadcast authentication scheme known as Prediction based Authentication (PBA) which not solely defend against computation-based DoS attacks, additionally resist packet losses caused by high quality of vehicles. In contrast to most existing authentication schemes, PBA is an efficient and lightweight scheme since it is primarily built on symmetric cryptography. Again to reduce the verification delay for some emergency applications, PBA is designed to exploit the sender vehicle's ability to predict future beacons earlier. Addition, to stop memory-based DoS attacks, PBA solely stores shortened re-keyed Message Authentication Codes (MACs) of signatures without decreasing security. An overview and qualitative comparison of PBA with authentication and without authentication is presented. Evaluation of the performance metrics such as Delivery Rate, Overall Storage Size, Loss Rate, Throughput and Control Overhead using NS-2 simulator are done.
Keywords: VANETs; broadcast communication; signatures; DoS attacks; prediction-based authentication.
Abstract
Josephus Cube: A Novel Interconnection
Rayees Ahmad, Zahoor Ahmad Shah
DOI: 10.17148/IJARCCE.2017.6850
No abstract available.
Abstract
WBAN- An Experimental Approach
Vishesh S, Arjuna C Reddy, Nagapragathi SV, Pooja Manjunath, Kavya P Hathwar, Anusha U
DOI: 10.17148/IJARCCE.2017.6851
No abstract available.
Abstract
Money Transaction during Online Shopping
Payal D. Satokar, Hirendra H. Hajare, Rashmi H. Varma
DOI: 10.17148/IJARCCE.2017.6852
No abstract available.
Abstract
Study and Analysis on Image Edge finding, Noises with Histogram Model
Pundaraja, Tejaswini.D, Priyadarshini A. Das, Leema.M, Megha.M
DOI: 10.17148/IJARCCE.2017.6853
Abstract: Picture edge location is one of the essential substance of picture preparing. In this paper, we demonstrate another edge location administrator, which is Log Sobel. In the identified result is in ward of iridescence. The analyze comes about demonstrate that the impact for picture handled by Log Sobel administrator is superior to those administrators, including Roberts calculation, Prewitt calculation and Sobel calculation, proposed by forerunner Picture clamor is irregular variety of shine or shading data in pictures, and is generally a part of electronic commotion. It can be created by the sensor and computerized camera. Picture commotion can likewise begin in film grain and in the unavoidable shot clamor of a perfect photon identifier with various noises of image and histogram model is also discussed.
Keywords: Image processing, Image noises, Edge detection, Histogram, operators.
Abstract
Low Power FinFET Based Full Adder Design
M. Vamsi Prasad, K. Naresh Kumar
DOI: 10.17148/IJARCCE.2017.6854
Abstract: The great challenge in the nanometer regime is due to Short Channel Effects that cause an exponential increase in the leakage current. With the advancement in technology, Conventional CMOS has Short Channel Effects. In order to reduce the Short Channel Effects, FinFET is used. FinFETs are the new emerging transistors that can work in the nanometer range to overcome these Short Channel Effects. The Low Power FinFET based Full Adder is implemented by using CADENCE VIRTUOSO tools in 45nm technology with the supply voltage of 1V in CMOS and 15nm technology with the supply voltage of 0.7V in FinFET. The Simulation is done to compare power, delay and power- delay product. The result shows that the PDP of GDI FinFET Full Adder is reduced to 67% compared to FinFET Full Adder.
Keywords: Low Power; Full Adder; CMOS; FinFET; GDI.
Abstract
Eventó – Local Events Android Application
Prof. Parag Naik, Akshay Kumar, Deepak Talan, Hemant Diwate
DOI: 10.17148/IJARCCE.2017.6855
Abstract: Event� is a student focused application for Android that helps you discover local college events. Find college events to attend near you, quickly access your event information from your Android device, and start your next event countdown today! Discover popular local events; get event recommendations just for you from your Android device. Find something new to do -- workshops, seminars, webinars, technical and cultural events, sports events and more -- right in the palm of your hand.
Keywords: Event�, Event Discovery, Local Events, Events for students, Android Application.
Abstract
An Efficient Parallel Density based Clustering Algorithm
G.V.S. Swetha
DOI: 10.17148/IJARCCE.2017.6856
Abstract: Data clustering is a challenging issue because of the complex and heterogeneous natures of multidimensional information. On the other hand very few clustering methods can successfully deal with the multidimensional datasets and it becomes even hard to handle such large amounts of information. For datasets that don't conceivable to store even on a solitary plate, parallelism is a fantastic choice. Map Reduce is a programming framework to process large scale data in a massively parallel way. We utilized DBScan calculation for creating groups and tested the device on manufactured and constant datasets got from UCI. We adopt a quick partitioning strategy for large scale non-indexed data. We consider the metric of converge among circumscribing parcels and make advancements on it. Finally, we assess our work on genuine expansive scale datasets utilizing Hadoop platform. Results reveal that the speedup and scale up of our work are very efficient.
Keywords: Data clustering, MapReduce, DBScan, Hadoop.
Abstract
Cryptographic Methods to Securing Big-Data Analytics in Cloud using Parallel Computing
Adi Maheswara Reddy G, Dr K Venkata Rao, Dr JVR Murthy
DOI: 10.17148/IJARCCE.2017.6857
Abstract: Evaluating the efficacy of several methods. Key managing predominantly uses up the power of battery in two ways: one way using the algorithm computations accomplished by the core processor and the other way is the extra communications energy expanded to communicate and to collect information related to key management. From the time when the quantity of energy utilized by various processors and the systems involved for the communications differs extensively, providing privacy and security in data centres for mobile is very challengeable as we need effective security for the managing the keys. Here we have analysed numerous standard parallel programming techniques to effectively use the processors and do the jobs in parallel with less time complexity.
Keywords: Security, Big Data, Cloud, Parallel Programming.
Abstract
Web-Based Portal for Food and Breweries
Vishesh S, Parth Sharma, Supriya Yadati Narasimhulu, Nandan AS, Kavya P Hathwar, Nikhil RS
DOI: 10.17148/IJARCCE.2017.6858
Abstract: In this era of the internet and the World Wide Web, almost everything-from clothing to footwear and accessories; from Electronics to electrical appliances; from furniture to home appliances; sporting goods, beauty and personal care etc. is available online. A user/customer has the privilege to view and purchase his/her required product/service. In this paper, we have made an attempt to construct a web-based portal which brings various foods and breweries prepared by various food manufacturing/processing companies or firms directly to the online customer. By duly filling the request form for delivery, a particular product is shipped to address and an automated bill is generated. MySQL is used as the back-end tool. PHP, HTML and JavaScript are the front-end development tools. CSS is responsible for the attractive appearance of the webpages. An admin login is provided to enable the administrator of the website to do the following- add new product, edit or delete product, add new employee, delete or edit employee, password settings and verify or regenerate sales report.
Keywords: web-based portal, World Wide Web, ER diagram, MySQL, database, PHP, HTML and JavaScript.
Abstract
To Study the Impact of Black Hole Attack in MANET using AODV & DYMO Protocols
Manju, Mr. Kapil Kaswan
DOI: 10.17148/IJARCCE.2017.6859
Abstract: A Mobile Ad-hoc Network (MANET) is a dynamic wireless network that can be formed without the need for any pre-existing infrastructure in which each node can act as a router. Mobile ad hoc network (MANET) is an autonomous system of mobile nodes connected by wireless links. Wireless Networks enable users to communicate and transfer data with each other without any wired medium between them. The main classes of routing protocols are Proactive, Reactive and Hybrid. In this work an attempt has been made to compare the performance of prominent on demand reactive routing protocols for MANETs:- Ad hoc On Demand Distance Vector (AODV), OLSR (Optimized Link State Routing) and Dynamic Manet on demand (DYMO). AODV is a reactive protocol: the routes are created only when they are needed. The simulation is carried out using the ns-2 network simulator. The Blackhole attack has been implemented on the routing protocol. The Research proposal considered five different simulation environments with different number of nodes which are 5, 10, 15, 20 and 25 and results are compared in a graphical representation. There are number of parameters considered for compare the performance among these protocols. The parameters are Throughput (Good put), packet delivery ratio and Routing Overload. The results presented in this work illustrate the importance in carefully evaluating and implementing routing protocols in an ad hoc environment.
Keywords: AODV (Ad hoc On-Demand Distance Vector); OLSR (Optimized Link State Routing); Dynamic Manet on demand (DYMO), MANET (Mobile Ad Hoc Networks), PDR (Packet Delivery Ratio), Throughput.
Abstract
Survey of Router Link Failure Detection in Wireless Mesh Network
Ms. Divya Jose, Mr. I. Gobi
DOI: 10.17148/IJARCCE.2017.6860
Abstract: Routers are small electronic devices that join multiple computer networks together via either wired or wireless connections. A tree topology is used to construct a wireless sensor network for data delivery applications. Data delivery failures occur in the form of mobile node movements and topology changes. To increase the data delivery ratio and mitigate the effects of packet loss caused by the mobile nodes. A wireless mesh networks is one of the most advanced wireless network, used for the wireless communication. Wireless network may suffer from frequent link failure which degrades the network performance. The proposed survey paper presents the review of the various detection techniques used to recover the router link failure in Wireless Mesh Network.
Keywords: mesh topology, Link Failure detection, multipath routing, recovery techniques, router firmware, HELLO message.
Abstract
An Enhanced Wavelet Based Neural Network Algorithm for Diabetic Retinopathy Image
R. Divya, Mrs. M. Kirthika Devi
DOI: 10.17148/IJARCCE.2017.6861
Abstract: This Diabetic retinopathy contributes to serious health problem in many parts of the world. With the motivation of the needs of the medical community system for early screening of diabetics and other diseases, a computer aided diagnosis system is proposed. This work is aimed to develop an automated system to analyze the retinal images for important features of diabetic retinopathy using image processing techniques and an image classifier based on artificial neural network which classify the images according to the disease conditions. Retinal haemorrhage is a disorder of the eye in which bleeding occurs into the retina. A retinal hemorrhage can be caused by hypertension, retinal vein occlusion (a blockage of a retinal vein), or diabetes mellitus (which causes small fragile blood vessels to form, which are easily damaged). Exudates is a fluid with a high content of protein and cellular debris which has escaped from blood vessels and has been deposited in tissues or on tissue surfaces, usually as a result of inflammation. Different findings such as exudates and hemorrhage in the retina over time can be used for the early detection of diabetic retinopathy. For the detection the scope of digital image processing and artificial neural networking is utilized and the working environment used in our project is matlab.
Keywords: Artificial Neural Network Algorithm, Diabetic Retinopathy, Image Processing.
Abstract
Efficient System for Load Balancing in Cloud using Artificial Neural Network
Ashwini Y. Gudadhe, Mukul Pande
DOI: 10.17148/IJARCCE.2017.6862
Abstract: Cloud computing is the long dreamed vision of computing as a utility, where users can remotely store their data into the cloud so as to enjoy the on-demand high quality applications and services from a shared pool of configurable computing resources. Job scheduling is one of the biggest issues in cloud computing. Main motivation is to schedule users� requests to allocate resources to these requests to finish the tasks in minimum time. In this paper, experimental results showed that scheduling using Artificial Neural Network (ANN) can perform better scheduling than existing approach.
Keywords: Cloud computing, service-level agreement (SLA), Job Scheduling, Artificial Intelligence, Artificial Neural Networks (ANN), Load balancing.
Abstract
Android Based Student Information System
Chandrakala G C, Geeta Kalshety, Suma Paddki, Anuradha T
DOI: 10.17148/IJARCCE.2017.6863
Abstract: Student management system is to create an application that can provide query management system through android mobile phones. As teacher staffs there will be reduce in manual work they can easily upload the exam time table and respective subject also notices. Changes in information technology (IT) allow colleges to utilize database and applications such as student information system (SIS), thus making the accessing of records centralized. Student management system is to create an application that can provide query management system through android mobile phones. Student query management system android application tracks all the difficulties of a student from the day one to the end of his course which can be used for all reporting purpose, tracking enrolment, progress in the course, completed semesters years, final exam query and all these will be available for future reference too.
Keywords: Android Technology, administration, maintains records, Smart connect, Student Information System (SIS).
Abstract
Intelligent Washing Machine Using Soft Computing
Sayali N. Patil, Dinkar L. Bhombe, Dr. Devesh D. Nawgaje
DOI: 10.17148/IJARCCE.2017.6864
Abstract: The general washing machine is an example of the advance washer control with a great technology. This advancement helped the household scenario very well. But we need to make it more advance from the previous one. Here, the system will consist of the neuro- fuzzy and fuzzy techniques that will help the system to take its own decisions like release of water and washing powder as per need of cloth. Also the fabric detection technique will implement with the help of these techniques.
Keywords: Fuzzy �controller, Neuro-fuzzy logic, Washing machine, Fuzzy techniques.
Abstract
Automated Social Media Mining System in Health Care
Oleena Thomas
DOI: 10.17148/IJARCCE.2017.6865
Abstract: Social media, by its nature, will bring different individuals with different experiences and viewpoints. Extracting knowledge from social media has great applications. In health care area, the advent in social media has created greater improvements in communicating. The users of social media post comments regarding different diseases and their remedies with the users' experiences in this regard. This could be so informative to other users as well. Others could get an overview regarding the diseases and their treatments. Taking the effect of social media into consideration, the information could reach a mass population. Sentiment analysis is the major focus here. Hence data preprocessing is a requisite. This is followed by the network modeling and side effect terms extraction. Through these the comments being considered for information extraction could be worth enough.
Keywords: Sentiment Analysis, Term Frequency, Inverse Document Frequency Scores, Data Pre-processing, Text Mining, Self Organizing Map.
Abstract
Data Mining Approach to Wind Data Preprocessing
Oleena Thomas
DOI: 10.17148/IJARCCE.2017.6866
Abstract: Wind energy being a major source of energy has become an interesting area of research. Wind farm power curve monitoring and wind power prediction are the constituent elements of the integrated wind energy research. As absolute modeling of wind source is nearly impossible and as wind turbines are nonlinear, data mining methods are preferred over analytic method to obtain high level information from low level data collected from data acquisition systems. The inputs required are wind power and wind speed magnitudes. Based on that raw wind data are classified into valid or invalid data using unsupervised algorithm. The categorization of data is done into six categories mainly valid, missing, constant, exceeding, irrational and unnatural. Outlier detection is done to filter out the data. Variance and bias are taken into consideration while using dif-ferent approximation power curve models for data detection. Local Outlier Factor is incorporated, along with the similarity measures used. Weighted distance is calculated to avoid non detection of relevant data points.
Keywords: Data Mining, Wind Data Preprocessing, Wind energy, Local Outlier Factor, Weighted distance.
Abstract
A Survey on Energy Aware Resource Allocation in a Cloud
J. Divyabharathi, Dr. M. Punithavalli
DOI: 10.17148/IJARCCE.2017.6867
Abstract: Cloud computing is essential in the field of modern computing systems, where cloud providers have to provide effective resource for the users to increase the quality of service. A data centre consists of a large number of servers or hosts which are the key factor of cloud environment. The use of the enormous amount of computing and data centres generally leads to consumption of large amount of energy Therefore, the datacentre resources have to be distributed such that energy efficiency is maximized. The present paper surveys various resource allocation strategies and methods that are efficient in terms of energy. These strategies have been compared on the basis of their techniques. We analyse the most promising existing research in resource management and examine monitored values, supported application classes and the most important criteria for evaluating the effectiveness of the approach. It discusses methods to evaluate and model the energy consumed by these resources, and describes techniques that operate at a distributed system level, trying to improve aspects such as resource allocation.
Keywords: Cloud computing, energy efficiency, resource allocation.
Abstract
Agents Based Countermeasures to DDoS Attacks
Upinder Kaur, Dr. Payal Jain
DOI: 10.17148/IJARCCE.2017.6868
Abstract: Distributed Denial of Service (DDoS) attack combines resources of multiple Zombies (Compromised Systems) to attack a single victim makes it impossible to work properly. DDoS is one of the various supreme challenges and the existing literature reveals the fact that although there exist various mechanisms to handle DDoS attacks but still there exist a gap amongst the security requirements & existing mechanisms. Therefore, a mechanism that is strong and reliable is desired. Software agents seem to be a strong candidate for defending DDoS attack. This work highlights the importance of software agents as a security staff for avoiding DDOS attacks. Also it proposes a multi agent framework detecting, protecting and source tracing DDOS attack.
Keywords: Distributed Denial of Service (DDoS), Compromised Systems, Software agents, DDOS attacks.
Abstract
Unified Investigation of Spectrum Sensing Schemes for Cognitive Radio Networks
Dipak P. Patil, Priyanka V. Ahire, Bharat D. Deore, Vijay M. Wadhai
DOI: 10.17148/IJARCCE.2017.6869
Abstract: A better Quality of Service (QoS) is the prime objective for the wireless applications and which can be satisfied by proper management of the available spectrum. In recent time Cognitive Radio (CR) is arise as promising technology to support spectrum management dynamically. Spectrum sensing is an important issue in dynamic spectrum management. There are number of spectrum sensing techniques presented in frequent literatures. This paper consist of the comparative analysis of different eigenvalue based spectrum sensing techniques is presented. The Maximum Minimum Eigen value detection, Energy detection, Mean Eigen value detection and Roys Largest root test are considered for the evaluation. Closed form analysis of equation is traced and from that it is confirmed that Maximum Minimum eigen value gives better execution and can be useful for spectrum sensing for dynamic spectrum management perspective.
Keywords: Cognitive Radio, Eigen Value Detection, Energy Detection, Roys Largest Root Test, Dynamic Spectrum Management.
