Volume-1 Issue-2, May 2011 – International Journal of Soft Computing and Engineering (IJSCE)

A035041211

IJSCE Journal — Wed, 29 Sep 2021 10:11:33 +0000

The International Journal of Soft Computing and Engineering (IJSCE) has ISSN: 2231-2307 (online), an open-access, peer-reviewed, periodical bi-monthly international journal. This journal is published by Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) in January, March, May, July, September and November.The journal aims to publish high-quality peer–reviewed original articles in the area of Soft Computing and Engineering that covers Data Communication and Networking, Artificial Intelligence and Neural Networking, Image Processing and Recognition, Software Engineering and Project Management (SEPM), Computer Graphics and Multimedia (CGM), Data Mining, Cryptography and Network Security, Smart Computing and Information Processing, Internet of Things (IoT), Computation Intelligence and Analytics, Machine Learning (ML) and Knowledge Mining (KM), Operating System, Data Base Management System (DBMS), Data Structure and Algorithm (DSA), Object Oriented Analysis and Design (OOAD), and all interdisciplinary streams of Soft Computing and Engineering. #Addressing, Routing, Switching and Location Management #Broadband, Mobile, Wired, Wireless Internet #Networks: Adhoc and Sensor Networks, High Speed Networks, Mobile and #Wireless Networks #Network Architectures #Network Based Applications #Network Protocols #Network Operations & Management #Network Security Trust & Privacy #Cross Layer Design and Optimization #Internet and Web Applications #Network Measurement & Performance Analysis #Next Generation Internet & Web Architectures #Peer to Peer and Overlay Networks #QOS And Resource Management #Recent Trends & Developments in Computer Networks #Self-Organizing Networks and Networked Systems #Ubiquitous Networks #Virtual & Overlay Networks #Wireless Mesh Networks and Protocols #Wireless Multimedia Systems #Personal and Wearable Networks #Information-Centric Networking #Embedded Networks #Opportunistic Networking #Delay-Tolerant Networks #Cognitive Radio Networks #Vehicular Networks #Smart Grid Communications #Underwater Sensor Networks #Cyber-Physical Systems #Social Networks #Green Networking #Overlay and Peer-To-Peer Networks #Local-Area and Metropolitan-Area Networks #Storage-Area Networks #Routing and Transport Protocols #Big Data Networking #Cloud Computing and Networking #Software Defined Networking and Network Function Virtualization #Internet of Things #Link Technologies #Adaptive Networking Applications #Authentication, Authorization, Accounting #Security and Privacy #Cross-Layer Optimization #Multimedia and Real-Time Communication #Machine-To-Machine Communications for Smart Environments #Smart Cities #Network Traffic Characterization and Measurements #Network Management, Reliability and QoS #Performance Evaluation of Networks #Testbeds for Network Experiments #Network Coding #Optical and High-Speed Access Networks #High Performance Computing #Digital System and Logic Design #Networked-Driven Multicourse Chips #Information-Centric Networking #Opportunistic Networking #Mobile and Ubiquitous Networking #Big Data Networking #Cloud Computing and Networking #Software Defined Networking and Network Function Virtualization #Adaptive Networking Applications #Antenna and Communications Devices #Microstrip Antenna #Microwave #Radar and Satellite #Smart Antenna #MIMO Antenna #Wireless Communication #RFID Network and Applications #5G Communication #6G Communication #Neural Networks #Fuzzy Logic #Simulated Biological Evolution Algorithms (Like Genetic Algorithm) #Ant Colony Optimization(etc) #Reasoning and Evolution #Intelligence Applications #Computer Vision and Speech Understanding #Multimedia and Cognitive Informatics #Data Mining and Machine Learning Tools #Heuristic and Ai Planning Strategies and Tools #Computational Theories of Learning #Technology and Computing (Like Particle Swarm Optimization) #Intelligent System Architectures #Knowledge Representation #Bioinformatics #Natural Language Processing #Multiagent Systems #Supervised Learning #Unsupervised Learning #Deep Learning #Big Data and Ai Approaches #Reinforcement Learning #And Learning with Generative Adversarial Networks #Regression and Prediction #Problem Solving and Planning #Clustering #Classification #Neural Information Processing #Vision and Speech Perception #Heterogeneous and Streaming Data #Probabilistic Models and Methods #Reasoning and Inference #Marketing and Social Sciences #Knowledge Discovery #Web Mining #Information Retrieval #Design and Diagnosis #Game Playing #Streaming Data #Music Modelling and Analysis #Robotics and Control #Multi-Agent Systems #Active Vision and Robotic Systems #Architecture of Imaging and Vision Systems #Autonomous Vehicles #Character and Handwritten Text Recognition #Chemical and Spectral Sensitization #Chemistry of Photosensitive Materials #Coating Technologies #Coding and Transmission #Cognitive Aspects of Image Understanding #Color Imaging #Communication of Visual Data #Data Fusion from Multiple Sensor Inputs #Display and Printing #Document Image Understanding # Generation and Display #Holography #Image Analysis and Interpretation #Image Capturing #Image Databases #Image Generation #Image Manipulation #Image Permanence #Image Processing #Image Processing Applications #Image Processing: Coding Analysis and Recognition #Image Representation #Image Sensing #Imaging Systems and Image Scanning #Implementation and Architectures #Latent Image #Materials for Electro-Photography #Monitoring and Surveillance #Network Architecture for Real-Time Video Transport #New Visual Services Over ATM/Packet Network #Non-Impact Printing Technologies #Object Modeling and Knowledge Acquisition #Photoconductors #Photographic Emulsions #Photopolymers #Prepress and Printing Technologies #Processing and Analysis #Protocols for Packet Video #Remote Image Sensing #Retrieval and Multimedia #Scene Modeling #Signal-Processing Aspects of Image Processing #Storage and Transmission #Video Coding Algorithms and Technologies for ATM/P #Ethics of Software Engineering and Management #Software Life Cycles Development Models #Project Planning and Management #Software Requirements Analysis #Software Design Analysis #Software Testing and Integration #Software Implementation and Maintenance #Software Maintenance and Maintainability #Software Metrics or Attributes #Software Risk Assessment and Containment #Reliability #Software Quality and Quality Assurance #Software Cost Estimation #Object Oriented Developments #Object Oriented Metrics #Object Oriented Testing #Formal Notations #3D Reconstruction #Computer Animation #Computational Fabrication #Computational Geometry #Computational Photography #Computer Vision for Computer Graphics #Data Compression for Graphics #Geometric Modelling #Geometric Processing #HCI and Computer Graphics #Human Modelling #Image Analysis #Image Based Rendering #Image Processing #Machine Learning for Graphics #Medical Imaging #Pattern Recognition #Physically Based Modelling #Illumination and Rendering ethods #Robotics and Vision #Saliency Methods #Scientific Visualization #Shape and Surface Modelling #Shape Analysis and Image Retrieval #Shape Matching #Sketch-based Modelling #Solid Modelling #Stylized rendering #Textures #Virtual and Augmented Reality #Visual Analytics #Volume Rendering #Data Mining #Data Science #Big Data #Data Warehouse #Visualization #Security #Privacy #Big DaaS #Scalable Computing #Cloud Computing #Knowledge Discovery #Integration #Transformation #Information Retrieval #Social Data and Semantics #Mining Functions #Data Regression #Data Classification #Anomaly Detection #Data Clustering #Data Association #Data Regression #Data Cleaning #Feature Selection and Extraction #Data Mining Algorithms #Apriori #Decision Tree #Generalized Linear Models #K-Means #Minimum Description Length #Naive Bayes #Non-Negative Matrix Factorization #0-Cluster #Support Vector Machines #Data Preparation #Mining Unstructured Data #Artificial Intelligence #Future Directions and Challenges in Data Mining #Industrial Challenges in Data Mining #Cryptographic Protocols #Cryptography and Coding #Untrace-Ability #Privacy and Authentication #Key Management #Authentication #Trust Management #Quantum Cryptography #Computational Intelligence in Security #Artificial Immune Systems #Biological & Evolutionary Computation #Intelligent Agents and Systems #Reinforcement & Unsupervised Learning #Autonomy-Oriented Computing #Coevolutionary Algorithms #Fuzzy Systems #Biometric Security #Trust Models and Metrics #Regulation and Trust Mechanisms #Data Integrity #Models for Authentication #Trust and Authorization #Wireless Network Security #Information Hiding #Data & System Integrity #Access Control and Intrusion Detection #Intrusion Detection and Vulnerability Assessment #Authentication and Non-Repudiation #Identification and Authentication #Insider Threats and Countermeasures #Intrusion Detection & Prevention #Secure Cloud Computing #Security Information Systems Architecture and Design and Security Patterns #Security Management #Security Requirements (Threats, Vulnerabilities, Risk, Formal Methods, etc.) #Sensor and Mobile ad hoc Network Security #Service and Systems Design and QOS Network Security #System Security #Intrusion Detection #Secure end Systems #Secure Operating Systems #Data Base Security #Security Infrastructures #Security Evaluation #Software Security #Security and Privacy in Mobile Systems#Security and Privacy in Pervasive/Ubiquitous Computing #Security and Privacy in Web Services #Security and Privacy Policies #Security Area Control #Security Deployment #Security Engineering #Security for Grid Computing #Security in Distributed Systems #Network Security #Internet Security #Firewalls #Mobile Security #Security Agents #Protocols #Anti-Virus and Anti-Hacker Measures #Content Protection #Software Protection #Tamper Resistant Software #Electronic Commerce #Electronic Government #Health #Telecommunications #Mobility #Foundations #Privacy #Access Control #Authentication #Identification #Applied Cryptography #Formal Methods in Information Security #IoT & IoE & Edge Computing #Distributed Mobile Applications Utilizing IoT #Security, Privacy and Trust in IoT & IoE #Standards for IoT Applications #Ubiquitous Computing #Blockchain-enabled IoT Device and Data Security and Privacy #Application of WSN in IoT #Cloud Resources Utilization in IoT #Wireless Access Technologies for IoT #Mobile Applications and Services for IoT #Machine/ Deep Learning with IoT & IoE #Smart Sensors and Internet of Things for Smart City #Logic, Functional programming and Microcontrollers for IoT #Sensor Networks, Actuators for Internet of Things #Data Visualization using IoT #IoT Application and Communication Protocol #Big Data Analytics for Social Networking using IoT #IoT Applications for Smart Cities #Emulation and Simulation Methodologies for IoT #IoT Applied for Digital Contents #Soft Computing #Advance Ubiquitous Computing #Parallel Computing #Distributed Computing #Machine Learning #Information Retrieval #Expert Systems #Data Mining #Text Mining #Data Warehousing #Predictive Analysis #Data Management #Big Data Analytics #Big Data Security #Nature Inspired Computing #Reconfigurable Computing #Cloud, Cluster, Grid and P2P Computing #Biomedical Computing #Green Computing #Mobile Computing #Nano Ubiquitous Computing #Context Awareness and Personalization, Autonomic and Trusted Computing #Internet Computing #Sequential, Parallel and Distributed Algorithms and Data Structures #Approximation and Randomized Algorithms #Graph Algorithms And Graph Drawing #On-Line and Streaming Algorithms #Analysis of Algorithms and Computational Complexity #Algorithm Engineering #Web Algorithms #Exact And Parameterized Computation #Algorithmic Game Theory #Computational Biology #Foundations of Communication Networks #Computational Geometry #Discrete Optimization #Software Engineering Methodologies #Agent-based Software Engineering #Artificial Intelligence Approaches to Software Engineering #Component-based Software Engineering #Embedded and Ubiquitous Software Engineering #Aspect-based Software Engineering #Empirical Software Engineering #Search-Based Software Engineering #Automated Software Design and Synthesis #Computer-Supported Cooperative Work #Automated Software Specification #Reverse Engineering #Software Engineering Techniques and Production Perspectives #Requirements Engineering #Software Analysis, Design and Modelling #Software Maintenance and Evolution #Software Engineering Tools and Environments #Software Engineering Decision Support #Software Design Patterns #Software Product Lines #Process and Workflow Management #Reflection and Metadata Approaches #Program Understanding and System Maintenance #Software Domain Modelling and Analysis #Software Economics #Multimedia and Hypermedia Software Engineering #Software Engineering Case Study and Experience Reports #Enterprise Software, Middleware, and Tools #Artificial Intelligent Methods, Models, Techniques #Artificial Life and Societies #Swarm Intelligence #Smart Spaces #Autonomic Computing and Agent-Based Systems #Autonomic Computing #Adaptive Systems #Agent Architectures, Ontologies, Languages and Protocols #Multi-Agent Systems #Agent-Based Learning and Knowledge Discovery #Interface Agents #Agent-Based Auctions and Marketplaces #Secure Mobile and Multi-Agent Systems #Mobile agents #SOA and Service-Oriented Systems #Service-Centric Software Engineering #Service Oriented Requirements Engineering #Service Oriented Architectures #Middleware for Service Based Systems #Service Discovery and Composition #Service Level Agreements (Drafting, Negotiation, Monitoring and Management) #Runtime Service Management #Semantic web #Data Modelling, Mining and Data Analytics #Aggregation, Integration, and Transformation #Web and Text Mining #Data Mining Methods, Techniques, and Tools #Data Analytics Modelling and Algorithms #Patterns and Frameworks #Data Visualization #Knowledge Systems and Engineering #Knowledge Acquisition #Knowledge-based and Expert Systems #Knowledge Representation and Retrievals #Knowledge Engineering Tools and Techniques #Time and Knowledge Management Tools #Knowledge Modelling, Integration, Transformation, and Management #Uncertainty Knowledge Management #Knowledge Visualization #Mobile Computing and Mobile System Engineering #Mobile App Design and Development #Innovative Mobile Applications #Pervasive Computing #Mobile System Validation and Test Automation #Software & System Quality of Service #Soft Computing #Software and System Testing Methods #Quality Assurance Process, Standards, and Systems #Software Safety Systems #Software Test Automation and Tools #Software Dependability, Reliability, Scalability #Software & System Security #Software and System Security and Privacy #Mobile App Security and Privacy #Encryption Methods and Tools #Security Service Systems #Cloud, Sensor Cloud and Mobile Cloud Security #Mobile System Integrity, Security, And Fault Tolerance #Emergent Topics #Cloud Computing and Innovative Cloud-Based Application Systems #Mobile Cloud Computing and Application Services #Big Data Analytics Application Systems #Innovative Sensing Cloud and Systems #Large-Scale Cyber Systems #IoT and Smart City Application Systems #Big Data Quality Validation #Big Data Application Quality Services #Smart Learning and Innovative Education Systems #Learning Software Design Engineering #Smart Learning Methods and Environments #Online Learning Systems #Mobile Enabled Learning Systems and Tools #PhD Academic #Scopus #SCI #LatticeScience #Springer, #ScienceDirect #IEEE #Mendeley #Research #Scholarship #UGC #SSRN #ESCI #Science #Journal #Conference #SSRN #PubLons #PhD #Academic #Scopus #SCI #LatticeScience #Springer, #ScienceDirect #IEEE #Mendeley #Research #Scholarship #UGC #SSRN #LatticeScience #ESCI #Science #Journal #Conference #SSRN #PubLon

Outlier Detection Using Support Vector Machine in Wireless Sensor Network Real Time Data
M. Syed Mohamed¹, T. Kavitha²
¹M.Syed Mohamed, M.E. Scholar (CSE), Anna University of Technology, Tirunelveli, Tamilnadu, India.
²T. Kavitha, Assistant Professor, Department of Computer Science and Engineering, Anna University of Technology, Tirunelveli, Tamilnadu, India.
Manuscript received on April 25, 2011. | Revised Manuscript received on May 01, 2011. | Manuscript published on May 05, 2011. | PP: 68-72 | Volume-1 Issue-2, May 2011. | Retrieval Number: A035041211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Outlier detection has many important applications in sensor networks, e.g., abnormal event detection, animal behavior change, intruder detection etc. Outliers in wireless sensor networks (WSNs) are sensor nodes that issue attacks by abnormal behaviours and fake message broadcasting. The probable sources of outliers include noise and errors, events, and malicious attacks on the network. Wireless sensor networks (WSNs) are more likely to generate outliers due to their special characteristics, e.g. constrained available resources, frequent physical failure, and often harsh deployment area. In this project we motivate our technique in the context of the problem of outlier detection. This paper is going to present the real time network outlier detection method in the wireless sensor networks. We proposed the technique to classify the sensor node data as local outlier or cluster outlier or network outlier using Standard Support Vector Machine classification method which is one of the best classification methods among the various outlier detection methods. If the data is classified as network outlier then it may be due an event otherwise if it is classified as a cluster outlier then it is an error in the cluster due to some environmental factor or network otherwise is an error in the sensor node due to some defect in that sensor. Experiments with real data show that our method is efficient and accurate to detect the outliers in real time. The real time data are collected from the Sensor Scope system and implemented using MATLAB.
Keywords: Outliers, Support Vector Machine (SVM), Wireless Sensor Network (WSN).

Download PDF

The post A035041211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A040051211

IJSCE Journal — Wed, 29 Sep 2021 10:07:44 +0000

A Survey of Efficient Algorithms and New Approach for Fast Discovery of Frequent Itemset for Association Rule Mining (DFIARM)
Anurag Choubey¹, Ravindra Patel², J.L. Rana³
¹Anurag Choubey, Dean Academic, Technocrats Institute of Technology, Bhopal (Madhya Pradesh), India.
²Dr. Ravindra Patel, Reader & Head, Department of Computer Application, UIT-RGPV, Bhopal(M.P.), India Bhopal (Madhya Pradesh), India.
²Dr. J. L. Rana, Ex. Professor & Head, Department of Computer Science & Engineering, MANIT, Bhopal (Madhya Pradesh), India
Manuscript received on April 25, 2011. | Revised Manuscript received on May 01, 2011. | Manuscript published on May 05, 2011. | PP: 62-67 | Volume-1 Issue-2, May 2011. | Retrieval Number: A040051211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The problem of mining association rules has attracted lots of attention in the research community. Several techniques for efficient discovery of association rule have appeared. With abundant literature published in research into frequent itemset mining and deriving association rules, if the question is raised that whether we have solved most of the critical problems related to frequent itemset mining and association rule discovery. Based on the scope of the recent literature, the answer will be negative. The most time consuming operation in discovering association rule, is the computation of the frequency of the occurrences of interesting subset of items (called candidates) in the database of transactions. Can one develop a method that may avoid or reduce candidate generation and test and utilize some novel data structures to reduce the cost in frequent pattern mining? This is the motivation of my study for mining frequent-item sets and association rules. In this paper we review some existing algorithms for frequent itemset mining and present a proposal of our new approach.
Keywords: Data mining, Frequent Item-set mining, Association Rule Mining.

Download PDF

The post A040051211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A038051211

IJSCE Journal — Wed, 29 Sep 2021 10:02:04 +0000

Analysis of Digitally Modulated Signals using Instantaneous and Stochastic Features, for Classification
Jaspal Bagga¹, Neeta Tripathi²
¹Jaspal Bagga Electronics and telecommunication, Shri Shankaracharya College of Engineering and Technology. Bhilai, India.
²Neeta tripathi, Principal, Shri Shankaracharya institute of Technology and Management, Bhilai, India.
Manuscript received on April 25, 2011. | Revised Manuscript received on May 02, 2011. | Manuscript published on May 05, 2011. | PP: 57-61 | Volume-1 Issue-2, May 2011. | Retrieval Number: A038051211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Automatic modulation classification is a procedure performed at the receiver based on the received signal before demodulation when the modulation format is not known to the receiver. AMR is also believed to play an important role in the implementation of Software Defined Radio (SDR) of the 4th-Generation (4G) communication system. The ability to automatically select the correct modulation scheme used in an unknown received signal is a major advantage in a wireless network This paper describes one application that exploits the flexibility of a software radio. As compared to the previous work this approach uses stochastic features to distinguish modulated signals for varying Signal to Noise Ratio (SNR). The proposed method is simple effective and robust. It is based on the stochastic features derived from instantaneous features to classify digital modulation signals.. This method is capable of differentiating ASK2, ASK4, FSK2, FSK4, PSK2 and PSK4 signals at the output of a typical high frequency channel with white Gaussian noise, Unlike most other existing methods, proposed method assumes no prior information of the incoming signal (symbol rate, carrier frequency, amplitude etc.). Extensive simulation results demonstrate that this approach is robust in various practical situations in identifying the modulated signals. When SNR is less than 5 dB, the percentage of correct identification is about 97%which increases to almost 100% for SNR 20db.
Keywords: Digital signals, Modulation Classification, Signal To Noise Ratio, Stochastic features.

Download PDF

The post A038051211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A034041211

IJSCE Journal — Wed, 29 Sep 2021 09:57:50 +0000

Design and Profile Optimization for Dispersion Shifted Fiber (DSF)
A.M. Agarkar¹, D.R. Dhabale²
¹A.M. Agarkar, Shree Sant Gajanan Maharaj College of Engineering, Shegaon, India.
²D.R. Dhabale, Shree Sant Gajanan Maharaj College of Engineering, Shegaon, India.
Manuscript received on April 25, 2011. | Revised Manuscript received on May 02, 2011. | Manuscript published on May 05, 2011. | PP: 53-56 | Volume-1 Issue-2, May 2011. | Retrieval Number: A034041211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In designing of SM fibers, dispersion behavior is a major distinguishing feature which limits long distance and high speed transmission. Dispersion of SMF is lowest at 1.3 um, but the attenuation is minimum at 1.55 um. At 1.55um dispersion is higher. For achieving maximum transmission distance in a high capacity link ,dispersion null should be at the wavelength of minimum attenuation .This may be achieved by mechanisms like reduction in fiber core with an accompanying increase in the relative RI to create Dispersion Shifted Fibers (DCF) [3]. In the proposed work by optimizing the fiber profile a fiber with minimum dispersion slope at the desired wavelength will be carried out.
Keywords: Optical Fiber, Dispersion, DSF, MFD.

Download PDF

The post A034041211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A039051211

IJSCE Journal — Wed, 29 Sep 2021 09:52:46 +0000

An Open Source Framework for PRTF Protocol
Ashok Bhansali¹, H.R. Sharma²
¹Roli Pradhan, Department of Management Studies, MANIT, Bhopal, (MP), India.
²Prof. K. K. Pathak, Scientist E ,AMPRI, Bhopal, (MP), India.
³Prof. V.P. Singh , Director Sagar Institute, Bhopal, (MP), India.
Manuscript received on April 25, 2011. | Revised Manuscript received on May 02, 2011. | Manuscript published on May 05, 2011. | PP: 46-52 | Volume-1 Issue-2, May 2011. | Retrieval Number: A039051211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Social networking websites contain vast amount of data inside them. Volume of data is enormous and growing at a very fast rate. Social network data can be classified in three major categories – user profile data, user communication data and group communication data. Data mining can be applied effectively to discover the knowledge and to extract the useful patterns from this gigantic data set, which is called as the social network mining. Person Related to a Field (PRTF) is a protocol to mine the information across all the social networking data, in general, and use the extracted pattern to search an expert in particular. It also proposes the mechanism to rank the searched experts. In this paper we propose an open source implementation of the PRTF (Person related to a Field) protocol. Using this proposed framework, apart from expert identification, number of useful patterns can be discovered from social networking data. The proposed framework is implemented using open source technologies and is explained with the help of an illustrative example.
Keywords: Social network mining, data mining, expert finding, PRTF.

Download PDF

The post A039051211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A037041211

IJSCE Journal — Wed, 29 Sep 2021 09:50:41 +0000

Application of Neural Network in Prediction of Financial Viability
Roli Pradhan¹, K.K. Pathak², V.P. Singh³
¹Roli Pradhan, Department of Management Studies, MANIT, Bhopal, (MP), India.
²Prof. K. K. Pathak, Scientist E ,AMPRI, Bhopal, (MP), India.
³Prof. V.P. Singh , Director Sagar Institute, Bhopal, (MP), India.
Manuscript received on April 25, 2011. | Revised Manuscript received on May 02, 2011. | Manuscript published on May 05, 2011. | PP: 41-45 | Volume-1 Issue-2, May 2011. | Retrieval Number: A037041211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Bankruptcy prediction is very important for all the organization since it affects the economy and causes a rise in many social problems with incremental high costs. There are large number of techniques that have been developed to predict the bankruptcy of firms, which helps the decision makers such as investors and financial analysts to plan in accordance to the financial position of the firm regarding the terms of credit as well as the recovery of the lent amount. The Altman Model for prediction of financial bankruptcy has been considered in this work. The backpropagation neural networks been used to forecast the Z Score for the firms. The research work first estimates the internal parameters of the Z score for a firm from 2001-2008 to the train the BPNN and uses the estimates of the year 2009 and 2010 values for the validation process. Finally it dwells to draw predictions for the period 2011-2015 and emphasizes the growing role of BPNN application based Z Score computation of financial Bankruptcy.
Keywords: Bankruptcy prediction, financial ratio models, BPNN.

Download PDF

The post A037041211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A033041211

IJSCE Journal — Wed, 29 Sep 2021 09:42:34 +0000

A Modified Method to Segment Sharp and Unsharp Edged Brain Tumors in 2 D MRI Using Automatic Seeded Region Growing Method
Mukesh Kumar¹, Kamal Mehta²
¹Mukesh Kmar, (M.E.) C.S.E. Department, S.S.C.E.T., Bhilai, India.
²Prof. Kamal Mehta, H.O.D,CSE Department, S.S.C.E.T. Bhilai, India.
Manuscript received on April 25, 2011. | Revised Manuscript received on May 02, 2011. | Manuscript published on May 05, 2011. | PP: 37-40 | Volume-1 Issue-2, May 2011. | Retrieval Number: A033041211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Segmentation of Brain tumor accurately is a challenging task in MRI. The MRI image is an image that produces a high contrast images indicating regular and irregular tissues that help to distinguish the overlapping in margin of each limb. But when the edges of tumor is not sharped then the segmentation results are not accurate i.e. segmentation may be over or under. This may be happened due to initial stage of the tumors [5]. So , in this paper a modified method of tumor line detection and segmentation is used to separate the irregular from the regular surrounding tissue to get a real identification of involved and noninvolved area that help the surgeon to distinguish the involved area precisely. The method used in this paper is seeded region growing method and it was implemented using MATLAB 7.6.0.324 on 25 Magnetic Resonance Images to detect the tumor boundaries in 2D MRI for different cases.
Keywords: Gray level, MRI image, Region growing, tumour, segmentation etc.

Download PDF

The post A033041211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A021031211

IJSCE Journal — Wed, 29 Sep 2021 09:38:28 +0000

A Proposed Method for Image Retrieval using Histogram values and Texture Descriptor Analysis
Wasim Khan¹, Shiv Kumar², Neetesh Gupta³, Nilofar Khan⁴
¹Wasim Khan is with the Technocrats Institute of Technology Bhopal, (M.P.), India.
²Shi Kumar is with the Technocrats Institute of Technology, Bhopal, (M.P.), India.
³Neetesh Gupta is with the Technocrats Institute of Technology Bhopal, (M. P.), India.
⁴Nilofar Khan is with the Chameli Devi Group of Institutions, Indore, (M. P.), India.
Manuscript received on April 19, 2011. | Revised Manuscript received on April 29, 2011. | Manuscript published on May 05, 2011. | PP: 33-36 | Volume-1 Issue-2, May 2011. | Retrieval Number: A021031211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Color and Texture information have been the primitive image descriptors in content based image retrieval systems. In this article, a method is proposed for image mining based on analysis of color Histogram values and texture descriptor of an image. For this purpose, three functions are used for texture descriptor analysis such as entropy, local range and standard deviation. To extract the color properties of an image, histogram values are used. The combination of the color and texture features of the image provides a robust feature set for image retrieval.
Keywords: Content-based image retrieval, color histogram, image texture.

Download PDF

The post A021031211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A031041211

IJSCE Journal — Wed, 29 Sep 2021 09:26:09 +0000

To Reduce the False Alarm in Intrusion Detection System using self Organizing Map
Ritu Ranjani Singh¹, Neetesh Gupta², Shiv Kumar³
¹Ritu ranjani singh, Information Technology, Technocrats Institute of Technology, Bhopal, (M.P.), India.
²Prof. Neetesh Gupta, Asst. Professor & Head, Department Of Information Technology, Technocrats Institute of Technology, Bhopal (M.P.), India.
³Prof. Shiv Kumar, Asst. Professor, Department Of Information Technology, Technocrats Institute of Technology Bhopal (M. P.), India.
Manuscript received on April 19, 2011. | Revised Manuscript received on April 29, 2011. | Manuscript published on May 05, 2011. | PP: 27-32 | Volume-1 Issue-2, May 2011. | Retrieval Number: A031041211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Intrusion detection systems aim to identify attacks with a high detection rate and a low false alarm rate. Classification-based data mining models for intrusion detection are often ineffective in dealing with dynamic changes in intrusion patterns and characteristics. Consequently, unsupervised learning methods have been given a closer look for network intrusion detection. Traditional instance-based learning methods can only be used to detect known intrusions, since these methods classify instances based on what they have learned. They rarely detect new intrusions since these intrusion classes has not been able to detect new intrusions as well as known intrusions. In this paper, we propose a soft Computing technique such as Self organizing map for detecting the intrusion in network intrusion detection. Problems with k-mean clustering are hard cluster to class assignment, class dominance, and null class problems. The network traffic datasets provided by the NSL-KDD Data set in intrusion detection system which demonstrates the feasibility and promise of unsupervised learning methods for network intrusion detection.
Keywords: Data mining, False alarm, Intrusion detection system, neural network, Self organizing map.

Download PDF

The post A031041211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).

A028031211

IJSCE Journal — Wed, 29 Sep 2021 09:20:38 +0000

Multistage VQ Based GMM For Text Independent Speaker identification System
Piyush Lotia¹, M.R. Khan²
¹Piyush Lotia, Associate Professor, Department of Electronics and Telecommunication, SSCET-Bhilai (C.G.), India.
²Dr. M.R. Khan, Associate Professor, Department of Electronics and Telecommunication, GEC Raipur (C.G.), India.
Manuscript received on April 19, 2011. | Revised Manuscript received on April 29, 2011. | Manuscript published on May 05, 2011. | PP: 21-26 | Volume-1 Issue-2, May 2011. | Retrieval Number: A028031211
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The use of Gaussian Mixture Models (GMM) are most common in speaker identification due to it can be performed in a completely text independent situation. However, it sounds efficient to speaker identification application, but it results long time processing in practice. In this paper, we propose a decision function by using vector quantization (VQ)techniques to decrease the training model for GMM in order to reduce the processing time. In our proposed modeling, we take the superiority of VQ, which is simplicity computation to distinguish between male and female speaker. Then, in second phase of classification, decision tree rule are applied to separate out the similar speaker in same gender into two difference group. While in phase 3, GMM is applied into the subgroup of speaker to get the accuracy rates. Experimental result shows that our hybrid VQ/GMM method always yielded better improvements in accuracy and bring almost 20% reduce in time processing.
Keywords: MFCC, VQ, Cepstrum, LBG Algorithim.

Download PDF

The post A028031211 appeared first on International Journal of Soft Computing and Engineering (IJSCE).