As the data volumes continue to increase and the ways of information dispersion across the globe continue to diversify, new scalable methods and structures are needed for efficiently processing those distributed and autonomous data. Grid computing, P2P technology, distributed information retrieval technology and networking technology all must be merged to address the scalability concern.

The scope of the journal includes:

Scalable distributed information systems
Scalable grid information systems
Parallel information processing and systems
Web information searching and retrieval
Data mining
Content delivery networks (CDN)
VLDB
P2P systems
Scalable mobile and wireless database systems
Large scale sensor network systems
Index compression methods
Architectures for scalability
Scalable information system applications
Evaluation metrics for scalability
Information security

Guest editor: Robbi Rahim (Sekolah Tinggi Ilmu Manajemen Sukma, Indonesia)

Call for Papers: Special issue on: Smart System and Computational Intelligence and its Application (Manuscript submission deadline: 30 June 2019; Notification of acceptance: 5 July 2019; Submission of final revised paper: 14 July 2019; Publication of special issue (tentative): 30 July 2019)

Ajay Kattepur (Tata Consultancy Services)
Aniello Castiglione (University of Salerno)
Chang Choi (Chosun University)
Cho-Li Wang (University of Hong Kong)
Daniel S. Katz (University of Chicago)
Fabrizio Silvestri (ISTI – CNR, Italy)
Giancarlo Fortino (University of Calabria)
Hamed Taherdoost (Hamta Business Solution Snd)
Heng Tao Shen (University of Queensland)
Houbing Song (Embry-Riddle Aeronautical University)
José Manuel Machado (Uniiversity of Minho, Portugal)
Jose Merseguer (Universidad de Zaragoza)
Jie Li (University of Tsukuba)
Lin Yun (Harbin Engineering University)
Mirjana Ivanovic (University of Novi Sad)
Phan Cong Vinh (Nguyen Tat Thanh University)
Raj Gururajan (University of Southern Queensland)
Sherman Chow (Chinese University of Hong Kong)
Silva Fábio (University of Minho, Portugal)
Steve Beitzel (Telcordia)
Tuan Phung-Duc (University of Tsukuba, JP)
Tzung-Pei Hong (National University of Kaohsiung, Kaohsing City, Taiwan)
Wang-Chien Lee (The Pennsylvania State University)
Weili Wu (The University of Texas at Dallas)
Xueyan Tang (Nanyang Technological University)
Vijayakumar Ponnusamy (SRM University, India)
Yingshu Li (Georgia State University)

Recently Published
Most Popular

EODVGA: An Enhanced ODV Based Genetic Algorithm for Multi-Depot Vehicle Routing Problem
Appears in:
sis 19(21): e8

Authors:
Prabu U, Ravisasthiri P, Sriram R, Malarvizhi N, Amudhavel J

Published:
10th Jun 2019

Abstract:
Multi-Depot Vehicle Routing Problem (MDVRP) is a familiar combinative optimization problem that simultaneously determines the direction for different vehicles from over one depot to a collection of consumers. Researchers have suggested variety of meta-heuristic and heuristic algorithms to elucidate…Multi-Depot Vehicle Routing Problem (MDVRP) is a familiar combinative optimization problem that simultaneously determines the direction for different vehicles from over one depot to a collection of consumers. Researchers have suggested variety of meta-heuristic and heuristic algorithms to elucidate MDVRP, but none of the existing technique has
improved the fitness of the solution at the time of initial population generation. This motivates to propose an enhanced ODV based population initialization for Genetic Algorithm (GA) to solve MDVRP effectively. The Ordered Distance Vector (ODV) based population seeding method is a current and effective population initialization method for Genetic Algorithm to produce an early population with quality, individual diversity and randomness. In the proposed model, the customers are first grouped based on distance to their nearest depots and then routes are scheduled and optimized using
enhanced ODV based GA. The experiments are performed based on different types of instances of Cordeau. From the experimental results, it is very clear that the proposed technique outperforms the existing techniques in terms of convergence rate, error rate and convergence diversity.
more »
Load Balancing Policies of Web Servers: Research Analysis, Classification and Perspectives
Appears in:
sis 19(21): e7

Authors:
Prabu U, Malarvizhi N, Amudhavel J, Sriram R, Ravisasthiri P

Published:
10th Jun 2019

Abstract:
The usage of the internet has increased rapidly from the past few years. Thus it automatically increases the internet traffic. In the internet, a web server always responds to the client or web browser's requests. The major feature of a web server is to be available, scalable and predictable. So th…The usage of the internet has increased rapidly from the past few years. Thus it automatically increases the internet traffic. In the internet, a web server always responds to the client or web browser's requests. The major feature of a web server is to be available, scalable and predictable. So the core part to be concentrated is web server load balancing. Load balancing plays a vital role in allocating the jobs to the web server based on its status. There are various policies available for web server load balancing. Each of these policies came into existence based on the certain needs. In this paper, we have examined the latest policies of web server load balancing.
more »
An Experimental Study with Tensor Flow for Characteristic mining of Mathematical Formulae from a Document
Appears in:
sis 19(21): e6

Authors:
K. N. Brahmaji Rao, G. Srinivas, P. V. G. D. Prasad Reddy

Published:
10th Jun 2019

Abstract:
Through this article a deep learning technique is proposed for the extraction and classification of mathematical keywords from textual documents. Extraction of math keywords from textual data is predominant problem as textual documents contain a culmination of mathematical symbols and literals from…Through this article a deep learning technique is proposed for the extraction and classification of mathematical keywords from textual documents. Extraction of math keywords from textual data is predominant problem as textual documents contain a culmination of mathematical symbols and literals from natural language such as alphabets and words. Separation of these textual words embedded in the mathematical formulae is a complex task. Our proposed technique solves this critical problem of extracting mathematical keywords from textual documents using techniques such as stemming,
tokenization and clustering mathematical keywords based on a training set of mathematical keyword and formulae pairs. The performance of the proposed technique is measured using the metrics such as retrieval time, Sensitivity, Accuracy, FPR, FNR, and FDR are used for appraisal of the proposed technique.
more »
Email Phishing: An Enhanced Classification Model to Detect Malicious URLs
Appears in:
sis 19(21): e5

Authors:
Shweta Sankhwar, Dhirendra Pandey, R.A Khan

Published:
6th May 2019

Abstract:
Phishing is the process of enticing people into visiting fraudulent websites and persuading them to enter their personal information. Number in phishing email are spread with the aim of making web users believe that they are communicating with a trusted entity or organization. Phishing is deployed …Phishing is the process of enticing people into visiting fraudulent websites and persuading them to enter their personal information. Number in phishing email are spread with the aim of making web users believe that they are communicating with a trusted entity or organization. Phishing is deployed by the use of advanced and harmful tactics like malicious or phishing URLs. So, it becomes necessary to detect malicious or phishing URLs in the present scenario. Numerous anti- phishing techniques are in vogue to discriminate fake and the authentic website but are not effective. This research, focuses on the relevant URLs features that discriminate between legitimate and malicious/phishing URLs. The impact of email phishing can be largely reduced by adopting an appropriate combination of all these features with classification techniques. Therefore, an Enhanced Malicious URLs Detection (EMUD) model is developed with machine learning techniques for better classification and accurate results.
more »
An Adaptive Fault Tolerant Scheduling System for Desktop Grid
Appears in:
sis 19(21): e4

Authors:
Jyoti Bansal, Geeta Rani

Published:
6th May 2019

Abstract:
In Desktop Grid, managing faults is very crucial and challenging job. So a fault tolerant system is mandatory requirement in desktop grid for fault identification and their resolution. A fault tolerant system allows applications to continue execution despite having faults without termination. In th…In Desktop Grid, managing faults is very crucial and challenging job. So a fault tolerant system is mandatory requirement in desktop grid for fault identification and their resolution. A fault tolerant system allows applications to continue execution despite having faults without termination. In this paper,an adaptive fault tolerant scheduling system is presented that combines dynamic replication with rescheduling. The system initially schedules jobs depending upon the completion time and fault rate of resources and then fault-tolerant strategies are applied depending upon availability of resources. To measure the performance,experiments has been carried out and it has been observed that proposed scheduling system outperforms by a factor of 4.8% w.r.t. Average task response time and 0.02% w.r.t. Average flowtime as compared to existing system. On the other hand, there is no significant improvement is observed when BoT completion time and average execution time are compared to existing system.
more »
Knowledge Discovery for Scalable Data Mining
Appears in:
sis 19(21): e3

Authors:
Indu Chhabra, Gunmala Suri

Published:
6th May 2019

Abstract:
The scalable diverse data and increasing levels of complexity in engineering and management science have given a boost to Data mining technology. The purpose of the proposed research is to evaluate the rule-based technique to develop solutions for analyzing customer Post Purchase behavior through k…The scalable diverse data and increasing levels of complexity in engineering and management science have given a boost to Data mining technology. The purpose of the proposed research is to evaluate the rule-based technique to develop solutions for analyzing customer Post Purchase behavior through knowledge discovery paradigm of Association rule mining. Over the years, it has proved a good tool to predict because of the incorporation of actual mined patterns. The current work is focused on extracting knowledge about the customer purchasing psychology and behaviour for the most frequent item combinations. For the purchase implementation, association rule framework is assessed for its performance analysis. The inferences of this automated intelligent system are based on of real life data set of 120 item-set combinations of five computer peripherals. This knowledge will help in framing and executing the most appropriate market laws and rules for the overall business growth.
more »
Role and Performance of Different Traditional Classification and Nature-Inspired Computing Techniques in Major Research Areas
Appears in:
sis 19(21): e2

Authors:
Samriti Sharma, Gurvinder Singh, Dhanpreet Singh

Published:
16th Apr 2019

Abstract:
In the last few years, different machine learning techniques such as supervised, unsupervised, and reinforcement learning have been effectively employed to solve distinct real-life multidisciplinary problems. These techniques have been effectively applied to accurately predict the problems related …In the last few years, different machine learning techniques such as supervised, unsupervised, and reinforcement learning have been effectively employed to solve distinct real-life multidisciplinary problems. These techniques have been effectively applied to accurately predict the problems related to stock values, disease diagnosis, sentiment analysis, text processing, gene classification, crop prediction, and weather forecasting. The objective of this manuscript is to present the systematic review on the use of these techniques in five major domains i.e. agriculture, finance, healthcare, education and engineering. A standard review methodology has been adapted to include and exclude the related literature. The performance of different supervised and nature-inspired computing techniques have been accessed on the basis of different performance metrics. The publication trend on the use of machine learning techniques in these five research areas has been also explored. Finally, the gaps in the study have been identified that will assist prospective researchers who want to pursue their research in these areas.
more »
New Behavioural Big Data Methods for Predicting Housing Price
Appears in:
sis 19(21): e1

Authors:
Jiaying Kou, Yashar Gedik

Published:
16th Apr 2019

Abstract:
Housing market price prediction is a big challenge. The 2008 global recession strongly showed that even the most sophisticated traditional economic models failed to foresee the crisis. New developments of behavioural economic theory indicate that the information from micro-level’s decision making w…Housing market price prediction is a big challenge. The 2008 global recession strongly showed that even the most sophisticated traditional economic models failed to foresee the crisis. New developments of behavioural economic theory indicate that the information from micro-level’s decision making will bring new solution to the age-old problem of economic forecasting. Additionally, the information revolution and big data methods have provided a new lens to study economic problems apart from traditional methodologies.
This research provides the theoretical link between irrationality and big data methods. Empirically, big data methods will be used in forecasting the housing market cycle in Australia. Speciﬁcally, Google trends is included as a new variable in a time series auto-regression model to forecast housing market cycles.
more »
Exploiting Data-Centric Social Context in Phone Call Prediction: A Machine Learning based Study
Appears in:
sis 19(20): e8

Author:
Iqbal H. Sarker

Published:
19th Feb 2019

Abstract:
Context-awareness in phone call prediction can help us to build many intelligent applications to assist the end mobile phone users in their daily life. Social context, particularly, the interpersonal relationship between individuals, is one of the key contexts for modeling and predicting mobile use…Context-awareness in phone call prediction can help us to build many intelligent applications to assist the end mobile phone users in their daily life. Social context, particularly, the interpersonal relationship between individuals, is one of the key contexts for modeling and predicting mobile user phone call activities. Individual’s diverse call activities, such as making a phone call to a particular person, or responding an incoming call are not identical to all; may diﬀer from person-to-person based on their interpersonal relationships, such as family, friend, or colleague. However, it is very diﬃcult to make the device understandable about such semantic relationships in phone call prediction. Thus, in this paper, we explore the data-centric social relational context generating from the mobile phone data, which can play a signiﬁcant role to achieve our goal. To show the eﬀectiveness of such contextual information in prediction model, we conduct our study using the most popular machine learning classiﬁcation techniques, such as logistic regression, decision tree, and support vector machine, utilizing individual’s mobile phone data.
more »
Cache Performance Optimization of QoC Framework
Appears in:
sis 19(20): e7

Authors:
Asif Ali Laghari, Hui He, Rashid Ali Laghari, Asiya Khan, Rahul Yadav

Published:
19th Feb 2019

Abstract:
The main aim of this paper is based on the cache performance test of the QoC: quality of experience framework for cloud computing on the server. QoC framework is based on the server-side design and implementation of the use of hierarchical architecture. Reverse proxy technology is used to build a s…The main aim of this paper is based on the cache performance test of the QoC: quality of experience framework for cloud computing on the server. QoC framework is based on the server-side design and implementation of the use of hierarchical architecture. Reverse proxy technology is used to build a server cluster, which is composed of front-end access layer to achieve the server for load balancing, improve the performance of the system and the use of built-in distributed cache server. The cluster consists of the cache acceleration layer, which reduces the load of the backend database. The second database server cluster, which is constructed by the database master and slave synchronization technology, forms the data storage layer, which realizes the database read and writes separation and data redundancy. The server-side hierarchical architecture improves the performance and stability of the entire system, and has a high degree of scalability, laying a solid foundation for future expansion of system business logic and increases user volume. This paper presents new cache replacement algorithm for inconsistent video file size and then analyzes the specific needs for the multi-terminal type of QoC framework, and gives the client and server-side outline design; it describes the implementation details of the client and the server-side and finally the whole system of detailed functional and performance testing.
more »

The impact of using social media and internet on academic performance case study Bahrain Universities
Appears in:
sis 17(13): e2

Author:
Abdulla Jaafar Desmal

Downloads:
2652

Abstract:
The internet and social media provide students with a range of academic benefits and opportunities to enhance their learning process. The main goal of this research is to examine the impact of using the social media on the academic performance. The new social networks, such as Instagram, Facebook, …The internet and social media provide students with a range of academic benefits and opportunities to enhance their learning process. The main goal of this research is to examine the impact of using the social media on the academic performance. The new social networks, such as Instagram, Facebook, Twitter, etc., can affect the behavior and academic performance of the universities' students; therefore the selected universities were Ahlia University, Applied Science University and University of Bahrain. The sample was (150) students distributed equally among the three universities. The research questions will answer (1) what is the evolution of ICTs and the Internet in the World; (2) what is the impact caused by ICT in education; (3) what are the effects of social media on the academic performance of students at Bahrain Universities; (4) what are the social networking sites that are more popular among students at Bahrain Universities. The results show that the social media has a positive impact on academic performance and 57% of students prefer the mobile application WhatsApp as a social media for their academic purpose.
more »
A Narrative Literature Review and E-Commerce Website Research
Appears in:
sis 18(17): e1

Author:
K.M. Rahman

Downloads:
948

Abstract:
In this study, a narrative literature review regarding culture and e-commerce website design has been introduced. Cultural aspect and e-commerce website design will play a significant role for successful global e-commerce sites in the future. Future success of businesses will rely on e-commerce. To…In this study, a narrative literature review regarding culture and e-commerce website design has been introduced. Cultural aspect and e-commerce website design will play a significant role for successful global e-commerce sites in the future. Future success of businesses will rely on e-commerce. To compete in the global e-commerce marketplace, local businesses need to focus on designing culturally friendly e-commerce websites. To the best of my knowledge, there has been insignificant research conducted on correlations between culture and e-commerce website design. The research shows that there are correlations between e-commerce, culture, and website design. The result of the study indicates that cultural aspects influence e-commerce website design. This study aims to deliver a reference source for information systems and information technology researchers interested in culture and e-commerce website design, and will show less-focused research areas in addition to future directions.
more »
A Parking Management System based on Background Difference Detecting Algorithm
Appears in:
sis 15(7): e3

Authors:
Xiaoling Wu, Yanwen Wang, Hainan Chen, Kangkang Liang, Lei Shu

Downloads:
933

Abstract:
The number of vehicles in cities has increased dramatically due to rapid economic development. However, the infrastructure for accommodating these vehicles has grown relatively slow. Alleviating the pressure on the urban transport system and solving the ‘parking difficulty’ problem have thus becom…The number of vehicles in cities has increased dramatically due to rapid economic development. However, the infrastructure for accommodating these vehicles has grown
relatively slow. Alleviating the pressure on the urban transport system and solving the ‘parking difficulty’ problem have thus become hot topics recently. In this paper, an intelligent parking system based on geomagnetic field variations is presented to solve
this problem. An algorithm which detects the presence of vehicles in parking spaces in a parking lot is designed and field test results are presented. Our results show that this system has an acceptably high accuracy with low cost, high feasibility, high efficiency and hence is recommended for wide use.
more »
An Advanced Conceptual Diagnostic Healthcare Framework for Diabetes and Cardiovascular Disorders
Appears in:
sis 18(18): e5

Authors:
M. Sharma, G. Singh, R. Singh

Downloads:
815

Abstract:
The data mining along with emerging computing techniques have astonishingly influenced the healthcare industry. Researchers have used different Data Mining and Internet of Things (IoT) for enrooting a programmed solution for diabetes and heart patients. However, still, more advanced and united solu…The data mining along with emerging computing techniques have astonishingly influenced the healthcare industry. Researchers have used different Data Mining and Internet of Things (IoT) for enrooting a programmed solution for diabetes and heart patients. However, still, more advanced and united solution is needed that can offer a therapeutic opinion to individual diabetic and cardio patients. Therefore, here, a smart data mining and IoT (SMDIoT) based advanced healthcare system for proficient diabetes and cardiovascular diseases have been proposed. The hybridization of data mining and IoT with other emerging computing techniques is supposed to give an effective and economical solution to diabetes and cardio patients. SMDIoT hybridized the ideas of data mining, Internet of Things, chatbots, contextual entity search (CES), bio-sensors, semantic analysis and granular computing (GC). The bio-sensors of the proposed system assist in getting the current and precise status of the concerned patients so that in case of an emergency, the needful medical assistance can be provided. The novelty lies in the hybrid framework and the adequate support of chatbots, granular computing, context entity search and semantic analysis. The practical implementation of this system is very challenging and costly. However, it appears to be more operative and economical solution for diabetes and cardio patients.
more »
Machine Learning and Predictive Analysis of Fossil Fuels Consumption in Mid-Term
Appears in:
sis 17(15): e4

Authors:
Mahmood Amerion, Mohammadmehdi Hosseini, Abdorreza Alavi Gharahbagh, Mohsen Amerion

Downloads:
771

Abstract:
In economies that are dependent on fossil fuel revenues, Realization of long-term plans, mid-term and annual budgeting requires a fairly accurate estimation of the amount of consumption and its price fluctuations. Accordingly, the present study is using machine learning techniques to predict the us…In economies that are dependent on fossil fuel revenues, Realization of long-term plans, mid-term and annual budgeting requires a fairly accurate estimation of the amount of consumption and its price fluctuations. Accordingly, the present study is using machine learning techniques to predict the usage of fossil fuels (Diesel, Black oil, Heating oil, and Petrol) in mid-term. Exponential Smoothing, a model of time series and the Neural Network model have been applied on the actual usage data obtained from Shahroud area from 2010 to 2015. For estimation of predictive value by Neural Network method, the training and testing samples, the highest and lowest errors with a range of 41% -0.89% and 88% -3% for the Mean Absolute Percent Deviation are the most appropriate predictions for Petrol consumption. And in the Single Exponential Smoothing, the forecast rate for each product is estimated on a
quarterly as well as monthly basis.
more »
Auto recalls and software quality in the automotive sector
Appears in:
sis 18(17): e3

Authors:
J. Pancik, A. Vemola, R. Kledus, M. Semela, A. Bradac

Downloads:
740

Abstract:
Software for automobiles is one from innovative factors in the automotive industry. Automobile is represented as an amount of embedded systems (embedded systems) and it is a very complex computing system. It is currently estimated that the average car has built-in software in the range of 100 milli…Software for automobiles is one from innovative factors in the automotive industry. Automobile is represented as an amount of embedded systems (embedded systems) and it is a very complex computing system. It is currently estimated that the average car has built-in software in the range of 100 million lines and in 2020 is already expected 300 million lines of code. The contribution is devoted to the management of safety and reliability of the software development for embedded systems designed for electromechanical (mechatronic) systems through quality assurance of embedded software. The contribution defines the term software quality assurance strategy, explains the role of standards such as ISO 26262 (Road vehicles - Functional safety), ISO 15504 (Automotive SPICE 3.0)
more »
Preventing DDoS using Bloom Filter: A Survey
Appears in:
sis 18(19): e3

Authors:
Ripon Patgiri, Sabuzima Nayak, Samir Kumar Borgohain

Downloads:
684

Abstract:
Distributed Denial-of-Service (DDoS) is a menace for service provider and prominent issue in network security. Defeating or defending the DDoS is a prime challenge. DDoS make a service unavailable for a certain time. This phenomenon harms the service providers, and hence, causes loss of business re…Distributed Denial-of-Service (DDoS) is a menace for service provider and prominent issue in network security. Defeating or defending the DDoS is a prime challenge. DDoS make a service unavailable for a certain time. This phenomenon harms the service providers, and hence, causes loss of business revenue. Therefore, DDoS is a grand challenge to defeat. There are numerous mechanism to defend DDoS, however, this paper surveys the deployment of Bloom Filter in defending the DDoS attack. The Bloom Filter is a probabilistic data structure for membership query that returns either true or false. Bloom Filter uses tiny memory to store information of large data. Therefore, packet information is stored in Bloom Filter to defend and defeat DDoS. This paper presents a survey on DDoS defending technique using Bloom Filter.
more »
Software-Defined Network Testbed Using ZodiacFX a Hardware Switch for OpenFlow
Appears in:
sis 17(14): e5

Authors:
Fahad Nazir, Qazi Humayun, R Badlishah Ahmad, Shamsul Jamel Elias

Downloads:
640

Abstract:
Software-defined network (SDN) is a new programmable networking designed to perform tasks easier by enabling network administrators to add network control via a centralized control platform and open interfaces. Common network use procedures such as traffic shifts, troubleshooting and various types …Software-defined network (SDN) is a new programmable networking designed to perform tasks easier by enabling network administrators to add network control via a centralized control platform and open interfaces. Common network use procedures such as traffic shifts, troubleshooting and various types of device configuration. Thus devices are needed to reconfigure with the network, in order to create a reaction with events. In this paper, we have developed an SDN testbed using Zodiac FX a hardware switch for OpenFlow experiment. This research is utilized Zodiac FX a hardware switch to test the usage and discuss about the SDN controllers. Ryu controller is configured for testbed development. The main contribution of this paper in threefold as follows: first it provides the configuration of Ryu controller, second, it provides the configuration of Zodiac FX switch and lastly it develops a simple SDN testbed for OpenFlow.
more »
Single and Multiple UAV Cyber-Attack Simulation and Performance Evaluation
Appears in:
sis 15(4): e4

Authors:
Ahmad Y. Javaid, Weiqing Sun, Mansoor Alam

Downloads:
639

Abstract:
Usage of ground, air and underwater unmanned vehicles (UGV, UAV and UUV) has increased exponentially in the recent past with industries producing thousands of these unmanned vehicles every year.With the ongoing discussion of integration of UAVs in the US National Airspace, the need of a cost-effect…Usage of ground, air and underwater unmanned vehicles (UGV, UAV and UUV) has increased exponentially in the recent past with industries producing thousands of these unmanned vehicles every year.With the ongoing discussion of integration of UAVs in the US National Airspace, the need of a cost-effective way to verify the security and resilience of a group of communicating UAVs under attack has become very important. The answer to this need is a simulation testbed which can be used to simulate the UAV Network (UAVNet). One of these attempts is - UAVSim (Unmanned Aerial Vehicle Simulation testbed) developed at the University of Toledo. It has the capability of simulating large UAV networks as well as small UAV networks with large number of attack nodes. In this paper, we analyse the performance of the simulation testbed for two
attacks, targeting single and multiple UAVs. Traditional and generic computing resource available in a regular computer laboratory was used. Various evaluation results have been presented and analysed which suggest the suitability of UAVSim for UAVNet attack and swarm simulation applications.
more »
A Hybrid Approach for Breast Cancer Classification and Diagnosis
Appears in:
sis 19(20): e2

Authors:
Bibhuprasad Sahu, Sachi Nandan Mohanty, Saroj Kumar Rout

Downloads:
552

Abstract:
Feature selection in breast cancer disease important and risky task for further analysis. Breast cancer is the second leading reason for death among the women. Cancer starts from breast and spread to other part of the body. People are unable to identify their disease before it become dangerous. It …Feature selection in breast cancer disease important and risky task for further analysis. Breast cancer is the second leading reason for death among the women. Cancer starts from breast and spread to other part of the body. People are unable to identify their disease before it become dangerous. It can be cured if the disease identified at early stage. Accurate classification of benign tumours can avoid patients undergoing unnecessary treatments. Data Analytics and machine learning methods provides framework for prognostic studies by errorless classification of data instances into relevant based on the cancer severity. In this study we have purposed a prediction model by combining artificial intelligent based learning technique with multivariate statistical method. For automation of the diagnosis process data mining plays an significant role. The data sets available in different repositories are noisy in nature. This study suggests a hybrid feature selection method to be used with PCA (Principal Component Analysis) and Artificial Neural Network (ANN). Preprocessing of data and extracting the most relevant features done by PCA. The proposed algorithm is tested by applying it on Wisconsin Breast Cancer Dataset from UCI Repository of Machine Learning Databases. In classification phase 10 fold cross validation was used. The suggested algorithm was measured against different classifier algorithms on the same database. The evaluation results of the algorithm proposed have achieved better accuracy with sensitivity and F measure comparison with others and by enhancing this concept we can provide a future scope to produce sophisticated learning models for diagnosis.
more »

Publisher: EAI
ISSN: 2032-9407
Number of Volumes: 6

Last Published: 10th Jun 2019