2014

Browse

Now showing 1 - 20 of 24

Hybrid Gene Selection Framework using Adaptive Wrapper and Filtering Techniques
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-10-15) Islam, Md Anisul; Mottalib, Md Mozaharul
Analysing the thousands of gene expression values is a difficult task due to the curse of dimensionality of data produced by Microarray chips. Primary role of an effective feature selection model is to simplify this task. To simplify the task of disease classification and predicting cancer, feature selection plays a vital role through removing less informative genes. In this study, we propose a hybrid approach to gene selection using adaptive filter and adaptive wrapper approach. As filter method exhibits some limitations, an adaptive form of filtering has been employed that iteratively selects genes in each iteration and emphasizes on the misclassified samples and in subsequent iteration tries to find out the effective genes for misclassified samples. This approach performs better than traditional filter methods as it focuses on its weaknesses. In gene selection, Artificial Neural Networks (ANN) are mostly used as a classifier. In this study, adaptive ANN has been used as an internal wrapper. This helps to generate a better subset of genes. The proposed hybrid approach is applied on leukaemia, colon and lung cancer benchmarked datasets. Better result has been found compared to other well-known approaches.
Nigerian international school website
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-10-15) Muhammad, Abubakar; Gonah, Abdulmalik Hassan; Mansoor, Abdulkhaleeq
In the early days the management of such systems was not easy and dynamic due to the lack of today’s technology; therefore the implementation of this website has come with some enhancement to improve the earlier disadvantages. The main objective or better still the aim of this website is to make it easier for the users (Students, Staffs and User) to access useful resources such as digital library, admission form, admission requirements, and view admission results. All these thanks to the very powerful and innovative evolution of sophisticated Information Technologies as exemplified by the rapid and dynamic growth of the Internet. Our website provides all the common facilities that a typical online Administration does; namely: a full-fledged interactive Digital Library in addition to the usual amenities that all websites provide such a home page, contact us module etc. Besides, another prominent feature of our website is an attractive gallery of photos implemented with J-Query that looks aesthetically appealing to the users (Students, Staffs and Student). The system is web based which by the way provide the applicants with many advantages. We need to note that most of the learning institution now are using web as a way to communicate. The communication is not the only advantage but many other advantages are considered such as the availability of the sys-tem and flexibility for the users to be able to interact with the system at any-time, anywhere
A Modified Algorithm For DNA Motif Finding & Ranking Considering Variable Length Motif & Mutation
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Ashrafi, Adnan Ferdous; Adit, A.K.M Iqtidar Newaz
With the evolution of time the gene composition of species have changed a lot. Consequently it has mutated to generate new diseases and traits. In order to identify genes or coding sections of a DNA sequence it is imperative to find out the promoter regions or the conserved regions of the DNA code first. But the main problem stands that the databases for these information are quite messy and needs to be researched. The main problems in finding motifs in a DNA sequence are finding a good and fast algorithm, considering mutations in those motifs, representing variable length motifs and being species general. In this thesis work we tried to formulate a new algorithm which is fast, accurate and effective. Instead of general string matching of DNA sequences we have done integer mapping and matching which are comparatively fast and accurate. Besides in order to formulate a complete DNA motif finding algorithm we also need a generalized and rational fitness function for evaluating the potential motifs. Thus we have formulated a desirable fitness function that enables us to compare the relativity among potential motifs and finally to predict a certain motif for the input DNA sequences.
Friend Recommendation System for the Social Network based on User Behavior
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Hasan, Mohammed Mehedi; Shaon, Noor Hussain
Social network sites have connected millions of users creating the social revolution in Web 2.0 now-a-days. If the group of people or organizations have the common interest then, a social network is constituted. In the present world, the most visited sites in the Internet are Twitter, Facebook, Orkut, Google plus etc. which is actually Online social networking sites. In the social network sites, a user makes friends with the other users and enjoy the communication with them. However, the large amount of online users and their diverse and dynamic interests possess great challenges to support such a novel feature in online social networks. In this thesis, we design a general friend recommendation framework based on user behavior. The main idea of the proposed method is consisted of the following stages- measuring the frequency of the activities and updating the dataset according to the activities, applying FP-Growth algorithm to find out the user behavior, then finding out the uncommon behavior containing the common behavior.
An Improved Cohesion Based Community Recommendation System
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Ahmed, Kazi Wasif; Rashid, Md. Mamunur
Social Networking Sites (SNS) are the dominating entities in the modern web. The importance of social networking sites in our life is increasing day by day as they are attracting millions of users by their interesting features and activities. It enables the researchers to use the information available in these sites. Online Community is appealing to people as they can enjoy sharing their ideas, view, and know about view of other people. At the same time, they are interested in joining different community. However, with the rapid growth of SNS’s resulting in information overload people are in dilemmas to choose right community from huge list of available communities and it is also time consuming. Potential choice of communities is influenced by many factors of user behavior and activeness in Social Networking Sites. The recent surge of research in recommendation algorithms is not surprising. But these algorithms have unsatisfactory results in community recommendation because of lack of intuition in judging rational behavior. Many researches are going on this point to find out recommendation system in various ways. To solve this problem, we introduce cohesion based community recommendation system. In this paper we design a general framework of community recommendation based on cohesion after analyzing the present methods of community recommendation. The main idea of the proposed approach is consisted of following stages- measuring friendship factor, measuring user factor, calculating threshold from present communities of user, community recommendation based on threshold, result analysis. We validated our idea on a small network in Facebook.
Community Recommendation in Social Network Using Strong Friends Based on Quasi-Clique Approach
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Matin, Anjum Ibna; Jahan, Sawgath
A social networking service is a platform to build social networks or social relations among people who, share interests, activities, backgrounds or real-life connections. Social network analysis is needed because the number of users is increasing rapidly day by day. Now days, users are involved themselves in to communities. They share post, their views, what they like in communities. So it is important for them to find suitable communities where they have common factors like friends, followers and their activities etc. Here we are working with a technique for recommending a community in social network like Facebook, twitter etc. We use some graph terminologies and graph mining techniques. Finding strong friends, we recommend communities for a user in a social network. We apply data mining techniques to help social users to pick out suitable community of a social network like Facebook, twitter etc. Big social network sites use their own algorithm. Here we are not improving an existing algorithm but giving a new method for community recommendation in social network. That is workable for both real and synthetic data. As real data are not given by any big social network so we use sample data to prove our algorithm. And we make a survey and thus we improve our Community Recommendation Algorithm (CRA).
A Statistical Approach for Off-Line Signature Verification Using Local Gradient Features
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Rahman, Ashikur; Mostaeen, Golam
Teacher Evaluation System of Islamic University of Technology
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Saleh, Abdullah Al; Bhuiyan, Ishmam Haque
Automation system is now being used in every aspects of life. It has made our life easier and the possibility of covering greater area of work has increased due to the automation process. Completing track of work and keeping records of work has become much easier because it reduced the huge amount of paper work which was needed before. The systematic automation of virtually every facet of life activity has today become more of a necessity than just mere luxury and the putting of such system online is even becoming increasingly imperative. With this respect the idea to develop an Online Teacher Evaluation System is being conceived. With a total population of over 1200 and each student each student evaluate the teaching of an average of six subjects and corresponding labs, the volume of paper work that has to be done, sorted and listed is enormous. Every semester around 12000 evaluation sheets are collected by the respective department secretaries. Getting to summarize those evaluation sheets is a time consuming and difficult work. So to make this evaluation system fully functional and the whole process easier, the idea of teacher evaluation system has been introduced. Each student is assigned a username and password with which he can access the system and evaluate only the teachers who were in that particular semester. Teachers can also access the system and see their evaluation. Head of the departments and vice chancellor can also access the system with various privileges. Only the VC has unrestricted access across the system. There will also be an admin in the system. He is the one who is responsible for creating new users and their passwords, granting different level of the system according to the user. In a nutshell, if the system is deployed, it will make the evaluation process suitable and easier and reduce the huge amount of paperwork. The system offers very user friendly interface, graphical representation of evaluation and gives an overview of whole evaluation system.
Determination Of Genetic Network From Time Series Gene Expression Data- A Modified Approach
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Alam, Hasan Md. Tusfiqur; Rupak, Nayreet Islam
Genetic Network is one of the most revolutionary discoveries in the field of Genetic Engineering. Gene regulatory networks control biological functions by regulating the level of gene expression. Discovering and understanding the complex causal relationships within gene networks has become a major issue in systems biology, computational biology and bioinformatics. The benefits of characterizing gene interaction are many, for example, Genetic networks provide knowledge about functional pathway in a given cell, representing processes such as metabolism, gene regulation, transport, and signal transduction , the effects of drugs on a regulatory pathway can be found, the development of cancer in a cell can be tracked, etc. Genes are the building blocks of a body. Genetic code directs functional property of every living organism. Genes directly encode proteins that make up the cell to function properly. At first DNA is converted into a mature messenger RNA (mRNA). Then mRNA is read and converted into amino acid sequence. The information contained in the nucleotide sequence is read as three –letter word called codon. Now amino acids coded by codon together form a polypeptide chain that is later folded into protein. Few proteins are parked into promoter region of another protein and performs various jobs like turn it on or off, regulate the protein production rate etc. Thus we can say that each gene here is responsible for influencing other gene or it might influence itself. For this reason expression level of the working genes always changes with time. DNA microarray experiments today allow to monitor the output of gene regulatory networks by measuring the gene expression levels of thousands of genes. Our primary focus on this paper is to find out methods for finding out those sets of genes that have some contribution for the growth of a bacteria called ‘Burkholderia Pseudomalli’. At various phases of the growth of ‘Burkholderia Pseudomalli’ we performed computation using Microarray gene expression time series dataset. The dataset was obtained from GEO data base of NCBI website. Initially dataset contained information about 5289 genes in 47 consecutive time. iii The entire work was divided into two phases. The first phase was data reduction as performing computation with this huge sizes of the microarray data is a pressure hardware of the computers as well as it is very much time consuming. So a data reduction methodology was applied which finds out the responsible genes actively taking part in the overall bacterial growth process or we can say that the dominant genes responsible for the growth was found out. The second phase was formation of genetic network from genetic dependencies in various time series. Finally genetic network was of those genes that are responsible for the growth.Once genetic network was determined this network can be used to study various unknown biological process, metabolic pathway engineering, drug discovery etc.
Online medical consultation
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Mohamed, Njingamndap Ousmanou; Javid, Mohammad
We are in the age of big changes, particularly the technology revolution and this has affected all aspect of our life. This modern-day revolution, at the global level, has manifested itself in the form of many innovations and breakthroughs and giant leaps in internetworking technology. With these changes, we have new opportunities, people can now transcend the barriers of time and distance with the internet’s speed. This has completely changed our living style, and every sector got changed and most of the traditional activities are going on now online like jobs, study and medicine. Online medicine has changed our old habit to go to hospital and wait so long to get a consultation, it has brought doctors near to patients anywhere and anytime. Being in this age of technology revolution, our goal is to build a website entitled “ONLINE MEDICAL CONSULTATION”. The aim of this project is to build a website for a medical consultation online which will allow anyone to get consultation online, create an environment where hospitals, doctors, patients and pharmacies will intercommunicate, and where people will focus on health and everything around it. Thus this project has five major parts, the admin part for managing the all system, the hospital part for managing all the doctors of the system, the doctor part to give consultation and advice to patients, the patient part for getting consultation and advices, and at last the pharmacy part for managing all the medicines and deliver the prescriptions to patients.
Prediction of a gene regulatory network from gene expression Profiles with Linear Regression and Pearson Correlation Coefficient
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Hasan, Mehedi; Nobin, Shakhawat Ahmmed
Reconstruction of gene regulatory networks is the process of identifying gene dependency from gene expression profile through some computation techniques. In our human body, all cells contain same genetic material but the same genes may or may not be active. This variation in the activation of genes assists researchers to understand more about the function of the cells. Microarray technology helps researchers to get insight about many different diseases such as various cancer disease, heart disease, mental illness, and infectious disease, etc. In this study, a cancer-specific gene regulatory network has been constructed using a simple and novel machine learning approach. First, significant genes differentially expressing them self in the disease condition has been identified using linear regression algorithm. Next, regulatory relationships between the identified genes has been computed using Pearson correlation coefficient. Finally The obtained results has been validated with the available databases and literatures. We can identify the hub genes and can be targeted for the cancer diagnosis.
Candidate Gene Prioritization Using Unique Pattern Indexing and Mapping Techniques
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Mutakabbir, Kazi Mahbub; Mahin, Shah S
“Prioritizing the candidate gene is amongst the notable work in bioinformatics. Techniques have been applied to reduce the number of promising genes for a certain disease. Previous works were done by using PageRank and HITS algorithm on graph based network. However using frequent pattern mining this prioritizing can be made more efficient. In this paper, we propose four algorithms. The first one indexes the unique sequences of length four using an integer value. The second algorithm finds the frequency of the frequent patterns of various lengths by searching through the integer values instead of the patterns themselves. Third one weights the candidate gene in compare with the genes of database. Fourth algorithm creates the graph network and ranks the candidate gene. All this is done highly efficiently by the use of mapping techniques e.g. HashMap. Due to its highly frugal nature, the proposed algorithm can reduce typical memory usage by 37.5% at the very minimum.”
Implementation of sip over VoIP
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Rahi, Mohammad Muntashir Are; Fuad, Nafis
Back in the days of wired telephony, when all phone calls went over the PSTN, businesses would purchase “trunks” – a dedicated line or a bundle of circuits – from their service provider. Today, we have adapted the concept of “trunking” to the IP-enabled landscape resulting in lower telephony costs and rapid return on investment (ROI) plus the opportunity for enhanced communications both within the enterprise and with vendors, customers and partners. A SIP trunk is a service offered by an ITSP to use SIP to set up communications between an enterprise PBX and the ITSP. A trunk includes multiple voice sessions – as many as the enterprise needs. While some see SIP as just voice, SIP trunking can also serve as the starting point for the entire breadth of real time communications possible with the protocol, including Instant Messaging, presence applications, white boarding and application sharing. The potential for a rapid return on investment is a key driver of SIP trunk deployments. However, maximum return on investment can be achieved when you extend VoIP outside of the corporate LAN. In terms of infrastructure purchases, SIP trunks provide an immediate cost-savings. They eliminate the need to purchase costly BRIs, PRIs or PSTN gateways. The productivity benefits with SIP and SIP trunking are also significant. By extending the SIP capabilities of the corporate network outside the LAN, satellite offices, remote workers and even customers can use VoIP and other forms of real-time communications applications to break down barriers of geography to share ideas and increase productivity. There are three components necessary to successfully deploy SIP trunks: a PBX with a SIP-enabled trunk side, an enterprise edge device understanding SIP and an Internet telephony or SIP trunking service provider. Equipment based on the SIP protocol – SIP phones, IP-PBXs etc. – have been around for some time. Now that SIP trunks have gained momentum, it has become 3 | P a g e important to ensure that equipment works together. It is for this reason that standards such as SIP connect™ have become so critical. SIP connect was developed by the SIP Forum as a set of best practices for interfacing an enterprise PBX implementation with an ITSP that attempts to eliminate some of the unknowns and incompatibilities of mixing equipment from different vendors in a single environment. Like any application that opens the network to the Internet, SIP trunking deployments have security considerations, but there are ways to maximize enterprise security. One of the most effective techniques is to address SIP security the same way data security is addressed - at the enterprise edge. SIP server and SIP proxy technologies offer maximum control over the flow of SIP traffic, enabling the administrator to ensure correct routing, apply verification and authentication policies and mitigate Denial-of-Service attacks. Voice quality is not an issue with SIP trunking if proper Quality of Service (QoS) measures are applied, such as over provisioning of links, and prioritization of voice traffic. Reliability is also a moot point. In fact, SIP trunks can be more reliable than the traditional PSTN as a number of failover solutions can be implemented.
An Optimized Algorithm to Find Maximum Parsimonious Tree Using PrimeNucleotide Based Approach
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Ajwad, Rasif; Hossain, Syed Nayem
Molecular phylogeny based on the nucleotide or amino acid sequence comparison has become a widespread tool for general taxonomy and evolutionary analysis. Molecular phylogeny methods are often free of problems which arise while applying phenotypic phylogeny. So, we prefer phylogenetic methods for classifying the organisms in any evolutionary situation. Phylogenetic inference methods like Maximum parsimony perform exhaustive search strategy to extract evolutionary information from genomic sequences. It is a simple but popular technique used in cladistics to infer a phylogenetic tree for a set of taxa (commonly of species or reproductively isolated populations of a single species) on the basis of some observed data on the similarities and differences among taxa. The relationships among organisms or genes are studied by comparing the homologues of DNA and protein sequences. However, complexity arises when we increase the number of sequences involved, as the number of possible solutions increase exponentially alongside. In our paper, we have proposed an algorithm which identifies the highest repeating nucleotide (PrimeNucleotide) from the informative site efficiently to fix one ParentNode with the best fitted nucleotide using a predefined WeightMatrix to find the most parsimonious phylogenetic tree in linear time. The algorithm has been applied on the genome sequences of different bacteria and viruses to ensure its efficiency and universality. The results obtained were similar to the traditional Transverse parsimony method and a significant improvement in both time consumption and memory usage rate were achieved.
Offline Bangla handwritten character recognition
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Islam, Yamin Bin; Rahman, Md. Taiyebur
Optical character recognition is an attractive subject for research work now days. In our study of this topic for Bangla Character domain, we have come around some methods of feature extraction and classification along with various preprocessing steps. We have exploited these techniques for their advantages and disadvantages. Among these, the methods that came to our attention because of their high accuracy are Stroke Extraction and encoding which is mainly mathematical, Chaincode extraction based on the direction of the points and Principal Component Analysis(PCA) of the character image. In our research, we have combined these methods and implemented the system in Matlab that gave us better accuracy than their individual implementation.
A QOS guaranteed resource allocation in cloud computing based on selective algorithm
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Kyser, Md. Tanbin Rahid; Ahmed, Zonayed
Cloud computing has become a new age technology that has got a huge potentials in enterprises and markets. It involves over a distributed computing over a network where a program or application may run on many connected computers at the same time. As cloud based system has become more and more numerous and dynamic, resource provisioning is become more and more challenging. At the same time energy has become an issue in this days. So, here we discuss resource allocation constraints with the energy and QoS based. Here QoS is the major part and Energy is minor part but we tried to consider both at the same time. Now, Energy and QoS are both depends on resource utilization. This utilization parameter based on two terms but this energy and QoS are reverse proportional. So, if we need to reach an equilibrium state then we need to use some kind of heuristics method. Here we use game theoretic approach for reaching an equilibrium state for getting a QoS and Energy aware system. Basically resource allocation depends on job scheduling. Several existed job scheduling algorithms was implemented. This algorithms are selected according to SLA. This phenomena is known as automated service provisioning for cloud computing. In this paper we provide a well-known Selective Approach for job scheduling including two popular algorithms known as Max-Min and Min-Min scheduling.
A modified algorithm for motif discovery Based on risotto and projection
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Galib, Marnim; Hasan, Nahid
An important part of gene regulation is mediated by specific proteins, called transcription factors, which influence the transcription of a particular gene by binding to specific sites on DNA sequences, called transcription factor binding sites (TFBS) or, simply, motifs. Such binding sites are relatively short segments of DNA, normally 5 to 25 nucleotides long, overrepresented in a set of co-regulated DNA sequences. There are two different problems in this setup: motif representation, accounting for the model that describes the TFBS’s; and motif discovery, focusing in unraveling TFBS’s from a set of co-regulated DNA sequences. This thesis proposes a discriminative scoring criterion that culminates in a discriminative mixture of Bayesian networks to distinguish TFBS’s from the background DNA. This new probabilistic model supports further evidence in nonadditivity among binding site positions, providing a superior discriminative power in TFBS’s detection. On the other hand, extra knowledge carefully selected from the literature was incorporated in TFBS discovery in order to capture a variety of characteristics of the TFBS’s patterns. This extra knowledge was combined during the process of motif discovery leading to results that are considerably more accurate than those achieved by methods that rely in the DNA sequence alone.
Human Activity Recognition using Dynamic Time Warping
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Hasan, G. M. Mukit; Iftekhar, Kazi MD
Human activity recognition is now a well-known field of Human Computer Interaction (HCI) because its capability of providing personalized support using different applications. The recognition of human activities has become a task of high interest within the field, especially for medical, military, and security applications. Its applications include surveillance systems, patient monitoring systems, and a variety of systems that involve interactions between persons and electronic devices such as human-computer interfaces. In our work we will try to recognize human activity using wearable sensors. The works done before had the problem of using multimodal system with satisfactory results. Computation of the inputs to recognize activities are not simple. So, we designed a multi-modal system that will take accelerometer, gyroscope and ultrasonic sensor’s data as input and use optimized Dynamic Time Warping algorithm to classify data to recognize activity with satisfactory success rate.
CXIDR cellular cross-layer intrusion detection and respons
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Kabir, Mohammad Raihan; Rahman, Rifat
Consumption of data through cellular devices are growing exponentially due to continuously growing popularity of smart phones and tablets. Because of their small size and reduced capabilities, it is sometimes hard to impose adequate security measures to these everyday used devices. Security measures are taken such as authentication, encryption or key management which can’t detect or solve all kinds of known and unknown attacks specially the new or unknown ones. Thus they have become a popular target for data theft and misuse. Because of the nature of the cellular network various kinds of attack on the cellular devices such as DOS are happening every day. Cellular network, being a wireless network, is prone to attacks because of the node’s shared nature, naturally broadcasted states, unclear perimeters, invisible access, limited resources and being not tolerant to physical attacks. So, security in wireless network is more complex than wired network. The conventional security measures regarding only the layered architecture cannot cope with this ever evolving security issue. So, here we are proposing a modified version of cross-layer design for security in wireless network entitled as Cellular Cross-layer Intrusion Detection and Response or CXIDR. It is an extended version of Cross-layer Intrusion Detection and Response (XIDR) framework. Here, we have tried to define the notion of cross-layer design which integrates features from various layers for detecting intrusions in wireless environment. We believe that this enhanced framework will do a great job in detecting intrusions in wireless area in near future.
A subset selection method using Filter and wrapper algorithms based on the nature of the expression values in microarray data sets for gene feature selection
(Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh, 2014-11-15) Azad, Tamzid; Islam, Md. Mazharul
In the field of micro-array data analysis the crucial first step is gene selection. The process refers to selecting a subset consisting of a few genes which are of genetic significance out of thousands of genes to make the job of the classifier algorithm computationally easy and efficient at the same time. Feature selection plays an important role in classification. The first set of data are gene expression profiles from Acute Lymphoblastic Leukemia (ALL) patients. In this paper an algorithm is proposed for feature subset selection (FFS) which is based on the nature of intensity values in microarray datasets. The proposed method is a combination of a filter and a wrapper algorithm which selects subsets. It is based on two assumptions. Our results demonstrate the importance of feature selection in accurately classifying new samples