M. Afshar Alam

Analysis on Credit Card Fraud Detection Techniques: Based on Certain Design Criteria

fraud is increasing significantly with the development of modern technology and the global superhighways of communication, resulting in the loss of billions of dollars worldwide each year. The companies and financial institution loose huge amounts due to fraud and fraudsters continuously try to find new rules and tactics to commit illegal actions. Thus, fraud detection systems have become essential for all credit card issuing banks to minimize their losses. The most commonly used fraud detection methods are Neural Network (NN), rule-induction techniques, fuzzy system, decision trees, Support Vector Machines (SVM), Artificial Immune System (AIS), genetic algorithms, K-Nearest Neighbor algorithms. These techniques can be used alone or in collaboration using ensemble or meta-learning techniques to build classifiers. This paper presents a survey of various techniques used in credit card fraud detection and evaluates each methodology based on certain design criteria.

A study on the Role of Intuitionistic Fuzzy Set in Decision making problems

The theory of fuzzy sets [1] proposed by Zadeh has achieved a great success in various fields. Out of several higher order fuzzy sets, the concept of an intuitionistic fuzzy set (IFS) introduced by Atanassov has been found to be highly useful to deal with vagueness/imprecision. IFS theory has been extensively applied to areas like Artificial Intelligence, networking, Soft decision making, Programming logic, operational research etc. One the promising role of IFS has been emerged in Decision making Problems. In some real-life situations, decision makers may not be able to accurately express their view for the problem as they may not possess a precise or sufficient level of knowledge of the problem or the decision makers are unable to discriminate explicitly the degree to which one alternative are better than others in such cases, the decision maker may provide their preferences for alternatives to a certain degree, but it is possible that they are not so sure about it [2]. Thus, it is very suitable to express the decision maker preference values with the use of fuzzy/intuitionistic fuzzy values rather than exact numerical values or linguistic variables [3-6]. To satisfy the need of decision making problem with imprecision and uncertainty many researchers have been concentrated on IFS theory. In this paper we reviewed the development of different approaches for solving decision making problem using IFS theory.

Schur decomposition and dither modulation: an efficient and robust audio watermarking technique

To protect the copyright for providing ownership in audio signal watermarking techniques are requisite. In this paper, a new robust audio watermarking algorithm is proposed, which is based on Schur decomposition and Dither modulation. In the Schur decomposition and Dither modulation based technique, watermark embedding is done using Dither modulation quantization which has a good performance in terms of imperceptibility, robustness and speed etc. Schur decomposition and Dither modulation is a blind audio watermarking technique which is robust against various attacks such as Additive White Gaussian Noise (AWGN), cropping, echoing, low pass filtering, requantization, resampling etc. The proposed technique has shown efficient and stable performance against various attacks and it is computationally faster.

To Developed Tool, an Intelligent Agent for Automatic Knowledge Acquisition in Rule-based Expert System

The complex stage in building expert system is knowledge acquisition from domain experts and translated it to representation approach in knowledge base of expert system. In this paper we present an automatic way to extract knowledge from domain experts directly and converted it to facts and rules in knowledge base for rule-based expert system using intelligent agent. That means, the construct of proposed system consists of three steps, in first step we are construct a Diagnosis Domain Tool for Expert System (DDTES) (a piece of software which contains the user interface, inference engine and a format for declarative knowledge in knowledge base). Secondly we are construct Knowledge Acquisition Agent (KAA) able to interview with domain experts to extract problem solving knowledge in specific diagnosis domain and converted it to production rules in knowledge base. Finally we captured complete rule-based expert system from combination the results of two previous steps which can works and produce advices in that domain. The proposed (DDTES) and (KAA) are implemented and executed by using Visual Prolog programming language Ver.7.1.

A Multi-Intelligent Agent for Knowledge Discovery in Database (MIAKDD): Cooperative Approach with Domain Expert for Rules Extraction

In last decade, autonomous intelligent agents or multi-intelligent agents and knowledge discovery in database are combined to produce a new research area in intelligent information technology. In this paper, we aim to produce a knowledge discovery approach to extract a set of rules from a dataset for automatic knowledge base construction using cooperative approach between a multi-intelligent agent system and a domain expert in a particular domain. The proposed system consists of several intelligent agents, each one has a specific task. The main task is assign to associative classification mining intelligent agent to deal with a database directly for rules extraction using Classification Based on Associations (CBA) rule generation and classification algorithm, and send them to a domain expert for a modification process. Then, the modified rules will be saved in a knowledge base which is used later by other systems (e.g. knowledge-based system). In other words, the aim of this work is to introduce a tool for extracting knowledge from database, more precisely this work has focused on produce the knowledge base automatically that used rules approach for knowledge representation. The MIAKDD is developed and implemented using visual Prolog programming language ver. 7.1 and the approach is tested for a UCI heart diseases dataset.

Design and Implementation of Intelligent Agent and Diagnosis Domain Tool for Rule-Based Expert System

The use of expert systems in different organizations can speed-up of human professional work. Expert System (ES) is one of the common application of Artificial Intelligence (AI) has focus on the construction of high performance programs in specific professional domain. In this paper we introduce a tool for constructing rule-based expert system called DDTRES (Diagnosis Domain Tool for Rule-based Expert System), this tool provide variety of functions to facilitate the development of expert systems for practical problems in different diagnosis domain. The DDTRES consists of four components: end-user interface, inference engine, explanation facility, and empty knowledge base. We proposed also an intelligent agent for data mining to extract set of rule from medical dataset and put it in empty knowledge base of DDTRES to capture complete rule-based expert system which can produce advices in that medical field. The proposed system is developed and implemented using visual PROLOG programming language ver. 7.1.

A Comparative Study of Fuzzy and Intuitionistic Fuzzy Techniques in a Knowledge based Decision Support

Through this paper we present the implementation of fuzzy decision making in case of a medical diagnostic system and compare the results with those of the Intuitionistic fuzzy decision making technique. Both the approaches are used to solve multi-criteria, complex decision making problems. Intuitionistic fuzzy differs from the fuzzy approach as it adds indeterminacy and imprecision to the fuzzy technology. Let us consider a simple diagnostic system where we diagnose the causes of obesity. Patients are treated for obesity according to the type of obesity they have or let us say the cause of their obesity. Obesity can be lifestyle related or it can be a pathological or genetic disorder. Both fuzzy and Intuitionistic fuzzy techniques will determine the cause of obesity. It is for us to decide which one is the efficient way to do it.

High-dimensional multimedia classification using deep CNN and extended residual units

Processing multimedia data has emerged as a key area for the application of machine learning methods Building a robust classification model to use in high dimensional space requires the combination of a deep feature extractor and a powerful classifier. We present a new classification pipeline to facilitate multimedia data analysis based on convolutional neural network and the modified residual network which can integrate with the other feedforward network style in an endwise training fashion. The proposed residual network is producing attention-aware features. We proposed a unified deep CNN model to achieve promising performance in classifying high dimensional multimedia data by getting the advantages of the residual network. In every residual module, up-down and vice-versa feedforward structure is implemented to unfold the feedforward and backward process into a unique process. The hybrid proposed model evaluated on four datasets and have been shown promising results which outperform the previous best results. Last but not the least, the proposed model achieves detection speeds that are much faster than other approaches.

Highly Discriminative Features for Phishing Email Classification by SVD

Unstructured text documents have drawn recently more attention, because with growing amount of text documents, there is a need to classify them automatically. But an important problem in field of text categorization is the huge dimensional and very sparse dataset which hurts generalization performance of classifiers. This paper presents a Singular Value Decomposition (SVD) technique to email classification, in order to compress optimally only the kind of documents (in our experiments email classes) and to retain the most informative and discriminate features from an email document. The performance evaluation is performed on email dataset which is publicly available to demonstrate the benefit of the LSA.

Ensuring Data Security and Performance Evaluation in Cloud Computing

Cloud computing is threatened by unanswered security issues that are risky for both the cloud providers and users. Cloud is a computing design that manages large sets of distributed resources, of which scientists benefit from their convergence. The aim of this paper is divided into two parts: firstly a brief review on cloud computing mainly focusing on security and secondly offer a solution that eradicates possible threats. In particular, we proposed a new data security model that can efficiently protect the data whether in the cloud database or in transition. We start with an established authentication server and data server providing user authentication, user verification, and data support. The system follows SSL protocol for data encryption and protection, and secure deliver report (SDR) is used for data reliability and integrity of communication.