|
Multilayered Perceptron Feed-Forward Artificial Neural Network
Approach for E-mail Classification -- Ogwueleka Francisca Nonyelum
E-mail messages are originally designed to be sent and accumulated in repository for periodical use which amounts to the details of an event or a meeting’s upcoming agenda for a particular organization. These messages range from static organizational knowledge to conversations and pose a lot of difficulties to users in terms of prioritizing and processing of the contents of both stored and new incoming messages. This research has established a classification model which classifies the accumulated e-mails in the mail inbox known as dataset into four classes: critical, urgent, important and others. Electronic mail extractor application was designed and implanted to extract e-mail contents. The application used heuristic technique based on Term Frequency- Inverse Document Frequency (TF-IDF) to determine what keywords in a dataset of e-mail messages might be more favorable to use in a query. Nuclass 7.1 Artificial Neural Network (ANN) software was used in the implementation of automated e-mail classification into userdefined word classes corresponding to preformatted class identity, and was able to learn in an associative learning approach, in which the network was trained by providing it with input and matching output patterns. This study showed that Neural Networks (NN) using Back Propagation (BP) technique combined with electronic mail extractor can be successfully used for automated e-mail classification into meaningful classes. © 2012 IUP. All Rights Reserved.
Machine Learning for Social Network Analysis:
A Systematic Literature Review
--Sagar S De, Satchidananda Dehuri and Gi-Nam Wang
The importance of machine learning for social network analysis is realized as an inevitable tool in forthcoming years. This is due to the unprecedented growth of social-related data, boosted by the proliferation of social media websites and the embedded heterogeneity and complexity. Alongside the machine learning derives much effort from psychologists to build computational model for solving tasks like recognition, prediction, planning and analysis even in uncertain situations. Therefore, it is significant to study the synergy of machine learning techniques in social network analysis, focus on practical applications, and open avenues for further research. In this paper, we have reviewed the theoretical aspects of social network analysis with a combination of machine learning-based techniques, its representation, tools and techniques used for analysis. Additionally, the source of data and its applications are also highlighted in this paper. © 2012 IUP. All Rights Reserved.
Windows-Based and Web-Enabled ATMs: Issues and Scopes --Jyotiranjan Hota
Single vendor ATM software applications and monitoring are less complex. However, it takes more time to monitor and update these ATMs with antiviruses and security patches. Closed operating systems like OS/2 were deployed along with X.25 or SNA-based network in single vendor ATMs. Multivendor ATMs were facilitated by central ATM monitoring software and open operating systems like Microsoft Windows with a support of TCP/IP-based networks. This paper discusses the scope and issues of common APIs in ATMs as well as ATM monitoring and application software in both single and multivendor ATMs. It also discusses the emergence of web-enabled ATMs. © 2012 IUP. All Rights Reserved.
A Newly Established Symmetric Key Encryption Algorithm
for Small Amount of Data
-- K S S Narayana and G Veereswara Swamy
During data transmission between the source and the destination in a computer network, the data is exposed to external modifications with malicious intentions. Cryptography is widely used to protect sensitive data from unauthorized access and modifications while on transit. There are various forms of cryptographic algorithms used in computer communications and are broadly divided into two types—symmetric key and asymmetric key. Symmetric key algorithms are the quickest and most commonly used type of encryption like Data Encryption Standard (DES), International Data Encryption Algorithm (IDEA), Advanced Encryption Standard (AES), etc. In symmetric key algorithms, a single key is used for both encryption and decryption. In this paper, a new symmetric key algorithm is proposed. The advantages of this new algorithm are also explained. © 2012 IUP. All Rights Reserved.
|
