A. B. M. Shawkat Ali

HMM based hand gesture recognition: A review on techniques and approaches

Gesture is one of the most natural and expressive ways of communications between human and computer in a virtual reality system. We naturally use various gestures to express our own intentions in everyday life. Hand gesture is one of the important methods of non-verbal communication for human beings for its freer in movements and much more expressive than any other body parts. Hand gesture recognition has a number of potential applications in human-computer interaction, machine vision, virtual reality, machine control in industry, and so on. As a gesture is a continuous motion on a sequential time series, the HMMs (Hidden Markov Models) must be a prominent recognition tool. The most important thing in hand gesture recognition is what the input features are that best represent the characteristics of the moving hand gesture.This paper presents part of literature review on ongoing research and findings on different technique and approaches in gesture recognition using HMMs for vision-based approach.

Above the Trust and Security in Cloud Computing: A Notion Towards Innovation

While the nascent Cloud Computing paradigm supported by virtualization has the upward new notion of edges, it lacks proper security and trust mechanisms. Edges are like on demand scalability and infinite resource provisioning as per the ‘pay-as-you-go’ manner in favour of a single information owner (abbreviated as INO from now onwards) to multiple corporate INOs. While outsourcing information to a cloud storage controlled by a cloud service provider (abbreviated as CSP from now onwards) relives an information owner of tackling instantaneous oversight and management needs, a significant issue of retaining the control of that information to the information owner still needs to be solved. This paper perspicaciously delves into the facts of the Cloud Computing security issues and aims to explore and establish a secure channel for the INO to communicate with the CSP while maintaining trust and confidentiality. The objective of the paper is served by analyzing different protocols and proposing the one in commensurate with the requirement of the security property like information or data confidentiality along the line of security in Cloud Computing Environment (CCE). To the best of our knowledge, we are the first to derive a secure protocol by successively eliminating the dangling pitfalls that remain dormant and thereby hamper confidentiality and integrity of information that is worth exchanging between the INO and the CSP. Besides, conceptually, our derived protocol is compared with the SSL from the perspectives of work flow related activities along the line of secure trusted path for information confidentiality.

Computational intelligence for microarray data and biomedical image analysis for the early diagnosis of breast cancer

The objective of this paper was to perform a comparative analysis of the computational intelligence algorithms to identify breast cancer in its early stages. Two types of data representations were considered: microarray based and medical imaging based. In contrast to previous researches, this research also considered the imbalanced nature of these data. It was observed that the SMO algorithm performed better for the majority of the test data, especially for microarray based data when accuracy was used as performance measure. Considering the imbalanced characteristic of the data, the Naive Bayes algorithm was seen to perform highly in terms of true positive rate (TPR). Regarding the influence of SMOTE, a well-known imbalanced data classification technique, it was observed that there was a notable performance improvement for J48, while the performance of SMO remained comparable for the majority of the datasets. Overall, the results indicated SMO as the most potential candidate for the microarray and image dataset considered in this research.

Automatic detection and recognition of traffic signs

Automatic detection of road sign is a challenging but demanding job. A new approach namely automatic detection and recognition of traffic signs (ADRTS) considering color segmentation, moment invariants, and neural networks has been proposed in this paper. Experimental result proves the superior performance in the detection and recognition of road signs. Computational time complexity is also quite low that makes it applicable for the real time system.

Spam Classification Using Adaptive Boosting Algorithm

Spam is no doubt a new and growing threat to the Internet and its end users. This paper investigates current approaches for blocking spam and proposes a new spam classification method by using adaptive boosting algorithm. Experiment is carried out to evaluate the results of spam filtering. We find adaptive boosting algorithm is an effective approach to solve the spam problem. We also find that default method in WEKA such as DecisionStump is not actually the best associated algorithm to filter spam. After comparing DecisionStump, J48, and NaiveBayes we conclude J48 is the most suitable associated algorithm to filter spam with high true positive rate, low false positive rate and low computation time.

Access Control Management for Cloud

Managing data access control in an authorized and authenticated way is still one of the key challenge in cloud security. In a complex environment like cloud, data owner and Cloud Service Provider (CSP) need to monitor continuously who is accessing which data in order to prevent unauthorized access. Moreover, it should be pre-defined that who can perform which operation on particular data, which can reduce unauthorized access to a great extent. In this regard, users access to any data, application and services reside in cloud should be controlled, managed dynamically and monitored continuously. Most of cases the traditional system is not efficient enough to cope up with dynamic cloud environment, due to high dynamicity, data virtualization and multi-tenancy, higher scalability and higher degree of integrity. Existing systems also merely provide efficient auditing and reporting functionality regarding access control management. In this research we have designed a data intensive dynamic access control model for cloud environment. Several authorization algorithms are devised in this paper. Our proposed access control model has portrayed the system framework and different module along with their functionalities. Multi Agent based System (MAS) is represented to define the accessibility and functionality of the proposed model. Moreover, an enhanced authorization scheme is driven in this work to improve the security of the proposed system. We have also represented security and efficiency analysis of proposed models which has shown that our proposed scheme is efficient and secured enough to deals with the access control management.

Estimation of Energy Storage and Its Feasibility Analysis

Storage significantly adds flexibility in Renewable Energy (RE) and improves energy management. This chapter explains the estimation procedures of required storage with grid connected RE to support for a residential load. It was considered that storage integrated RE will support all the steady state load and grid will support transient high loads. This will maximize the use of RE. Proper sized RE resources with proper sized storage is essential for best utilization of RE in a cost effective way. This chapter also explains the feasibility analysis of storage by comparing the economical and environmental indexes.

A Comparison Between Rule Based and Association Rule Mining Algorithms

Recently association rule mining algorithms are using to solve data mining problem in a popular manner. Rule based mining can be performed through either supervised learning or unsupervised learning techniques. Among the wide range of available approaches, it is always challenging to select the optimum algorithm for rule based mining task. The aim of this research is to compare the performance between the rule based classification and association rule mining algorithm based on their rule based classification performance and computational complexity. We consider PART (Partial Decision Tree) of classification algorithm and Apriori of association rule mining to compare their performance. DARPA (Defense Advanced Research Projects Agency) data is a well-known intrusion detection problem is also used to measure the performance of these two algorithms. In this comparison the training rules are compared with the predefined test sets. In terms of accuracy and computational complexity we observe Apriori is a better choice for rule based mining task.

Investigation of Energy Storage Systems, Its Advantage and Requirement in Various Locations in Australia

Storage minimizes the intermittent nature of renewable sources. Solar and wind are the two fostered source of renewable energy. However, the availability of useful solar radiation and wind speed varies with geographical locations, and also the duration of this energy sources varies with seasonal variation. With the available vast open land and geographical position, Australia has great potential for both solar and wind energies. However, both these sources require energy buffering to support load demand to ensure required power quality. Electricity demand is increasing gradually, and also Australia has target to achieve 20% electricity from renewable sources by 2020. For effective utilization of solar and wind energy potential location of these sources needs to be identified, and effective size of storage needs to be estimated for best utilization according to the load demand. Therefore this paper investigated wind speed and solar radiation data of 210 locations in Australia, identified the potential locations, and estimated required storage in various potential locations to support residential load demand. Advantages of storage were analyzed in terms of loading on distribution transformer and storage support during energy fluctuation from renewable energy. Further analysis showed that storage greatly reduces greenhouse gas emission and reduces overall cost of energy by maximizing the use of solar and wind energies.

Finding a unique Association Rule Mining algorithm based on data characteristics

This research compares the performance of three popular association rule mining algorithms, namely apriori, predictive apriori and tertius based on data characteristics. The accuracy measure is used as the performance measure for ranking the algorithms. A wide variety of association rule mining algorithms can create a time consuming problem for choosing the most suitable one for performing the rule mining task. A meta-learning technique is implemented for a unique selection from a set of association rule mining algorithms. On the basis of experimental results of 15 UCI data sets, this research discovers statistical information based rules to choose a more effective algorithm.