Rajasvaran Logeswaran

Behavioral factors influencing virtual knowledge sharing: theory of reasoned action

Purpose – The purpose of this paper is to report the results of an exploratory investigation of the behavioral factors in relation to virtual knowledge sharing among Multimedia University students, Malaysia, based on the theory of reasoned action (TRA).Design/methodology/approach – A search and review of the existing literature was followed by an empirical test of the proposed model in the pilot study (number of participants: n=50) and the main study (n=250).Findings – Trust, anticipated reciprocal relationship and willingness to share knowledge as an individuals attitude; while identification and organizational culture acting as subjective norms, indirectly have an impact on individuals intention to share knowledge virtually. No positive relationship was discovered between the degree of competition and an individuals attitude to share knowledge; nor between collectivism and subjective norms.Research limitations/implications – The results may have been influenced by self‐selection bias, as only one uni...

KGMO: A swarm optimization algorithm based on the kinetic energy of gas molecules

Swarm-based algorithms have acquired an important role in solving real-world optimization problems. In this paper, Kinetic Gas Molecule Optimization (KGMO), an optimization algorithm that is based on the kinetic energy of gas molecules, is introduced. The agents are gas molecules that are moving in the search space; they are subject to the kinetic theory of gases, which defines the rules for gas molecule interactions in the model. The performance of the proposed algorithm, in terms of its ability to find the global minima of 23 nonlinear benchmark functions, is evaluated against the corresponding results of two well-known benchmark algorithms, namely, Particle Swarm Optimization (PSO) and the recently developed high-performance Gravitational Search Algorithm (GSA). The simulations that were undertaken indicate that KGMO achieves better results in decreasing the Mean Square Error (MSE). Significant improvements of up to 107 and 1020 times were achieved by KGMO against PSO and GSA, respectively, in solving unimodal benchmark functions within 150 iterations. Improvements of at least tenfold were achieved in solving the multimodal benchmark functions. The proposed algorithm is more accurate and converges faster than does the benchmark algorithms, which makes this algorithm especially useful in solving complex optimization problems.

An enhanced hybrid method for time series prediction using linear and neural network models

The need for improving the accuracy of time series prediction has motivated researchers to develop more efficient prediction models. The accuracy rates resulting from linear models such as linear regression (LR), exponential smoothing (ES) and autoregressive integrated moving average (ARIMA) are not high as they are poor in handling the nonlinear time series data. Neural network models are considered to be better in handling such nonlinear time series data. In the real-world problems, the time series data consist of complex linear and nonlinear patterns and it may be difficult to obtain high prediction accuracy rates using only linear or neural network models. Hybrid models which combine both linear and neural network models can be used to obtain high prediction accuracy rates. In this paper, we propose an enhanced hybrid model which indicates for a given input data which choice is better between the two options, namely, a linear-nonlinear combination or a nonlinear-linear combination. The appropriate combination is selected based on a linearity test of data. From the experimental results, it is found that the proposed hybrid model comprising linear-nonlinear combination performs better than other models for the data that have a linear relationship. On the contrary, the hybrid model comprising nonlinear-linear combination performs better than other models for the data that have a nonlinear relationship.

Prediction Models for Early Risk Detection of Cardiovascular Event

Cardiovascular disease (CVD) is the major cause of death globally. More people die of CVDs each year than from any other disease. Over 80% of CVD deaths occur in low and middle income countries and occur almost equally in male and female. In this paper, different computational models based on Bayesian Networks, Multilayer Perceptron, Radial Basis Function and Logistic Regression methods are presented to predict early risk detection of the cardiovascular event. A total of 929 (626 male and 303 female) heart attack data are used to construct the models. The models are tested using combined as well as separate male and female data. Among the models used, it is found that the Multilayer Perceptron model yields the best accuracy result.

Lossless compression of Fluoroscopy medical images using correlation and the combination of Run-length and Huffman coding

Medical centers produce a massive amount of sequential medical images for examinations such as CT, MRI and Fluoroscopy, where each examination of a patient consists of a series of images. This takes up a large amount of storage space, in addition to the cost and time incurred during transmission. For medical data, lossless compression is preferred to the greater gains of lossy compression, in the interest of accuracy. This paper proposes a new method for lossless compression of pharynx and esophagus fluoroscopy images, using correlation and combination of Run Length and Huffman coding on the difference pairs of images classified by correlation. From the experimental results obtained, the proposed method achieved improved performance with a compression ratio of 11.41 for the proposed combination of Run-length and Huffman coding (RLHM-D) on the difference images as compared to 1.31 for the standard images.

Design and Development of Kinect-Based Technology-Enhanced Teaching Classroom

This paper presents an innovative use of the Kinect camera in designing a cost effective technology-enhanced teaching classroom consisting of a multi-touch interactive whiteboard and a teaching station. The design principle of the system is based on the capability of Kinect to send a fixed speckle pattern towards a plane, track the reflected IR sources in real time, undertake the necessary processing and finally achieve an interactive multi-touch surface. The classroom can operate with either existing teaching applications or the customized Multi-touch Teaching Module. The Teaching Module allows instructors to manipulate teaching content such as animations, streaming video lectures, schematic diagrams and so on more naturally through supported hand gestures such as panning, rotating, zooming in and out, etc. When the classroom is operating with existing teaching applications, instructors can intuitively interact with teaching content using their fingers on the large projected display or on the table surface, instead of relying on a mouse and keyboard. Initial evaluation results of the technology-enhanced teaching classroom by lecturers show positive feedback over standard computers as it is much easier to operate. The cost-effective technology-enhanced classroom is able to provide similar features offered by commercially available interactive whiteboards or multi-touch teaching stations and could be adopted as an alternative in a budget restricted environment.

Segmentation and compression of pharynx and esophagus fluoroscopic images

Enormous amounts of sequential medical images are produced in modern medical examinations, typically in Fluoroscopy. Although highly effective, such large quantities of images incur a high cost in terms of storage, processing time and transmission. This paper proposes a method for lossless compression of targeted parts within Fluoroscopy images, extracting the region of interest (ROI) - in this case the pharynx and esophagus, and employing customized correlation and the combination of Run Length and Huffman coding, to increase compression efficiency. The experimental results show that the proposed method improved performance with a compression ratio of 300% better than conventional methods.

A dual hybrid forecasting model for support of decision making in healthcare management

Forecasting of time series data such as fertility, morbidity and mortality rates is important for healthcare managers as these data serve as health indicators of a society. Accurate forecasting of these data based on past values helps the healthcare managers in taking appropriate decisions for avoiding possible calamity situations. Healthcare time series data consist of complex linear and nonlinear patterns and it may be difficult to obtain high forecasting accuracy rates using only linear or neural network models. In this paper, we present a dual hybrid forecasting model based on soft computing technology. The proposed method makes use of a combination of linear regression, neural network and fuzzy models. The inputs to the fuzzy model are the forecast values of healthcare time series data. Based on a set of rules, the fuzzy model yields a qualitative output which is useful for decision making in healthcare management.

Improved Adaptive Neuro-Fuzzy Inference System for HIV/AIDS Time Series Prediction

Improving accuracy in time series prediction has always been a challenging task for researchers. Prediction of time series data in healthcare such as HIV/AIDS data assumes importance in healthcare management. Statistical techniques such as moving average (MA), weighted moving average (WMA) and autoregressive integrated moving average (ARIMA) models have limitations in handling the non-linear relationships among the data. Artificial intelligence (AI) techniques such as neural networks are considered to be better for prediction of non-linear data. In general, for complex healthcare data, it may be difficult to obtain high prediction accuracy rates using the statistical or AI models individually. To solve this problem, a hybrid model such as adaptive neuro-fuzzy inference system (ANFIS) is required. In this paper, we propose an improved ANFIS model to predict HIV/AIDS data. Using two statistical indicators, namely, Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), the prediction accuracy of the proposed model is compared with the accuracies obtained with MA, WMA, ARIMA and Neural Network models based on HIV/AIDS data. The results indicate that the proposed model yields improvements as high as 87.84% compared to the other models.

A Computer-aided Multidisease Diagnostic System Using MRCP

Automated computer analysis of magnetic resonance cholangiopancreatography (MRCP) (a focused magnetic resonance imaging sequence for the pancreatobiliary region of the abdomen) images for biliary diseases is a difficult problem because of the large inter- and intrapatient variations in the images, varying acquisition settings, and characteristics of the images, defeating most attempts to produce computer-aided diagnosis systems. This paper proposes a system capable of automated preliminary diagnosis of several diseases affecting the bile ducts in the liver, namely, dilation, stones, tumor, and cyst. The system first identifies the biliary ductal structure present in the MRCP images, and then proceeds to determine the presence or absence of the diseases. Tested on a database of 593 clinical images, the system, which uses visual-based features, has shown to be successful in delivering good performance of 70–90% even in the presence of multiple diseases, and may be useful in aiding medical practitioners in routine MRCP examinations.