S. M. Aqil Burney

Information and Communication Technology in Healthcare Management Systems: Prospects for Developing Countries

and communication technologies (ICT) are being widely used in healthcare management systems. Rapid advancements in ICT in the last decade or so provide solutions to the problems in healthcare management systems. These include a wide spectrum of issues such as patient safety, dietary management, telemedicine, digital imaging, document management etc. This paper explores the emerging technologies which are being used for the improvement of the healthcare process and identify the problems and their probable solutions specifically in the context of developing countries. Telemedicine offers a way of improving the standard of healthcare especially in the developing world. The developing countries such as Pakistan, can exploit these to give better healthcare services as well health education. This paper highlights the growth of ICT sector in the developing world and explores its possible uses in health sector. These may help healthcare professionals and community health workers to carry out their work in a better way particularly in remote areas.

Forecasting Network Traffic Load Using Wavelet Filters and Seasonal Autoregressive Moving Average Model

A computer networks performance can be improved by increasing servers, upgrading the hardware, and gaining additional bandwidth. Another important issue to increase network performance is to use an appropriate mathematical model and using that model for forecasting the network load at peak hours. We analyze a network traffic time series of Internet requests made to a workstation. This series exhibits a long-range dependence and self-similarity in large time scale and exhibits multi-fractal in small time scale. With the growing demand of using computer networks, there is increasing demand to explore new techniques for forecasting. In this paper we used the wavelet filters based on multi-resolution analysis along with the Seasonal Autoregressive Moving Average (SARIMA) models for forecasting network traffic volume. We used the Daubechies 4 (db4) wavelet filters for compression of time series and SARIMA modeling for forecasting the series. Our proposed methodology is based on the theory that most of the network traffic signals are always having the noise and unnecessary details not required for further analysis hence forecasting directly from such signals may prove computationally intensive and prone to error. The denoised and compressed signals using wavelet filters will be comparatively more smoothed and helpful for speedy and accurate forecasts. We compare our results with simple SARIMA methodology and conclude that our proposed method give better and accurate forecasts. Using wavelet based SARIMA model, we believe that with the right choice of mother wavelet, moving towards a wavelet based forecasting system would significantly improve the forecasting efficiency.

Monthly average daily global beam and diffuse solar radiation and its correlation with hours of bright sunshine for Karachi, Pakistan

Correlation equations have been developed to obtain the monthly average of daily global, beam and diffuse solar radiation at Karachi, Pakistan from the fraction of maximum possible sunshine hours. The global, beam and diffuse solar radiation estimated via these equations are then compared with the measured values with excellent agreement. Diffuse and beam radiation can be estimated even in the absence of global radiation.

K-Means Cluster Analysis for Image Segmentation

K-Means reasonably divides the data into k groups is an important question that arises when one works on Image Segmentation? Which color space one should choose and how to ascertain that the k we determine is valid? The purpose of this study was to explore the answers to aforementioned questions. We perform K-Means on a number of 2-cluster, 3- cluster and k-cluster color images (k>3) in RGB and L*a*b* feature space. Ground truth (GT) images have been used to accomplish validation task. Silhouette analysis supports the peaks for given k-cluster image. Model accuracy in RGB space falls between 30% and 55% while in L*a*b* color space it ranges from 30% to 65%. Though few images used, but experimentation proves that K-Means significantly segment images much better in L*a*b* color space as compared to RGB feature space. Keywordsevaluation, L*a*b* Color Space, Precision Recall

Diffuse solar radiation estimates from sunshine hours and clearness index for Karachi, Pakistan

Abstract Correlations for the estimation of monthly average daily diffuse solar radiation as a function of the sunshine hours and clearness index have been obtained from Karachi. Generally, two types of correlations are used: (a) diffuse radiation as a function of relative sunshine hours and extraterrestrial radiation, and (b) diffuse radiation as a function of global and extraterrestrial radiation. These correlations are mostly first- and second-order polynomials in the sunshine hours and clearness index, indicating the presence of the diffuse solar radiation component. The diffuse solar radiation shows a peak value during the monsoon months of July–August. The diffuse to global ratio is found to be 0.32 from the analysis, and the diffuse to extraterrestrial radiation ratio is nearly 0.19 throughout the year. Among the established relations, Iqbal and Stanhill overestimate the radiation value, while Liu and Jordan underestimate it.

Fuzzy-temporal database ontology and relational database model

This paper presents ontology for temporal and fuzzy information representation in the context of relational database environment. Temporal information has its own semantics and there are approaches to deal with representation of temporal data in different database environments. Temporal data may not be precise or crisp in nature, there is an element of imprecision or vagueness in representing temporal attributes. This paper proposes general model for temporal and fuzzy ontology for building fuzzy-temporal database schema with illustrations.

Conversion of heterogeneous education system (HeES) into homogeneous education system (HoES) for ease of disabled persons using information technology

Even in this fast moving technological world, nothing productive has been done on educational grounds for the disabled people. There is no a single institute in this world provides a system where students with impaired vision and/or hearing disability can sit in common classroom with normal students to acquire pioneer education. The fundamental idea behind this paper is to convert the heterogeneous education system (HeES) into homogeneous education system (HoES) i.e. to provide a platform to special students by using speech technology, artificial intelligence and mathematical concepts. The proposed learning and collaboration system, which has been pilot-tested, is expected to provide the best possible education to special people so that they can be confident and stand firm in this world and compete with individuals.

Contour Extraction of Femur and Tibia Condyles on Plain Anteroposterior (AP) Radiograph

of femur (F) and tibia (T) are key bony landmarks around the knee joint. The condyles contour extraction is the first key step towards: quantification of femorotibial (FT) joint space width (JSW), to assess FT joint space narrowing (JSN), to determine knee joint alignment angles and in defining the lateral and medial condyle radii. This paper aims to contour extraction of femur and tibia condyles on plain anteroposterior (AP) knee radiograph. A number of standard OA and non-OA AP radiographs in DICOM format are acquired. The images are resized and filtered to detect femoral and tibia condyles edge pixels respectively. Thresholding is then applied which introduce outliers. After removing outliers spline interpolation and smoothing is applied to trace and extract the femur and tibia contours. The results demonstrates promising extracted contours on non-OA and moderate OA radiographs but needs improvement in radiographs showing severe OA. The femur and tibia contours obtained are well localized, smooth and have no broken lines.

A Generic Approach for Team Selection in Multi–player Games using Genetic Algorithm

This paper presents a solution to this problem with the help of genetic algorithm to find the optimal solution for the problem of cricket team selection and formation. Our approach is the combination of the existing quantitative approaches with some new extensions such as attributes regarding personal performances, team performance and the combination of players. Secondly our method is just not specific for cricket team but it is converted to generic model for other multiplayer games. We propose an adaptation of island genetic algorithm to optimize the selection of multiplayer sports team having multiple conflicting constraints with mixed crossover where the fitness of common solution is used to drive the selection.

Network Usage Security Policies for Academic Institutions

In any universities operation its managerial administration play an important characteristics. Universities have their Management Based System (MBS) but most of them are vulnerable to malicious activities such as virus attacks, spoofing attacks, and unauthorized access from outside network. We have to build a stable system of administration which guarantees us the operation of all academic affairs and monitor the real time traffic and detect possible attacks generated by hackers which basically want to destroy the important resources and information contents of the university. We also proposed a security policy especially for the universities networks. Furthest most, we can constitute an apt and accomplished system to secure the educational administration and bestow useful suggestions for university’s educational administration information security. The rapid increase of information technology usage demands the high level of security in order to protect the data assets and equipments of the user. This paper will give guidelines that allow the universities to manage network security effectively.