Md. Shahid Uz Zaman

An expert clinical decision support system to predict disease using classification techniques

Currently in the healthcare industry different data mining methods are used to mine the interesting pattern of diseases using the statistical medical data with the help of different machine learning techniques. The conventional disease diagnosis system uses the perception and experience of doctor without using the complex clinical data. The proposed system assists doctor to predict disease correctly and the prediction makes patients and medical insurance providers benefited. This research focuses on to diagnosis diabetes disease as it is a great threat to human life worldwide. The system uses the Decision Tree and K-Nearest Neighbor (KNN) Algorithms as supervised classification model. Finally, the proposed system calculates and compares the accuracy of C4.5 and KNN and the experimental result demonstrates that the C4.5 provides better accuracy for diagnosis diabetes. For the clinical database, the Pima Indians Dataset is used in this research.

GIS based heuristic solution of the vehicle routing problem to optimize the school bus routing and scheduling

The School bus routing and scheduling can be treated as a multi-objective Vehicle Routing Problem (VRP) that helps to transport the students in the safest, most economical and convenient way. The objective of this paper is to optimize the overall transportation cost by minimizing the fleet of vehicles and time spent in the journey. In this research, a Geographical Information System (GIS) based solution for School Bus Routing and Scheduling (SBRS) with time window is proposed using Clarke & Wrights algorithm. The result of this research helps the Transport Management to design a dynamic shortest and fastest route for the vehicles. The GIS helps to identify the real-world pickup stops according to the concentration of the students in a particular area as well as to visualize the current optimum route and pickup points. The proposed methodology is applied and tested to the Scholastica School in Dhaka city of Bangladesh with geo referenced data of school and pickup stops. A better result is obtained by the proposed method comparing to the existing semi-manual system.

Codebook design method for speaker identification based on Genetic Algorithm

In this paper, a novel method of designing a codebook for speaker identification purpose utilizing genetic algorithm has been proposed. Speech features have been extracted using standard speech parameterization method such as LPC, LPCC, RCC, MFCC, DeltaMFCC and DeltaDeltaMFCC. For each of these techniques, the performance of the proposed system has been compared. In this codebook design method, genetic algorithm has the capability of getting global optimal result and hence improves the quality of the codebook. Experimental results show the superiority (i.e. 92% accuracy has been achieved) of this proposed codebook design method.

Performance Evaluation of Pseudo-Code of Multi-user Environment CDMA Technology

This paper basically is an effort for finding the best possible PN codes used in multi-user environment. This includes the various types of PN codes and their techniques, benefits and shortcomings and as well as their properties. It has been seen that the length of the code, autocorrelation and cross correlation properties can help us to determine the best suitable code for any particular communication environment. We have tried to find out the PN codes with suitable autocorrelation properties along with low cross correlation values. We assumed only the bipolar case. In this paper we have worked on different types of PN codes. At first, we have tried to find out the best codes in 64 bit Walsh code. Then we have tried to find out those codes in 64 Walsh codes which have best auto correlation properties. Finally we have worked on the barker codes. The barker code has good autocorrelation properties and we have found the pairs with the low cross correlation so that they can be used in multi-user environment.

Multi-temporal FFT regression

Sequential data transmission regarding multi-temporal image analysis is mainly dependent upon prediction or forecasting. The transmission time can be substantially reduced by properly exploiting the temporal correlation. Multi-temporal images are often affected by sensor, and illumination variations, non-uniform attenuation, atmospheric absorption and other environmental effects which render system changes in them. Most of these changes are gradual and incremental. So a recent image can be predicted from a previous sequence of images if the amount of real land-cover change is limited. Regression based prediction is the most appropriate one in this case as it can quantify the relationships between images obtained by different measurement systems in different environments. FFT regression based temporal prediction is proposed in this paper whereby the least-squares minimization is conducted on the amplitude matrices of the readings via the FFT. For a given model, the value of squared coefficient of determination (R) is always increased beyond the value obtained by conventional regression which is a common quality measure of the chosen model.

A heuristic solution of the Vehicle Routing Problem to optimize the office bus routing and scheduling using Clarke & Wright's savings algorithm

Office bus routing is a rising problem because transportation service should be more efficient, safe and reliable. This research try to answer a question how to facilitate employees with transportation service that would be fast, cost effective, and in a timely manner. This research work discourse the Vehicle Routing Problem and scheduling issues of transportation service for Dhaka City, Bangladesh. Our implementation will help to develop office bus routing and scheduling prototype model. This model will help to design transportation management system of any organization. From this implementation, it will able to find shortest and fastest routes and schedule of office bus, and also allocate bus stops that will use to pick up and drop employees according to their residence. This application has considered cost matrix of time, routes length and the vehicles with same capacity. We have implemented this application with Clarke & Wrights savings algorithm. This paper concludes with the solutions of schedules and visualization of routes with GIS techniques that will helps to develop decision support system for any kind of Vehicle Routing Problem.

GIS-based extraction of open Space in Rajshahi city

In this paper we present a way to extract features and information from a digitize GIS-based map and for obtaining the open space in Rajshahi city. As we know the environment plays a most vital role for our living, the unplanned use of land can be a great threat to our environment and life. In this respect Geographic information system (GIS) gives us a way to keep track of land use through a digital map. We can capture, digitize, and store information and data in a GIS map. This paper aims to find out the useful data from the GIS based digitize map and analyze the information. After extracting the information a yearly based analysis is made and shows how terribly the number of building in Rajshahi area is increasing day by day since 1931 to 2000. And finally it is tried to make a forecast about the increasing the effect of it.

A graph rewriting approach to replace asynchronous RAMs in circuits with cycles for FPGAs

Circuit design that minimizes the number of clock cycles is easy if we use asynchronous read operations. However, most of FPGAs support synchronous read operations, but do not support asynchronous read operations. It is one of the main difficulties for users to implement parallel and hardware algorithms in FPGAs. The main contribution of this paper is to provide one of the potent approaches to resolve this problem. We assume that a circuit which includes cycles using asynchronous RAMs designed by a non-expert or quickly designed by an expert is given. Our goal is to convert this circuit with asynchronous RAMs into an equivalent synchronous ones. The resulting circuit with synchronous RAMs can be embedded into the FPGAs.