Ahmad Saikhu

Generalized Regression Neural Network for predicting traffic flow

Forecasting traffic flow is a popular research topic in Intelligent Transportation System. There have been several methods used for this forecasting, such as statistical methods, Bayesian Network, Neural Network Model, Hybrid ARIMA and ANN. Generalized Regression Neural Network (GRNN) is an interesting model to be used in forecasting traffic flow, as it can predict data with dynamic change and non-linear in nature, which is generally found in traffic flow data. In this research, a GRNN model is set up to process traffic flow data, and comparing its results and the results from other predicting methods (ARIMA, Single Exponential Smoothing, and Moving Average). Leave One Out Cross Validation (LOOCV) is used in testing traffic flow data and Mean Absolute Percentage Error (MAPE) is used as the evaluation criterion in the testing. The results show that using GRNN method on the testing data can improve the accuracy of predictions by reducing the value of MAPE when three other predicting methods: ARIMA, Single Exponential Smoothing, and Moving Average.

Intelligent Method for Dipstick Urinalysis Using Smartphone Camera

This paper introduces an intelligent method for helping people to maintain their healthy by doing a self urinalysis utilising a smartphone camera. A color sensing method using a smartphone camera is designed to determine the value of a reagent strip in a urinalysis dipstick. In the dipstick urinalysis, a color change in each reagent strip is examined. This color change is a result of the reaction of dipstick to the chemical contents of urine including pH, Protein, Glucose, Ketones, Leucocyte, Nitrite, Bilirubine, and Urobilinogen. Performing disptick urinalysis can be done in almost any places even on the very remote area where medical laboratory cannot be found, and it is much easier and cheaper than medical lab visit.

Mining fuzzy time interval sequential pattern on event log data using FP-Growth-Prefix-Span algorithms

Rapid technological developments caused the increasing number of computerized data processing. With the increasing complexity of business processes, business process management technologies such as ERP (Enterprise Resource Planning) are increasingly being used. This resulted in the availability of data more abundant so that excavation and search information from the dataset will be a valuable knowledge. In this paper, we have done the process mining to obtain an interesting pattern of event log data. In this research, data mining method that we are used is the sequential pattern mining algorithm using FP-Growth-Prefix Span. In addition, we are also used the fuzzy approach to handle the time interval of the analyzed data, so that the sequential pattern that produced become fuzzy time-interval sequential pattern. The application of these methods in a business processes that produce fuzzy time interval sequential pattern. From the analysis, the result shown that there is a minimum effect on the pattern of th...

Mobile application for scheduling of medical staff in emergency condition using integer programming

Unexpected events like disaster or accident often cause the emergency condition. For a disaster, mitigation is not only necessary, but also an emergency response plan for safety handling life of the victims are very important. Proper medical treatment by a professional will save many lives. Such event can occur at any or many locations and any time can occur in the same time that require some medical teams with qualified doctors or particular specialization and nurses for handling a number of victims. On the other hand, medical staff has a high mobility in performing his professional duties. Due to the limited number of medical staff with certain qualifications as required in an emergency and demands should arrive quickly, we need a reliable system in order to coordinating the assignment so for an emergency event can be handled properly. Those who have an authority can do coordination and scheduling. Scheduling optimization model has some special characteristics. Among the existence of a number of emergency events at several locations at the same time, the limited number of medical staff, special skills need for handling emergencies, and the presence of medical personnel who are mobile can be done by modeling one assignment optimizationl, namely Integer Linear Programming (ILP) model. As for fast communication for coordination between the management authority with a number of doctors, a mobile application can be applied. In this research, Bipartite Graph (BG) model, Ford-Fulkerson Algorithm (FFA) and ILP model as the main part of the decision making structure are implemented into a program. The first model (BG) present concordance between physicians with their expertises. The second model (FFA) helps the authority to determine medical staffwho meet the condition. The third, ILP model will help the authority to determine the best combination of medical staff assignment. Input, process, output, and feedback from the implementation are representing decision-making system for the medical staff assignment in to the emergency situation. So the medical team can quickly find out the assignments schedule through mobile applications.