Search

The detection of heart abnormality activity of a patient is important when an abnormal symptom occurred. This project is aimed to detect the disease by using hybrid multilayer perceptron (HMLP) network. Several data from the electrocardiogram (ECG) signal is extracted to be set as input parameters. In order to get the best result, several activation function are used such as logistic, hyperbolic, exponential, step and square root. The result obtained is then compared among the activation function and other detection techniques.

Heart abnormality refers to the irregular electrical activity of the heart. Heart abnormality sometimes does not show any symptom and it is not sensible which may lead to sudden death due to the heart cease functioning. This paper attempts to develop a program that capable to detect the heart abnormality activity through the implementation of Radial Basis Function (RBF). A certain amount of data of the heartbeat signals from electrocardiogram (ECG) will be used in this research to train the RBF network and to test the network performance.

Dissolved gas analysis is one of diagnostic technique for monitoring the internal condition of transformer. However, DGA analyses for natural ester especially palm oil and rice bran oil still lacking. Therefore, this paper presents the investigation on natural esters regarding gassing behaviour under lightning impulse breakdown. Two type of natural ester oils were used namely Palm oil (PO) and Rice Bran oil (RBO). The DGA result showed that C2H2 and H2 detected the highest amount of gases for both samples. The gaseous obtained from the experiments were interpreted in different DGA method such as Dornenburg ratio, Roger ratio, IEC Gas method and Duval Triangle method to find the best technique for natural ester oils. The conducted experiment shows that PO and RBO have comparable dielectric performance and gassing characteristics to mineral oil, but still requiring modification of design and operating parameters .

A new class of colloidal insulating transformer oil is formulated by dispersing CNT nanomaterials with mineral oil in purpose to enhance the breakdown strength performance of existing transformer oil. This paper represents the experimental studied dealing with the influence of CNT nanomaterials mix with transformer mineral oil in term of AC breakdown voltage at various gap distances. The concentrations of CNT nanomaterials were measured in range 0.01g/L to 0.2g/L. The impact of three gap distances (1.5mm, 2.5mm and 3.5mm) for mushroom-mushroom electrode configuration is studied in order to observe and compare the trend between conventional mineral oil and CNT nanofluids. To employ CNTs as effective reinforcement in mineral oil, proper dispersion methods need to be applied.