Mepco Schlenk Engineering College

About: Mepco Schlenk Engineering College is a based out in . It is known for research contribution in the topics: Wavelet & Wavelet transform. The organization has 1307 authors who have published 1665 publications receiving 18690 citations.

Prediction of Engine Emissions through Fuzzy Logic Modeling

Abstract: Pollution is a major problem for the present generation. The pollution from internal combustion engines contribute to nearly 30% of the total atmospheric pollution. Of the two engines namely petrol and diesel, the later contributes more smoke and Oxides of nitrogen (NOx) harmful to the health and environment. Prediction of these emissions would help in reducing them to a large extent. In this paper, the prediction of smoke and NOx using fuzzy logic has been attempted. Fuzzy logic is a multi-valued logic that allows intermediate values to be defined between conventional evaluations. The input parameters for prediction of emissions considered are Peak pressure, Load, Indicated mean effective pressure, Ignition delay and Combustion duration. Rules have been framed based on the engine system. The output parameters are pollutants NOx and smoke. The comparison between the actual experimental readings and the values through fuzzy logic shows that there is a good correlation. Once the fuzzy logic model has been validated, emissions can be predicted for any intermediate load conditions in the absence of the pollutant measurement devices, thus helping the manufacturers to meet the Euro norms for emission regulations.

Noninvasive method of epileptic detection using DWT and generalized regression neural network

Abstract: Epilepsy is a continual disorder, the characteristic of which is recurrent, motiveless seizures. Many people with epilepsy have more than one type of seizure and may have other symptoms of neurological problems as well. In this paper, a noninvasive method using discrete wavelet transform (DWT) and neural network is projected for automatic detection of epilepsy from EEG signals. DWT of the EEG signals is carried out using Haar Wavelets. Statistical features of approximate and detailed coefficients are extracted from the transformed signal. The entropy, as well as approximate entropy of the transformed signals, is determined. The features extracted from the transformed signal are used as the training set for the artificial neural network (ANN). Two types of ANNs viz. feedforward neural network (FFNN) and generalized regression neural network (GRNN) are trained. Three types of subjects viz. healthy, seizure-free period of an epileptic patient and epileptic patients are considered. The signals are classified accordingly as normal, seizure-free epileptic and abnormal. The results are compared on the basis of the confusion matrix, error histogram, and error plot. The quality measures used for comparison are sensitivity, specificity, precision, and accuracy. On all the evaluation parameters, GRNN is found to be best suited for anomaly detection in EEG signals.

Interfacing of MEMS motion sensor with FPGA using I2C protocol

Abstract: I2C abbreviation is Inter Integrated Circuit It is a serial bus protocol found by Philips Semiconductor I2C bus is popular because it is simple to use I2C protocol is used for communicating low speed devices to processors It is used to enable the faster device to communicate with slower devices without any data loss I2C bus controller interfaces the master and slave devices FPGA acts as a master and MEMS motion sensor (1TG MPU 6050) acts as a slave MEMS motion sensor data is passed to the FPGA using I2C protocol MEMS motion sensor has 16-bit ADCs for digitizing the accelerometer outputs I2C bus on FPGA gives more simplicity because it requires only two wires and less number of pin connections Hence in this paper we are going to design an I2C bus protocol using Verilog code which interfaces FPGA board with MEMS motion sensor Noisy data from the MEMS motion sensor is denoised by using haar wavelet coefficients