Abstract: Temperature prediction could be a temporal and statistic based mostly method. Weather prediction has drawn heap of analysis interest in recent years. The prediction of temperature has essential applications in numerous fields like climate watching, weather prediction, agriculture, energy, aviation, communication, pollution spread etc. The fuzzy aggregation has powerful logic expression ability and is in a position to precise inaccurate and unsure in sequence. during this paper, a Fuzzy data – Rule base technique is employed to predict the close part temperature for Indian coastal cities. The current study utilizes historical temperature likewise as info of varied meteorologic parameters to develop a prediction method in fuzzy rule domain to estimate temperature. Daily observations of Mean water level Pressure, ratio and Temperature for all three seasons area unit analyzed to predict the Temperature for a given values of Mean water level Pressure and ratio. Symbolic logic has principall

• Publication Date: 26-Sep-2016
• DOI: 10.15224/978-1-63248-104-7-14
• Views: 0
• Downloads: 0

Abstract: This study proposes feature extraction using wavelet transform (WT), sequential increment method, and phase space reconstruction (PSR) to classify normal sinus rhythm (NSR) and ventricular fibrillation (VF) from ECG episodes. We implemented four pre-processing steps to extract features from ECG episodes. In the first step, we use the WT for multi-scale representation and analysis, and then we extract wavelet coefficients from ECG episodes. In the second step, we use sequential increment method to extract peaks from the wavelet coefficients. In the third step, we make a three-dimensional phase space reconstruction (PSR) using the successive peaks. In the final step, we calculate the Euclidean distance between the peaks that are plotted in a three-dimensional phase space diagram and origin (0, 0), and then extract 20 features from the Euclidean distances by using statistical methods, including frequency distributions and their variabilities. We apply the 20 features as inputs to a neural

• Publication Date: 26-Sep-2016
• DOI: 10.15224/978-1-63248-104-7-15
• Views: 0
• Downloads: 0