Based on the fractional order of nonlinear system for love model with a periodic function as an external environment, we analyze the characteristics of the chaotic dynamic. We analyze the relationship between the chaotic dynamic of the fractional order love model with an external environment and the value of fractional order (α, β) when the parameters are fixed. Meanwhile, we also study the relationship between the chaotic dynamic of the fractional order love model with an external environment and the parameters (a, b, c, d) when the fractional order of the system is fixed. When the parameters of fractional order love model are fixed, the fractional order (α, β) of fractional order love model system exhibit segmented chaotic states with the different fractional orders of the system. When the fractional order (α = β) of the system is fixed, the system shows the periodic state and the chaotic state as the parameter is changing as a result.

Node-localization technology has been supported in the wireless sensor network (WSN) environment. Node localization is based on a few access-point (AP) nodes that comprises positioning information because they are fixed, and a beacon node that comprises unknown positioning information because it is moving. To determine the position of the unknown node, it must use two or three APs that comprise certain positioning information. There are a number of representative range-based methods, including time of arrival (TOA), weighted centroid locating algorithm, received signal strength intensity (RSSI), and time difference of arrival (TDOA) signal, that are received by the receiver. The RSSI method has its advantages. A simple device structure means that the RSSI method is easy to use. Because the structures of previous wireless local area network (LAN) technologies make them compatible with RSSI information, the RSSI method is widely used in the related area of position tracking. In addition, this algorithm has a hardware system that cannot be increased, has the advantage of the miniaturization of the node, and can wear through obstacles. This paper proposes the application of a robust ranging method that can be applied in robots and Internet of Things (IoT) using RSSI, especially in the tracing location of each nursing home patient, where the RSSI method with trilateral technique is used. This paper shows the results of the measured point from the application of the trilateral technique, and it also represents the results of the error distance between the ideal point and the measured point using computer simulation. Finally, this paper presents an estimation of localization using a real experimental device with a BLE (Bluetooth low-energy) transmitter and receiver, and beacon gateway, by applying an RSSI algorithm with the trilateral technique.

Youngchul Bae. IJFIS 2015;15:283-8. http://dx.doi.org/10.5391/IJFIS.2015.15.4.283

This paper describes a method for estimating the attitude of an underwater robot. The method employs a new concept of sine rotation vector and uses both an attitude heading and reference system (AHRS) and a Doppler velocity log (DVL) for the purpose of measurement. First, the acceleration and magnetic-field measurements are transformed into sine rotation vectors and combined. The combined sine rotation vector is then transformed into the differences between the Euler angles of the measured attitude and the predicted attitude; the differences are used to correct the predicted attitude. The method was evaluated according to field-test data and simulation data and compared to existing methods that calculate angular differences directly without a preceding sine rotation vector transformation. The comparison verifies that the proposed method improves the attitude estimation performance.

Deep learning algorithms developed in recent decades have performed well in prediction and classification using accumulated big data. However, as climate change has recently become a more serious global problem, natural disasters are occurring frequently. When analyzing natural disasters from the perspective of a data analyst, they are considered as outliers, and the ability to predict outliers (natural disasters) using deep learning algorithms based on big data acquired by computers is limited. To predict natural disasters, deep learning algorithms must be enhanced to be able to predict outliers based on information such as the correlation between the input and output. Thus, algorithms that specialize in one field must be developed, and specialized algorithms for abnormal values must be developed to predict natural disasters. Therefore, considering the correlation between the input and output, we propose a positive and negative perceptron (PNP) algorithm to predict the flow rate of rivers using climate change-sensitive precipitation. The PNP algorithm consists of a hidden deep learning layer composed of positive and negative neurons. We built deep learning models using the PNP algorithm to predict the flow of three rivers. We also built comparative deep learning models using long short-term memory (LSTM) to validate the performance of the PNP algorithm. We compared the predictive performance of each model using the root mean square error and symmetric mean absolute percentage error and demonstrated that it performed better than the LSTM algorithms .