scholarly journals Firefly, Teaching Learning Based Optimization and Kalman Filter Methods for GPS Receiver Position Estimation

2018 ◽  
Vol 143 ◽  
pp. 892-898 ◽  
Author(s):  
Lavanya Bagadi ◽  
G Sasibhushana Rao ◽  
N Ashok Kumar
Keyword(s):  
Kalman Filter ◽  
Position Estimation ◽  
Gps Receiver ◽  
Filter Methods ◽  
Teaching Learning Based Optimization ◽  
Teaching Learning

scholarly journals GPS Receiver Position Augmentation Using Correntropy Kalman Filter in Low Latitude Terrain

2022 ◽  
Author(s):  
Sirish Kumar Pagoti ◽  
Bala Sai Srilatha Indira Dutt Vemuri ◽  
Ganesh Laveti
Keyword(s):  
Kalman Filter ◽  
Indian Subcontinent ◽  
Estimation Algorithm ◽  
Position Estimation ◽  
Gps Receiver ◽  
Dual Frequency ◽  
Low Latitude ◽  
Position Accuracy ◽  
Aircraft Landing ◽  
Gps Accuracy

If any Global Positioning System (GPS) receiver is operated in low latitude regions or urban canyons, the visibility further reduces. These system constraints lead to many challenges in providing precise GPS position accuracy over the Indian subcontinent. As a result, the standalone GPS accuracy does not meet the aircraft landing requirements, such as Category I (CAT-I) Precision Approaches. However, the required accuracy can be achieved by augmenting the GPS. Among all these issues, the predominant factors that significantly influence the receiver position accuracy are selecting a user/receiver position estimation algorithm. In this article, a novel method is proposed based on correntropy and designated as Correntropy Kalman Filter (CKF) for precise GPS applications and GPS Aided Geosynchronous equatorial orbit Augmented Navigation (GAGAN) based aircraft landings over the low latitude Indian subcontinent. The real-world GPS data collected from a dual-frequency GPS receiver located in the southern region of the Indian subcontinent (IISc), Bangalore with Lat/Long: 13.021°N/ 77.5°E) is used for the performance evaluation of the proposed algorithm. Results prove that the proposed CKF algorithm exhibits significant improvement (up to 34%) in position estimation compared to the traditional Kalman Filter.

scholarly journals Kalman Filter Realization for Orientation and Position Estimation on Dedicated Processor

2014 ◽  
Vol 8 (2) ◽  
pp. 88-94 ◽  
Author(s):  
Sławomir Romaniuk ◽  
Zdzisław Gosiewski
Keyword(s):  
Kalman Filter ◽  
Inertial Measurement Unit ◽  
Filter Design ◽  
Position Estimation ◽  
Sensor Data ◽  
Measurement Unit ◽  
Gps Receiver ◽  
Measurement Devices ◽  
Proper Estimation ◽  
Gps Accuracy

Abstract This paper presents Kalman filter design which has been programmed and evaluated in dedicated STM32 platform. The main aim of the work performed was to achieve proper estimation of attitude and position signals which could be further used in unmanned aeri-al vehicle autopilots. Inertial measurement unit and GPS receiver have been used as measurement devices in order to achieve needed raw sensor data. Results of Kalman filter estimation were recorded for signals measurements and compared with raw data. Position actualization frequency was increased from 1 Hz which is characteristic to GPS receivers, to values close to 50 Hz. Furthermore it is shown how Kalman filter deals with GPS accuracy decreases and magnetometer measurement noise.

TLBO-FLN: Teaching-Learning Based Optimization of Functional Link Neural Networks for Stock Closing Price Prediction

2020 ◽  
Vol 10 (4) ◽  
pp. 522-532 ◽  
Author(s):  
Sarat Chandra Nayak ◽  
Subhranginee Das ◽  
Mohammad Dilsad Ansari
Keyword(s):  
Neural Networks ◽  
Computational Cost ◽  
Optimization Techniques ◽  
Fine Tuning ◽  
Functional Link ◽  
Price Prediction ◽  
Closing Price ◽  
Teaching Learning Based Optimization ◽  
Artificial Neural ◽  
Teaching Learning

Background and Objective: Stock closing price prediction is enormously complicated. Artificial Neural Networks (ANN) are excellent approximation algorithms applied to this area. Several nature-inspired evolutionary optimization techniques are proposed and used in the literature to search the optimum parameters of ANN based forecasting models. However, most of them need fine-tuning of several control parameters as well as algorithm specific parameters to achieve optimal performance. Improper tuning of such parameters either leads toward additional computational cost or local optima. Methods: Teaching Learning Based Optimization (TLBO) is a newly proposed algorithm which does not necessitate any parameters specific to it. The intrinsic capability of Functional Link Artificial Neural Network (FLANN) to recognize the multifaceted nonlinear relationship present in the historical stock data made it popular and got wide applications in the stock market prediction. This article presents a hybrid model termed as Teaching Learning Based Optimization of Functional Neural Networks (TLBO-FLN) by combining the advantages of both TLBO and FLANN. Results and Conclusion: The model is evaluated by predicting the short, medium, and long-term closing prices of four emerging stock markets. The performance of the TLBO-FLN model is measured through Mean Absolute Percentage of Error (MAPE), Average Relative Variance (ARV), and coefficient of determination (R2); compared with that of few other state-of-the-art models similarly trained and found superior.

Sign in / Sign up

Export Citation Format

Share Document