scholarly journals Magnetic Angular Rate and Gravity Sensor Based Supervised Learning for Positioning Tasks

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5364 ◽  
Author(s):  
Balázs Nagy ◽  
János Botzheim ◽  
Péter Korondi
Keyword(s):  
Noise Reduction ◽  
Supervised Learning ◽  
Sensor Fusion ◽  
Angular Rate ◽  
Translational Motion ◽  
Main Challenge ◽  
Different Types ◽  
Gravity Sensor ◽  
Position Data ◽  
Signal Processing Methods

This paper deals with sensor fusion of magnetic, angular rate and gravity sensor (MARG). The main contribution of this paper is the sensor fusion performed by supervised learning, which means parallel processing of the different kinds of measured data and estimating the position in periodic and non-periodic cases. During the learning phase, the position estimated by sensor fusion is compared with position data of a motion capture system. The main challenge is avoiding the error caused by the implicit integral calculation of MARG. There are several filter based signal processing methods for disturbance and noise estimation, which are calculated for each sensor separately. These classical methods can be used for disturbance and noise reduction and extracting hidden information from it as well. This paper examines the different types of noises and proposes a machine learning-based method for calculation of position and orientation directly from nine separate sensors. This method includes the disturbance and noise reduction in addition to sensor fusion. The proposed method was validated by experiments which provided promising results on periodic and translational motion as well.

Classification and Identification of Young Females’ Shoulder Shape Using the Fisher Discriminant Analysis Based on 3D Body Measurement

2011 ◽  
Vol 121-126 ◽  
pp. 4421-4425
Author(s):  
Feng Yuan Zou ◽  
Juan Feng Jin ◽  
Jie Sun ◽  
Ming Li
Keyword(s):  
Discriminant Analysis ◽  
Body Measurement ◽  
Excellent Performance ◽  
Fisher Discriminant Analysis ◽  
Young Females ◽  
Fisher Discriminant ◽  
Different Types ◽  
Position Data ◽  
High Prediction ◽  
Body Scanner

In order to improve the fitting of garment on shoulder, the measurement of 275 young females aged from 20-24 were taken with 3D-body scanner; the position data relating to the shoulder was conducted using cluster analysis, and extracted 5 characteristic indices that contained almost information of shoulder shape; the rationality of clustering shoulder shape to 4 different types was tested and verified through using one-way analysis of variance; then established the Fisher Discriminant Analysis (FDA) model to identify the young females’ shoulder shape. The result showed that the forecasting model of Fisher Discriminant Analysis (FDA) had excellent performance, high prediction accuracy, so it provided a new method to identify young females’ shoulder shape.

scholarly journals EFFECTIVE APPLICATION AND PROSPECTS OF IMPROVEMENT OF ANTI-TANK ROCKET COMPLEX MANAGEMENT SYSTEMS

2020 ◽  
pp. 56-63
Author(s):  
S. Moskalets ◽  
V. Zhyrnyi ◽  
O. Mokrinskyi ◽  
A. Rudyk
Keyword(s):  
Large Scale ◽  
Second Generation ◽  
Armed Forces ◽  
Weak Links ◽  
Automatic Guidance ◽  
Different Types ◽  
Signal Processing Methods ◽  
Weapons Control ◽  
Good Visibility ◽  
The Coordinator

Tanks are one of the main means of implementing aggressive plans to capture land territory. To combat tanks and other armored vehicles the projectiles with different types of warheads and anti-tank guided missiles are used. The best means of defeating tanks are anti-tank missile systems (ATMS), which are classified by aiming methods. The purpose of this work is to review the prospects for development and use of existing ATMS by analyzing the trends of new national and foreign weapons control systems. Anti-tank missile systems of most advanced world‟s armed forces are, predominantly, second-generation systems with a semi-automatic infrared or laser beam guided systems. Missiles of these systems have a high probability of hitting the target (and penetration of armor) when firing under good visibility conditions. The retrofit of the second- generation systems is being done by increasing the protection against jamming caused to aiming systems due to creating combined infrared and thermal coordinators, improving signal processing methods, and increasing the flight speed of missiles and the reliability of command transmission. The tank engine is a powerful contrasting source of thermal energy. The main weak links of systems with semi-automatic guidance systems in terms of jamming counteraction are the operator who tracks the target along the missile's flight, and the coordinator of the missile's command aiming that can be “blinded”. Large-scale works on the creation of next generation anti-tank missile systems based on the latest scientific and technological achievements have been considered. The system‟s operator is one of the weakest links. Careful attitude to the life of every Ukrainian warrior should be a priority, as it is in the modern militaries of the world. This attitude can be ensured by using a reliable missile weapons both natioanl and foreign that would be capable of hitting enemy tanks from a safe distance with a remote control using “fire-and- forget”principle.

Research on vehicle attitude and heading reference system based on multi-sensor information fusion

2020 ◽  
Vol 234 (13) ◽  
pp. 3056-3067
Author(s):  
Jiacheng Fan ◽  
Zengcai Wang ◽  
Mingxing Lin ◽  
Susu Fang ◽  
Xiangpeng Liu ◽  
...  
Keyword(s):  
Magnetic Field ◽  
Low Cost ◽  
Angular Rate ◽  
Estimation Method ◽  
Linear Acceleration ◽  
Operating Conditions ◽  
Frequency Noise ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Gravity Sensor

To improve the accuracy of attitude and heading reference systems for moving vehicles, an effective orientation estimation method is proposed. The method uses an odometer, a low-cost magnetic, angular rate, and gravity sensor. This study addresses the problems of non-orthogonal error, carrier magnetic field interference and calibration to obtain accurate, long-term, stable magnetic field strength. A neural network fusion 12-parameter ellipse fitting method is proposed to eliminate the soft magnetic field and hard magnetic field interference. The interference to the accelerometer from linear acceleration is eliminated by using an odometer and a gyroscope, and the high-frequency noise from the accelerometer is eliminated by using a low-pass filter. An improved method to evaluate vehicle attitude is proposed and utilized to compensate for filtered accelerometer measurement when the vehicle is moving at a uniform, accelerate and steering state. The proposed method uses an effective adaptive Kalman filter based on the error state model to reduce dynamic perturbations. Filter gain is adaptively tuned under different moving modes by adjusting the noise matrix. The effectiveness of the algorithm is verified by experiments and simulations in multiple operating conditions.

scholarly journals Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1081
Author(s):  
Spyros Theocharides ◽  
Marios Theristis ◽  
George Makrides ◽  
Marios Kynigos ◽  
Chrysovalantis Spanias ◽  
...  
Keyword(s):  
Machine Learning ◽  
Supervised Learning ◽  
Regression Tree ◽  
Training Data ◽  
Support Vector ◽  
Learning Models ◽  
Bayesian Neural Network ◽  
Production Forecasting ◽  
Main Challenge ◽  
Machine Learning Models

A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%.

scholarly journals Clinical and Epidemiological Aspects Related to Infection of Orthopedic Prostheses in Argentinean Children. A 10-Year Period Study

2017 ◽  
Vol 4 (suppl_1) ◽  
pp. S100-S100
Author(s):  
Carlos Mauricio Vergara Lobo ◽  
Fausto M Ferolla ◽  
Elen Contreras ◽  
Carolina Carballo ◽  
Walter Yfran ◽  
...  
Keyword(s):  
Pediatric Patients ◽  
High Morbidity ◽  
Pediatric Hospital ◽  
C Reactive Protein ◽  
Blood Cell Count ◽  
Bacterial Isolation ◽  
Reactive Protein ◽  
Main Challenge ◽  
Different Types ◽  
Total Treatment

Abstract Background Management of orthopedic prostheses infections (PI) in children is a main challenge, not only for the complexity of the disease but also for the scarce of evidence in this field. Objectives To describe the burden of PI and to analyze clinical and epidemiological aspects in pediatric patients. Methods Retrospective study in a tertiary pediatric hospital. Clinical charts of patients <18 years who underwent surgery for bone and/or joint implantation at “R. Gutierrez” Children’s Hospital in Buenos Aires from January 2007 to December 2016 were reviewed, and all PI cases were analyzed. PI was defined as early (E) when presentation was within 3 months of prothesis implantation, delayed (D) when presenting between 3–24 months and late (L) if presenting beyond 2 years. Results 811 surgeries performed; 89 PI detected: E(n = 63); D(n = 9), L(n = 17); 58% male; median(m) age: 13 years (range[r] 4–20); m hospital stay 30 days (r 6–180). Annual incidence: 11% (CI95%: 8.9–13.1) (Figure 1). Underlying conditions: scoliosis (58.4%), malignancy (16.8%). Clinical features are detailed in Figure 2. Bacterial isolation in 63 (70.8%) cases, 51(57.3%) with a single microorganism (Figure 3). Gram(+) bacteria were isolated in 58% of E PI, 86% of D PI and 49% of L PI. Gram(−) pathogens in 49% of E PI and in 38% of L PI. Three febrile PI (3,4%) had Gram(+) bacteremia, two of them L PI. No differences were seen in white blood cell count (WBC) and C-reactive protein(CRP) levels on admission in children with and without bacteremia, nor among the different types of PI; m WBC 9000/mm3 (r 3200–25550), m CRP 37 mg/l (r 1–270). WBC on admission in MRSA PI was significantly higher, P < 0,01. Duration of EV treatment was different according to type of microorganism (P 0.03), higher in PI by Gram(−). Forty-eight (53.9%) cases continued with trimethoprim-sulfamoxazole orally, without side effects requiring its discontinuation. Total treatment duration (m): 189 days (r 28–756). Eighty-two children (92.1%) underwent surgical toilette, 37 (45.1%) required more than one. Six (6.7%) presented relapse and eight (9%) reinfection. Conclusion · PI in children is a considerable burden, with high morbidity. · Incidence of bacteremia was low. · Results of the study could help to delineate preventive strategies and improve decision making in PI in children. Disclosures All authors No reported disclosures.

Test and Analysis of Bush Roller Chains for Noise Reduction

2011 ◽  
Vol 52-54 ◽  
pp. 430-435
Author(s):  
Xiao Lun Liu ◽  
Wei Sun ◽  
Song Ding ◽  
Jian Fang Liu ◽  
Yu Ying Wang ◽  
...  
Keyword(s):  
Noise Reduction ◽  
Impact Energy ◽  
Noise Level ◽  
Low Noise ◽  
Working Environment ◽  
The Other ◽  
Chain Drive ◽  
Noise Characteristics ◽  
Testing Data ◽  
Different Types

A low noise duplex bush chains with split rollers was developed through changing roller structure to reduce noise of bush roller chains. The split rollers could absorb more impact energy, mitigate meshing impact and reduce chain drive noise. The noise generated by different types of duplex bush roller chains was carried out to test in same speed, low noise characteristics of duplex sleeve chains with split rollers was verified. By analysis of testing data, noise level of duplex sleeve chains with split rollers compared with that of the other duplex bush roller chains was reduced by the average 3 ~ 8dB, and low 10 ~ 13dB than that of 16A simplex sleeve roller chains. The chains made chain drive significantly improve in the working environment, with steady transmission, strong bearing, low noise, and a significant noise reduction was achieved.

scholarly journals Supervised learning in the presence of concept drift: a modelling framework

2021 ◽  
Author(s):  
M. Straat ◽  
F. Abadi ◽  
Z. Kan ◽  
C. Göpfert ◽  
B. Hammer ◽  
...  
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Statistical Physics ◽  
Concept Drift ◽  
Activation Function ◽  
High Dimensional ◽  
Weight Decay ◽  
Modelling Framework ◽  
Different Types ◽  
Gradient Based

AbstractWe present a modelling framework for the investigation of supervised learning in non-stationary environments. Specifically, we model two example types of learning systems: prototype-based learning vector quantization (LVQ) for classification and shallow, layered neural networks for regression tasks. We investigate so-called student–teacher scenarios in which the systems are trained from a stream of high-dimensional, labeled data. Properties of the target task are considered to be non-stationary due to drift processes while the training is performed. Different types of concept drift are studied, which affect the density of example inputs only, the target rule itself, or both. By applying methods from statistical physics, we develop a modelling framework for the mathematical analysis of the training dynamics in non-stationary environments. Our results show that standard LVQ algorithms are already suitable for the training in non-stationary environments to a certain extent. However, the application of weight decay as an explicit mechanism of forgetting does not improve the performance under the considered drift processes. Furthermore, we investigate gradient-based training of layered neural networks with sigmoidal activation functions and compare with the use of rectified linear units. Our findings show that the sensitivity to concept drift and the effectiveness of weight decay differs significantly between the two types of activation function.

scholarly journals Empirical Investigation of Noise Reduction Filter for a Flow-based Spirometer Accuracy Improvement

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Noise Reduction ◽  
Respiratory Function ◽  
Empirical Investigation ◽  
Respiratory Function Tests ◽  
Inspiratory Flow Rate ◽  
Use Of Data ◽  
Air Volume ◽  
Function Tests ◽  
Different Types ◽  
Data Error

A turbine spirometer with an IR rotary encoder is designed and fabricated for performing Respiratory Function Tests (RFT). The system includes a hardware for gathering breath inspiratory flow rate and a user software which represents analyzed data of patients' breath flow and volume parameters in real-time. A major challenge in design of flow-based spirometers is the accuracy of device in measuring volume parameters of RFTs which is due to large effects of sensing data error and noise. The purpose of the paper is evaluating the efficiency of three different types of digital noise reduction filters in term of improving the accuracy of system in calculation of air volume passing through the spirometer turbine by use of data obtained by the innovative flow sensor. Three distinct kinds of flow waves are experimented and the most sufficient filter for corresponding respiratory function tests are reported.

Sign in / Sign up

Export Citation Format

Share Document