AEEE. 2022, vol. 20

Permanent URI for this collectionhttp://hdl.handle.net/10084/145995

Browse

Now showing 1 - 20 out of 48 results

Enhancing PDC Functional Connectivity Analysis for Subjects with Dyslexia Using Artifact Cancellation Techniques
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Al-Naimi, Taha Mahmoud; Naidu, Shanthini Chandra Sekara; Sha'ameri, Ahmad Zuri; Safri, Norlaili Mat; Samah, Narina Abu
The neurobiological origin of dyslexia allows the study of this disorder by examining functional con- nectivity between regions of the brain. During rest-state or at task completion, Electroencephalograms (EEG) are used to observe brain signals. By using Partial Directed Coherence (PDC) analysis, the correct anal- ysis of functional connectivity was assessed. In spite of that, the estimation of functional connectivity can be inaccurate due to the presence of artifacts. Several methods have been employed by researchers to remove artifacts, including Moving Average Filters (MAF), Wiener Filters (WF), Wavelet Transforms (WT), and hybrid filters. Despite this, no research has been con- ducted on the effects of artifact removal methods on functional connectivity. Consequently, Artifact Can- cellation (AC) algorithms are developed to reduce the effects of eye blinks, eye movements, and muscle move- ments on functional connectivity estimation. In this work, the denoising filters discussed earlier are utilized as part of the AC algorithm. Additionally, a compar- ison was conducted to determine the effectiveness of the filters. According to the results, AC-MAF removed all artifacts with the least computational complexity after improving the MAF. In order to test its efficacy in real-world conditions, it was applied to the real signals recorded while children with dyslexia were participat- ing in rapid automatized naming activities. Utilizing the PDC approach, the developed algorithm accurately assessed functional connectivity.
Reliability-Security in Wireless-Powered Cooperative Network with Friendly Jammer
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Phan, Van Duc; Nguyen, Thanh Luan; Phu, Tran Tin; Nguyen, Van Vinh
n this paper, we study the Outage Probabil- ity (OP) and the Intercept Probability (IP) of Wireless- Powered Cooperative Networks (WPCNs) in the pres- ence of a malicious eavesdropper and a friendly jam- mer. We specifically present the system model and the power splitting Energy Harvesting (EH) architec- ture to increase system reliability and security. In ad- dition, we obtain exact analytical equations for the OP and IP. Asymptotic analysis in the low Signal-to-Jam Ratio (SJR) regimes expressed in integral-form expres- sions are provided to observe the lower bound of the IP. Finally, all derivations are validated by simulation results using the Monte Carlo method.
Mitigating the Signaling Resources Expended in 5G Location Management Procedures at Millimeter-Wave Frequencies
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Adikpe, Agburu Ogah; Tekanyi, Abdoulie Momodou Sunkary; Yaro, Abdulmalik Shehu
The signaling resources expended and the power consumed by User Equipments (UEs) in the Location Management (LM) procedures are expected to be higher in Fifth Generation (5G) than in legacy wireless communications networks. To mitigate this challenge, this work proposes a hybrid scheme that mitigates the signaling resources expended in paging and RAN-based Notification Area Update (RNAU) procedures in 5G. The approach utilizes a hybrid scheme that embeds a UE Identifier (UEID) partitioning scheme that directional pages UEs into a gNB-based UE Mobility Tracking (UEMT) scheme. The approach configures a gNB in an RRC_Inactive state to beam sweep a UEs last registered cell area before directionally paging the UE. The approach proposed in this work is implemented on a modified network architecture to reduce the signaling resources expended on both paging and RNAU of UEs at higher frequencies which is an enabling factor for mmWave systems. Simulation results of the total accumu- lated cost of paging showed a 65.13 % and 8.69 % reduction in signaling resources expended against the conventional approach and the existing gNB-based UEMT approach, respectively. Additionally, the total accumulated resources expended in both procedures over 24 hours showed that the modified gNB-based UEMT scheme outperformed the conventional scheme and the gNB-based UEMT scheme by 90.96 % and 38.36 %, respectively.
IoT Supervised PV-HVDC Combined Wide Area Power Network Security Scheme Using Wavelet-Neuro Analysis
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Garika, Gantaiah Swamy; Kottala, Padma
Power system networks are one of the most widely used methods in the real world for trans- ferring large amounts of electrical energy from one location to another. At present, High Voltage Direct Current Transmission is preferred for long distances over hundreds of miles due to minimal power loss and transmission cost of transmission.Due to an increase in power demand, integration of renewable sources to minimise the voltage uctuations and compensate for power loss is necessary. This is a mandatory re- quirement to produce sophisticated protection methods for mainly smart systems under various balanced and unbalanced fault conditions. The system protection scheme must respond as quickly as possible to protect the connected devices in a smart environment. The network must be monitored and protected under var- ious weather conditions as well as electrical paramet- ric problems. The proposed research work is carried on the basis of physical monitoring with the aid of the Internet-of-Things and electrical parameters cali- brated with the help of wavelet analysis. A wavelet is a mathematical tool to investigate the behaviour of transient signals at di erent frequencies, which pro- vides important information related to the detailed analysis of faults in power networks. The ma- jor goals of this research are to analyse faults us- ing detailed coe cients of current signals through the bior-1.5 mother wavelet for fault identi cation and arti cial neural network analysis for fault localiza- tion. This proposed approach furnishes an IoT su- pervised Photovoltaic - High Voltage Direct Current (HVDC) combined wide area power network secu- rity scheme using wavelet detailed coe cients under various types of faults with Fault-Inception-Angles.
Data-Driven Hyperparameter Optimized Extreme Gradient Boosting Machine Learning Model for Solar Radiation Forecasting
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Namrata, Kumari; Kumar, Mantosh; Kumar, Nishant
The uncertainty of the non-conventional sources especially solar energy caused due to spatio- temporal factors like temperature, pressure, relative humidity etc. is continuously disrupting the productivity and reliability of an integrated power system which motivates the researcher or energy industry for strategic forecasting solutions to enhance the proper scheduling and control of solar generation power plants. Several studies have been carried out; but still the objective of achieving accurate forecasting dependent on the spatio- temporal features is not achieved. To address this critical forecasting issue in this research article a hyper parametric tuning of the Extreme Gradient Boosting (XGB) machine learning model has been carried out using two met heuristic algorithms: Moth Flame Optimiza- tion (MFO) and Grey Wolf Optimization (GWO). The dataset comprises five years of metrological at- tributes collected from the National Renewable Energy Laboratory (NREL) for analysis. The validation of the proposed model has been done based on the five statistical errors: Max Error (ME), Mean Absolute Error (MAE), Coefficient of Determination (R2), Mean Square Error (MSE) and Root Mean Square Error (RMSE). The regressive assessment of all three models has confirmed that the XGB-MFO model out- performed the others as showing the highest R2 score of 0.9337, 0.9011, 0.8744 and lowest RMSE values of 76.29 W·m−2, 41.90W·m−2 and 95.94W·m−2 for Global Horizontal Irradiance (GHI), Diffuse Horizon- tal Irradiance (DHI) and Direct Normal Irradiance (DNI) respectively which ensures the proposed model implementation for the prediction and production of solar power.
Application of Equilibrium Optimizer Algorithm for Solving Linear and non Linear Coordination of Directional Overcurrent Relays
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Guerraiche, Khaled; Midouni, Feriel; Sahraoui, Nour Elhouda; Dekhici, Latifa
The safety and reliability of an electrical network depend on the performance of the protections utilized. Therefore, the optimal coordination of the pro- tective devices plays an essential role. In this paper, a new algorithm, Equilibrium Optimizer (EO), which is based on the physical equation of the mass balance, is implemented in the problem of the Optimal Coor- dination of Directional Overcurrent Relays (DOCRs). Moreover, the proposed method uses Linear Program- ming (LP), Nonlinear Programming (NLP) and Mixed- Integer Nonlinear Programming (MINLP) in order to optimize the Time Dial Setting (TDS), as well as the Plug Setting (PS), satisfying all possible constraints. Additionally, the performance of EO is evaluated using several benchmarks with different topologies. The results demonstrated the applicability and efficacy of the proposed approach. A comparison with other stud- ies reported in specialized literature is provided to demonstrate the benefits of the proposed approach.
Optimal Battery Energy Storage System Management with Wind Turbine Generator in Unbalanced Low Power Distribution System
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Patnaik, Samarjit; Nayak, Manas Ranjan; Viswavandya, Meera
Wind Turbine Generators (WTG) are being integrated into distribution systems on a large scale worldwide as part of a global effort to capture green energy. Wind turbine generator inter- mittency may be mitigated by Battery Energy Storage Systems (BESS), which have emerged as a viable option in recent years. To find the best position and capacity for wind power generation and BESS charging/discharging dispatches, a Red Fox Optimi- sation (RFO) algorithm is used while optimising the imbalanced distribution network’s performance under technological restrictions. The charging or discharging criteria for this method is the average feeder load. The charging techniques for BESS using WTG and Sustainable Average Load (SAL) are evaluated in terms of the free-running mode of dispatch cycle. The suggested approach is tested on an IEEE-37 bus Unbalanced Radial Distribution Network (UDN). It has been shown that the suggested method enhances several performance objectives of the distribution system.
Mitigation of Power Losses and Enhancement in Voltage Profile by Optimal Placement of Capacitor Banks With Particle Swarm Optimization in Radial Distribution Networks
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Shaikh, Muhammad Fawad; Shaikh, Abdul Majeed; Shaikh, Shoaib Ahmed; Nadeem, Raheel; Shaikh, Abdul Moiz; Khokhar, Arif Ali
The prime purpose of placing a capaci- tor bank in a power system is to provide reactive power, reduce power losses, and enhances voltage profile. The main challenge is to determine the optimum capacitor position and size that reduces both system power losses and the overall cost of the sys- tem with rigid constraints. For this purpose, different optimization techniques are used, for example Particle Swarm Optimization (PSO) which converges the com- plex non-linear problem in a systematic and method- ological way to find the best optimal solution. In this paper, the standard IEEE 33-bus and 69-bus systems are used to find the optimum location and size of the capacitors bank. These power networks are simu- lated in Siemens PSS®E software. For the optimum solution of capacitor banks, the PSO algorithm is used. The PSO fitness function is modelled in such a way which contains the high average bus voltage, the small size of capacitor banks, and low power losses. The fitness function used is a weighted type to reduce the computation time and multi-objective function complexity.
Meta Heuristic Algorithm Based Multi Objective Optimal Planning of Rapid Charging Stations and Distribution Generators in a Distribution System Coupled with Transportation Network
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Vijay, Vutla; Venkaiah, Chintham; Mallesham, Vinod Kumar Dulla
The application of Electric Vehicles (EVs) is increasing in many countries, causing many researchers to focus on EV Rapid Charging Station (RCS) related issues. The optimal planning of RCS considering only distribution networks is not a reli- able approach. Moreover, the RCS location should be convenient to the EV user in a given EV driv- ing range and the performance of the distribution sys- tem. In this paper, a multi-objective approach for optimal planning of RCS and Distributed Generators (DG) in a distributed system coupled with a trans- portation network is analyzed. The proposed opti- mal planning method aims to achieve reduced active power loss, EV user costs, and voltage deviation for effective RCS and DG planning. The approach in- cludes the analysis of the test system with the base case, solo planning of RCS, planning of DGs with fixed RCS, and simultaneous optimal planning of RCS and DGs. Daily load variation at buses and hourly charging probability of EVs have been used in the analysis. IEEE 33 bus distribution system superimposed with a 25-node transportation network is considered the test system. Rao 3 algorithm is applied for optimization, and the results have been compared with PSO and JAYA algorithms.
Improved PSO with Disturbance Term for Solving ORPD Problem in Power Systems
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Mezaache, Mohamed; Benaouda, Omar Fethi; Sekhane, Hocine; Chaouch, Saad; Babes, Badreddine
The essential purpose of an energy sys- tem is to provide electricity to its loads effectively and economically, as well as safely and reliably. Therefore, the solutions to the problems of Optimal Power Flow (OPF) and Optimal Reactive Power Dispatch (ORPD) to enable the efficient employment of various energy distributions should be found. Our work focuses on the ORPD issue; it can be formulated as a non-linear con- straint and with single or multiple objectives optimiza- tion problems. Minimizing total losses is one of the main objective functions to solve the ORPD problem. This paper presents the use of an improved particle swarm optimization -with a disturbance term- (called PSO-DT) algorithm, to find the solution of ORPD in the standard IEEE 30-bus power system for reduc- ing electrical power transmission losses. The obtained results demonstrate that the proposed method is more efficient and has a more extraordinary ability to get better solutions compared to the basic PSO method.
Zero Crossing Point Detection in a Distorted Sinusoidal Signal Using Decision Tree Classifier
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Veeramsetty, Venkataramana; Jadhav, Pravallika; Ramesh, Eslavath; Srinivasula, Srividya; Salkuti, Surender Reddy
Zero-crossing point detection in a sinusoidal signal is essential in the case of various power systems and power electronics applications like power system protection and power converters controller design. In this paper, 96 data sets are created from a distorted sinusoidal signal based on MATLAB simulation. Dis- torted sinusoidal signals are generated in MATLAB with various noise and harmonic levels. In this pa- per, a decision tree classi er is used to predict the zero crossing point in a distorted signal based on input fea- tures like slope, intercept, correlation and Root Mean Square Error (RMSE). Decision tree classi er model is trained and tested in the Google Colab environment. As per simulation results, it is observed that decision tree classi er is able to predict the zero-crossing points in a distorted signal with maximum accuracy of 98.3 % for noise signals and 100 % for harmonic distorted signals.
A Platform Independent Web-Application for Short-Term Electric Power Load Forecasting on a 33/11 kV Substation Using Regression Model
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Veeramsett, Venkataramana; Vaishnavi, Gudelli Sushma; Kumar, Modem Sai Pavani; Kiran, Prabhu; Sumanth, Sumanth; Prasanna, Potharaboina; Salkuti, Surender Reddy
Short-term electric power load forecasting is a critical and essential task for utilities of the elec- tric power industry for proper energy trading and that enable the independent system operator to operate the network without any technical and economical is- sues. In this paper, machine learning model such as linear regression model is used to forecast the active power load one hour and one day ahead. Real time active power load data to train and test the machine learning model is collected from a 33/11 kV substation located in Telangana State, India. Based on the simu- lation results, it is observed that linear regression model can forecast the load with less mean absolute error i.e. 0.042 with training data and 0.045 with testing data in comparison with support vector regressor model for an hour ahead operation. Whereas in the case of the day ahead operation, linear regression model can forecast the load with less mean absolute error i.e. 0.055 with training data and 0.057 with testing data in comparison with support vector regressor model. A platform independent web application is developed to help the operators of the 33/11 kV substation which is located in Godishala, Telangana State, India.
Power Loss Minimization by Optimal Placement of Distributed Generation Considering the Distribution Network Configuration Based on Artificial Ecosystem Optimization
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Nguyen, Thuan Thanh; Nguyen, Thang Trung
Power loss in the Distribution System (DS) is often higher than that of other parts of the power system because of its low voltage level. Therefore, reducing losses is always an important task in de- sign and operation of the DS. This paper aims to apply a new approach based on Artificial Ecosystem Optimization (AEO) for the Distributed Generation Placement (DGP) and combination of DGP and net- work REConfiguration (DGP-REC) problems to reduce power loss of the DS to satisfy the technical constraints including power balance, radial topology, voltage and current bounds, and DG capacity limit. The AEO is a recent algorithm that has no special control parame- ters, inspired from the behaviours of living organisms in the ecosystem including production, consumption, and decomposition. The efficiency of the AEO is eval- uated on two test systems including the 33-node and 119-node systems. The numerical results validated on the 33-node and 119-node systems show that DGP-REC is a more effective solution for reducing power loss com- pared to the DGP solution. In addition, evaluation re- sults on small and large systems also indicate that AEO is an effective approach for the DGP and DGP-REC problems.
Evaluation of Wavelet Transform Based Feature Extraction Techniques for Detection and Classification of Faults on Transmission Lines Using WAMS Data
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Harish, Ani; Asok, Prince; Vasudevan, Jayan Madasser
The smart grid is an intelligent power system network that should be reliable and resilient for sustainable operation. Wide-Area Measurement Sys- tems (WAMS) are deployed in the power grid to provide real-time situational awareness to the power grid oper- ators. An excellent strategy for exploiting the WAMS data effectively is to extract relevant insights from the increasing volume of data collected. Feature extrac- tion techniques are pivotal in developing data-driven models for power systems. This paper proposes an ensemble feature extraction method for developing intelligent data-driven models for transmission line fault detection and classification. A comparative ef- ficacy analysis of the proposed ensemble feature extrac- tion method is carried out with state-of-the-art feature extraction methods. The models developed and eval- uated with the feature data derived with the proposed method give an accuracy of 100 % for fault detection and 99.78 % for fault classification. This method also has the advantage of significantly reducing training and testing time. Features are extracted from the WAMS data collected by simulating an IEEE 39 bus test system in the PowerWorld simulator.
WAMS-based Hierarchical Active Power Differential Signal Algorithm for Backup Protection of a FACTS Compensated Transmission Network
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Venugopal, Sreelekha; Asok, Prince; Raj Arya, Sabha
This paper proposes a hierarchical active power differential signal-based generalized backup protection algorithm using Wide Area Mea- surement System (WAMS) data for Flexible AC Transmission System (FACTS)-compensated trans- mission networks. The proposed algorithm can be used for backup protection of transmission systems with any shunt and series-type FACTS devices. The increased number of FACT compensators affects the reliable operation of primary and backup protection of the transmission lines. Both shunt and series com- pensated lines cause malfunctioning of existing backup protection schemes. The proposed algorithm utilizes the sequence components of bus voltages and active power differential signals of lines to identify the faulty line. The algorithm is validated on a modified 9-bus system under MATLAB/SIMULINK platform. It is observed that the algorithm is suitable for identifying a faulty line in transmission systems containing both uncompensated and compensated lines with series or shunt-type FACTS controllers. This algorithm has the advantage that it uses a generalized backup protection logic and can be used for the accurate identification of a faulty line irrespective of the type of compensation devices.
ANN Control for Improved Performance of Wind Energy System Connected to Grid
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Kumar, Brijesh; Sandhu, Kanwarjit Singh; Sharma, Rahul
This paper proposes the novel control strat- egy to improve the power quality injection of wind energy system using Doubly Fed Induction Generator (DFIG) into the grid by implementing artificial neu- ral network. The torque ripple produced in DFIG due to loading by grid tied inverter, which leads to poor power quality injection into the system. Also, these ripples transferred by DC link and causes heating losses and generator phase current distortion. There- fore, this paper modelled ANN based control scheme to reduce the torque ripple content and restrict the trans- fer of ripple by DC link to improve the outcome of wind energy system while operating in variable conditions. The DFIG system under studied are modelled and simulated in MATLAB SIMULINK to verify the improvement using proposed control strategy. The recent control technique is also simulated for reflecting the effectiveness in the proposed control method. The outcomes obtained are studied and analysed with the existing control scheme to highlight the improvement obtained by proposed control.
Torque Quality Improvement in Induction Motor for Electric Vehicle Application Based on Teamwork Optimization
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Sahoo, Anjan Kumar; Jena, Ranjan Kumar
The tailpipe emission caused by the vehi- cles using internal combustion engines is a significant source of air pollution. To reduce the health hazards caused by air pollution, advanced countries are now adopting the use of Electric Vehicles (EVs). Due to the advancement of electric vehicles, research and devel- opment efforts are being made to improve the perfor- mance of EV motors. With a nominal reference sta- tor flux, the classical induction motor drive generates significant flux, torque ripple, and current harmon- ics. In this work, a Teamwork Optimization Algorithm (TOA)-based optimal stator flux strategy is suggested for torque ripple reduction applied in a Classical Direct Torque Controlled Induction Motor (CDTC-IM) drive. The suggested algorithm’s responsiveness is investi- gated under various steady-state and dynamic operat- ing conditions. The proposed Direct Torque Controlled Induction Motor (DTC-IM) drive’s simulation results are compared to those of the CDTC-IM and Fuzzy Di- rect Torque Controlled Induction Motor (FDTC-IM) drives. The proposed system has been evaluated and shown to have reduced torque ripple, flux ripple, cur- rent harmonics, and total energy consumption by the motor. Further, a comparative simulation study of the above methods at different standard drive cycles is presented. Experimental verification of the proposed algorithm using OPAL-RT is presented. The results represent the superiority of the proposed algorithm compared to the CDTC- and FDTC-IM drive. The torque ripple reduction approach described in this study can also be applied to all types of induction motors, not only those for electric vehicles or Hybrid Electric Vehicles (HEVs).
Advanced Dispatching of a Wind Farm Based on Doubly Fed Induction Generators for the Improvement of LVRT Capability by the ADRC Approach
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Laghridat, Hammad; Essadki, Ahmed; Nasser, Tamou
This paper aims to explore a viable monitoring and management of active and reactive powers for a large-scale wind farm based on Doubly- Fed Induction Generators (DFIG) considering the volt- age Fault-Ride-Through capability (FRT), especially Low-Voltage-Ride-Through (LVRT) capability by using a new control strategy, known as Active Disturbance Rejection Control. This strategy uses real-time estima- tion and compensation of the generalized "total" dis- turbance before it affects the system. The wind farm supervisory unit is used to coordinate the control of the powers production by the entire wind farm, which must take into account the couplings between each wind gen- erator while producing the individual power commands. The turbine control units (local supervisory units) send the appropriate power references depending on the sit- uation. This can be to produce the maximum power, to manage the active and reactive power given by the Transmission System Operator (TSO) or to meet the requirements of the grid code (LVRT capacity). How- ever, to ensure the dispatching of the references of the active and reactive powers over the all wind generators of the wind farm and to satisfy the security of the power grid, we utilized mean of the proportional distribution algorithm. The effectiveness of the proposed supervisory approach and control strategies are tested and vali- dated through a multiples scenarios of simulations that are made under the MATLAB/Simulink Environment. The results obtained have demonstrated the efficiency and robustness of the control methods, and also the fact that they guarantee good performance and safety of the integration of wind farms into the grid while complying with the requirements of the grid code during power system faults.
30 Years of Video Coding Evolution - What Can We Learn from it in Terms of QoE?
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Mizdoš, Tomáš; Barkowsky, Marcus; Počta, Peter; Uhrina, Miroslav
From the beginnings of ITU-T H.261 to H.265 (HEVC), each new video coding standard has aimed at halving the bitrate at the same perceptual quality by redundancy and irrelevancy reduction. Each improvement has been explained by comparably small changes in the video coding toolset. This contribu- tion aims at starting the Quality of Experience (QoE) analysis of the accumulated improvements over the last thirty years. Based on an overview of the changes in the coding tools, we analyze the changes in the quan- tized residual information. Visual comparison and sta- tistical measures are performed and some interpreta- tions are provided towards explaining how irrelevancy reduction may have led to such a huge reduction in bitrate. The interpretation of the results in terms of QoE paves the way towards an understanding of the coding tools in terms of visual quality. It may help in understanding how the irrelevancy reduction has been improved over the decades. Understanding how the differences of the residuals relate to known or yet un- known properties of the human visual system, may en- able a closer collaboration between perception research and video compression research.
Adaptive Filtering of Accelerometer and Electromyography Signals Using Extended Kalman Filter for Chewing Muscle Activities
(Vysoká škola báňská - Technická univerzita Ostrava, 2022) Sonmezocak, Temel; Kurt, Serkan
Today Electromyography (EMG) and ac- celerometer (MEMS) based signals can be used in the clinical diagnosis of physical states of muscle activities such as fatigue, muscle weakness, pain, and tremors and in external or wearable robotic exoskeletal systems used in rehabilitation areas. During the record- ing of these signals taken from the skin surface through non-invasive processes, analysis of the signal becomes difficult due to the electrodes attached to the skin not fully contacting, involuntary body movements, and noises from peripheral muscles. In addition, param- eters such as age and skin structure of the subjects can also affect the signal. Considering these nega- tive factors, a new adaptive method based on Extended Kalman Filtering (EKF) model for more effective fil- tering of the muscle signals based on both EMG and MEMS is proposed in this study. Moreover, the accu- racy of the parametric values determined by the filter automatically according to the most effective time and frequency features that represent noisy and filtered sig- nals was determined by different machine learning and classification algorithms. It was verified that the fil- ter performs adaptive filtering with 100 % effectiveness with Linear Discriminant.

Browse

Recent Submissions