Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : International Journal of Robotics and Control Systems

Capability of Hybrid Long Short-Term Memory in Stock Price Prediction: A Comprehensive Literature Review Furizal, Furizal; Ma'arif, Alfian; Firdaus, Asno Azzawagama; Suwarno, Iswanto
International Journal of Robotics and Control Systems Vol 4, No 3 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i3.1489

Abstract

Stocks are financial instruments representing ownership in a company. They provide holders with rights to a portion of the company's assets and earnings. The stock market serves as a means for companies to raise capital. By selling shares to the public, companies can obtain funds needed for expansion, research and development, as well as various other investments. Though significant, predicting stock prices poses a challenge for investors due to their unpredictable nature. Stock price prediction is also an intriguing topic in finance and economics due to its potential for significant financial gains. However, manually predicting stock prices is complex and requires in-depth analysis of various factors influencing stock price movements. Moreover, human limitations in processing and interpreting information quickly can lead to prediction errors, while psychological factors such as bias and emotion can also affect investment decisions, reducing prediction objectivity and accuracy. Therefore, machine processing methods become an alternative to expedite and reduce errors in processing large amounts of data. This study attempts to review one of the commonly used prediction algorithms in time series forecasting, namely hybrid LSTM. This approach combines the LSTM model with other methods such as optimization algorithms, statistical techniques, or feature processing to enhance the accuracy of stock price prediction. The results of this literature review indicate that the hybrid LSTM method in stock price prediction shows promise in improving prediction accuracy. The use of optimization algorithms such as GA, AGA, and APSO has successfully produced models with low RMSE values, indicating minimal prediction errors. However, some methods such as LSTM-EMD and LSTM-RNN-LSTM still require further development to improve their performance.
Long Short-Term Memory vs Gated Recurrent Unit: A Literature Review on the Performance of Deep Learning Methods in Temperature Time Series Forecasting Furizal, Furizal; Fawait, Aldi Bastiatul; Maghfiroh, Hari; Ma’arif, Alfian; Firdaus, Asno Azzawagama; Suwarno, Iswanto
International Journal of Robotics and Control Systems Vol 4, No 3 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i3.1546

Abstract

Temperature forecasting is a crucial aspect of meteorology and climate change studies, but challenges arise due to the complexity of time series data involving seasonal patterns and long-term trends. Traditional methods often fall short in handling this variability, necessitating more advanced solutions to enhance prediction accuracy. LSTM and GRU models have emerged as promising alternatives for modeling temperature data. This study is a literature review comparing the effectiveness of LSTM and GRU based on previous research in temperature forecasting. The goal of this review is to evaluate the performance of both models using various evaluation metrics such as MSE, RMSE, and MAE to identify gaps in previous research and suggest improvements for future studies. The method involves a comprehensive analysis of previous studies using LSTM and GRU for temperature forecasting. Assessment is based on RMSE values and other metrics to compare the accuracy and consistency of both models across different conditions and temperature datasets. The analysis results show that LSTM has an RMSE range of 0.37 to 2.28. While LSTM demonstrates good performance in handling long-term dependencies, GRU provides more stable and accurate performance with an RMSE range of 0.03 to 2.00. This review underscores the importance of selecting the appropriate model based on data characteristics to improve the reliability of temperature forecasting.
Self-Motion Control Exoskeleton for Upper Limb Rehabilitation with Perceptron Neuron Motion Capture Osman, Mohamad Afwan; Azlan, Norsinnira Zainul; Suwarno, Iswanto; Samewoi, Abdul Rahman; Kamarudzaman, Nohaslinda
International Journal of Robotics and Control Systems Vol 5, No 1 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i1.1030

Abstract

Upper limb rehabilitation robot can facilitate patients to regain their original impaired arm function and reduce therapist’ workload. However, the patient does not have a direct control over his/ her arm movement, which may lead to discomfort or even injury. This paper focuses on the development of a self-motion rehabilitation robot using Perception Neuron motion capture, where the movement of the impaired arm imitates the motion of the healthy limb.  The Axis Neuron software receives the healthy upper limb’s motion data from Perception Neuron. Unity serves as the simulation engine software that provides a 3-dimensional animation. ARDUnity acts as the communication platform between Unity software with Arduino. Arduino code is generated using Wire Editor, which avoids the need of the programming to be written in C++ or C#. Finally, Arduino instructs the exoskeleton motors that are connected to the impaired arm to move, following the healthy joint’s motion. The forward kinematics analysis for the robotic exoskeleton has been carried out to identify its workspace. Hardware experimental tests on the elbow and wrist flexion/ extension have shown the root-mean-square errors (RMSE) between the healthy and impaired arms movement to be 1.5809○ and 12.1955○ respectively. The average time delay between the healthy and impaired elbow movement is 0.1 seconds. For the wrist motion, the time delay is 1 second. The experimental results verified the feasibility and effectiveness of the Perception Neuron in realizing the self-motion control robot for upper limb rehabilitation. The proposed system enables the patients to conduct the rehabilitation therapy in a safer and more comfortable way as they can directly adjust the speed or stop the movement of the affected limb whenever they feel pain or discomfort.
Selection and Evaluation of Robotic Arm based Conveyor Belts (RACBs) Motions: NARMA(L2)-FO(ANFIS)PD-I based Jaya Optimization Algorithm Fadhil Mohammed, Abdullah; Basil, Noorulden; Abdulmaged, Riyam Bassim; Marhoon, Hamzah M.; Ridha, Hussein Mohammed; Ma'arif, Alfian; Suwarno, Iswanto
International Journal of Robotics and Control Systems Vol 4, No 1 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i1.1243

Abstract

Scholars worldwide have shown considerable interest in the industrial sector, mainly due to its abundant resources, which have facilitated the adoption of conveyor belt technologies like Robotic Arm-Based Conveyor Belts (RACBs). RACBs rely on four primary movements: (i.e., joint, motor, gear, and sensor), which can have a significant impact on the overall motions and motion estimation. To optimize these operations, an assistive algorithm has been developed to enhance the effectiveness of motion by achieving favorable gains. However, each motion requires specific criteria for Fractional Order Proportional Integral Derivative (FOPID) controller gains, leading to various challenges. These challenges include the existence of multiple evaluation and selection criteria, the significance of these criteria for each motion, the trade-off between criterion performance for each motion, and determining critical values for the criteria. As a result, the evaluation and selection of the Proposed Jaya optimization algorithm for RACB motion control becomes a complex problem. To address these challenges, this study proposes a novel integrated approach for selecting the Jaya optimization algorithm in different RACB motions. The approach incorporates two evaluation methods: the Nonlinear Autoregressive Moving Average with exogenous inputs (NARMA-L2) controller for Neural Network (NN) weighting of the criteria, and the Adaptive Neuro-Fuzzy Inference System (ANFIS) for selecting the Jaya optimization algorithm. The approach consists of three main phases: RACB-based NARMA-L2 Controller Identification and Pre-processing, Development of NARMA-L2 controller-based NARMA(L2)-FO(ANFIS)PD-I, and Evaluation of FOPID criteria based on JOA. The proposed approach is evaluated based on NARMA(L2)-FO(ANFIS)PD-I that given 0.4074, 0.3156, 0.3724, 0.1898 and 0.2135 for K_p_joint, K_i_motor, K_d_sensor, λ_gear, and µ_N respectively, which verifies the soundness of the proposed methodology.
Function Approximation Technique-based Adaptive Force-Tracking Impedance Control for Unknown Environment Azlan, Norsinnira Zainul; Yamaura, Hiroshi; Suwarno, Iswanto
International Journal of Robotics and Control Systems Vol 5, No 1 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i1.1029

Abstract

An accurate force-tracking in various applications may not be achieved without a complete knowledge of the environment parameters in the force-tracking impedance control strategy. Adaptive control law is one of the methods that is capable of compensating parameter uncertainties. However, the direct application of this technique is only effective for time-invariant unknown parameters. This paper presents a Function Approximation Technique (FAT)-based adaptive impedance control to overcome uncertainties in the environment stiffness and location with consideration of the approximation error in the FAT representation. The target impedance for the control law have been derived for unknown time-varying environment location and constant or time-varying environment stiffness using Fourier Series. This allows the update law to be derived easily based on Lyapunov stability method. The update law is formulated based on the force error feedback. Simulation results in MATLAB environment have verified the effectiveness of the developed control strategy in exerting the desired amount of force on the environment in x-direction, while precisely follows the required trajectory along y-direction, despite the constant or time-varying uncertainties in the environment stiffness and location. The maximum force error for all unknown environment tested has been found to be less than 0.1 N. The test outcomes for various initial assumption of unknown stiffness between 20000N/m to 120000N/m have shown consistent and excellent force tracking. It is also evident from the simulation results that the proposed controller is effective in tracking time-varying desired force under the limited knowledge of the environment stiffness and location.