IAES International Journal of Robotics and Automation (IJRA)
Not a member yet
460 research outputs found
Sort by
Feature extraction techniques for cognitive stimuli-based electroencephalogram signals: an experimental analysis
Get PDFOver the past decades, brain-computer interface (BCI) has gained a lot of attention in various fields ranging from medicine to entertainment, and electroencephalogram (EEG) signals are widely used in BCI. Brain-computer interface made human-computer interaction possible by using information acquired from EEG signals of the person. The raw EEG signals need to be processed to obtain valuable information which could be used for communication purposes. The objective of this paper is to identify the best combination of features that could discriminate cognitive stimuli-based tasks. EEG signals are recorded while the subjects are performing some arithmetical based mental tasks. Statistical, power, entropy, and fractional dimension (FD) features are extracted from the EEG signals. Various combinations of these features are analyzed and validated using random forest classifier, K-nearest neighbors (KNN), multilayer perceptron, linear discriminant analysis, and support vector machine. The combination of entropy-FD features gives the highest accuracy of 90.47% with the KNN algorithm when compared to individual entropy and FD features which achieves 79.36% with random forest classifier, multilayer perceptron, and 82.53% with linear discriminant analysis, respectively. Our results show that the hybrid of entropy-FD features with KNN classifier can efficiently classify the cognition-based stimuli
Kinematic analysis and design of a new two-limb parallel Schonflies-motion generator considering isotropic configuration
Get PDFThis paper presents a new two-limb parallel Schonflies-motion generator, which adopts a pair of alternative spatial modules equivalent to the parallelogram structure. This modular architecture can ensure the enhanced stiffness of the manipulator normal to the motion of the planar parallelogram structure due to the trapezoidal architecture. The preliminary kinematic problems, namely, the mobility, forward/inverse geometry and singularity, are studied as well as the kinematic isotropy. A neutral isotropic configuration of the robot is identified for the structural design of the link lengths
A wireless bionic soft robotic fish using shape-memory alloy actuators
Get PDFIn this study, we present the construction of a wireless bionic soft robotic fish that has a silicone tail and uses shape-memory alloys (SMAs) as actuators. Even though there have been a lot of recent advancements in the field of soft robotics, the use of SMAs as actuators for soft robots is still not something that is investigated very often. In the course of this research, we plan to work toward the creation of a realistic bionic fish robot that possesses a high level of mobility in the water, in addition to being light enough, strong enough, and flexible enough. The purpose of this study is to expound on the process of optimizing the morphologies of the fish body, as well as the optimization of the electromechanical behavior of the SMAs, in order to generate swimming motions in the fish. Our attention will be on the optimization of these two aspects. This report also outlines some preliminary but promising physical tests that were conducted to create a robotic fish with the similar shape
Stabilization of liquid level in a tank system based on fuzzy logic controller
Get PDFProcess industry needed a fast executed automatic control system capable of handling uncertain, vague problems and nonlinear control variables. Liquid level control is one of the emerging control problems getting the interest of technical experts in the area of control. This paper is based on a fuzzy logic control strategy to maintain and stabilize the liquid level in a tank system that deals with pumping of liquid in tanks as well as regulating liquid level and pushing off the liquid into another tank. Fuzzy controller attains optimum performance by eliminating perturbation in steady state and vanishing the overshoot as compared to proportional, integral, and derivative (PID) controller. The proposed fuzzy logic controller shows minimal steady error as compared to PID controller. The defuzzification of the proposed scheme is based on the centroid method to obtain optimum results. The settling time is nearly 50 second while using fuzzy logic control as compared to 80 seconds in PID control strategy. The overshoot observed is minimal, nearly less than 1% using a fuzzy logic control scheme
Recognizing facial emotions for educational learning settings
Get PDFEducational learning settings exploit cognitive factors as ultimate feedback to enhance personalization in teaching and learning. But besides cognition, the emotions of the learner which reflect the affective learning dimension also play an important role in the learning process. The emotions can be recognized by tracking explicit behaviors of the learner like facial or vocal expressions. Despite reasonable efforts to recognize emotions, the research community is currently constraints by two issues, namely: i) the lack of efficient feature descriptors to accurately represent and prospectively recognize (detecting) the emotions of the learner; ii) lack of contextual datasets to benchmark performances of emotion recognizers in the learning-specific scenarios, resulting in poor generalizations. This paper presents a facial emotion recognition technique (FERT). The FERT is realized through results of preliminary analysis across various facial feature descriptors. Emotions are classified using the multiple kernel learning (MKL) method which reportedly possesses good merits. A contextually relevant simulated learning emotion (SLE) dataset is introduced to validate the FERT scheme. Recognition performance of the FERT scheme generalizes to 90.3% on the SLE dataset. On more popular but noncontextually datasets, the scheme achieved 90.0% and 82.8% respectively extended Cohn Kanade (CK+) and acted facial expressions in the wild (AFEW) datasets. A test for the null hypothesis that there is no significant difference in the performances accuracies of the descriptors rather proved otherwise (χ2=14.619,df=5,p=0.01212) for a model considered at a 95% confidence interval
Smart energy conservation system for study rooms
Get PDFMost individuals in public and private sector offices are uninterested in turning off electronic equipment like fans and lamps while they are not present. For example, most students fail to turn off the fans and lighting in their classrooms, study rooms, residence halls, and so forth. As a result of this attitude, power usage in these places tends to rise. Several automation systems have been designed and implemented to decrease power waste in these locations, but the majority of these systems are either inefficient or inappropriate for their intended use. This study presents a proposed smart energy conservation system in a study room that employs an infrared remote-control mechanism to turn on or off an energy system in the absence of humans. Embedded technology was used to create an energy-saving solution. The testing was done with a range of scenarios and key performance indicators. The test results showed that the proposed system was effectively implemented, and a comparison of the system to a case study system demonstrated that it had a better design, lower cost, and higher operational efficiency. The findings of this study will be essential to a wide variety of stakeholders
Fuzzy logic track control of an automated lawnmower
Get PDFAutomation of agricultural and horticultural operations keeps received great attention for over a decade. The control parameters adopted depend on the location and characteristics of likely obstacles and navigation requirements. An automated lawnmower (ALM) with fuzzy logic control is presented in this study. Fuzzy logic was chosen to improve a previous work which was controlled via Bluetooth. Three ultrasonic sensors and two proximity sensors served as the eyes of the ALM for navigation and obstacle avoidance while the cutting blade was made of stainless steel and controlled by a brushless direct current (BLDC) motor. A fuzzy algorithm was implemented on an Arduino controller with the inputs and outputs as directional instructions. Obstacle avoidance was achieved by setting a range of values for the sensors interpreted by the fuzzy logic for the corresponding output in the form of navigations. Three trials tests were conducted on the ALM on a 5 m2 portion of land with an average grass height of 0.09 m. The average cut area was 4.46 m2, therefore achieving an efficiency of 89.2%, which is highly productive. It was observed that the power consumption was minimal compared to the previous design because at the end of the three trials 46% of the battery was left after over 3 hours of operation
An alternative technique to reduce time, cost and human effort during natural or manufactured disasters
Get PDFThe world suffers from a very large number of missing persons, ranging from about 250,000 to about one million people for various reasons in recent years. Therefore, the process of finding and tracing the missing persons as a result of a plane crash, fire or explosion in a particular area is a humanitarian and religious and national duty, and is one of the most important issues in our country. So, the idea of using a drone to find missing people was invested. We have designed system that collects real-time data and analyzes in a smart way and utilizes global positioning system (GPS) to locate people and track their impact. The idea of this work has been developed and implemented. They represent it in the form of a triangular problem, which included: First, how to locate the missing persons and send video broadcasts to a calculator or mobile device remotely. Analyze the data collected in real time, and send a report identifying the safe path that can be taken to reach the missing persons. The second stage is collection the data in the master computer and analysis it, while the final stage determines the coordinates of the location to the missing persons and the best possible way to reach of them
Unmanned aerial vehicle design for disaster victim search and rescue operation using wireless sensor network localization
Get PDFThe search for disaster victims carried out by search-and-rescue (SAR) team mainly uses traditional methods, which are considered to take much time and effort, and pose a high risk for the search team and the victim. Based on this problem, we conducted research to assist disaster victim search. In this research, we designed a system using passive infrared (PIR) sensors to detect and measure the direction angle of the victim. Given the direction angle from different observation points’ perspectives, we determine the victim’s position using the triangulation method. we also designed a quadcopter unmanned aerial vehicle (UAV) to carry this sensor system across the disaster area. For monitoring purposes, a local website was designed to display data generated by the system. Based on test results, the system can determine a victim’s position with a distance difference of less than 5 m. The system can search victim in an empty land ±35 m×15 m wide in 14 minutes 20 seconds. The data monitoring system also displayed the victim’s position, the position of the observation points, and the UAV’s flight path
Miniature pellet extruder concept for robotic 3D printing application
Get PDFAdditive manufacturing more commonly known as 3D printing has been in the limelight of manufacturing research for a long. Many advances have been made in the past in elementary printing techniques, materials, and post-processing schemes. In this paper, a concept of a miniature pellet extruder is added at the end of the articulated robotic arm. The idea is to create a system that capable to print larger and more complex shapes of any parts with the help of a low payload capacity robotic arm and provide output as a single-piece structure. It also helps to print and handle objects with larger and more complex geometry with an optimized cycle time. Knowledge from this research work will also help to choose not only the right low payload capacity robotic arm, but also provides a logical approach for selecting a pellet extruder over a filament extruder