Abstract:In the process of rehabilitation training for stroke patients, the rehabilitation effect is positively affected by how much physical activity the patients take part in. Most of the signals used to measure the patients’ participation are EMG signals or oxygen consumption, which increase the cost and the complexity of the robotic device. In this work, we design a multi-sensor system robot with torque and six-dimensional force sensors to gauge the patients’ participation in training. By establishing the static eq… Show more
“…An alternative to the process of rehabilitation training for stroke patients, compared to most of the methods, which process EMG signals or oxygen consumption for patients’ participation measurements, uses high cost and high complexity robotic devices, a multi-sensor system robot with torque and six-dimensional force sensors integrated in advanced intelligent control, applying the support vector machines [ 4 ]. The support vector classifiers and regression machines were used to predict the degree of the patient’s task participation, taking into account the small sample and non-linear data of the patients’ training and questionnaire data.…”
Section: Review Of the Contributions In This Special Issuementioning
Deep research and communicating new trends in the design, control and applications of the real time control of intelligent sensors systems using advanced intelligent control methods and techniques is the main purpose of this research. The innovative multi-sensor fusion techniques, integrated through the Versatile Intelligent Portable (VIP) platforms are developed, combined with computer vision, virtual and augmented reality (VR&AR) and intelligent communication, including remote control, adaptive sensor networks, human-robot (H2R) interaction systems and machine-to-machine (M2M) interfaces. Intelligent decision support systems (IDSS), including remote sensing, and their integration with DSS, GA-based DSS, fuzzy sets DSS, rough sets-based DSS, intelligent agent-assisted DSS, process mining integration into decision support, adaptive DSS, computer vision based DSS, sensory and robotic DSS, are highlighted in the field of advanced intelligent control.
“…An alternative to the process of rehabilitation training for stroke patients, compared to most of the methods, which process EMG signals or oxygen consumption for patients’ participation measurements, uses high cost and high complexity robotic devices, a multi-sensor system robot with torque and six-dimensional force sensors integrated in advanced intelligent control, applying the support vector machines [ 4 ]. The support vector classifiers and regression machines were used to predict the degree of the patient’s task participation, taking into account the small sample and non-linear data of the patients’ training and questionnaire data.…”
Section: Review Of the Contributions In This Special Issuementioning
Deep research and communicating new trends in the design, control and applications of the real time control of intelligent sensors systems using advanced intelligent control methods and techniques is the main purpose of this research. The innovative multi-sensor fusion techniques, integrated through the Versatile Intelligent Portable (VIP) platforms are developed, combined with computer vision, virtual and augmented reality (VR&AR) and intelligent communication, including remote control, adaptive sensor networks, human-robot (H2R) interaction systems and machine-to-machine (M2M) interfaces. Intelligent decision support systems (IDSS), including remote sensing, and their integration with DSS, GA-based DSS, fuzzy sets DSS, rough sets-based DSS, intelligent agent-assisted DSS, process mining integration into decision support, adaptive DSS, computer vision based DSS, sensory and robotic DSS, are highlighted in the field of advanced intelligent control.
“…Before and after going to the toilet, there is also the problem of transferring a patient from a bed to the toilet. However, due to the need for privacy during the toilet process, the presence of nursing staff during this process will create a great psychological burden for patients [ 7 ]. Therefore, it is of social value and practical significance to develop a safe and stable wheelchair that can enable patients to complete the toilet process independently.…”
Due to the fixed size of the structure or the possibility of only simple manual adjustment, the traditional toilet wheelchair cannot easily be adapted to the size of the user or the toilet. In this paper, a planar two-degree-of-freedom parallel mechanism with coupling branch chains is proposed to enable both seat height adjustment and body posture adjustment of a toilet chair, solving the problems of posture adaptability between the user and the machine, and height matching in the process of using the wheelchair-assisted toilet. The model of the parallel mechanism was designed after analyzing the general rules of posture transformation in the human body before and after the toilet process, and the dimensions of each linkage were then determined according to the constraint conditions. By analyzing the degree of freedom, kinematics, workspace, singularity and position of the center of gravity, the rationality of the design was ensured. The weighted average function was used to find the optimal fixed point of the horizontal moving slider, and the actual trajectory at the end of the single driving mode was close to the ideal trajectory. The experimental results show that the adjustable seat height range is 290~550 mm and the adjustable angle range is 0~90°, which can enable disabled people to use the toilet independently.
“…In terms of model optimization for robotic applications, the studies reveal different approaches such as developing advanced control systems for the upper and lower limb [19,20], applying Dezert-Smarandache Theory (DSmT) for decision-making algorithms [21], Extenics control [22], and fuzzy dynamic modelling [23].…”
This paper presents an extensive research carried out for enhancing the performances of convolutional neural network (CNN) object detectors applied to municipal waste identification. In order to obtain an accurate and fast CNN architecture, several types of Single Shot Detectors (SSD) and Regional Proposal Networks (RPN) have been fine-tuned on the TrashNet database. The network with the best performances is executed on one autonomous robot system, which is able to collect detected waste from the ground based on the CNN feedback. For this type of application, a precise identification of municipal waste objects is very important. In order to develop a straightforward pipeline for waste detection, the paper focuses on boosting the performance of pre-trained CNN Object Detectors, in terms of precision, generalization, and detection speed, using different loss optimization methods, database augmentation, and asynchronous threading at inference time. The pipeline consists of data augmentation at the training time followed by CNN feature extraction and box predictor modules for localization and classification at different feature map sizes. The trained model is generated for inference afterwards. The experiments revealed better performances than all other Object Detectors trained on TrashNet or other garbage datasets with a precision of 97.63% accuracy for SSD and 95.76% accuracy for Faster R-CNN, respectively. In order to find the optimal higher and lower bounds of our learning rate where the network is actually learning, we trained our model for several epochs, updating the learning rate after each epoch, starting from 1 × 10−10 and decreasing it until reaching 1 × 10−1.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.