Search results

This paper aims to present an application of design of experiments techniques to determine the optimized parameters of artificial neural networks (ANNs), which are used to estimate human force from Electromyogram (sEMG) signals for rehabilitation robotics. Physiotherapists believe, to make a precise therapeutic exercise, we need to design and perform therapeutic exercise base on patient muscle activity. Therefore, sEMG signals are the best tool for using in therapeutic robots because they are related to the muscle activity. Using sEMG signals as input for therapeutic robots need precise human force estimation from sEMG. Furthermore, the ANN estimator performance is highly dependent on the accuracy of the target date and setting parameters.

In the previous studies, the force data, which are collected from the force sensors or dynameters, has widely been used as target data in the training phase of learning ANN. However, force sensors or dynameters could measure only contact force. Therefore, the authors consider the contact force, limb’s dynamic and time in target data to increase the accuracy of target data.

There are plenty of algorithms that are used to obtain optimal ANN settings. However, to the best of our knowledge, they do not use regression analysis to model the effect of each parameter, as well as present the contribution percentage and significance level of the ANN parameters for force estimation.

In this paper, a new model to estimate the force from sEMG signals is presented. In this method, the sum of the limb’s dynamics and the contact force is used as target data in the training phase. To determine the limb’s dynamics, the patient’s body and the rehabilitation robot are modeled in OpenSim. Furthermore, in this paper, sEMG experimental data are collected and the ANN parameters based on an orthogonal array design table are regulated to train the ANN. Taguchi is used to find the optimal parameters settings. Next, analysis of variance technique is used to obtain significance level, as well as contribution percentage of each parameter, to optimize ANN’s modeling in human force estimation. The results indicate that the presented model can precisely estimate human force from sEMG signals.

In today’s digital world, real-time health monitoring is becoming a most important challenge in the field of medical research. Body signals such as electrocardiogram (ECG), electromyogram and electroencephalogram (EEG) are produced in human body. This continuous monitoring generates huge count of data and thus an efficient method is required to shrink the size of the obtained large data. Compressed sensing (CS) is one of the techniques used to compress the data size. This technique is most used in certain applications, where the size of data is huge or the data acquisition process is too expensive to gather data from vast count of samples at Nyquist rate. This paper aims to propose Lion Mutated Crow search Algorithm (LM-CSA), to improve the performance of the LMCSA model.

A new CS algorithm is exploited in this paper, where the compression process undergoes three stages: designing of stable measurement matrix, signal compression and signal reconstruction. Here, the compression process falls under certain working principle, and is as follows: signal transformation, computation of Θ and normalization. As the main contribution, the theta value evaluation is proceeded by a new “Enhanced bi-orthogonal wavelet filter.” The enhancement is given under the scaling coefficients, where they are optimally tuned for processing the compression. However, the way of tuning seems to be the great crisis, and hence this work seeks the strategy of meta-heuristic algorithms. Moreover, a new hybrid algorithm is introduced that solves the above mentioned optimization inconsistency. The proposed algorithm is named as “Lion Mutated Crow search Algorithm (LM-CSA),” which is the hybridization of crow search algorithm (CSA) and lion algorithm (LA) to enhance the performance of the LM-CSA model.

Finally, the proposed LM-CSA model is compared over the traditional models in terms of certain error measures such as mean error percentage (MEP), symmetric mean absolute percentage error (SMAPE), mean absolute scaled error, mean absolute error (MAE), root mean square error, L1-norm and L2-normand infinity-norm. For ECG analysis, under bior 3.1, LM-CSA is 56.6, 62.5 and 81.5% better than bi-orthogonal wavelet in terms of MEP, SMAPE and MAE, respectively. Under bior 3.7 for ECG analysis, LM-CSA is 0.15% better than genetic algorithm (GA), 0.10% superior to particle search optimization (PSO), 0.22% superior to firefly (FF), 0.22% superior to CSA and 0.14% superior to LA, respectively, in terms of L1-norm. Further, for EEG analysis, LM-CSA is 86.9 and 91.2% better than the traditional bi-orthogonal wavelet under bior 3.1. Under bior 3.3, LM-CSA is 91.7 and 73.12% better than the bi-orthogonal wavelet in terms of MAE and MEP, respectively. Under bior 3.5 for EEG, L1-norm of LM-CSA is 0.64% superior to GA, 0.43% superior to PSO, 0.62% superior to FF, 0.84% superior to CSA and 0.60% better than LA, respectively.

This paper presents a novel CS framework using LM-CSA algorithm for EEG and ECG signal compression. To the best of the authors’ knowledge, this is the first work to use LM-CSA with enhanced bi-orthogonal wavelet filter for enhancing the CS capability as well reducing the errors.

This paper aims to avoid the precise modeling and controlling problems of rigid structures of hand recovery device, by proposing a hand rehabilitator based on flexible pneumatic actuator with its safety and adaptability.

The hand rehabilitator is designed based on a flexible pneumatic bending joint. The recovery training program for an injured finger is developed via forearm sEMG (surface electromyogram) sampling, analysis, classification and motion consciousness identification. Four typical movement models of the index finger and middle finger were defined and the corresponding sEMG signals were sampled. After simulation and comparative analysis, autoregressive (AR) model back propagation (BP) network was selected for sEMG analysis and hand recovery planning because of its best recognition performance. A verification test was designed and the results showed that the soft hand rehabilitator and recovery conception are feasible.

AR model BP network can identify the index finger and middle finger movement intention via an sEMG analysis. The developed flexible pneumatic hand rehabilitator is safe and suitable for finger recovering therapy.

Because of the limitation of experimental samples, the prototype rehabilitator of this work may lack generalizability for other situations. Therefore, for further study and application, systematic structure revising, experiments, data and training are necessary to improve the performance.

The paper includes implications for the development and application of a new style, safe and dexterous hand rehabilitator.

The paper tries a new approach to design a safe, flexible and easily controlled hand rehabilitator.

The purpose of this paper is to investigate how the center of pressure (COP) changes depending on the type and wearing method of baby carriers, which is fundamental research for the development of smart baby carriers. In addition, the most comfortable and least burdensome type and method of wearing baby carriers is suggested.

The COP and muscle fatigue were measured depending on the three types and wearing method of baby carriers. And then, the subjective stability, comfort, and fatigue were analyzed.

The results of this study show that horizontal changes to the COP are greater and when baby carriers are worn loosely, subjective comfort is worse. Furthermore, when the shoulder straps are worn loosely, the center of mass moves downwards, lowering the muscle fatigue of the shoulders, but greatly raising the muscle fatigue of the waist and thighs. Comparison of the shapes of baby carriers showed that X-type produced greater muscle fatigue in the shoulders, waist, and thighs, as well as greater subjective fatigue in the shoulders. However, subjective fatigue in the waist decreases when baby carriers without waist support are worn.

It is expected that changes in COP values based on the type and method of wearing baby carriers will be applied as fundamental data for the development of automatic-adjusting smart baby carriers that prevent muscular pain and concentrated pressure.

This study is dedicated to critically analysing research addressing human resource management (HRM) and the adoption of artificial intelligence (AI) with the purpose of driving development in the field of human resources (HR) at the strategic and managerial level.

A systematic literature review (SLR) was conducted using the Scopus database, which gathered 61 articles between 2002 and 2022. The SLR process has the potential to, in addition to generating knowledge and theories, support and guide policy development and practice in many disciplines.

The results of this study allowed the author to identify three main conclusions: (a) there are four thematic clusters – (i) Strategic HR and AI, (ii) Recruitment and AI, (iii) Training and AI and (iv) Future of work; (b) there is a growing academic interest in studying the implementation of AI to develop the HR sector and (c) the application of AI stands out in the strategic HR and AI cluster as a means of achieving profit maximisation and the overall development of the organisation.

This study is the first SLR to present a strategic and managerial view on AI applications associated with specific HRM dimensions. The study is also the first SLR to identify key trends in the literature, drivers and obstacles to the development of AI in HRM and then place them within the landscape of positive and negative approaches in a framework. Also, as a contribution, the study has practical implications for HR managers and practitioners in adopting AI as a decision support in the area's processes.

The study investigated the effects of two mental training strategies separately and combined on subjects’ shooting performance following an endurance march. Further, the study examined the suitability of a ten‐session training programme for the police force. On Trial 1, following a three hour march, 44 subjects shot 25 rounds. Subjects were then randomly assigned to four groups (biofeedback, relaxation, combined biofeedback and relaxation and control). After two weeks of mental training, subjects performed both tasks again on Trial 2. A repeated two‐way ANOVA indicated a significant improvement (p < 0.01) in shooting accuracy by the combined group. Suitability for this mental training programme was strongly supported by the experimental groups (71 per cent to 80 per cent). Subjects were generally better able to relax and focus. They were also more aware of their body and their physiological control. Results are discussed in light of potential benefits for cognitive strategies in precision tasks following endurance activities.

The EPOC neuroheadset is a commercially available device that allows game players to control a computer using their facial expressions or their thoughts. This paper aims to examine whether it has the potential to be used as an input for assistive technology (AT) devices.

Two experiments were conducted. In the first, 12 non‐impaired subjects used the neuroheadset to control a computer with their facial expressions. They also used a simple system of two head switches for comparison. In the second experiment, three non‐impaired subjects were trained to use the neuroheadset to control a computer with their thoughts.

In the first experiment, the neuroheadset was slower and less accurate than the head switches (p<0.05), and was also harder to use. It is unlikely to be preferred to existing methods of accessing AT for those that retain a small amount of head movement. In the second experiment, by the end of the week, all three subjects achieved accuracy rates greater than chance.

All subjects were non‐impaired, and the sample size in the second experiment was small. Further research should concentrate on the second experiment, using larger sample sizes and impaired subjects.

The EPOC neuroheadset is substantially cheaper than similar specialist devices, and has the potential to allow those with no voluntary muscle control to access AT with their thoughts.

The results of these two experiments show that the Emotiv EPOC neuroheadset can be used as an interface for non‐impaired users to transfer information to a computer, which could in turn be used to control AT.

Consumers' emotions have a significant influence on purchase and consumption decisions for a wide variety of products. A good example of this phenomenon can be found in the candy and snack market, where consumer responses are a product of a sizable number of emotion‐laden situations that may be exploited in advertising strategy. Candy is often used as a reward for appropriate behavior in childhood, as well as a gift or positive “message” among adults for events such as Valentine's Day, anniversaries, and birthdays. On the other hand, many consumers believe that candy and snacks have negative consequences if they are used excessively. By capitalizing on these and similar past experiences through the firm's advertising efforts, the marketer of confections can either attempt to alleviate negative, or accentuate positive emotional feelings directed toward the brand or product class. Emotions appear to play a similar role in other consumer products such as tobacco, liquor, automobiles as well as many food products. Emotional, experiential, and aesthetic behaviors that normally lie beyond the scope of traditional marketing are currently receiving extraordinary attention. Although some have argued that these aspects of consumption activity are deserving of study in their own right, practitioners have realized that understanding the dynamics of activities such as emotional experience can assist in developing marketing strategy. Although our present knowledge of buyer and consumer emotional experience is relatively limited, this article will provide some structure to what we do know, in an effort to apply it to the advertising area.