A novel multi-dimensional features fusion algorithm for the EEG signal recognition of brain's sensorimotor region activated tasks

2020 ◽  
Vol 13 (2) ◽  
pp. 239-260
Author(s):  
Minghua Wei ◽  
Feng Lin
Keyword(s):  
Spatial Frequency ◽  
Action Observation ◽  
Classification Performance ◽  
Eeg Signals ◽  
Feature Maps ◽  
Content Type ◽  
Sensorimotor Region ◽  
The Impact ◽  
Frequency Features ◽  
Fusion Features

PurposeAiming at the shortcomings of EEG signals generated by brain's sensorimotor region activated tasks, such as poor performance, low efficiency and weak robustness, this paper proposes an EEG signals classification method based on multi-dimensional fusion features.Design/methodology/approachFirst, the improved Morlet wavelet is used to extract the spectrum feature maps from EEG signals. Then, the spatial-frequency features are extracted from the PSD maps by using the three-dimensional convolutional neural networks (3DCNNs) model. Finally, the spatial-frequency features are incorporated to the bidirectional gated recurrent units (Bi-GRUs) models to extract the spatial-frequency-sequential multi-dimensional fusion features for recognition of brain's sensorimotor region activated task.FindingsIn the comparative experiments, the data sets of motor imagery (MI)/action observation (AO)/action execution (AE) tasks are selected to test the classification performance and robustness of the proposed algorithm. In addition, the impact of extracted features on the sensorimotor region and the impact on the classification processing are also analyzed by visualization during experiments.Originality/valueThe experimental results show that the proposed algorithm extracts the corresponding brain activation features for different action related tasks, so as to achieve more stable classification performance in dealing with AO/MI/AE tasks, and has the best robustness on EEG signals of different subjects.

Motor imagery-based EEG signals classification by combining temporal and spatial deep characteristics

2020 ◽  
Vol 13 (4) ◽  
pp. 437-453
Author(s):  
Li Xiaoling
Keyword(s):  
Motor Imagery ◽  
Classification Performance ◽  
Classification Algorithm ◽  
Eeg Signals ◽  
Spatial Characteristics ◽  
Content Type ◽  
The Arts ◽  
Temporal And Spatial ◽  
Temporal And Spatial Characteristics

PurposeIn order to improve the weak recognition accuracy and robustness of the classification algorithm for brain-computer interface (BCI), this paper proposed a novel classification algorithm for motor imagery based on temporal and spatial characteristics extracted by using convolutional neural networks (TS-CNN) model.Design/methodology/approachAccording to the proposed algorithm, a five-layer neural network model was constructed to classify the electroencephalogram (EEG) signals. Firstly, the author designed a motor imagery-based BCI experiment, and four subjects were recruited to participate in the experiment for the recording of EEG signals. Then, after the EEG signals were preprocessed, the temporal and spatial characteristics of EEG signals were extracted by longitudinal convolutional kernel and transverse convolutional kernels, respectively. Finally, the classification of motor imagery was completed by using two fully connected layers.FindingsTo validate the classification performance and efficiency of the proposed algorithm, the comparative experiments with the state-of-the-arts algorithms are applied to validate the proposed algorithm. Experimental results have shown that the proposed TS-CNN model has the best performance and efficiency in the classification of motor imagery, reflecting on the introduced accuracy, precision, recall, ROC curve and F-score indexes.Originality/valueThe proposed TS-CNN model accurately recognized the EEG signals for different tasks of motor imagery, and provided theoretical basis and technical support for the application of BCI control system in the field of rehabilitation exoskeleton.

The More Control, the Better?

2014 ◽  
Vol 26 (2) ◽  
pp. 81-91 ◽  
Author(s):  
Jeeyun Oh ◽  
Mun-Young Chung ◽  
Sangyong Han
Keyword(s):  
Mixed Design ◽  
Negative Effects ◽  
Story Structure ◽  
Content Type ◽  
High User ◽  
User Control ◽  
Rigorous Research ◽  
Control Versus ◽  
The Media ◽  
The Impact

Despite of the popularity of interactive movie trailers, rigorous research on one of the most apparent features of these interfaces – the level of user control – has been scarce. This study explored the effects of user control on users’ immersion and enjoyment of the movie trailers, moderated by the content type. We conducted a 2 (high user control versus low user control) × 2 (drama film trailer versus documentary film trailer) mixed-design factorial experiment. The results showed that the level of user control over movie trailer interfaces decreased users’ immersion when the trailer had an element of traditional story structure, such as a drama film trailer. Participants in the high user control condition answered that they were less fascinated with, absorbed in, focused on, mentally involved with, and emotionally affected by the movie trailer than participants in the low user control condition only with the drama movie trailer. The negative effects of user control on the level of immersion for the drama trailer translated into users’ enjoyment. The impact of user control over interfaces on immersion and enjoyment varies depending on the nature of the media content, which suggests a possible trade-off between the level of user control and entertainment outcomes.

Perceived workplace gender-bias and psychological impact

2019 ◽  
Vol 43 (3/4) ◽  
pp. 339-353 ◽  
Author(s):  
Siham Lekchiri ◽  
Cindy Crowder ◽  
Anna Schnerre ◽  
Barbara A.W. Eversole
Keyword(s):  
Gender Bias ◽  
Critical Incident ◽  
Psychological Impact ◽  
Working Women ◽  
Content Type ◽  
Treatment Bias ◽  
Male Dominated ◽  
The Impact ◽  
Organizational Mechanisms ◽  
Practical Implications

Purpose The purpose of this paper is to explore the experiences of working women in a male-dominated country (Morocco) and unveil the unique challenges and everyday gender-bias they face, the psychological impact of the perceived gender-bias and, finally, identify a variety of coping strategies or combatting mechanisms affecting their motivation and retention in the workplace. Design/methodology/approach Empirical evidence was obtained using a qualitative research method. The Critical Incident Technique (CIT) was used to collect incidents recalled by women in the select institution reflecting their perceptions of their managers’ ineffective behaviors towards them and the impact of these behaviors. The critical incidents were inductively coded, and behavioral statements were derived from the coded data. Findings The qualitative data analysis led them to structure the data according to two theme clusters: The perceived gender-bias behaviors (Covert and evident personal and organizational behaviors) and Psychological impacts resulting from the perceived bias. These behavioral practices included abusive behaviors, unfair treatment, bias and lack of recognition. The psychological impact elements involved decreased productivity, depression, anxiety and low self-esteem. Practical implications Understanding these experiences can facilitate the identification of strategies geared towards the retention of women in the workforce, and Moroccan organizations can develop and implement strategies and policies that are geared towards eliminating gender-bias in the workplace and to retaining and motivating women who remain ambitious to work in male-dominated environments and cultures. Originality/value This paper provides evidence that sufficient organizational mechanisms to support women in male-dominated environments are still unavailable, leaving them to find the proper coping mechanisms to persevere and resist.

An empirical examination of firm financial performance along dimensions of supply chain resilience

2017 ◽  
Vol 40 (3) ◽  
pp. 254-269 ◽  
Author(s):  
Xun Li ◽  
Qun Wu ◽  
Clyde W. Holsapple ◽  
Thomas Goldsby
Keyword(s):  
Supply Chain ◽  
Financial Performance ◽  
Three Dimensions ◽  
Empirical Examination ◽  
Content Type ◽  
Supply Chain Resilience ◽  
Critical Dimensions ◽  
Firm Financial Performance ◽  
Supply Chain Agility ◽  
The Impact

Purpose This paper aims to investigate the impact of three critical dimensions of supply chain resilience, supply chain preparedness, supply chain alertness and supply chain agility, all aimed at increasing a firm’s financial outcomes. In a turbulent environment, firms require resilience in their supply chains to prepare for potential changes, detect changes and respond to actual changes, thus providing superior value. Design/methodology/approach Using survey data from 77 firms, this study develops scales for preparedness, alertness and agility. It then tests their hypothesized relationships with a firm’s financial performance. Findings The results reveal that the three dimensions of supply chain resilience (i.e. preparedness, alertness and agility) significantly impact a firm’s financial performance. It is also found that supply chain preparedness, as a proactive resilience capability, has a greater influence on a firm’s financial performance than the reactive capabilities including alertness and agility, suggesting that firms should pay more attention to proactive approaches for building supply chain resilience. Originality/value First, this study develops a comparatively comprehensive definition for supply chain resilience and explores its dimensionality. Second, this study provides empirically validated instruments for the dimensions of supply chain resilience. Third, this study is one of the first to provide empirical evidence for direct impact of supply chain resilience dimensions on a firm’s financial performance.

Proprietary information and the cost of bank debt

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
HyunJun Na
Keyword(s):  
Least Square ◽  
Bank Loan ◽  
Content Type ◽  
Loan Contracts ◽  
Proprietary Information ◽  
Banking Deregulation ◽  
Interstate Banking ◽  
Innovative Firms ◽  
Bank Loan Contracts ◽  
The Impact

PurposeThis study explores how the firm’s proprietary information has an impact on the bank loan contracts. It explains the propensity of using the competitive bid option (CBO) in the syndicate loans to solicit the best bid for innovative firms and how it changes based on industry competition and the degree of innovations. This research also examines how the interstate banking deregulation (Interstate Banking and Branching Efficiency Act) in 1994 affected the private loan contracts for innovative borrowers.Design/methodology/approachThe study uses various econometric analyses. First, it uses the propensity score matching analysis to see the impact of patents on pricing terms. Second, it uses the two-stage least square (2SLS) analysis by implementing the litigation and non-NYSE variables. Finally, it studies the impact of the policy change of the Interstate Banking and Branching Efficiency Act of 1994 on the bank loan contracts.FindingsFirms with more proprietary information pays more annual facility fees but less other fees. The patents are the primary determinants of the usage of CBO in the syndicate loans to solicit the best bid. While innovative firms can have better contract conditions by the CBO, firms with more proprietary information will less likely to use the CBO option to minimize the leakage of private information and the severe monitoring from the banks. Finally, more proprietary information lowered the loan spread for firms dependent on the external capital after the interstate banking deregulation.Originality/valueThe findings of this research will help senior executives with responsibility for financing their innovative projects. In addition, these findings should prove helpful for the lawmakers to boost economies.

The effect of emotions, eWOM quality and online review sequence on consumer intention to follow advice obtained from digital services

2020 ◽  
Vol 31 (3) ◽  
pp. 465-487 ◽  
Author(s):  
Carla Ruiz-Mafe ◽  
Enrique Bigné-Alcañiz ◽  
Rafael Currás-Pérez
Keyword(s):  
Structural Model ◽  
Online Reviews ◽  
Moderating Effect ◽  
Online Information ◽  
Bias Effect ◽  
Content Type ◽  
Digital Services ◽  
Information Cues ◽  
Cognitive Information ◽  
The Impact

PurposeThis paper analyses the interrelationships between emotions, the cognitive information cues of online reviews and intention to follow the advice obtained from digital platforms, paying special attention to the moderating effect of the sequencing of review valence.Design/methodology/approachThe data were collected from 830 Spanish Tripadvisor users. In a two-step approach, a measurement model was estimated and a structural model analysed to test the proposed hypotheses. SmartPLS 3.0 software was used. The moderating effect of sequencing of reviews is tested.FindingsThe data analysis showed a bias effect of review sequence on the impact of online information cues and emotions on intention to follow advice obtained from Tripadvisor. When the online reviews of a restaurant begin with positive commentaries, their perceived persuasiveness is a stronger driver of the pleasure and arousal elicited by online reviews than when they begin with negative reviews. On the other hand, the perceived helpfulness of online reviews only triggers arousal when the user reads negative, followed by positive, comments. The impact of pleasure on intention to follow the advice provided in an online travel community is higher with positive-negative than with negative-positive sequences.Originality/valueWhile researchers have demonstrated the benefits of customer reviews on company sales, a largely uninvestigated issue is the interplay between emotions and cognitive information cues in the processing of online reviews. This is one of the first studies to examine the moderating effect of conflicting reviews on the impact of emotions and cognitive information cues on consumer intention to follow the advice obtained from digital services.

The role of innovation in building competitive advantages: an empirical investigation

2018 ◽  
Vol 21 (1) ◽  
pp. 44-69 ◽  
Author(s):  
Prodromos Chatzoglou ◽  
Dimitrios Chatzoudes
Keyword(s):  
Competitive Advantage ◽  
Conceptual Framework ◽  
Empirical Investigation ◽  
Primary Data ◽  
Empirical Literature ◽  
Competitive Advantages ◽  
Manufacturing Companies ◽  
Content Type ◽  
The Impact ◽  
Structured Questionnaire

Purpose Nowadays, innovation appears as one of the main driving forces of organisational success. Despite the above fact, its impact on the propensity of an organisation to develop and sustain a competitive advantage has not yet received sufficient empirical investigation. The purpose of this paper is to enhance the existing empirical literature by focusing on the antecedents of innovation and its impact on competitive advantage. It proposes a newly developed conceptual framework that adopts a three-step approach, highlighting areas that have rarely been simultaneously examined before. Design/methodology/approach The examination of the proposed conceptual framework was performed with the use of a newly developed structured questionnaire that was distributed to a group of Greek manufacturing companies. The questionnaire has been successfully completed by chief executive officers (CEOs) from 189 different companies. CEOs were used as key respondents due to their knowledge and experience. The reliability and the validity of the questionnaire were thoroughly examined. Empirical data were analysed using the structural equation modelling technique. The study is empirical (based on primary data), explanatory (examines cause and effect relationships), deductive (tests research hypotheses) and quantitative (includes the analysis of quantitative data collected with the use of a structured questionnaire). Findings Results indicate that knowledge management, intellectual capital, organisational capabilities and organisational culture have significant direct and indirect effects on innovation, underlining the importance of their simultaneous enhancement. Finally, the positive effect of innovation on the creation of competitive advantages is empirically validated, bridging the gap in the relevant literature and offering avenues for additional future research. Originality/value The causal relationship between innovation and competitive advantage, despite its significant theoretical support, has not been empirically validated. The present paper aspires to bridge this gap, investigating the impact of innovation on the development of competitive advantages. Moreover, the present study adopts a multidimensional approach that has never been explored in the existing innovation literature, making the examination of the proposed conceptual framework an interesting research topic.

scholarly journals Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Kun Zeng ◽  
Yibin Xu ◽  
Ge Lin ◽  
Likeng Liang ◽  
Tianyong Hao
Keyword(s):  
Clinical Trial ◽  
Ensemble Learning ◽  
Metric Learning ◽  
Classification Performance ◽  
Ensemble Model ◽  
Automated Classification ◽  
Eligibility Criteria ◽  
Data Imbalance ◽  
The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

scholarly journals Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain

2021 ◽  
Vol 11 (2) ◽  
pp. 796
Author(s):  
Alhanoof Althnian ◽  
Duaa AlSaeed ◽  
Heyam Al-Baity ◽  
Amani Samha ◽  
Alanoud Bin Dris ◽  
...  
Keyword(s):  
Empirical Evaluation ◽  
Classification Performance ◽  
Support Vector ◽  
Robust Model ◽  
Original Distribution ◽  
C4.5 Decision Tree ◽  
Dataset Size ◽  
Overall Performance ◽  
Medical Domain ◽  
The Impact

Dataset size is considered a major concern in the medical domain, where lack of data is a common occurrence. This study aims to investigate the impact of dataset size on the overall performance of supervised classification models. We examined the performance of six widely-used models in the medical field, including support vector machine (SVM), neural networks (NN), C4.5 decision tree (DT), random forest (RF), adaboost (AB), and naïve Bayes (NB) on eighteen small medical UCI datasets. We further implemented three dataset size reduction scenarios on two large datasets and analyze the performance of the models when trained on each resulting dataset with respect to accuracy, precision, recall, f-score, specificity, and area under the ROC curve (AUC). Our results indicated that the overall performance of classifiers depend on how much a dataset represents the original distribution rather than its size. Moreover, we found that the most robust model for limited medical data is AB and NB, followed by SVM, and then RF and NN, while the least robust model is DT. Furthermore, an interesting observation is that a robust machine learning model to limited dataset does not necessary imply that it provides the best performance compared to other models.

Farm wages and public works

2015 ◽  
Vol 8 (1) ◽  
pp. 19-72 ◽  
Author(s):  
Kanika Mahajan
Keyword(s):  
Theoretical Model ◽  
Wage Rate ◽  
Fixed Effects ◽  
Positive Impact ◽  
Wage Growth ◽  
State Level ◽  
Random Allocation ◽  
Farm Sector ◽  
Content Type ◽  
The Impact

Purpose – The purpose of this paper is to examine the impact of National Rural Employment Guarantee Scheme (NREGS) on farm sector wage rate. This identification strategy rests on the assumption that all districts across India would have had similar wage trends in the absence of the program. The author argues that this assumption may not be true due to non-random allocation of districts to the program’s three phases across states and different economic growth paths of the states post the implementation of NREGS. Design/methodology/approach – To control for overall macroeconomic trends, the author allows for state-level time fixed effects to capture the differences in growth trajectories across districts due to changing economic landscape in the parent-state over time. The author also estimates the expected farm sector wage growth due to the increased public work employment provision using a theoretical model. Findings – The results, contrary to the existing studies, do not find support for a significantly positive impact of NREGS treatment on private cultivation wage rate. The theoretical model also shows that an increase in public employment work days explains very little of the total growth in cultivation wage post 2004. Originality/value – This paper looks specifically at farm sector wage growth and the possible impact of NREGS on it, accounting for state specific factors in shaping farm wages. Theoretical estimates are presented to overcome econometric limitations.

Sign in / Sign up

Export Citation Format

Share Document