Search results

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

The development of information technologies has led to a considerable transformation in human resource management from conventional or commonly known as personnel management to modern one. Data mining technology, which has been widely used in several applications, including those that function on the web, includes clustering algorithms as a key component. Web intelligence is a recent academic field that calls for sophisticated analytics and machine learning techniques to facilitate information discovery, particularly on the web. Human resource data gathered from the web are typically enormous, highly complex, dynamic, and unstructured. Traditional clustering methods need to be upgraded because they are ineffective. Standard clustering algorithms are enhanced and expanded with optimization capabilities to address this difficulty by swarm intelligence, a subset of nature-inspired computing. We collect the initial raw human resource data and preprocess the data wherein data cleaning, data normalization, and data integration takes place. The proposed K-C-means-data driven cuckoo bat optimization algorithm (KCM-DCBOA) is used for clustering of the human resource data. The feature extraction is done using principal component analysis (PCA) and the classification of human resource data is done using support vector machine (SVM). Other approaches from the literature were contrasted with the suggested approach. According to the experimental findings, the suggested technique has extremely promising features in terms of the quality of clustering and execution time.

This study aims to identify an automated machine learning algorithm with high accuracy that sport practitioners can use to identify the specific factors for predicting Major League Baseball (MLB) attendance. Furthermore, by predicting spectators for each league (American League and National League) and division in MLB, the authors will identify the specific factors that increase accuracy, discuss them and provide implications for marketing strategies for academics and practitioners in sport.

This study used six years of daily MLB game data (2014–2019). All data were collected as predictors, such as game performance, weather and unemployment rate. Also, the attendance rate was obtained as an observation variable. The Random Forest, Lasso regression models and XGBoost were used to build the prediction model, and the analysis was conducted using Python 3.7.

The RMSE value was 0.14, and the R2 was 0.62 as a consequence of fine-tuning the tuning parameters of the XGBoost model, which had the best performance in forecasting the attendance rate. The most influential variables in the model are “Rank” of 0.247 and “Day of the week”, “Home team” and “Day/Night game” were shown as influential variables in order. The result was shown that the “Unemployment rate”, as a macroeconomic factor, has a value of 0.06 and weather factors were a total value of 0.147.

This research highlights unemployment rate as a determinant affecting MLB game attendance rates. Beyond contextual elements such as climate, the findings of this study underscore the significance of economic factors, particularly unemployment rates, necessitating further investigation into these factors to gain a more comprehensive understanding of game attendance.

The discontinuous usage behavior of short video social media presents an ongoing challenge to platform development. The purpose of this study is to investigate the antecedents of intentions to short media discontinuous usage.

This study adopts a Cognition–Affection–Conation (CAC) framework to analyze short video social media discontinuous intention on the basis of cognitive dissonance theory (CDT) and self-efficacy theory. The empirical evaluation of the research model was conducted using SmartPLS 2.0 and was based on questionnaire data obtained from participants in China.

The results show information overload and user addiction have a significant positive association with cognitive dissonance, which is, in turn, found to significantly impact discontinuous usage intention. Self-efficacy moderates the relationships between information overload, user addiction, cognitive dissonance and discontinuous usage.

This study contributes to the understanding of the factors that influence short video discontinuous usage intention and it achieves this by engaging from a CDT perspective and by applying Self-Efficacy Theory. Theoretical implications for future short video platform research, as well as practical suggestions for short video platform operators and users, are also discussed.

Reducing the number of generated mutants by clustering redundant mutants, reducing the execution time by decreasing the number of generated mutants and reducing the cost of mutation testing are the main goals of this study.

In this study, a method is suggested to identify and prone the redundant mutants. In the method, first, the program source code is analyzed by the developed parser to filter out the effectless instructions; then the remaining instructions are mutated by the standard mutation operators. The single-line mutants are partially executed by the developed instruction evaluator. Next, a clustering method is used to group the single-line mutants with the same results. There is only one complete run per cluster.

The results of experiments on the Java benchmarks indicate that the proposed method causes a 53.51 per cent reduction in the number of mutants and a 57.64 per cent time reduction compared to similar experiments in the MuJava and MuClipse tools.

Developing a classifier that takes the source code of the program and classifies the programs' instructions into effective and effectless classes using a dependency graph; filtering out the effectless instructions reduces the total number of mutants generated; Developing and implementing an instruction parser and instruction-level mutant generator for Java programs; the mutant generator takes instruction in the original program as a string and generates its single-line mutants based on the standard mutation operators in MuJava; Developing a stack-based evaluator that takes an instruction (original or mutant) and the test data and evaluates its result without executing the whole program.

Bearings play a critical role in the reliable operation of induction machines, and their failure can lead to significant operational challenges and downtime. Detecting and diagnosing these defects is imperative to ensure the longevity of induction machines and preventing costly downtime. The purpose of this paper is to develop a novel approach for diagnosis of bearing faults in induction machine.

To identify the different fault states of the bearing with accurately and efficiently in this paper, the original bearing vibration signal is first decomposed into several intrinsic mode functions (IMFs) using variational mode decomposition (VMD). The IMFs that contain more noise information are selected using the Pearson correlation coefficient. Subsequently, discrete wavelet transform (DWT) is used to filter the noisy IMFs. Second, the composite multiscale weighted permutation entropy (CMWPE) of each component is calculated to form the features vector. Finally, the features vector is reduced using the locality-sensitive discriminant analysis algorithm, to be fed into the support vector machine model for training and classification.

The obtained results showed the ability of the VMD_DWT algorithm to reduce the noise of raw vibration signals. It also demonstrated that the proposed method can effectively extract different fault features from vibration signals.

This study suggested a new VMD_DWT method to reduce the noise of the bearing vibration signal. The proposed approach for bearing fault diagnosis of induction machine based on VMD-DWT and CMWPE is highly effective. Its effectiveness has been verified using experimental data.

Automation of detecting cracked surfaces on buildings or in any industrially manufactured products is emerging nowadays. Detection of the cracked surface is a challenging task for inspectors. Image-based automatic inspection of cracks can be very effective when compared to human eye inspection. With the advancement in deep learning techniques, by utilizing these methods the authors can create automation of work in a particular sector of various industries.

In this study, an upgraded convolutional neural network-based crack detection method has been proposed. The dataset consists of 3,886 images which include cracked and non-cracked images. Further, these data have been split into training and validation data. To inspect the cracks more accurately, data augmentation was performed on the dataset, and regularization techniques have been utilized to reduce the overfitting problems. In this work, VGG19, Xception and Inception V3, along with Resnet50 V2 CNN architectures to train the data.

A comparison between the trained models has been performed and from the obtained results, Xception performs better than other algorithms with 99.54% test accuracy. The results show detecting cracked regions and firm non-cracked regions is very efficient by the Xception algorithm.

The proposed method can be way better back to an automatic inspection of cracks in buildings with different design patterns such as decorated historical monuments.

This study aims to explore the different effects of inter-community group networks and intra-community group networks on group innovation.

The authors used a pooled panel dataset of 12,111 self-organizing innovation groups in 463 game product creative workshop communities from Steam support to test the hypothesis. The pooled ordinary least squares (OLS) model is used for analyzing the data.

The results show that network constraint is negatively associated with the innovation performance of online groups. The average path length of the inter-community group network negatively moderates the relationship between network constraint and group innovation, while the average path length of the intra-community group network positively moderates the relationship between network constraint and group innovation. In addition, both the network density of inter-community group networks and intra-community group networks can negatively moderate the negative relationship between network constraint and group innovation.

The findings of this study suggest that network structural characteristics of inter-community networks and intra-community networks have different effects on online groups’ product innovation, and therefore, group members should consider their inter- and intra-community connections when choosing other groups to form a collaborative innovation relationship.

Because family businesses are highly complex enterprises, researchers need appropriate theoretical and methodological tools to study them. The neoconfigurational perspective and its accompanying method, qualitative comparative analysis, are particularly well suited to phenomena characterized by complex causality, but their uptake in family business research has been slow and fragmented. To remedy this, the authors highlight their unique ability to address research questions for which other approaches are not well suited and discuss how they might be applied to family business phenomena.

The authors introduce the core tenets of the neoconfigurational perspective and how its set-theoretic epistemology differs from traditional approaches to theorizing and analysis. The authors then use a dataset of family firms to present a primer on conducting qualitative comparative analysis and interpreting the results.

The authors find that family firm resources can be combined in multiple ways to affect business survival, suggesting that resources are substitutable and complementary. The authors discuss how the unique features of the neoconfigurational approach, namely equifinality, conjunctural causation and causal asymmetry, can be fruitfully applied to break new ground in scholarly understanding of family businesses.

This article allows family business researchers to apply the neoconfigurational approach without first having to consult multiple and disparate sources often written for other disciplines. This article explicates how to leverage the theoretical and empirical advantages of the neoconfigurational approach in the context of family businesses, supporting a more widespread adoption of the neoconfigurational perspective in family business research.

This paper aims to demonstrate how the new generative artificial intelligence (AI) tool ChatGPT changes knowledge work for individuals and what are the implications of this change for companies.

Based on 22 interviews from informants across different industries, the authors conducted an inductive analysis on the use and utility of ChatGPT in knowledge work. Based on this initial analysis, they discovered different ways in which ChatGPT either augments human agency, makes it redundant or lacks capability in that regard.

The authors develop a 2 × 2 framework of algorithmic assistance, which demonstrates four ways in which ChatGPT (and generative AI in general) interacts with knowledge workers, depending on the usefulness of ChatGPT in particular tasks and the type of the task (routine vs creative).

Based on the insights from the interviews, the authors propose a set of actionable questions for individual knowledge workers and companies from four viewpoints: skills and capabilities; team structure and workflow coordination; culture and mindset; and business model innovation.

To the best of the authors’ knowledge, this study is among the first to identify and analyze the use of ChatGPT by knowledge workers across different industries.