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.

A clickbait is a deceptive headline designed to boost ad revenue without presenting closely relevant content. There are numerous negative repercussions of clickbait, such as causing viewers to feel tricked and unhappy, causing long-term confusion, and even attracting cyber criminals. Automatic detection algorithms for clickbait have been developed to address this issue. The fact that there is only one semantic representation for the same term and a limited dataset in Chinese is a need for the existing technologies for detecting clickbait. This study aims to solve the limitations of automated clickbait detection in the Chinese dataset.

This study combines both to train the model to capture the probable relationship between clickbait news headlines and news content. In addition, part-of-speech elements are used to generate the most appropriate semantic representation for clickbait detection, improving clickbait detection performance.

This research successfully compiled a dataset containing up to 20,896 Chinese clickbait news articles. This collection contains news headlines, articles, categories and supplementary metadata. The suggested context-aware clickbait detection (CA-CD) model outperforms existing clickbait detection approaches on many criteria, demonstrating the proposed strategy's efficacy.

The originality of this study resides in the newly compiled Chinese clickbait dataset and contextual semantic representation-based clickbait detection approach employing transfer learning. This method can modify the semantic representation of each word based on context and assist the model in more precisely interpreting the original meaning of news articles.

The purpose of this study is to identify the main perspectives and trends in educational data mining (EDM) in the e-learning environment from a managerial perspective.

This paper proposes a systematic literature review to identify the main perspectives and trends in EDM in the e-learning environment from a managerial perspective. The study domain of this review is restricted by the educational concepts of e-learning and management. The search for bibliographic material considered articles published in journals and papers published in conferences from 1994 to 2023, totaling 30 years of research in EDM.

From this review, it was observed that managers have been concerned about the effectiveness of the platform used by students as it contains the entire learning process and all the interactions performed, which enable the generation of information. From the data collected on these platforms, there are improvements and inferences that can be made about the actions of educators and human tutors (or automatic tutoring systems), curricular optimization or changes related to course content, proposal of evaluation criteria and also increase the understanding of different learning styles.

This review was conducted from the perspective of the manager, who is responsible for the direction of an institution of higher education, to assist the administration in creating strategies for the use of data mining to improve the learning process. To the best of the authors’ knowledge, this review is original because other contributions do not focus on the manager.

The purpose of this study is to develop a domain independent, cost-effective, time-saving and semi-automated ontology generation framework that could extract taxonomic concepts from unstructured text corpus. In the human disease domain, ontologies are found to be extremely useful for managing the diversity of technical expressions in favour of information retrieval objectives. The boundaries of these domains are expanding so fast that it is essential to continuously develop new ontologies or upgrade available ones.

This paper proposes a semi-automated approach that extracts entities/relations via text mining of scientific publications. Text mining-based ontology (TmbOnt)-named code is generated to assist a user in capturing, processing and establishing ontology elements. This code takes a pile of unstructured text files as input and projects them into high-valued entities or relations as output. As a semi-automated approach, a user supervises the process, filters meaningful predecessor/successor phrases and finalizes the demanded ontology-taxonomy. To verify the practical capabilities of the scheme, a case study was performed to drive glaucoma ontology-taxonomy. For this purpose, text files containing 10,000 records were collected from PubMed.

The proposed approach processed over 3.8 million tokenized terms of those records and yielded the resultant glaucoma ontology-taxonomy. Compared with two famous disease ontologies, TmbOnt-driven taxonomy demonstrated a 60%–100% coverage ratio against famous medical thesauruses and ontology taxonomies, such as Human Disease Ontology, Medical Subject Headings and National Cancer Institute Thesaurus, with an average of 70% additional terms recommended for ontology development.

According to the literature, the proposed scheme demonstrated novel capability in expanding the ontology-taxonomy structure with a semi-automated text mining approach, aiming for future fully-automated approaches.

Building information modeling (BIM) is a striking development in the architecture, engineering and construction (AEC) industry, which provides in-depth information on different stages of the building lifecycle. Real estate valuation, as a fully interconnected field with the AEC industry, can benefit from 3D technical achievements in BIM technologies. Some studies have attempted to use BIM for real estate valuation procedures. However, there is still a limited understanding of appropriate mechanisms to utilize BIM for valuation purposes and the consequent impact that BIM can have on decreasing the existing uncertainties in the valuation methods. Therefore, the paper aims to analyze the literature on BIM for real estate valuation practices.

This paper presents a systematic review to analyze existing utilizations of BIM for real estate valuation practices, discovers the challenges, limitations and gaps of the current applications and presents potential domains for future investigations. Research was conducted on the Web of Science, Scopus and Google Scholar databases to find relevant references that could contribute to the study. A total of 52 publications including journal papers, conference papers and proceedings, book chapters and PhD and master's theses were identified and thoroughly reviewed. There was no limitation on the starting date of research, but the end date was May 2022.

Four domains of application have been identified: (1) developing machine learning-based valuation models using the variables that could directly be captured through BIM and industry foundation classes (IFC) data instances of building objects and their attributes; (2) evaluating the capacity of 3D factors extractable from BIM and 3D GIS in increasing the accuracy of existing valuation models; (3) employing BIM for accurate estimation of components of cost approach-based valuation practices; and (4) extraction of useful visual features for real estate valuation from BIM representations instead of 2D images through deep learning and computer vision.

This paper contributes to research efforts on utilization of 3D modeling in real estate valuation practices. In this regard, this paper presents a broad overview of the current applications of BIM for valuation procedures and provides potential ways forward for future investigations.

The aim of this paper is to explore the possibility of using the Define-Measure-Analyze-Improve-Control (DMAIC) cycle, process mining (PM) and multi-criteria decision methods in an integrated way so that these three elements combined result in a methodology called the Agile DMAIC cycle, which brings more agility and reliability in the execution of the Six Sigma process.

The approach taken by the authors in this study was to analyze the studies arising from this union of concepts and to focus on using PM tools where appropriate to accelerate the DMAIC cycle by improving the first two steps, and to test using the AHP as a decision-making process, to bring more excellent reliability in the definition of indicators.

It was indicated that there was a gain with acquiring indicators and process maps generated by PM. And through the AHP, there was a greater accuracy in determining the importance of the indicators.

Through the results and findings of this study, more organizations can understand the potential of integrating Six Sigma and PM. It was just developed for the first two steps of the DMAIC cycle, and it is also a replicable method for any Six Sigma project where data acquisition through mining is possible.

The authors develop a fully applicable and understandable methodology which can be replicated in other settings and expanded in future research.

This paper aims to introduce a model using a digital twin concept in a cold heading manufacturing and develop a digital visual management (VM) system using Lean overall equipment effectiveness (OEE) tool to enhance the process performance and establish Fourth Industrial Revolution (I4.0) platform in small and medium enterprises (SMEs).

This work utilised plan, do, check, act Lean methodology to create a digital twin of each machine in a smart manufacturing facility by taking the Lean tool OEE and digitally transforming it in the context of I4.0. To demonstrate the effectiveness of process digitisation, a case study was carried out at a manufacturing department to provide the data to the model and later validate synergy between Lean and I4.0 platform.

The OEE parameter can be increased by 10% using a proposed digital twin model with the introduction of a Level 0 into VM platform to clearly define the purpose of each data point gathered further replicate in projects across the value stream.

The findings suggest that researchers should look beyond conversion of stored data into visualisations and predictive analytics to improve the model connectivity. The development of strong big data analytics capabilities in SMEs can be achieved by shortening the time between data gathering and impact on the model performance.

The novelty of this study is the application of OEE Lean tool in the smart manufacturing sector to allow SME organisations to introduce digitalisation on the back of structured and streamlined principles with well-defined end goals to reach the optimal OEE.

Both technological and human-centric perspectives need to be acknowledged when combining lean production practices and Industry 4.0 (I4.0) technologies. This study aims to explore and explain how lean production practices and I4.0 technologies may coexist to enhance the human-centric perspective of manufacturing operations in the era of Industry 5.0 (I5.0).

The research approach is an explorative and longitudinal case study. The qualitative data collection encompasses respondents from different job functions and organizational levels to cover the entire organization. In total, 18 interviews with 19 interviewees and five focus groups with a total of 25 participants are included.

Identified challenges bring forth that manufacturing organizations must have the ability to see beyond lean production philosophy and I4.0 to meet the demand for a human-centric perspective in socially sustainable manufacturing in the era of Industry 5.0.

The study suggests that while lean production practices and I4.0 practices may be considered separately, they need to be integrated as complementary approaches. This underscores the complexity of managing simultaneous organizational changes and new digital initiatives.

The research presented illuminates the elusive phenomena comprising the combined aspects of a human-centric perspective, specifically bringing forth implications for the co-existence of lean production practices and I4.0 technologies, in the transformation towards I5.0.

The study contributes to new avenues of research within the field of socially sustainable manufacturing. The study provides an in-depth analysis of the human-centric perspective when transforming organizations towards Industry 5.0.

Studies show that building information modelling (BIM) technology can improve construction productivity regarding the design, construction and maintenance of a project life cycle in the 21st century. Revit has been identified as a frequently used tool for delivering BIM in the built environment. Studies about BIM technology via Revit are scarce in training middle-level workforce higher education institutions. Thus, this study aims to investigate the relevance of BIM technology and offer measures to promote digitalisation in Nigeria’s built environment polytechnic undergraduates via Revit.

Given the unexplored nature of training the middle-level workforce in Nigeria, 37 semi-structured virtual interviews were conducted across Nigeria, and saturation was achieved. The participants were knowledgeable about construction-related BIM. The researchers used a thematic analysis for the collected data and honed them with secondary sources.

Improved visualisation of design, effective and efficient work productivity, automatic design and quantification, improved database management and collaboration and data storage in the centrally coordinated model, among others, emerged as BIM’s benefits. BIM technology via Revit is challenging, especially in Nigeria’s polytechnic education curriculum. The 24 perceived issues were grouped into government/regulatory agencies-related, polytechnic management-related and polytechnic undergraduate students-related hindrances in Nigeria’s built environment.

This study is limited to BIM implications for Nigeria’s built environment polytechnic undergraduates.

This study contributes to the literature paucity in attempting to uncover perceived issues hindering the implementation of BIM technology via Revit in training Nigeria’s built environment polytechnic undergraduates via a qualitative approach.

Achieving swift and even flow of cargo through the border, the ultimate objective of cross-border logistics (CBL) requires the close coordination and collaboration of a multitude of stakeholders, as well as optimally configured systems. To achieve and sustain competitiveness in a dynamic international trade environment, CBL processes must undergo periodic analysis, improvement and optimization. This study aims to develop a modelling framework to capture CBL processes for analysis and improvement.

Relying on the extant literature, a meta-model is developed incorporating significant perspectives required to model CBL processes. Popular process modelling notations are evaluated against the meta-model and their ease of comprehension is also evaluated. The selected notation through evalution is augmented with addendums for a comprehensive depiction of CBL processes.

The capacity of role activity diagrams (RADs) to depict all perspectives, including interactions in a single diagram, makes them particularly suitable for modelling CBL processes. RADs have been complemented with physical flow diagrams and methods to capture temporal dimension, enabling a comprehensive view of CBL processes laying the foundation for insightful analysis.

The meta-model developed in this paper paves the way to develop an analysis framework which requires further research.

The lack of well-accepted modelling notations for studying CBL processes prompts researchers to search and adapt different formalisms. This study has filled this gap by proposing a comprehensive modelling framework able to capture CBL processes at different granularities in rich detail. Not only does the developed meta-model aid in selecting the notation, it is also useful in analysing the constituent elements of CBL processes.