Search results

The first purpose is to assess the quality of containerized multimodal export and the second is to develop and demonstrate the design of a service network with quality approach.

The article used the structural equation model to develop a model to measure the quality of multimodal transportation for containerized exports and finalized the model with an alternative approach. The evolutionary algorithm had been used to design a service network based on quality.

Provided factors affecting quality of multimodal transportation and reverse to one hypothesis, the construct variation in cost, time shape and quantity did not affect the quality of multimodal transportation for containerized exports. The model without variation construct was finalized by exploring causality.

This research had scope till container loading onto the vessel and assessed the quality for containerized cargo only, and second research purpose is limited by assumed values of fitness function and the limited number of nodes, in service network design demonstration.

This research provided a tool to measure the quality of multimodal transportation for containerized exports and demonstrated the field application of the model developed in service network design. This approach included all factors applicable across the container movement. The integrated approach of the article provided an organized method to design a service network for containerized exports.

This work provided the tool to assess the quality of multimodal transportation for containerized exports and developed an approach to design a service network of multimodal transportation based on quality. This approach has considered the factors of multimodal transportation comprehensively in contrast to the optimization approaches based on operation research techniques.

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.

With the rapid development of short videos in China, the public has become accustomed to using short videos to express their opinions. This paper aims to solve problems such as how to represent the features of different modalities and achieve effective cross-modal feature fusion when analyzing the multi-modal sentiment of Chinese short videos (CSVs).

This paper aims to propose a sentiment analysis model MSCNN-CPL-CAFF using multi-scale convolutional neural network and cross attention fusion mechanism to analyze the CSVs. The audio-visual and textual data of CSVs themed on “COVID-19, catering industry” are collected from CSV platform Douyin first, and then a comparative analysis is conducted with advanced baseline models.

The sample number of the weak negative and neutral sentiment is the largest, and the sample number of the positive and weak positive sentiment is relatively small, accounting for only about 11% of the total samples. The MSCNN-CPL-CAFF model has achieved the Acc-2, Acc-3 and F1 score of 85.01%, 74.16 and 84.84%, respectively, which outperforms the highest value of baseline methods in accuracy and achieves competitive computation speed.

This research offers some implications regarding the impact of COVID-19 on catering industry in China by focusing on multi-modal sentiment of CSVs. The methodology can be utilized to analyze the opinions of the general public on social media platform and to categorize them accordingly.

This paper presents a novel deep-learning multimodal sentiment analysis model, which provides a new perspective for public opinion research on the short video platform.

COVID-19 continues to spread, and cause increasing deaths. Physicians diagnose COVID-19 using not only real-time polymerase chain reaction but also the computed tomography (CT) and chest x-ray (CXR) modalities, depending on the stage of infection. However, with so many patients and so few doctors, it has become difficult to keep abreast of the disease. Deep learning models have been developed in order to assist in this respect, and vision transformers are currently state-of-the-art methods, but most techniques currently focus only on one modality (CXR).

This work aims to leverage the benefits of both CT and CXR to improve COVID-19 diagnosis. This paper studies the differences between using convolutional MobileNetV2, ViT DeiT and Swin Transformer models when training from scratch and pretraining on the MedNIST medical dataset rather than the ImageNet dataset of natural images. The comparison is made by reporting six performance metrics, the Scott–Knott Effect Size Difference, Wilcoxon statistical test and the Borda Count method. We also use the Grad-CAM algorithm to study the model's interpretability. Finally, the model's robustness is tested by evaluating it on Gaussian noised images.

Although pretrained MobileNetV2 was the best model in terms of performance, the best model in terms of performance, interpretability, and robustness to noise is the trained from scratch Swin Transformer using the CXR (accuracy = 93.21 per cent) and CT (accuracy = 94.14 per cent) modalities.

Models compared are pretrained on MedNIST and leverage both the CT and CXR modalities.

The conflict in Russian Ukraine is a problem for the world economy because it hinders growth and drives up inflation when it is already high. The trade route between India and Russia is also impacted by the Russia-Ukraine crisis. This study aims to compile the most recent data on how the present global economic crisis is affecting it, with particular emphasis on the Indian economy.

This research develops a mathematical forecasting model to evaluate how the Russia-Ukraine crisis would affect the Indian economy when perturbations are applied to the major transport sectors. Input-output modeling (I-O model) and interval programing (IP) are the two precise methods used in the model. The inoperability I-O model developed by Wassily Leontief examines how disruption in one sector of the economy spreads to the other. To capture data uncertainties, IP has been added to IIM.

This study uses the forecasted inoperability value to analyze how the sectors are interconnected. Economic loss is used to determine the lowest and highest priority sectors due to the Russia-Ukraine crisis on the Indian economy. Furthermore, this study provides a decision-support conclusion for studying the sectors under various scenarios.

In future studies, other sectors could be added to study the Russian-Ukrainian crises’ effects on the Indian economy. Perturbation is only applied to transport sectors and could be applied to other sectors for studying the effects of the crisis. The availability of incomplete data is a significant concern in this study.

Russia-Ukraine conflict is a significant blow to the global economy and affects the global transportation network. This study discusses the application of the IIM-IP model to the Russia-Ukraine conflict. It also forecasts the values to examine how the crisis affected the Indian economy. This study uses a variety of scenarios to create a decision-support conclusion table that aids decision-makers in analyzing the Indian economy’s lowest and most affected sectors as a result of the crisis.

This paper aims to provide an overview of key definitions related to ChatGPT, a public tool developed by OpenAI, and its underlying technology, Generative Pretrained Transformer (GPT).

This paper includes an interview with ChatGPT on its potential impact on academia and libraries. The interview discusses the benefits of ChatGPT such as improving search and discovery, reference and information services; cataloging and metadata generation; and content creation, as well as the ethical considerations that need to be taken into account, such as privacy and bias.

ChatGPT has considerable power to advance academia and librarianship in both anxiety-provoking and exciting new ways. However, it is important to consider how to use this technology responsibly and ethically, and to uncover how we, as professionals, can work alongside this technology to improve our work, rather than to abuse it or allow it to abuse us in the race to create new scholarly knowledge and educate future professionals.

This paper discusses the history and technology of GPT, including its generative pretrained transformer model, its ability to perform a wide range of language-based tasks and how ChatGPT uses this technology to function as a sophisticated chatbot.

This study proposes a description of the civil society diplomacy that emerged in the early solutions found to fight the COVID-19 crisis. The author analyses this concept as the intersection of the social movements of individuals and civil society organisations' and international health care. Its purpose is to determine the international structure of the connective actors aimed to find concrete solutions against COVID-19 and to characterize the communication visible on Twitter towards this civil society engagement.

Based on a data-driven approach, the author collected a large dataset of tweets from Switzerland between March and June 2020 and conducted a computational text analysis methodology.

The results showed who the participants were, provided a visualisation of the digital networking process between engaged and mentioned participants at national and international levels, and determined the emotions that emerged during three event phases.

The study reveals that features of connective social care actions and strategic collective communication can illustrate civil society diplomacy for a shared cause in times of health crisis.

Inland shipping has been extensively recognised as a sustainable, efficient and good alternative to rail and road modes of transportation. In recent years, various authorities and academic researchers have advocated shifting from road to other sustainable modes like inland waterway transport (IWT) or rail transport. Academic work on modernisation and technological innovations to enhance the effectiveness and efficiency of waterborne transportation is becoming apparent as a growing body of literature caused by the need to achieve a sustainable transport system. Thus, it became apparent to explore the research trends on IWT.

A systematic and structured literature review study was employed in this paper to identify the challenges and concepts in modernising inland waterways for freight transportation. The review analysed 94 articles published in 54 journals from six well-known databases between 2010 and 2022.

The key findings of this review are that despite various challenges confronting the sector, there have been successful cases of technological advancement in the industry. The main interest among scholars is improving technical and economic performance, digitalisation, and safety and environmental issues. The review revealed that most of the literature is fragmented despite growing interest from practitioners and academic scholars. Academic research to address the strategic objectives, including strengthening competitiveness (shipbuilding, hydrodynamics, incorporating artificial intelligence into the decision-making process, adopting blockchain technology to ensure transparency and security in the transactions, new technologies for fleets adaptation to climate change, more effective handling, maintenance and rehabilitation technologies), matching growth and changing trade patterns (intermodal solutions and new logistics approaches) are major causes of concerns.

By employing the approach of reviewing previously available literature on IWT review papers, this review complements the existing body of literature in the field of IWT by providing in a single paper a consolidation of recent state-of-the-art research on technological developments and challenges for inland waterways freight transport in the intermodal supply chain that can act as a single resource to keep researchers up to date with the most recent advancements in research in the domain of inland waterway freight transport. Additionally, this review identified gaps in the literature that may inspire new research themes in the field of IWT.

This study aims to reduce data bias during human activity and increase the accuracy of activity recognition.

A convolutional neural network and a bidirectional long short-term memory model are used to automatically capture feature information of time series from raw sensor data and use a self-attention mechanism to learn select potential relationships of essential time points. The proposed model has been evaluated on six publicly available data sets and verified that the performance is significantly improved by combining the self-attentive mechanism with deep convolutional networks and recursive layers.

The proposed method significantly improves accuracy over the state-of-the-art method between different data sets, demonstrating the superiority of the proposed method in intelligent sensor systems.

Using deep learning frameworks, especially activity recognition using self-attention mechanisms, greatly improves recognition accuracy.

Currently, China’s manufacturing industry chain still faces the danger of chain breakage due to the persistent “lack of technology” issue. The definition and detection of key nodes in the industry chain are significant to the enhancement of the stability of the industry chain. Therefore, detecting the key nodes in the manufacturing industry chain is necessary.

A complex network based on the links amongst listed manufacturing enterprises is built, and the authors analyse the network’s basic characteristics and vulnerability, taking into account the impact of scientific and technological innovation on the stability of the industry chain.

It is found that the high structural characteristic of midstream nodes in the naval architecture and marine engineering equipment industry chain determines their importance to stability, and the key status of upstream nodes is reflected in the weakness of technological innovation. The upstream nodes should focus on improving their independent innovation and R&D capability, whilst the midstream nodes should maintain a close supply–demand cooperation relationship.

The key node detection model for industry chain stability is constructed by considering various factors from the perspective of network and technological innovation. Empirical study is conducted to verify effectiveness of proposed method.