Search results

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

General Data Protection Regulation (GDPR) of the European Union (EU) was passed to protect data privacy. Though the GDPR intended to address issues related to data privacy in the EU, it created an extra-territorial effect through Articles 3, 45 and 46. Extra-territorial effect refers to the application or the effect of local laws and regulations in another country. Lawmakers around the globe passed or intensified their efforts to pass laws to have personal data privacy covered so that they meet the adequacy requirement under Articles 45–46 of GDPR while providing comprehensive legislation locally. This study aims to analyze the Malaysian and Saudi Arabian legislation on health data privacy and their adequacy in meeting GDPR data privacy protection requirements.

The research used a systematic literature review, legal content analysis and comparative analysis to critically analyze the health data protection in Malaysia and Saudi Arabia in comparison with GDPR and to see the adequacy of health data protection that could meet the requirement of EU data transfer requirement.

The finding suggested that the private sector is better regulated in Malaysia than the public sector. Saudi Arabia has some general laws to cover health data privacy in both public and private sector organizations until the newly passed data protection law is implemented in 2024. The finding also suggested that the Personal Data Protection Act 2010 of Malaysia and the Personal Data Protection Law 2022 of Saudi Arabia could be considered “adequate” under GDPR.

The research would be able to identify the key principles that could identify the adequacy of the laws about health data in Malaysia and Saudi Arabia as there is a dearth of literature in this area. This will help to propose suggestions to improve the laws concerning health data protection so that various stakeholders can benefit from it.

In 2020, an outbreak of Salmonella Stanley linked to imported dried wood ear mushrooms affected 55 individuals in the United States of America. These mushrooms, commonly used in Asian cuisine, require processing, like rehydration and cutting, before serving. The US Centres for Disease Control and Prevention advise food preparers to use boiling water for rehydration to inactivate vegetative bacterial pathogens. Little is known about how food handlers prepare this ethnic ingredient and which handling procedures could enable Salmonella proliferation.

This study used content analysis to investigate handling practices for dried wood ear mushrooms as demonstrated in YouTube recipe videos and to identify food safety implications during handling of the product. A total of 125 Chinese- and English-language YouTube videos were analysed.

Major steps in handling procedures were identified, including rehydration, cutting/tearing and blanching. Around 62% of the videos failed to specify the water temperature for rehydration. Only three videos specified a water temperature of 100 °C for rehydrating the mushrooms, and 36% of the videos did not specify the soaking duration. Only one video showed handwashing, cleaning and sanitising of surfaces when handling the dried wood ear mushrooms.

This study found that most YouTube videos provided vague and inconsistent descriptions of the rehydration procedure, including water temperature and soaking duration. Food preparers were advised to use boiling water for rehydration to inactivate vegetative bacterial pathogens. However, boiling water alone is insufficient to inactivate all bacterial spores. Extended periods of soaking and storage could be of concern for spore germination and bacterial growth. More validation studies need to be conducted to provide guidance on how to safely handle the mushrooms.

This study will make a distinctive contribution to the field of food safety by being the first to investigate the handling procedure of a unique ethnic food ingredient, dried wood ear mushrooms, which has been linked to a previous outbreak and multiple recalls in the United States of America. The valuable data collected from this study can help target food handling education as well as influence future microbial validation study design and risk assessment.

This paper aims to clarify the resistance degree of group road logistics to flood disaster resilience. The paper measures the resilience of group road logistics by establishing network structure model. The purpose of this study is to improve the resilience of road log.

This paper adopts Delphi method to collect data, interviews mainly flood management experts and supply chain risk management experts, and then analyzes the data through the network structure model combined with interpretative structure model (ISM) and analytical network process (ANP).

The results show that flood frequency and drainage systems are the main factors affecting the resilience of road transport logistics in urban areas. These research results provide useful guidance for the effective planning and design of urban road construction and infrastructure.

However, the main factors affecting the resilience of road transport logistics are likely to change with the development of factors such as climate, economy and environment. Therefore, in future work, the authors' research will focus on the further application of this evaluation method.

The results show that the impact of flooding on the four dimensions of road logistics resilience varies. This shows that in deciding what intervention measures are to be taken to improve the resilience of the road network to flooding, various measures need to be considered.

This paper provides a more scientific analysis of the risk management ability of the road network in the face of floods. In addition, it also provides a useful reference for urban road planners.

This paper addresses a clear need to study how to build models to improve the resilience of road logistics in flood risk.