In recent years, due to the rapid development of information techniques and network technologies, more and more medical documents have been replaced by electronic files for sharing and transmitting in real time. However, medical data transmitted over public communication channels may suffer from security attacks and privacy threats. Blockchain technology has been gotten many attentions in different areas due to its unique properties such as anonymity, verifiability, immutability and decentralization. In order to secure patient privacy and provide more personal healthcare services, in this paper, we propose a data aggregation scheme based on Blockchain technology for medical environments. Moreover, in order to implement remote medical monitoring, we design a group authentication mechanism for multiple authorized users (such as patient, doctors, caregivers, family and friends) to freely access patient’s personal health records. The authorized group members in a group will agree on a group session key and use it to protect patient’s sensitive information. In case of a new member joins the medical group or an old member leaves the medical group, the group session key needs to be updated at any time. Finally, the electronic medical system will become more secure, reliable and useful by our proposed scheme.

In recent years, due to the rise in the population and aging, the prevalence of neurological diseases is also increasing year by year. Among these patients with Parkinson’s disease, stroke, cerebral palsy, and other neurological symptoms, dysarthria often appears. If these dysarthria patients are not quickly detected and treated, it is easy to cause difficulties in disease course management. When the symptoms worsen, they can also affect the patient’s psychology and physiology. Most of the past studies on dysarthria detection used machine learning or deep learning models as classification models. This study proposes an integrated CNN-GRU model with convolutional neural networks and gated recurrent units to detect dysarthria. The experimental results show that the CNN-GRU model proposed in this study has the highest accuracy of 98.38%, which is superior to other research models.

With the rapid development of e-commerce services, online retail has evolved from multi-channel to omni-channel in order to provide customers with more services. However, reverse logistics services (returns and exchanges) have become the target of many fraudulent activities, causing a lot of economic losses for many online retail companies. The current challenge of the traditional countermeasure is it requires a lot of manpower and training resources. In this study, we propose ESPRES, a system that adopts blockchain technology to prevent fraudulent behavior in the process of returns and exchanges with the smart contract and multi-attribute decision-support method to help consumers choose a suitable payment program. A practical implication of this study is that by adopting blockchain technology, a great amount of manpower used on determining whether each return or exchange is fraudulent can be reduced since merchants can check the product ownership. In addition, due to the fact that the footprint of goods cannot be forged, it can also prevent counterfeit or parallel imports of goods.

This study constructs a theory of eco-innovation in circular agri-business. Although previous studies have discussed eco-innovation in circular agri-business, they did not address eco-innovation from the perspective of a closed-loop sustainable supply chain. Hence, this study applied the fuzzy TOPSIS method to conduct the analysis and determine the interrelationship between eco-innovation and the closed-loop concept. The results are consistent with the theory and a significant improvement in terms of the decisive attributes. The findings suggest that improving water management, relationships with suppliers, knowledge sharing, environmental management systems, and new product and service development are the most effective and efficient ways to build eco-innovation in circular agri-business. The managerial and theoretical implications are discussed.

Motivation: Changes in the normal rhythm of a human heart may result in different cardiac arrhythmias, which may be immediately fatal or cause irreparable damage to the heart sustained over long periods of time. Therefore, the ability to automatically identify arrhythmias from ECG recordings is important for clinical diagnosis and treatment. In this article, classification by using associative Petri net (APN) for personalized ECG-arrhythmia-pattern identification is proposed for the first time in literature. Results: A rule-based classification model and reasoning algorithm of APN are created for ECG arrhythmias classification. The performance evaluation using MIT-BIH arrhythmia database shows that our approach compares well with other reported studies. Contact:shihdh@yuntech.edu.tw