This paper presents a blind dual watermarking mechanism for digital color images in which invisible robust watermarks are embedded for copyright protection and fragile watermarks are embedded for image authentication. For the purpose of copyright protection, the first watermark is embedded using the discrete wavelet transform in YCbCr color space, and it can be extracted blindly without access to the host image. However, fragile watermarking is based on an improved least significant bits' replacement approach in RGB components for image authentication. The authenticity and integrity of a suspicious image can be verified blindly without the host image and the original watermark. The combination of robust and fragile watermarking makes the proposed mechanism suitable for protecting valuable original images. The experimental results indicated that the proposed watermarking mechanism can withstand various processing attacks and accurately locate the tampered area of an image.

Although the blockchain technology was first introduced through Bitcoin, extending its usage to nonfinancial applications, such as managing electronic medical records, is an attractive mission for recent research to balance the needs for increasing data privacy and the regular interaction among patients and health providers. Various systems that adopts the blockchain in managing medical records have been proposed. However, there is a need for more work to better characterize, understand and evaluate the employment of blockchain technology in the healthcare industry. In this paper, a design of blockchain based system, namely MedChain, for managing medical records is proposed. MedChain is designed to improve the current systems as it provides interoperable, secure, and effective access for medical records by patients, health care providers, and other third parties, while keeping the patients’ privacy. MedChain employs timed-based smart contracts for governing transactions and controlling accesses to electronic medical records. It adopts advanced encryption techniques for providing further security. This work proposes a new incentive mechanism that leverages the degree of health providers regarding their efforts on maintaining medical records and creating new blocks. Extensive experiments are conducted to evaluate the MedChain performance, and results indicate the efficiency of our proposal in handling a large dataset at low latency.

This study describes an effective web-based learning strategy, peer review, used by 143 computer science undergraduate students in an operating systems class at a Taiwanese university. Peer review, based on social constructivism, can be easily implemented via the authors' well-developed web-based peer review (WPR) system. Through peer review, the authors hope to form an authentic learning environment similar to an academic society in which a researcher submits a paper to a journal and receives reviews from society members before publication. Students using this learning strategy are expected to develop higher level thinking skills. The WPR system functioned in the following roles in this study: (1) an information distribution channel and management center for assignment submissions and peer review; (2) a forum for peer interaction and knowledge construction; and (3) storage for knowledge construction procedures. An evaluation of learning effects and students' perceptions about peer review during the spring of 1998 revealed that students not only performed better under peer review, but also displayed higher level thinking skills, i.e., critical thinking, planning, monitoring, and regulation. Students perceived peer review as an effective strategy that promoted their learning motivation. However, merely being an effective reviewer or an effective author may not excel in a peer review environment. The most effective individual appears to be the strategic adapter who effectively constructs a project, adjusts to peers' comments, and serves as a critical reviewer as well.

Lung sounds remain vital in clinical diagnosis as they reveal associations with pulmonary pathologies. With COVID-19 spreading across the world, it has become more pressing for medical professionals to better leverage artificial intelligence for faster and more accurate lung auscultation. This research aims to propose a feature engineering process that extracts the dedicated features for the depthwise separable convolution neural network (DS-CNN) to classify lung sounds accurately and efficiently. We extracted a total of three features for the shrunk DS-CNN model: the short-time Fourier-transformed (STFT) feature, the Mel-frequency cepstrum coefficient (MFCC) feature, and the fused features of these two. We observed that while DS-CNN models trained on either the STFT or the MFCC feature achieved an accuracy of 82.27% and 73.02%, respectively, fusing both features led to a higher accuracy of 85.74%. In addition, our method achieved 16 times higher inference speed on an edge device and only 0.45% less accuracy than RespireNet. This finding indicates that the fusion of the STFT and MFCC features and DS-CNN would be a model design for lightweight edge devices to achieve accurate AI-aided detection of lung diseases.