A Dual-Discriminator Generative Adversarial Network for Anomaly Detection.

Multivariate time series anomaly detection has shown potential in various fields, such as finance, aerospace, and security. The fuzzy definition of data anomalies, the complexity of data patterns, and the scarcity of abnormal data samples pose significant challenges to anomaly detection. Researchers have extensively employed autoencoders (AEs) and generative adversarial networks (GANs) in studying time series anomaly detection methods.

Research advance of 3D printing for articular cartilage regeneration.

Articular cartilage lesion frequently leads to dysfunction and the development of degenerative diseases, posing a significant public health challenge due to the limited self-healing capacity of cartilage tissue. Current surgical treatments, including marrow stimulation techniques and osteochondral autografts/allografts, have limited efficacy or have significant drawbacks, highlighting the urgent need for alternative strategies. Advances in 3D printing for cartilage regeneration have shown promising potential in creating cartilage-mimicking constructs, thereby opening new possibilities for cartilage repair.

Meta-analysis of factors influencing anterior knee pain after total knee arthroplasty.

Background: Total knee arthroplasty (TKA) is a mature procedure recommended for correcting knee osteoarthritis deformity, relieving pain, and restoring normal biomechanics. Although TKA is a successful and cost-effective procedure, patient dissatisfaction is as high as 50%. Knee pain after TKA is a significant cause of patient dissatisfaction; the most common location for residual pain is the anterior region.

Black-box attacks on dynamic graphs via adversarial topology perturbations.

Research and analysis of attacks on dynamic graph is beneficial for information systems to investigate vulnerabilities and strength abilities in resisting malicious attacks. Existing attacks on dynamic graphs mainly focus on rewiring original graph structures, which are often infeasible in real-world scenarios. To address this issue, we adopt a novel strategy by injecting both fake nodes and links to attack dynamic graphs.