Publications by authors named "K O Kou"
This paper presents cutting-edge advancements in exponential synchronization and encryption techniques, focusing on Quaternion-Valued Artificial Neural Networks (QVANNs) that incorporate two-sided coefficients. The study introduces a novel approach that harnesses the Cayley-Dickson representation method to simplify the complex equations inherent in QVANNs, thereby enhancing computational efficiency by exploiting complex number properties. The study employs the Lyapunov theorem to craft a resilient control system, showcasing its exponential synchronization by skillfully regulating the Lyapunov function and its derivatives.
View Article and Find Full Text PDFArticle Synopsis
- Gliomas are aggressive brain tumors with poor patient prognosis, highlighting the need for new biomarkers and treatments.
- Researchers employed machine learning techniques to identify key genes involved in glioma prognosis, focusing on those related to angiogenesis and epithelial-mesenchymal transition (EMT).
- The study found that CALU is a significant gene linked to glioma progression, suggesting it could serve as a new prognostic marker and that inhibiting CALU may slow down tumor growth.
This paper develops a neurodynamic model for distributed nonconvex-constrained optimization. In the distributed constrained optimization model, the objective function and inequality constraints do not need to be convex, and equality constraints do not need to be affine. A Hestenes-Powell augmented Lagrangian function for handling the nonconvexity is established, and a neurodynamic system is developed based on this.
View Article and Find Full Text PDFArticle Synopsis
- Induction chemotherapy (IC) doesn’t always improve survival for patients with locoregionally advanced nasopharyngeal carcinoma (LANPC), and traditional methods of choosing IC often lead to poor treatment decisions.
- This study developed a new system called projected individual treatment effect (PITE) to better personalize IC recommendations, analyzing data from 1,213 patients using imaging and clinical data to predict individual survival chances.
- The results showed that PITE could effectively categorize patients into three groups, leading to better outcomes: IC significantly improved survival for those who should receive it, had no effect on some, and even worsened survival for others where it wasn't suitable.
Article Synopsis
- Breast cancer is the most common cancer among women globally, and while urban-rural differences in outcomes exist, there's limited knowledge about variations within those areas.
- A study in Queensland, Australia, analyzed data from nearly 59,000 women diagnosed with breast cancer from 2000-2019 to evaluate various outcomes, using advanced statistical models to assess small geographic areas.
- The findings revealed higher breast cancer incidence in urban regions, with an overall 92% five-year survival rate, but little geographic variation in diagnosis or treatment outcomes, suggesting effective practices could be applied to improve care for other cancer types.