Cerebrovascular accidents (CVA) cause a range of impairments in coordination, such as a spectrum of walking impairments ranging from mild gait imbalance to complete loss of mobility. Patients with CVA need personalized approaches tailored to their degree of walking impairment for effective rehabilitation. This paper aims to evaluate the validity of using various machine learning (ML) and deep learning (DL) classification models (support vector machine, Decision Tree, Perceptron, Light Gradient Boosting Machine, AutoGluon, SuperTML, and TabNet) for automated classification of walking assistant devices for CVA patients. We reviewed a total of 383 CVA patients’ (1623 observations) prescription data for eight different walking assistant devices from five hospitals. Among the classification models, the advanced tree-based classification models (LightGBM and tree models in AutoGluon) achieved classification results of over $90\%$ accuracy, recall, precision, and F1-score. In particular, AutoGluon not only presented the highest predictive performance (almost $92\%$ in accuracy, recall, precision, and F1-score, and $86.8\%$ in balanced accuracy) but also demonstrated that the classification performances of the tree-based models were higher than that of the other models on its leaderboard. Therefore, we believe that tree-based classification models have potential as practical diagnosis tools for medical rehabilitation.

In this study, neural networks are utilized to develop a stock price prediction model based on the constituent stocks of the China Securities Index 300 (CSI300). This research investigates various prediction methods and models through experiments, comparing their advantages, limitations, and applicability to improve the accuracy and efficiency of stock price forecasting. Furthermore, we analyze the characteristics of CSI300 constituent stocks and explore the relationships among key variables and influential factors, enhancing our understanding of stock market behavior. Additionally, we explore the impact of the attention mechanism on stock price prediction, assess its contribution to enhancing predictive performance, and propose an optimized CSI300 stock prediction model based on neural networks.

We present a differentially private actor and its eligibility trace in an actor-critic approach, wherein an actor takes actions directly interacting with an environment; however, the critic estimates only the state values that are obtained through bootstrapping. In other words, the actor reflects the more detailed information about the sequence of taken actions on its parameter than the critic. Moreover, their corresponding eligibility traces have the same properties. Therefore, it is necessary to preserve the privacy of an actor and its eligibility trace while training on private or sensitive data. In this paper, we confirm the applicability of differential privacy methods to the actors updated using the policy gradient algorithm and discuss the advantages of such an approach with regard to differentially private critic learning. In addition, we measured the cosine similarity between the differentially private applied eligibility trace and the non-differentially private eligibility trace to analyze whether their anonymity is appropriately protected in the differentially private actor or the critic. We conducted the experiments considering two synthetic examples imitating real-world problems in medical and autonomous navigation domains, and the results confirmed the feasibility of the proposed method.

The random walk hypothesis (RWH) formalizes the inherent difficulty of predicting stock returns by characterizing successive price changes as largely unpredictable.Recent deep learning (DL) methods have sought to improve stock-return prediction by learning temporal patterns and cross-sectional dependencies from historical market data.However, these methods treat predictability as an empirical learning problem without explicitly reformulating the RWH as a constructive principle for modeling next-day returns.We propose Adaptive Signed Correlation TimeMixer (ASCTM), a stock-return prediction model grounded in a reformulation of the RWH in which next-day returns comprise historical information states and stochastic noise rather than a fixed drift term and noise alone.ASCTM first applies a Multi-head Adaptive Exponential Smoothing module that uses causal, decay-aware coefficients to construct denoised information states.It then applies a Signed Correlation-aware Multi-scale TimeMixing module to model signed cross-stock correlations over temporal patches at multiple scales and derive return-relevant representations.Experiments on three benchmark datasets show that ASCTM outperforms state-of-the-art baselines across predictive and trading metrics.The main contribution is to recast the RWH, conventionally used to explain stock-return unpredictability, as a modeling principle and translate this interpretation into a DL architecture.