Forecasting short-term traffic flow has been a critical topic in transportation research for decades, which aims to facilitate dynamic traffic control proactively by monitoring the present traffic and foreseeing its immediate future. In this paper, we focus on forecasting short-term passenger flow at subway stations by utilizing the data collected through an automatic fare collection (AFC) system along with various external factors, where passenger flow refers to the volume of arrivals at stations during a given period of time. Along this line, we propose a data-driven three-stage framework for short-term passenger flow forecasting, consisting of traffic data profiling, feature extraction, and predictive modeling. We investigate the effect of temporal and spatial features as well as external weather influence on passenger flow forecasting. Various forecasting models, including the time series model auto-regressive integrated moving average, linear regression, and support vector regression, are employed for evaluating the performance of the proposed framework. Moreover, using a real data set collected from the Shenzhen AFC system, we conduct extensive experiments for methods validation, feature evaluation, and data resolution demonstration.

Falls have been recognized as the major cause of accidental death and injury in people aged 65 and above. The timely prediction of fall risks can help identify older adults prone to falls and implement preventive interventions. Recent advancements in wearable sensor-based technologies and big data analysis have spurred the development of accurate, affordable, and easy-to-use approaches to fall risk assessment. The objective of this study was to systematically assess the current state of wearable sensor-based technologies for fall risk assessment among community-dwelling older adults. Twenty-five of 614 identified research articles were included in this review. A comprehensive comparison was conducted to evaluate these approaches from several perspectives. In general, these approaches provide an accurate and effective surrogate for fall risk assessment. The accuracy of fall risk prediction can be influenced by various factors such as sensor location, sensor type, features utilized, and data processing and modeling techniques. Features constructed from the raw signals are essential for predictive model development. However, more investigations are needed to identify distinct, clinically interpretable features and develop a general framework for fall risk assessment based on the integration of sensor technologies and data modeling.

Rapid advances in information and sensor technology have led to the development of tools and methods for personalized health monitoring. These techniques support timely and efficient healthcare services by tracking the vital signs, detecting physiological changes and predicting health risks. In this paper, we propose an integrated system to monitor the wellness condition of elderly. This system is conceptualized to provide a computer-aided decision support for clinicians and community nurses, by means of which they can easily monitor and analyze an elderly’s overall activity and vital signs using a wearable wellness tacker and an all-in-one satiation based monitoring device, offering an efficient solution with a reduction in time cost and human error. We design a data-preparing scheme for acquiring data and processing data from multiple monitoring devices, and propose a personalized scheme for forecasting the elderly’s one-day-ahead wellness condition via data integration and statistical learning. We conduct a pilot study at a nursing home in Hong Kong to demonstrate the implementation of the proposed system. The proposed forecasting scheme is validated by the collected data.

Background: Reminiscence therapy (RT) is a commonly used nonpharmaceutical treatment for cognitive impairment. Artifacts or conversations are used in RT to recall individuals’ memories and past experiences. Virtual reality (VR) has increasingly been used as an assistive technology during RT. However, the effects of VR-based RT (VR-RT) methods remain unclear, and insights into the related benefits and challenges are urgently needed. Objective: The study aims to systematically review the effects of VR-RTs for older adults with cognitive impairment. Methods: Seven databases (MEDLINE, Academic Search Premier, CINAHL, Web of Science, PubMed, the Cochrane Central Register of Controlled Trials, and ScienceDirect) were searched to identify relevant articles published from inception to August 10, 2023. Peer-reviewed publications that assessed the effect of VR-RTs (ie, using virtual clues to evoke participants’ memories or past experiences) on cognitive-related outcomes were included. Two independent researchers conducted the literature search, review, and data extraction processes. A narrative synthesis approach was used to analyze the extracted data. Results: Of the 537 identified articles, 22 were ultimately included in the data analysis. The results revealed that VR-RTs could maintain cognitive status (4/4, 100%) and reduce anxiety (2/2, 100%) in older adults with cognitive impairment. Nevertheless, one study found a cognitive improvement after VR-RTs, whereas cognitive degradation was observed at a 3- to 6-month follow-up measure. Around 88% (7/8) of the included studies indicated that VR-RTs improved memory; however, the evidence regarding the beneficial effects of VR-RTs was limited in improving quality of life (1/4, 25%) and reducing apathy (0/2, 0%) and depression (1/3, 33%). The results indicated that VR-RTs are safe, engaging, acceptable, and satisfying for older adults with cognitive impairment. In VR scenarios, personalized stimulus materials related to the users’ youth experiences were more effective for treating cognitive impairment than other stimulus materials. Conclusions: The results of this systematic review demonstrate the potential benefits of VR-RT for older adults with cognitive impairment, especially in improving emotion and memory and maintaining cognitive status. VR-RT is also safe and enjoyable for older adults. However, due to the trial heterogeneity of included studies, we can only provide qualitative results instead of performing meta-analysis to quantify the effect size of VR-RTs. Thus, more randomized controlled trials are required to examine the designs and effects of VR-RTs for groups of older adults with specific needs.

Finding low-dimensional representation of high-dimensional data sets is an important task in various applications. The fact that data sets often contain clusters embedded in different subspaces poses barrier to this task. Driven by the need in methods that enable clustering and finding each cluster's intrinsic subspace simultaneously, in this paper, we propose a regularized Gaussian mixture model (GMM) for clustering. Despite the advantages of GMM, such as its probabilistic interpretation and robustness against observation noise, traditional maximum-likelihood estimation for GMMs shows disappointing performance in high-dimensional setting. The proposed regularization method finds low-dimensional representations of the component covariance matrices, resulting in better estimation of local feature correlations. The regularization problem can be incorporated in the expectation maximization algorithm for maximizing the likelihood function of a GMM, with the M-step modified to incorporate the regularization. The M-step involves a determinant maximization problem, which can be solved efficiently. The performance of the proposed method is demonstrated using several simulated data sets. We also illustrate the potential value of the proposed method in applications using four real data sets.