Studying frailty is crucial for enhancing the health and quality of life among older adults, refining healthcare delivery methods, and tackling the obstacles linked to an aging demographic. Approaches to frailty modeling often utilise simple analytic techniques rather than available advanced machine learning methods, which may be sub-optimal. There is no large-scale systematic review on applications of machine learning methods on frailty modeling. In this study we explore the use of machine learning methods to predict or classify frailty in older persons in routinely collected data. We reviewed 181 research articles, and categorised analytic methods into three categories: generalised linear models, survival models, and non-linear models. These methods have a moderate agreement with existing frailty scores and predictive validity for adverse outcomes. Limited evidence suggests that non-linear methods outperform generalised linear methods. The top-three predictor/input variables are specific diagnosis or groups of diagnoses, functional performance (e.g., ADLs), and impaired cognition. Mortality, hospital admissions and prolonged hospital stay are the mainly predicted outcomes. Most studies utilise classical machine learning methods with cross-sectional data. Longitudinal data collected by wearable sensors have been used for frailty modeling. We also discuss the opportunities to use more advanced machine learning methods with high dimensional longitudinal data for more personalised and accessible frailty tools.

The Bell-Bloom magnetometer is an instrument for measuring weak magnetic fields that are widely used in geophysical exploration, earthquake monitoring, natural disaster monitoring, and other fields. In geophysical exploration, the magnetometer can detect changes in underground materials; and in magnetic field monitoring, it can accurately detect magnetic field anomalies caused by earthquakes. Relaxation is a crucial characteristic of the Bell-Bloom magnetometer, and unclear relaxation information can hinder the design and improvement of the Bell-Bloom magnetometer, thereby affecting its potential applications. This study proposes an intelligent algorithm called relaxation time of free precession signal (RT-FPS) for measuring the relaxation time of the Bell-Bloom magnetometer parameters to address these issues. Experimental results demonstrate the algorithm’s superior convergence efficiency, fitting accuracy, and noise robustness. Moreover, the algorithm exhibits rapid convergence and high computational accuracy with a minimum sum of squared residuals$1.8386 \times 10^{-11} \text { s}^{2}$. The algorithm is robust against different types of noise and is minimally affected by data quality, with minimum errors of 0.1 ms and$0.71~\mu \text{s}$for$T_{1}$and$T_{2}$, respectively. This study can enhance the performance of the Bell-Bloom magnetometer and its potential applications in magnetic anomaly detection and geomagnetic field monitoring. Our shareable code and data sources are available athttps://github.com/baicaidezhenshi/RT-FPS-DATA.git.

The free precession style Bell–Bloom atomic magnetometer is widely used in geophysical exploration, earthquake monitoring, and natural disaster monitoring to obtain magnetic field information by measuring the Larmor frequency of the free precession signal. However, the free precession signal complexity makes it challenging to accurately acquire the Larmor frequency using conventional frequency measurement methods, limiting its applicability. This study proposes a magnetic information of free precession signal data (MI-FPD) algorithm for measuring the Larmor frequency of the free precession signal in the Bell–Bloom atomic magnetometer. The MI-FPD algorithm accurately determines the Larmor precession frequency based on free precession signal data, providing precise magnetic field information. The algorithm outperforms established algorithms regarding convergence efficiency, accuracy, and noise resistance, with an optimal determination coefficient$R^{2}$of 0.99984, an optimal range of less than 1.04 nT, and an optimal root mean square error (RMSE) of 189 pT. These results demonstrate the effectiveness of the proposed algorithm in accurately obtaining magnetic field information in the free precession style Bell–Bloom atomic magnetometer. This capability enables widespread application of the free precession style Bell–Bloom atomic magnetometer in geomagnetic monitoring and disaster early warning within the geoscience domain. The shareable data are available athttps://github.com/baicaidezhenshi/MI-FPD-DATA.git.

The encoder-decoder model is a commonly used Deep Neural Network (DNN) model for medical image segmentation. Conventional encoder-decoder models make pixel-wise predictions focusing heavily on local patterns around the pixel. This makes it challenging to give segmentation that preserves the object's shape and topology, which often requires an understanding of the global context. In this work, we propose a Fourier Coefficient Segmentation Network (FCSN)—a novel global context-aware DNN model that segments an object by learning the complex Fourier coefficients of the object's masks. The Fourier coefficients are calculated by integrating over the whole contour. Therefore, for our model to make a precise estimation of the coefficients, the model is motivated to incorporate the global context of the object, leading to a more accurate segmentation of the object's shape. This global context awareness also makes our model robust to unseen local perturbations during inference, such as additive noise or motion blur that are prevalent in medical images. We compare FCSN with other state-of-the-art global context-aware models (UNet++, DeepLabV3+, UNETR) on 5 medical image segmentation tasks, of which 3 are camera imaging datasets (ISIC_2018, RIM_CUP, RIM_DISC) and 2 are medical imaging datasets (PROSTATE, FETAL). When FCSN is compared with UNETR, FCSN attains significantly lower Hausdorff scores with 19.14 (6%), 17.42 (6%), 9.16 (14%), 11.18 (22%), and 5.98 (6%) for ISIC_2018, RIM_CUP, RIM_DISC, PROSTATE, and FETAL tasks respectively. Moreover, FCSN is lightweight by discarding the decoder module, which incurs significant computational overhead. FCSN only requires 29.7 M parameters which are 75.6 M and 9.9 M fewer parameters than UNETR and DeepLabV3+, respectively. FCSN attains inference and training speeds of 1.6 ms/img and 6.3 ms/img, which is 8× and 3× faster than UNet and UNETR. The code for FCSN is made publicly available athttps://github.com/nus-mornin-lab/FCSN.

The substitute-based recommendation is widely used in E-commerce to provide better alternatives to customers. However, existing research typically uses customer behavior signals like co-view and view-but-purchase-another to capture the substitute relationship. Despite its intuitive soundness, such an approach might ignore the functionality and characteristics of products. In this paper, we adapt substitute recommendations into language matching problem. It takes the product title description as model input to consider product functionality. We design a new transformation method to de-noise the signals derived from production data. In addition, we consider multilingual support from the engineering point of view. Our proposed end-to-end transformer-based model achieves both successes from offline and online experiments. The proposed model has been deployed in a large-scale E-commerce website for 11 marketplaces in 6 languages. Our proposed model is demonstrated to increase revenue by 19% based on an online A/B experiment.

In this paper, a two-stage method for segmenting blurry images in the presence of Poisson or multiplicative Gamma noise is proposed. The method is inspired by a previous work on two-stage segmentation and the usage of an I-divergence term to handle the noise. The first stage of our method is to find a smooth solution $u$ to a convex variant of the Mumford--Shah model where the $\ell_2$ data-fidelity term is replaced by an I-divergence term. A primal-dual algorithm is adopted to efficiently solve the minimization problem. We prove the convergence of the algorithm and the uniqueness of the solution $u$. Once $u$ is obtained, in the second stage, the segmentation is done by thresholding $u$ into different phases. The thresholds can be given by the users or can be obtained automatically by using any clustering method. In our method, we can obtain any $K$-phase segmentation ($K\geq 2$) by choosing $(K-1)$ thresholds after $u$ is found. Changing $K$ or the thresholds does not require $u$ to be recomputed. Experimental results show that our two-stage method performs better than many standard two-phase or multiphase segmentation methods for very general images, including antimass, tubular, magnetic resonance imaging, and low-light images.