Persona-based, empathetic approaches can foster sustainable long-term user-agent engagement in aging-in-place contexts. We present PersonaBot, a persona-driven persuasive agent built on a Dual-Persona framework that constructs user personas and generates culturally diverse, gender- and personality-varied agent personas, pairing users with preferred agent personas and adapting them over time. In an eight-week field deployment (8 participants; 1005 participant messages; 2432 agent messages), PersonaBot significantly increased perceived empathy, slowed engagement decline relative to a non-persona baseline, and elicited more elaborative interactions. Effectiveness varied with users’ technological self-efficacy, autonomy preferences, cultural identity, and social patterns, underscoring heterogeneous persona needs. Contrary to our initial assumptions, participants sometimes chose cross-cultural agents for perceived professionalism (over demographic similarity) and favored teacher-like personas balancing authority and warmth. Many framed the agent as a co-pilot rather than a caregiver replacement and engaged selectively, indicating agent personas should respect autonomy and invite—rather than demand—interaction.

Deep neural networks have recently been applied to long-term time series forecasting (LTSF) tasks, aiming to capture dynamic temporal features from historical data for more accurate predictions. However, time series data inevitably contain noise, influencing prediction accuracy. Recent denoising studies suggest that high-frequency components in the frequency domain are the source of noise, and these studies use filters to remove them. While these filters effectively suppress noise, they also unintentionally discard valuable high-frequency information. To tackle this problem, we propose a Wavelet-Enhanced Long Short-Term Memory (WE-LSTM). Specifically, we introduce an Enhanced Spectral Denoising module that combines Fourier Transform and Discrete Wavelet Transform (DWT) for joint denoising. This module achieves effective denoising through adaptive wavelet decomposition with multiple wavelet bases. Additionally, this work presents an Enhanced LSTM module, which integrates exponential gating units into LSTM to capture complex patterns and enhance LTSF capabilities. Extensive experiments on seven real-world datasets with varying noise levels demonstrate that the WE-LSTM architecture achieves performance comparable to current state-of-the-art models in LTSF tasks, validating the superiority of our model.

Knowledge graph embedding, which aims at learning the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently. However, most knowledge graph embedding methods focus on the structural relationships in fixed triples while ignoring the temporal information. Currently, existing time-aware graph embedding methods only focus on the factual plausibility, while ignoring the temporal smoothness, which models the interactions between a fact and its contexts, and thus can capture fine-granularity temporal relationships. This leads to the limited performance of embedding related applications. To solve this problem, this article presents a Robustly Time-aware Graph Embedding (RTGE) method by incorporating temporal smoothness. Two major innovations of our article are presented here. At first, RTGE integrates a measure of temporal smoothness in the learning process of the time-aware graph embedding. Via the proposed additional smoothing factor, RTGE can preserve both structural information and evolutionary patterns of a given graph. Secondly, RTGE provides a general task-oriented negative sampling strategy associated with temporally aware information, which further improves the adaptive ability of the proposed algorithm and plays an essential role in obtaining superior performance in various tasks. Extensive experiments conducted on multiple benchmark tasks show that RTGE can increase performance in entity/relationship/temporal scoping prediction tasks.

Activity recognition is a key problem in multi-sensor systems. In this work, we introduce Computational Assumption-based Argumentation, an argumentation approach that seamlessly combines sensor data processing with high-level inference. Our method gives classification results comparable to machine learning based approaches with reduced training time while also giving explanations.

Activity recognition system is the key part in E-Health field. Traditional system needs more labeled training data to meet higher recognition accuracy. This means more calibration effort and time consumption. In this paper, with collaboration of heterogeneous multimodal sensors like a microphone, a camera and an accelerometer etc, we propose to design and implement a system to reduce the required amount of labeled data as well as achieve even better performance than traditional systems. The system consists of three phases: collaborative data collection, collaborative classifier training and collaborative classifier combination. The experimental results validate that with only 9% labeled data, our system can obtain as high accuracy as other systems which use 100% unimodal labeled data.

The geographically weighted regression (GWR) has been widely applied to many practical fields for exploring spatial non-stationarity of a regression relationship. However, this method is inherently not robust to outliers due to the least squares criterion in the process of estimation. Outliers commonly exist in data sets and may lead to a distorted estimate of the underlying regression relationship. Using the least absolute deviation criterion, we propose two robust scenarios of the GWR approaches to handle outliers. One is based on the basic GWR and the other is based on the local linear GWR (LGWR). The proposed methods can automatically reduce the impact of outliers on the estimates of the regression coefficients and can be easily implemented with modern computer software for dealing with the linear programming problems. We then conduct simulations to assess the performance of the proposed methods and the results demonstrate that the methods are quite robust to outliers and can retrieve the underlying coefficient surfaces satisfactorily even though the data are seriously contaminated or contain severe outliers.