Jie Hu

Online reviews of home medical devices are noisy, heterogeneous, and uneven in information density, which makes it hard to turn the voice of the customer into engineering design decisions. This study proposes and validates a review-mining framework that couples rule-based data governance with a locally deployed large language model (LLM) and complex-network analysis. Taking home oxygen concentrators as the case, we collected 25,893 raw review entries from JD.com, Taobao, and Tmall. Because overlapping collection windows made 80.4% of these rows redundant (5084 unique review texts), a four-stage pipeline combining regular-expression cleaning, domain-relevance filtering, low-value review removal, and exact-plus-prefix deduplication refined them into a 2238-review corpus (44.0% of the unique review texts). A locally hosted Qwen3-8B model then performed aspect-level extraction within nine predefined design aspects, yielding 6068 structured aspect–topic–confidence records from 2214 reviews (98.9% parsing success), and scored sentiment for 6052 unique review–aspect pairs on a [−1, 1] scale. From these records, we built a topic co-occurrence network (202 nodes and 1895 edges after low-frequency filtering) and ranked design requirements with a Composite Centrality Index (CCI; weights 0.4/0.4/0.2 over min–max-normalized degree, betweenness, and closeness). Simple Operation (CCI = 1.000) and Low Noise (0.981) dominate user preference, followed by Solid Build Quality (0.611) and Oxygen Concentration (0.574); sentiment is strongly polarized on acoustic experience (Low Noise +0.755 vs. Excessive Noise −0.560). Five checks support these findings: an LDA baseline produced substantially coarser, partly brand-dominated topics; the CCI ranking is stable under five alternative weightings (Spearman’s ρ ≥ 0.978) and across 16 combinations of network-construction thresholds; bootstrap resampling (B = 1000) places the top two topics within ranks 1–2 with 95% confidence; the leading themes replicate in a JD.com-only subnetwork; and manual validation of a stratified 450-pair sample (two blinded annotators, adjudicated gold standard) gave 87.6% aspect accuracy and 94.4% sentiment-polarity accuracy. The framework converts unstructured reviews into a quantified, traceable design-priority list for oxygen concentrator development; we interpret the resulting associations as descriptive evidence for prioritization, not as causal effects.

1. Sedentary behaviour has emerged as a pervasive occupational health concern among contemporary working populations. For most of human evolutionary history, prolonged inactivity was rare; however,...

1. Aesthetic evaluation is a core dimension of human experience, shaping how people perceive, interpret, and emotionally engage with visual stimuli (Chatterjee & Vartanian, 2014, 2016; Leder et al....

High-altitude environments characterized by low air pressure, hypoxia, and strong solar radiation have a significant impact on human thermal comfort; however, existing thermal comfort theories and evaluation models are primarily developed under low-altitude climatic conditions, and their applicability in plateau regions remains limited. With the acceleration of urbanization and the increase in residential, tourism, and occupational activities in high-altitude areas, systematically reviewing the research progress on thermal comfort in such environments is of great practical significance. This study combines systematic literature retrieval and bibliometric analysis, based on the Web of Science Core Collection and China National Knowledge Infrastructure (CNKI) databases, to analyze relevant studies published since 2001. Using CiteSpace, research hotspots, collaboration networks, and evolutionary trends are visualized. The results indicate that current research hotspots mainly focus on physiological responses and thermal adaptation mechanisms under low-pressure and hypoxic conditions, thermal comfort regulation strategies for high-altitude buildings and environments, and the applicability and modification of conventional thermal comfort models. Emerging trends include multi-environmental factor coupling analysis, adaptive model development, region-specific building design approaches, and health-oriented comprehensive evaluation frameworks. The findings provide valuable references for building thermal environment design, regional revision of thermal comfort evaluation standards, and policy-making in high-altitude regions.

As technologies become increasingly diverse and complex, Intelligent Massage Systems (IMS) are evolving from traditional mechanically executed modes toward personalized and predictive health interventions. However, the field still lacks a unified grading standard for intelligence, making it difficult to quantitatively assess a system’s overall intelligence level. To address this gap, this paper proposes a task-driven six-level (L0–L5) classification framework and constructs a Massage-Driven Task (MDT) model that decomposes the massage process into six subtasks (S1–S6). Building on this, we design a three-dimensional evaluation scheme comprising a Functional Delegation Structure (FDS), an Anomaly Perception Mechanism (APM), and a Human–Machine Interaction Boundary (HMIB), and we select eight key performance indicators to quantify IMS intelligence across the perception–decision–actuation–feedback closed loop. We then determine indicator weights via the Delphi method and the Analytic Hierarchy Process (AHP), and obtain dimension-level scores and a composite intelligence score S0 using normalization and weighted aggregation. Threshold intervals for L0–L5 are defined through equal-interval partitioning combined with expert calibration, and sensitivity is verified on representative samples using ±10% data perturbations. Results show that, within typical error ranges, the proposed grading framework yields stable classification decisions and exhibits strong robustness. The framework not only provides the first reusable quantitative basis for grading IMS intelligence but also supports product design optimization, regulatory certification, and user selection.

Wearable sensing has gained considerable attention for its effectiveness in gesture recognition, offering convenient, natural, and efficient interaction in human-machine systems. However, practical deployment in resource-constrained settings remains challenging due to data-intensive acquisition demands, high training overhead, and limited computing capacity—factors that hinder large-scale applicability. To address these issues, we proposed a lightweight model for fine-grained gesture recognition under sparse-site sensing conditions. Experiments were conducted on a custom multimodal dataset comprising 15 static and 18 dynamic gestures. Modal assessments across diverse gesture types revealed the complementarity of wrist surface electromyography and kinematic signals, validating the effectiveness of multimodal fusion. In addition, we leveraged transfer learning to improve model generalization to unseen subjects while reducing data acquisition burden and computational overhead. To achieve the Accuracy-Cost trade-off, we formulated an objective function and validated its generalizability across diverse sensing configurations, hardware platforms, and standardization strategies. Experimental results showed that an average accuracy sacrifice of 3.8% can yield substantial resource savings, with an average reduction of 87.8% in data collection and fine-tuning time, facilitating resource-efficient allocation of gesture recognition systems in Internet of Things (IoT) environments. Finally, an online gesture recognition prototype was developed and evaluated, demonstrating the method’s robustness and practical utility in cross-domain transfer scenarios. These findings provide both theoretical and practical foundations for deploying gesture recognition-based rehabilitation systems within IoT settings.