Articles in this Volume

Research Article Open Access
Balancing Affordability and Accuracy: A Hardware Selection Guide for Wearable Fall Detection Systems
Unintentional falls among older adults represent a severe global health concern, necessitating reliable, automated wearable Fall Detection Systems (FDS). However, developing practical wearable solutions requires navigating intricate engineering trade-offs among diagnostic accuracy, power consumption, memory footprint, and software development overhead. This paper presents a structured hardware selection guide evaluating three representative embedded design paradigms: low-cost threshold logic on 8-bit microcontrollers (Profile A), balanced classical machine learning on standard 32-bit platforms (Profile B), and compressed on-chip TinyML neural networks on edge-capable microcontrollers (Profile C). Comparative analysis reveals that while threshold methods achieve multi-week battery longevity at sub-$12 costs, they suffer from high false-alarm rates during dynamic daily activities. Conversely, TinyML architectures deliver superior classification accuracy (98%) on raw kinematic streams, but introduce steep memory quantization barriers, complex toolchains, and shorter battery recharge intervals. Classical machine learning emerges as the optimal design compromise for most developers, achieving robust diagnostic discrimination (95% sensitivity and specificity) with manageable computational demands at $15-$25. Finally, this review evaluates sensor placement ergonomics, addresses pervasive demographic bias in youth-simulated training datasets, and delivers a practical hardware selection framework for student researchers and independent developers.
Show more
Read Article PDF
Cite
Research Article Open Access
Multi-agent Reinforcement Learning for Coordinated Emergency Building Sweeps
Article thumbnail
We develop a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) framework for coordinating emergency responders during building sweeps. The problem is formulated as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) that captures building topology, occupant vulnerability, dynamic hazards, and partial observability. In the six-room office baseline, MADDPG reaches a 134-second sweep time after 5,000 episodes, within 6.3% of the 126-second theoretical optimum and outperforming PPO and DQN. Extensions to a two-story school and a U-shaped warehouse achieve 120 seconds with five responders and 105 seconds with four responders, respectively, with diminishing returns beyond these staffing levels. Under communication failure, coverage remains about 98% while sweep time rises 15–20%; reduced staffing triggers workload redistribution, and dynamic hazards cause threatened areas to be prioritized. Occupancy sensing, mesh networks, and environmental sensing are projected to reduce sweep time by 35–50%. Sensitivity analysis confirms robust performance across realistic parameter ranges.
Show more
Read Article PDF
Cite
Research Article Open Access
Multi-Robot Collaborative SLAM in Warehouses: A Review
With the rapid growth of e-commerce, Automated Guided Vehicles (AGVs) are increasingly deployed in intelligent warehouses, where Simultaneous Localization and Mapping (SLAM) provides the core localization capability. Warehouses differ from domestic or outdoor scenarios in four respects: highly structured regular rack layouts, quasi-static conditions with dynamic goods movement, GPS-denied weak-network communication, and perceptual degradation caused by long corridors and repetitive textures. This paper reviews recent progress in multi-robot collaborative SLAM tailored for warehouse scenarios. It analyzes warehouse-specific environmental characteristics, discusses single-robot SLAM solutions under weak-network constraints, examines anti-drift localization methods for degraded scenes, and compares multi-robot collaborative architectures and map fusion techniques. The review also identifies a gap between academic algorithms and industrial practice, and points to future directions including semantic-geometric fusion, edge computing, and large-model empowered intelligent warehouses.
Show more
Read Article PDF
Cite
Research Article Open Access
Pricing Audits in Verifier-Guided Test-Time Scaling: Proxy Reliability and Budgeted Candidate Selection
Article thumbnail
In verifier-guided test-time scaling, a cheap proxy ranks candidates and an audit obtains the target score of the selected output. The best split of a budget between generation and audits depends on proxy reliability among still-competitive candidates. We study this reliability through decision-granularity correlation: the proxy–target association within a prompt's top-ranked shortlist. We connect classical range restriction to an audit-efficiency threshold for linear proxy-assisted estimation, then evaluate candidate selection under a shared generation-and-audit budget. PickScore–HPS correlation falls from 0.84 within full diffusion prompt pools to 0.32 in their top 10%, and an API judge agrees with the target on 53.4% of near-ties. On text, an approximate correlation diagnostic accepts GSM8K and abstains on ARC. Across five diffusion models, we separate ranking gains from allocation gains. On 80 new Stable Diffusion XL prompts, reallocating a random-audit policy improves the composite preference score by 0.01196, while screening retains only 0.00076 over tuned random auditing (95% interval includes zero); higher audit prices favor screening.
Show more
Read Article PDF
Cite
Research Article Open Access
Traditional Relational Databases vs. NoSQL Databases: A Review of Differences and Application Scenarios
Article thumbnail
Since Codd proposed the relational model in 1970, relational databases have been widely adopted in enterprise data management because of their structured model, standardized SQL, and ACID transactions. With the growth of the Internet, cloud computing, and the Internet of Things, data volume, types, and business requirements have become increasingly diverse. Traditional relational databases therefore face new technical requirements in large-scale distributed, high-concurrency, and frequently changing schema scenarios. NoSQL databases have emerged with document, graph, key-value, and column-family models and distributed architectures. Using MongoDB and Neo4j as examples, this paper compares relational and NoSQL databases in technical characteristics and application scenarios, and examines e-commerce, social networks, financial risk control, and enterprise production management. It argues that the two paradigms are complementary rather than substitutive, and that database selection should balance data structure, transactional requirements, access patterns, and scalability. This study provides references for database selection, system architecture design, and data management optimization.
Show more
Read Article PDF
Cite
Research Article Open Access
Preparation of Vanadium Pentoxide Materials and Their Supercapacitor Performance
Article thumbnail
The large-scale development of renewable energy is still advancing, and the efficient and stable electrochemical energy storage technology has been pushed to a more important position, which has gradually become an indispensable key pillar in energy transformation. Supercapacitors rely on high power density and long cycle life, so there has been a lot of attention in the field of energy storage ; but it has a limited energy density, which would restrict a wider range of applications. Based on this background, this paper takes vanadium pentoxide (V 2 O 5 )-based electrode materials as the core. Firstly, the energy storage mechanism of supercapacitors is systematically reviewed, and the preparation methods and morphology control strategies of V 2 O 5 and its composites are also reviewed. Looking further down, pure-phase V 2 O 5 has the disadvantages of poor conductivity and unstable structure, which cannot be ignored. In view of them, this paper summarizes the modification methods such as carbon compositing, porous structure construction, heteroatom doping, and ternary synergistic effect, and also summarizes the mechanism of these methods to improve electrochemical performance. In addition, this study further examines the inherent limitations of the above modification strategies in practical applications, that is, after putting these strategies into real scenarios, what are the limitations.Among these limitations, there are not only the trade-off of carbon content, but also the lattice distortion caused by doping, and the volumetric capacitance loss caused by porous structure. Focusing on these problems, this work first distinguishes the intrinsic pseudocapacitance from the diffusion-controlled energy storage mechanism, clarifies the role of oxygen vacancies in regulating ion diffusion kinetics, and reviews the differences in the existing literature on dopant selection, optimal doping concentration and vanadium dissolution suppression mechanism. In practice, low-loading thin-film electrodes in the laboratory often have excellent performance. However, once the actual devices based on high-loading thick electrodes are corresponding, the stringent requirements are completely different, and the significant gap between the two is thus highlighted. On the basis of these analyses, this paper proposes a feasible and targeted research direction. The purpose is to provide practical guidance for the design of high-energy-density and long-cycle-life supercapacitor electrodes suitable for practical applications.
Show more
Read Article PDF
Cite
Research Article Open Access
Research on the Diagnosis and Dynamic Intervention of Interaction Design Efficiency Bottlenecks Based on User Experience Metrics
Article thumbnail
A delayed review tells a design manager that work has stalled, but says little about why. The same difficulty arises with repeated requirement changes and clarification requests from developers after delivery. This paper uses user experience measurement to investigate such constraints during interaction design. Interview material, analyzed through grounded theory, yields four bottleneck categories: cognitive, process-related, collaborative, and tool-related. Observable indicators are assigned to these categories, and constraint theory informs the selection of responses. The resulting MLIE model repeats monitoring, identification, intervention, and evaluation as conditions change. Its application in an internet company's design team covered three intervention rounds. The procedure gives managers a way to examine evidence for a suspected constraint and then assess the response, reducing reliance on experience alone.
Show more
Read Article PDF
Cite
Research Article Open Access
AI-Assisted Adaptive Interface Design for Lowering Entry Barriers in Real-Time Strategy Games
Article thumbnail
Real-time strategy (RTS) games require players to make strategic decisions while executing numerous commands. This paper presents a qualitative synthesis of recent academic research on game accessibility, human–Artificial Intelligence (AI) assistance, interface design, and community content. Six design directions are examined against accessibility, strategic depth, long-term engagement, and practical value. A layered control model is proposed with beginner, traditional, and competitive profiles sharing the same strategic rules. Routine automation requires player approval and remains visible and reversible, while tutoring uses information available to the player. Cooperative practice, hybrid interactions, and community content are considered as supporting design contexts. A conceptual mission walkthrough examines how the model could separate repeated operations from consequential decisions. The analysis yields design requirements and testable hypotheses; no prototype or new participant experiment was conducted. Controlled player studies, including unassisted transfer tasks and return-session measures, are needed to determine whether the model lowers entry barriers while preserving strategic depth.
Show more
Read Article PDF
Cite
Research Article Open Access
Progress and Trends of Deep Learning in CT Image Lesion Area Detection
Deep learning has achieved some good results in the field of medical image analysis to date, but most existing models for CT lesion detection have been developed for a single organ and lack a cross-site universal framework; in addition, their detection performance is highly dependent on specific clinical conditions. The following is an overview of the current stage, development and application cases of deep learning detection methods for four types of CT images: pulmonary nodules, brain lesions, liver lesions and bone lesions. The problems in Model Design and how to solve them are presented in this paper. Based on the comparison of the quantitative results and technical attributes of the main models, it can be observed that the general direction of development is moving towards three-dimensional representations, multiple tasks, integration of clinical knowledge, and so on. At the same time, the main bottlenecks in current research have also been identified in the three areas of data, clinical diagnosis and algorithms; high annotation costs, poor interpretability, insufficient use of three-dimensional information and weak generalisation ability are among them. This paper points out that there are deficiencies in assessing the strengths and weaknesses of methods that are not tied to particular situations. According to the kind of anatomical place and clinical conditions, a specific detection plan will be chosen. In the future, semi-supervised learning, multi-task integrated models and interpretable AI will be employed to increase the accuracy and clinical applicability of this field.
Show more
Read Article PDF
Cite
Research Article Open Access
Cross-Game Generalization and Context Dependence of Cybersickness Prediction Using Consumer-Grade HMD Motion Data
Article thumbnail
Cybersickness remains a persistent barrier to sustained virtual reality (VR) use. Consumer-grade head-mounted displays (HMDs) provide motion data that can support symptom prediction, but most prior models have been evaluated within a single game or data environment, leaving cross-game generalization uncertain. This study reanalyzes HMD motion trajectories and Simulator Sickness Questionnaire (SSQ) responses from 60 complete participants across four commercial VR games in the publicly available Questset dataset. Fifteen session-level motion features were extracted, symptom change was represented as ΔSSQ, and Ridge Regression and Random Forest were evaluated under within-game and cross-game conditions. Cross-game error increased most clearly when Beat Saber was the target game under both models, whereas other transfer directions showed smaller penalties. Several feature–symptom correlation directions also changed across games, although none of the 60 exploratory correlations remained significant after False Discovery Rate (FDR) correction. These results suggest that HMD-based cybersickness prediction may be context-dependent and should not be assumed to transfer automatically to unseen VR content; larger within-subject, multi-game studies are needed to confirm this pattern.
Show more
Read Article PDF
Cite