Scholarlink

<p>The convergence of Wireless Internet of Things (WIoT) and wearable healthcare technologies has enabled pervasive monitoring of individuals with Autism Spectrum Disorder (ASD), facilitating continuous collection of behavioral and sensory data such as motion, temperature, and skin conductance in real-world environments. However, challenges such as user mobility, heterogeneous data urgency, and energy-constrained sensor nodes hinder reliable and efficient data acquisition. Existing cluster-based routing frameworks often suffer from uneven energy consumption and communication bottlenecks near gateway nodes, compromising both network longevity and data fidelity. To overcome these limitations, this paper introduces the Autistic Children Sensory-Behavior Quality and Effectiveness Information Collection (ACSBQEIC) framework, a novel WIoT-enabled solution tailored for dynamic WBAN environments, particularly in community school settings. The proposed system integrates three core innovations: (i) an unequal clustering mechanism that adaptively organizes nodes based on gateway proximity, residual energy, and ASD-related behavioral urgency; (ii) a multi-objective cluster head (CH) and hop node selection strategy incorporating mobility awareness and MAC-level contention minimization; and (iii) a reinforced routing optimization model utilizing Reinforcement Learning to ensure energy-efficient, low-latency, and high-reliability data delivery. Comparative simulation analysis demonstrates that ACSBQEIC significantly outperforms recent benchmarks, including High-Energy and Reliable Sensory-Behavior Data Collection (HERSBDC), Hybrid WBAN (HyWBAN), and Throughput and Priority Optimization Strategy (TPOS), achieving marked improvements in delivery ratio, network lifetime, and end-to-end latency. These results confirm the framework’s potential to support quality-of-service (QoS)-driven ASD health monitoring and real-time intervention in mobile WIoT environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Energy- and behavior-aware sensory data collection for ASD monitoring over IoT using unequal clustering and reinforcement learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月3日

查看全文
  • Kavitha Gangaraju,
  • Yogisha Hullukere Kadegowda,
  • Sangeeta Sangani

摘要

The convergence of Wireless Internet of Things (WIoT) and wearable healthcare technologies has enabled pervasive monitoring of individuals with Autism Spectrum Disorder (ASD), facilitating continuous collection of behavioral and sensory data such as motion, temperature, and skin conductance in real-world environments. However, challenges such as user mobility, heterogeneous data urgency, and energy-constrained sensor nodes hinder reliable and efficient data acquisition. Existing cluster-based routing frameworks often suffer from uneven energy consumption and communication bottlenecks near gateway nodes, compromising both network longevity and data fidelity. To overcome these limitations, this paper introduces the Autistic Children Sensory-Behavior Quality and Effectiveness Information Collection (ACSBQEIC) framework, a novel WIoT-enabled solution tailored for dynamic WBAN environments, particularly in community school settings. The proposed system integrates three core innovations: (i) an unequal clustering mechanism that adaptively organizes nodes based on gateway proximity, residual energy, and ASD-related behavioral urgency; (ii) a multi-objective cluster head (CH) and hop node selection strategy incorporating mobility awareness and MAC-level contention minimization; and (iii) a reinforced routing optimization model utilizing Reinforcement Learning to ensure energy-efficient, low-latency, and high-reliability data delivery. Comparative simulation analysis demonstrates that ACSBQEIC significantly outperforms recent benchmarks, including High-Energy and Reliable Sensory-Behavior Data Collection (HERSBDC), Hybrid WBAN (HyWBAN), and Throughput and Priority Optimization Strategy (TPOS), achieving marked improvements in delivery ratio, network lifetime, and end-to-end latency. These results confirm the framework’s potential to support quality-of-service (QoS)-driven ASD health monitoring and real-time intervention in mobile WIoT environments.