[论文解读] Extended Report: Fine-grained Recognition of Abnormal Behaviors for Early Detection of Mild Cognitive Impairment
本文提出FABER,一种混合统计符号方法,用于在居家环境中对老年人进行细微行为异常的识别,以实现轻度认知障碍(MCI)的早期检测。通过结合非侵入式智能家居基础设施收集的传感器数据与异常活动模式的医学模型,FABER利用监督学习和基于规则的推理检测细微异常(如不规律的用餐时间或重复的子动作),在21天内实现超过0.96的高召回率和仅6个假阳性的低误报率。
According to the World Health Organization, the rate of people aged 60 or more is growing faster than any other age group in almost every country, and this trend is not going to change in a near future. Since senior citizens are at high risk of non communicable diseases requiring long-term care, this trend will challenge the sustainability of the entire health system. Pervasive computing can provide innovative methods and tools for early detecting the onset of health issues. In this paper we propose a novel method to detect abnormal behaviors of elderly people living at home. The method relies on medical models, provided by cognitive neuroscience researchers, describing abnormal activity routines that may indicate the onset of early symptoms of mild cognitive impairment. A non-intrusive sensor-based infrastructure acquires low-level data about the interaction of the individual with home appliances and furniture, as well as data from environmental sensors. Based on those data, a novel hybrid statistical-symbolical technique is used to detect the abnormal behaviors of the patient, which are communicated to the medical center. Differently from related works, our method can detect abnormal behaviors at a fine-grained level, thus providing an important tool to support the medical diagnosis. In order to evaluate our method we have developed a prototype of the system and acquired a large dataset of abnormal behaviors carried out in an instrumented smart home. Experimental results show that our technique is able to detect most anomalies while generating a small number of false positives.
研究动机与目标
- 为应对老年人口增长带来的医疗系统可持续性挑战,通过实现轻度认知障碍(MCI)的早期检测。
- 克服现有方法依赖自我报告或粗粒度行为指标的局限性,这些方法缺乏持续监测和细粒度的诊断细节。
- 开发一种非侵入式、持续监测系统,检测日常活动模式中细微但具有临床意义的异常,以指示早期MCI。
- 通过基于认知神经科学洞察的异常行为建模,将医学专业知识与普适计算相结合。
- 利用在智能家庭中收集的大规模数据集,在真实世界条件下评估系统性能。
提出的方法
- 系统采用非侵入式传感器基础设施,收集关于与家用电器、家具及环境条件交互的低层次数据。
- 通过基于马尔可夫逻辑网络(MLN)的技术执行活动识别,以推断最可能的活动边界和序列。
- 通过结合监督学习、基于规则的推理和概率推理的混合符号-统计方法检测异常行为。
- 异常行为基于临床专业知识建模,包括低层次偏差(如重复子动作)和高层次模式(如食用冷餐)。
- 在活动识别后应用符号推理,检测细微异常,如不恰当的时间点或不必要的重复。
- 结果发送至医疗中心以供临床解读,支持MCI的早期诊断。
实验结果
研究问题
- RQ1混合统计符号方法能否以高准确率和低假阳性率检测居家老年人日常活动中的细微异常行为?
- RQ2将MCI相关行为改变的医学模型与基于传感器的普适计算相结合,在早期检测中效果如何?
- RQ3活动边界检测错误在多大程度上影响异常识别性能?是否可被缓解?
- RQ4系统能否以足够高的精度区分关键与非关键异常,以支持临床决策?
- RQ5在具有自然行为的智能家居环境中,系统在真实世界长期监测场景下的表现如何?
主要发现
- FABER在所有异常中召回率均高于0.96,表明其对关键与非关键行为均具备强大的检测能力。
- 在两个参与组的21天连续监测中,系统仅产生6个假阳性,表明假阳性率极低。
- 精确率接近0.9,但因活动边界检测错误,非关键异常的精确率略低。
- 在复杂异常较多的组(第2组)中未观察到假阴性,表明系统在检测关键行为偏差方面具有鲁棒性。
- 假阳性主要由活动边界检测的误预测引起,表明改善传感器覆盖范围或活动识别模型可进一步减少错误。
- 临床医生的初步评估支持所检测异常的临床相关性,尤其在识别早期MCI症状方面具有价值。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。