论文部分内容阅读
对于神经系统疾病,其主要的生理特性可以反映在患者日常的人机交互行为中.对交互过程中产生的相关生理信息进行获取和分析,有助于神经系统疾病辅助诊断与早期预警.传统的神经系统疾病自动检测系统常常只分析单一交互通道中包含的信息,会造成其他通道中包含的重要信息的缺失.为此,本文提出了一个云端融合的神经系统疾病多通道辅助诊断系统.首先,提出一种基于多通道信息的疾病自动诊断方法,获取并分析了用户在多个交互通道中释放的生理信息,并将结果进行融合,提升自动诊断的精确性与鲁棒性;其次,提出了一个云端融合的框架,将从不同地区、不同时刻提取的用户生理信息在云端存储,降低了数据采集的地域限制与时间限制;再次,基于云计算强大的运算能力,系统亦可以实时地对用户在自然交互过程中产生的多通道生理信息进行分析,做出实时、精确的自动诊断;最后,通过语音与笔的交互混合诊断系统实例,验证基于云端融合的神经系统疾病多通道辅助诊断方法的有效性.
For the nervous system diseases, the main physiological characteristics can be reflected in the daily human-computer interaction.The acquisition and analysis of relevant physiological information generated during the interaction contribute to the diagnosis and early warning of neurological diseases.Traditional The system of automatic detection of neurological diseases often only analyzes the information contained in a single interaction channel, which will result in the loss of important information contained in other channels.Therefore, a multi-channel auxiliary diagnosis system for neurological diseases is proposed in this paper.Firstly, An automatic diagnosis method based on multi-channel information is proposed. The physiological information released by users in multiple channels is acquired and analyzed, and the results are fused to improve the accuracy and robustness of automatic diagnosis. Secondly, A cloud-based framework for storing user physiological information extracted from different regions and at different times in the cloud reduces the geographical limitation and time limit of data collection. Thirdly, based on the powerful computing power of cloud computing, the system can also provide real-time control of users Multi-channel physiological information generated during natural interactions is analyzed in real time Accurate automatic diagnosis; Finally, by mixing the interactive voice system instances and the diagnostic pen, to verify the validity of nervous system disorders based multi-channel method of diagnosis Drive fused.