基于GAN和LSTM的协作震分类方法,用于下一代医疗保健系统
Hetav Modi1, Jigna Hathaliya1, Rajesh Gupta1
1Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad, Gujarat, 382481, India.
本研究引入了一种结合GAN,Autoencoder和LSTM的深度学习方法,用于分类基本震 (ET) 和帕金森震 (PST). 该方法提高了对震的诊断准确性,并有助于区分健康,ET,PST和中风后抑郁症患者.
科学领域:
- 神经学 神经学
- 生物医学工程 生物医学工程
- 人工智能的人工智能
背景情况:
- 基本震 (ET) 和帕金森震 (PST) 分享类似的频率模式,导致误诊.
- 准确的分类对于有效治疗至关重要,并将其与其他疾病 (如中风后抑郁症) 区分开来.
研究的目的:
- 开发和评估一个协作深度学习 (DL) 框架来对ET和PST进行分类.
- 通过分析震频率模式和严重程度来解决误诊问题.
- 为了区分健康个体,ET,PST和PSD患者.
主要方法:
- 利用PDBioStamp时间序列数据集对动作和休息震进行分类.
- 采用了DL模型的组合:合成数据的生成对抗网络 (GAN),缩小维度的自动编码器和时间特征提取的长短期内存 (LSTM).
- 使用精度,F1分数和AUC评估模型性能,与最先进的方法进行比较.
主要成果:
- 组合的GAN-Autoencoder-LSTM模型实现了80.0%的训练准确率和80.3%的测试准确率.
- 该模型获得了0.82的F1得分和0.89.8的AUC.
- 性能指标超过了现有的震分类深度学习模型.
结论:
- 拟议的DL方法在分类ET和PST方面表现出卓越的表现.
- 这种分类系统有助于临床医生提高震患者的诊断准确度.
- 该框架有效地帮助识别PSD患者并将其与健康对照区分开来.
更多相关视频
11:06A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
Published on: April 12, 2016
06:37Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
相关概念视频
Seizures: Classification
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Classification of Skeletal Muscle Relaxants
Peripherally acting skeletal muscle relaxants interfere with the neurotransmission at the neuromuscular end plate to induce paralysis during...
Classification of Systems-II
Classification of Systems-I
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Aggregates Classification
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
