Gait Anomaly Detection of Subjects With Parkinson’s Disease Using a Deep Time Series-Based Approach

Paragliola, Giovanni; Coronato, Antonio

doi:10.1109/access.2018.2882245

Cited by 42 publications

(19 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning models are trained on data collected from a wide variety of sensors for PD diagnosis and quantifying severity of symptoms. These sensors could be body-worn accelerometers for recording fine-grained kinematic information related to tremor [4] and gait [5] or microphones for speech patterns [6]. Due to the heterogeniety of the symptoms, multimodal learning methods have been used to combine the data collected from various assessments [7].…”

Section: Machine Learning For Pd Diagnosismentioning

confidence: 99%

Towards Parkinson’s Disease Prognosis Using Self-Supervised Learning and Anomaly Detection

Jiang

Lim

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Parkinson's disease (PD) is a chronic disease with a high risk of incidence after the age of 60 and is a problem for many countries facing an aging population. Current works have mainly focused on supervised learning using data collected from various sensors to differentiate between PD and healthy subjects. However, such supervised methods are not ideal for prognosis where there are no labels (i.e., we do not know in advance which subjects will develop PD in the future). We propose to tackle the problem as a semi-supervised anomaly detection task, where we model the physiological patterns of healthy subjects instead. A self-supervised learning technique first learns a good representation of the sensor signals. The representations are then adapted to capture inter-class patterns for anomaly detection. Evaluation on a large-scale PD dataset shows that our approach can learn discriminative features.

show abstract

Section: Machine Learning For Pd Diagnosismentioning

confidence: 99%

Towards Parkinson’s Disease Prognosis Using Self-Supervised Learning and Anomaly Detection

Jiang

Lim

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…RL may also be applied for risk management the during nuclear medical examination at hospitals [102] and healthcare examinations centers ( [103] and [104]). Some studies using DL for cognitive impaired people are found in [105] and [106].…”

Section: A Healthcarementioning

confidence: 99%

A Gentle Introduction to Reinforcement Learning and its Application in Different Fields

Naeem

Rizvi

Coronato³

2020

IEEE Access

Self Cite

142

View full text Add to dashboard Cite

Due to the recent progress in Deep Neural Networks, Reinforcement Learning (RL) has become one of the most important and useful technology. It is a learning method where a software agent interacts with an unknown environment, selects actions, and progressively discovers the environment dynamics. RL has been effectively applied in many important areas of real life. This article intends to provide an in-depth introduction of the Markov Decision Process, RL and its algorithms. Moreover, we present a literature review of the application of RL to a variety of fields, including robotics and autonomous control, communication and networking, natural language processing, games and self-organized system, scheduling management and configuration of resources, and computer vision.

show abstract

“…Gait analysis conducted in a hospital is a basic test method that helps diagnose Parkinson’s disease with the patient’s motor ability. Recently, studies are being conducted to detect abnormal walking of patients using data processing of sensor data, waveform analysis, and deep learning technology [ 4 , 5 ]. Furthermore, gait test research is applied to real-time data collection and gait abnormality analysis in patient life through smartphones and wearable devices.…”

Section: Introductionmentioning

confidence: 99%

Self-Organizing IoT Device-Based Smart Diagnosing Assistance System for Activities of Daily Living

Park

Jung

Son

et al. 2021

Sensors

View full text Add to dashboard Cite

Activity of daily living (ADL) is a criterion for evaluating the performance ability of daily life by recognizing various activity events occurring in real life. However, most of the data necessary for ADL evaluation are collected only through observation and questionnaire by the patient or the patient’s caregiver. Recently, Internet of Things (IoT) device studies using various environmental sensors are being used for ADL collection and analysis. In this paper, we propose an IoT Device Platform for ADL capability measurement. Wearable devices and stationary devices recognize activity events in real environments and perform user identification through various sensors. The user’s ADL data are sent to the network hub for analysis. The proposed IoT platform devices support many sensor devices such as acceleration, flame, temperature, and humidity in order to recognize various activities in real life. In addition, in this paper, using the implemented platform, ADL measurement test was performed on hospital patients. Through this test, the accuracy and reliability of the platform are analyzed.

show abstract

Gait Anomaly Detection of Subjects With Parkinson’s Disease Using a Deep Time Series-Based Approach

Cited by 42 publications

References 28 publications

Towards Parkinson’s Disease Prognosis Using Self-Supervised Learning and Anomaly Detection

Towards Parkinson’s Disease Prognosis Using Self-Supervised Learning and Anomaly Detection

A Gentle Introduction to Reinforcement Learning and its Application in Different Fields

Self-Organizing IoT Device-Based Smart Diagnosing Assistance System for Activities of Daily Living

Contact Info

Product

Resources

About