Automatic and non-invasive Parkinson’s disease diagnosis and severity rating using LSTM network

Balaji, E; Brindha, D; Elumalai, Vinodh Kumar; Vikrama, R

doi:10.1016/j.asoc.2021.107463

Cited by 56 publications

(20 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, Xia et al [53] achieved the highest model accuracy of 99.1% (Figure 9, Appendix A Table A2), using a dataset that came from three research groups: [55][56][57]. Similarly, two other studies that had proposed DNN [58] and LSTM [59] model also achieved high-performance results that are on par with the CNN-LSTM model (Figure 9, Appendix A Table A2). Hence, future deep learning studies based on gait analysis could focus on the development and implementation of these three models.…”

Section: Motor Symptomsmentioning

confidence: 89%

Application of Deep Learning Models for Automated Identification of Parkinson’s Disease: A Review (2011–2021)

Loh

Hong²,

Ooi

et al. 2021

Sensors

View full text Add to dashboard Cite

Parkinson’s disease (PD) is the second most common neurodegenerative disorder affecting over 6 million people globally. Although there are symptomatic treatments that can increase the survivability of the disease, there are no curative treatments. The prevalence of PD and disability-adjusted life years continue to increase steadily, leading to a growing burden on patients, their families, society and the economy. Dopaminergic medications can significantly slow down the progression of PD when applied during the early stages. However, these treatments often become less effective with the disease progression. Early diagnosis of PD is crucial for immediate interventions so that the patients can remain self-sufficient for the longest period of time possible. Unfortunately, diagnoses are often late, due to factors such as a global shortage of neurologists skilled in early PD diagnosis. Computer-aided diagnostic (CAD) tools, based on artificial intelligence methods, that can perform automated diagnosis of PD, are gaining attention from healthcare services. In this review, we have identified 63 studies published between January 2011 and July 2021, that proposed deep learning models for an automated diagnosis of PD, using various types of modalities like brain analysis (SPECT, PET, MRI and EEG), and motion symptoms (gait, handwriting, speech and EMG). From these studies, we identify the best performing deep learning model reported for each modality and highlight the current limitations that are hindering the adoption of such CAD tools in healthcare. Finally, we propose new directions to further the studies on deep learning in the automated detection of PD, in the hopes of improving the utility, applicability and impact of such tools to improve early detection of PD globally.

show abstract

Section: Motor Symptomsmentioning

confidence: 89%

Application of Deep Learning Models for Automated Identification of Parkinson’s Disease: A Review (2011–2021)

Loh

Hong²,

Ooi

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…To overcome the major limitations of RNN, LSTM adopts gate structure to avoid exploding and vanishing gradient problems, so it can learn long-term information in sequence data [29]. LSTM uses multiple nonlinear gates to control the output and state of neurons, compared with the single tanh layer in the RNN.…”

Section: Lstmmentioning

confidence: 99%

Job runtime prediction of HPC cluster basedon PC-Transformer

chen

2023

Preprint

View full text Add to dashboard Cite

Job scheduling of high performance cluster has been generally achieved using the job scheduling system. The efficiency of job scheduling can be significantly increased by filling accurate job runtime. To increase the accuracy of prediction, it is necessary to use job category information that is acquired by clustering job logs. After the data are sorted out, Transformer with plain connection in accordance with attention mechanism is adopted to predict job runtime. For data processing, 6-dimensional features are selected from the historical log datasets, inaccordance with the correlation with job runtime, the integrity of the features and the validity of data. The datasets are divided into multiple job sets in accordance with the length of the job runtime, each job set will be trained and predicted respectively. As revealed by the results, the proposed method exhibits better prediction performance and achieves, an average accuracy of 0.892 on the HPC2N, with 15.2% MAPE. Furthermore, the proposed time embedding method shows obvious advantages in training time and prediction performance, suggesting that the proposed model can be employed in the actual scheduling environment.

show abstract

“…In this study, extreme learning machine (ELM), [ 36,37 ] general regression neural network model (GRNN), [ 38,39 ] LSTM, [ 40–42 ] and support vector regression (SVR) model [ 43 ] are selected to predict wind speed sequences after processing, respectively. To ensure the reliability of the results, four sites from spring, summer, autumn, and winter are applied, which have the same samples

s = 2001

.…”

Section: The Framework Of Cfsmentioning

confidence: 99%

A Novel Prediction‐Integration Forecasting System for Short Wind Speed Based on Combined Data Preprocessing Technique and Weight Determination Strategy

Wang,

An,

Wang

et al. 2023

Energy Tech

View full text Add to dashboard Cite

Based on the advanced theory research of artificial intelligence and data analysis strategy, a multimodel‐integrated wind speed prediction system is designed in this study, which contains a combined data preprocessing technique, weight determination strategy, and uncertainty prediction. The proposed system not only eliminates the impact of noise but also integrates the results of individual prediction models based on a weight determination strategy. In addition, uncertainty prediction is used to quantify the uncertainty caused by point prediction. The experimental results show that: 1) the mean absolute percentage error values of the proposed model at Site 1 are about 1% and 2%, respectively, which outperform some common basic models such as back propagation neural network (about 7% and 9%). 2) At the significant level α = 0.05, the prediction interval coverage probability values of the proposed model at Site 1 are about 98% and 94%, respectively, for the uncertainty forecasting, which is significantly better than most traditional methods such as extreme learning machine (about 86% and 41%). It is reasonable to conclude that the proposed system is superior to the traditional model in accuracy and stability, which can be a powerful tool for power grid planning.

show abstract

Automatic and non-invasive Parkinson’s disease diagnosis and severity rating using LSTM network

Cited by 56 publications

References 33 publications

Application of Deep Learning Models for Automated Identification of Parkinson’s Disease: A Review (2011–2021)

Application of Deep Learning Models for Automated Identification of Parkinson’s Disease: A Review (2011–2021)

Job runtime prediction of HPC cluster basedon PC-Transformer

A Novel Prediction‐Integration Forecasting System for Short Wind Speed Based on Combined Data Preprocessing Technique and Weight Determination Strategy

Contact Info

Product

Resources

About