Machine Learning and Data Mining Methods for Managing Parkinson’s Disease

Miljković, Dragana; Aleksovski, Darko; Podpečan, Vid; Lavrač, Nada; Malle, Bernd; Holzinger, Andreas

doi:10.1007/978-3-319-50478-0_10

Cited by 30 publications

(23 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, because the proposed method can be regarded as a fusion of classificationbased and regression-based method, its application is not limited to human age estimation. It could also be of great importance for the medical domain, particularly, on predicting Parkinson's disease, where typical symptoms (e.g., tremors) appear in gait patterns [28].…”

Section: Resultsmentioning

confidence: 99%

Gait-based human age estimation using age group-dependent manifold learning and regression

Makihara

et al. 2018

Multimed Tools Appl

View full text Add to dashboard Cite

Human age estimation from gait is expected to be an important technology for a variety of applications such as automatic customer counting for marketing research or automatic age-based access control restriction for a specific area because the gait can be observable at a distance from a camera (e.g., CCTV). Although the aging process of gait significantly differs among age groups (e.g., children, adults, and the elderly), previous studies on gait-based human age estimation employ a single age group-independent estimation model that suffers from large estimation errors when the age variation increases. We therefore propose an age group-dependent gait-based human age estimation method for better accuracy. Specifically, in the training phase, we first compose age groups that are well-separated from each other by clustering gait features along with their age labels. We then learn a classifier that classifies the gait features for multiple age groups using a directed acyclic graph support vector machine. Next, we learn an age regression model for each age group using support vector regression with a Gaussian kernel in conjunction with a manifold learning technique, i.e., orthogonal locality preserving projection, to better

show abstract

Section: Resultsmentioning

confidence: 99%

Gait-based human age estimation using age group-dependent manifold learning and regression

Makihara

et al. 2018

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…So, we used five patients affected by stroke or Parkinson's disease (hereinafter, PD) as case studies. The patients were distributed among three exercises commonly used in PD treatment [46,59,64,90,74]. The exercises included mixed hands and body rehabilitation tasks.…”

Section: Combination Of the Modelsmentioning

confidence: 99%

MIFTel: a multimodal interactive framework based on temporal logic rules

Avola

Cinque

Bimbo

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Human-computer and multimodal interaction are increasingly used in everyday life. Machines are able to get more from the surrounding world, assisting humans in different application areas. In this context, the correct processing and management of signals provided by the environments is determinant for structuring the data. Different sources and acquisition times can be exploited for improving recognition results. On the basis of these assumptions, we are proposing a multimodal system that exploits Allen's temporal logic combined with a prevision method. The main object is to correlate user's events with system's reactions. After post-elaborating coming data from different signal sources (RGB images, depth maps, sounds, proximity sensors, etc.), the system is managing the correlations between recognition/detection results and events in real-time to create an interactive environment for the user. For increasing the recognition reliability, a predictive model is also associated with the proposed method. The modularity of the system grants a full dynamic development and upgrade with custom modules. Finally, a comparison with other similar systems is shown, underlining the high flexibility and robustness of the proposed event management method. Ringraziamenti Questo percorso di crescita personale ha portato ad interiorizzare conoscenze notevoli in ambito della computer vision e non solo. Devo molto al Prof. Luigi Cinque per questa opportunità offertami. Inoltre, la sua umanità è stata la virtù più rara che abbia trasmesso. Contestualmente, ho avuto il piacere e l'onore di poter lavorare con un gruppo di ricerca tra i migliori d'Italia. Il Visionlab è diventato un punto di riferimento in questi 3 anni e senza Daniele, Cristiano e Marco probabilmente non avrei raggiunto i risultati di oggi. Devo molto anche a loro. Infine, devo fare un ringraziamento speciale a Danilo Avola, colui che ha fornito un supporto determinante alla ricerca dell'intero laboratorio. Una guida, un maestro ed anche un amico.

show abstract

“…The comparative analysis scheme is adopted from [1]. Furthermore, the accuracy performance is compared with state-of-art techniques such as adaptive fuzzy [5], Hybrid SVR [6], Rule mining with POA [7], Modified PSO [8], Re-RX with J48graft [9], Re-RX with C4.5 [9], QFAM-GA [10] and DNN-SAE [11].…”

Section: (A)mentioning

confidence: 99%

“…In the medical field, the pattern recognition and data mining play pivotal role to predict the diseases. Generally, researchers have focused on the classification based data mining schemes for early prediction of different types of diseases such as breast cancer [4], heart disease [5], Liver disorder [6], Thyroid [7], Lymphography [8], Parkinson's [9] and diabetes [10] etc. Significant amount of works have been carried out in these fields.…”

Section: Introductionmentioning

confidence: 99%

ENN Ensemble based Neural Network method for Diabetes Classification

Kumari,

2020

IJEAT

View full text Add to dashboard Cite

Diabetes is considered as one of the most chronic disease which has serious impact on human health and leading cause of mortality worldwide. The early prediction of diabetes can help clinicians to provide a better diagnosis to the patients. Recently, computed aided diagnosis systems have gained attention due to significant growth in data mining, and machine learning. Several approaches are present based on the machine learning techniques but due to poor classification performance and computational complexity, it becomes difficult to utilize for real-time applications. Ensemble classification approaches have reported a noteworthy improvement in diabetes classification but desired accuracy is still a challenging task. Hence, in this work we introduce a combined hybrid approach called as ENN-Ensemble based neural network approach for diabetes classification. In this approach, a feature selection process is presented using neighboring search technique; the selected features are processed through the feature ranking model to generate the efficient feature subset for better classification accuracy. Finally, these features are learned and classified using neural network classifier. The experimental study shows that the proposed approach achieves better accuracy when compared with the existing techniques.

show abstract

Machine Learning and Data Mining Methods for Managing Parkinson’s Disease

Cited by 30 publications

References 40 publications

Gait-based human age estimation using age group-dependent manifold learning and regression

Gait-based human age estimation using age group-dependent manifold learning and regression

MIFTel: a multimodal interactive framework based on temporal logic rules

ENN Ensemble based Neural Network method for Diabetes Classification

Contact Info

Product

Resources

About