Detection Possibilities of Depression and Parkinson’s disease Based on the Ratio of Transient Parts of the Speech

Kiss, Gábor; Takacs, Artur Bendeguz; Schiferl, D.; Vicsi, Klára

doi:10.1109/coginfocom.2018.8639901

Cited by 14 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coarse KNN is the best performing model. T he results are as follows: Precision: 59% Recall: 77% F-measure:67% Kiss et al (2018) [117] T hey found the speech modality helps in detecting depression. T hey used LLD to balance the pressure of the speech sample.…”

Section: He Et Al (2018)mentioning

confidence: 98%

A review and meta-analysis of machine intelligence approaches for mental health issues and depression detection

Chahar¹,

Dubey²,

Narang³

2021

IJATEE

View full text Add to dashboard Cite

Section: He Et Al (2018)mentioning

confidence: 98%

A review and meta-analysis of machine intelligence approaches for mental health issues and depression detection

Chahar¹,

Dubey²,

Narang³

2021

IJATEE

View full text Add to dashboard Cite

“…The Random Forest algorithm has a 0.38247 error rate, and the Decision Tree algorithm has 0.20744. Hoping this study on Parkinson's disease prediction adds to this glorious legacy [13]. It is known that any experiment will have some limitations.…”

Section: Discussionmentioning

confidence: 95%

Higher Prediction Accuracy on Parkinson Disease Patients Using Random Forest Algorithm over DTA

Manoj

Rajendran

2022

Advances in Parallel Computing Algorithms, Tools and Paradigms

View full text Add to dashboard Cite

Improving the prediction accuracy for Parkinson’s patients is achieved by applying Innovative Parkinson’s disease prediction utilizing classifiers that use machine learning methods and evaluating their performance. In this proposed work, the Innovative Parkinson’s disease prediction has been carried out using the Random Forest algorithm and the Decision Tree algorithm. It was tested over a dataset consisting of 757 records. Both algorithms were subjected to a programming experiment in which N=10 iterations were used to discover the symptoms of Innovative Parkinson’s disease prediction and their accurate analysis. The G-power test is around 80% accurate. From the implemented experiment by performing the independent sample t-test, the Random Forest algorithm’s Parkinson’s disease prediction accuracy is significantly (0.028) better than the Decision Tree algorithm. The accuracy of Innovative Parkinson’s disease prediction was compared between two algorithms, and the Random Forest algorithm appears to be higher at 93% than the Decision Tree algorithm’s accuracy of 91%. This research will use the most up-to-date Machine Learning Classifiers to create an innovative Parkinson’s disease prediction technique for the early detection of Parkinson’s disease and other related issues.

show abstract

“…Depression is usually accompanied by features such as voice, video, and text because it affects the patient's speech state or sentences [7][8][9]. Based on these various characteristics, it is used in research to detect suicide and depression [10].…”

Section: Depression Detectionmentioning

confidence: 99%

Design and Implementation of Attention Depression Detection Model Based on Multimodal Analysis

Park

Moon

2022

Sustainability

View full text Add to dashboard Cite

Depression is becoming a social problem as the number of sufferers steadily increases. In this regard, this paper proposes a multimodal analysis-based attention depression detection model that simultaneously uses voice and text data obtained from users. The proposed models consist of Bidirectional Encoders from Transformers-Convolutional Neural Network (BERT-CNN) for natural language analysis, CNN-Bidirectional Long Short-Term Memory (CNN-BiLSTM) for voice signal processing, and multimodal analysis and fusion models for depression detection. The experiments in this paper are conducted using the DAIC-WOZ dataset, a clinical interview designed to support psychological distress states such as anxiety and post-traumatic stress. The voice data were set to 4 seconds in length and the number of mel filters was set to 128 in the preprocessing process. For text data, we used the subject text data of the interview and derived the embedding vector using a transformers tokenizer. Based on each data set, the BERT-CNN and CNN-BiLSTM proposed in this paper were applied and combined to classify depression. Through experiments, the accuracy and loss degree were compared for the cases of using multimodal data and using single data, and it was confirmed that the existing low accuracy was improved.

show abstract

Detection Possibilities of Depression and Parkinson’s disease Based on the Ratio of Transient Parts of the Speech

Cited by 14 publications

References 13 publications

A review and meta-analysis of machine intelligence approaches for mental health issues and depression detection

A review and meta-analysis of machine intelligence approaches for mental health issues and depression detection

Higher Prediction Accuracy on Parkinson Disease Patients Using Random Forest Algorithm over DTA

Design and Implementation of Attention Depression Detection Model Based on Multimodal Analysis

Contact Info

Product

Resources

About