Bipolar Disorder Recognition via Multi-scale Discriminative Audio Temporal Representation

Du, Zhengyin; Li, Weixin; Huang, Di; Wang, Yunlong

doi:10.1145/3266302.3268997

Cited by 27 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Temporal factor is considered as prominent indicator towards this process. Existing approach reports of using temporal representation of signal in discriminative manner for recognizing the state of bipolar disorder in Du et al [21]. Yang et al [22] an interesting study has been carried out towards using gestures of subject for identifying bipolar disorder.…”

Section: Related Workmentioning

confidence: 99%

Stochastic modelling of transition dynamic of mixed mood episodes in bipolar disorder

Kumar¹,

Saxena²

2022

IJECE

View full text Add to dashboard Cite

In the present state of health and wellness, mental illness is always deemed less importance compared to other forms of physical illness. In reality, mental illness causes serious multi-dimensional adverse effect to the subject with respect to personal life, social life, as well as financial stability. In the area of mental illness, bipolar disorder is one of the most prominent type which can be triggered by any external stimulation to the subject suffering from this illness. There diagnosis as well as treatment process of bipolar disorder is very much different from other form of illness where the first step of impediment is the correct diagnosis itself. According to the standard body, there are classification of discrete forms of bipolar disorder viz. type-I, type-II, and cyclothymic. Which is characterized by specific mood associated with depression and mania. However, there is no study associated with mixed-mood episode detection which is characterized by combination of various symptoms of bipolar disorder in random, unpredictable, and uncertain manner. Hence, the model contributes to obtain granular information with dynamics of mood transition. The simulated outcome of the proposed system in MATLAB shows that resulting model is capable enough for detection of mixed mood episode precisely

show abstract

Section: Related Workmentioning

confidence: 99%

Stochastic modelling of transition dynamic of mixed mood episodes in bipolar disorder

Kumar¹,

Saxena²

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…SVMs (A) [26] 55.0 50.0 GEWELMs (A) [30] 55.0 48.2 Multistream (A+V) [35] 78.3 40.7 IncepLSTM (A+V) [12] 65.1 -Hierarchical recall model(A+V) [33] 86.8 57.4 Multi-instance learning (A only) 61.6 57.4…”

Section: Uar[%] Dev T Estmentioning

confidence: 99%

“…The best result obtained by our proposed method is highly competitive with those obtained by state-of-the-art methods (Table 4). Except for [35] which also segmented the speech files, these methods fed features obtained from the full audio/video records into SVMs [26], Greedy Ensembles of Weighted Extreme Learning Machines (GEWELMs) [30], Inception LSTM (IncepLSTM) [12], or a hierarchical recall decision tree model [33]. Our multi-instance learning method performs better than all other audio-based methods, and better than, or comparable with, the methods using both speech and visual information.…”

Section: Uar[%] Dev T Estmentioning

confidence: 99%

“…The authors of [35] trained a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) [15] on affective data from the RECOLA dataset [27], and used it to extract 'emotion' based features from the BD corpus. A data-driven deep learning approach was presented in [12]. This approach consisted of an Inception Net [31] combined with an LSTM-RNN designed to learn multi-resolution features from a Mel Frequency Cepstral Coefficients (MFCCs) feature space.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-instance Learning for Bipolar Disorder Diagnosis using Weakly Labelled Speech Data

Ren

Cummins

Kong

et al. 2019

Proceedings of the 9th International Conference on Digital Public Health

View full text Add to dashboard Cite

While deep learning is undoubtedly the predominant learning technique across speech processing, it is still not widely used in healthbased applications. The corpora available for health-style recognition problems are often small, both concerning the total amount of data available and the number of individuals present. The Bipolar Disorder corpus, used in the 2018 Audio/Visual Emotion Challenge, contains only 218 audio samples from 46 individuals. Herein, we present a multi-instance learning framework aimed at constructing more reliable deep learning-based models in such conditions. First, we segment the speech files into multiple chunks. However, the problem is that each of the individual chunks is weakly labelled, as they are annotated with the label of the corresponding speech file, but may not be indicative of that label. We then train the deep learning-based (ensemble) multi-instance learning model, aiming at solving such a weakly labelled problem. The presented results demonstrate that this approach can improve the accuracy of feedforward, recurrent, and convolutional neural nets on the 3-class mania classification tasks undertaken on the Bipolar Disorder corpus. CCS CONCEPTS • Computing methodologies → Supervised learning by classification; • Applied computing → Health care information systems; Health informatics.

show abstract

“…have been used to explore the relevance of specific data and disease, and then the methods of machine learning, such as regression model [13], support vector machine [14] and neural networks have been employed and become more popular. The deep learning methods (DNN), such as Convolutional Neural Network [15] and Long Short-term Memory [16] were used to achieve long-term tracking to obtain better prediction results. Although there were many models and methods proposed in the past, the selection of them depends on the research goal and data characteristics.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Bipolar Disorder Using Heterogeneous Data of Smartphone-Based Digital Phenotyping

Liou

et al. 2021

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

View full text Add to dashboard Cite

In mental health disorder, Bipolar Disorder (BD) is one of the most common mental illness. Using rating scales for assessment is one of the approaches for diagnosing and tracking BD patients. However, the requirement for manpower and time is heavy in the process of evaluation. In order to reduce the cost of social and medical resources, this study collects the user's data by the App on smartphones, consisting of location data (GPS), self-report scales, daily mood, sleeping time and records of multi-media (text, speech, video) which are heterogeneous digital phenotyping data, to build a database. The features of each heterogeneous digital phenotyping data are extracted independently. Lasso Regression and ElasticNet Regression methods are employed to predict the score of Hamilton Depression Rating Scale (HAM-D) and Young Mania Rating Scale (YMRS), as a reference for the evaluation of BD. As incomplete and missing data are very common in medical research, the ensemble method is adopted to combine the results from different models trained with different combinations of missing data. The collected heterogeneous digital phenotyping data from 84 BD patients were used for training and evaluation of the proposed approach based on five-fold cross validation method. Experimental results show that the performance of the assessment system using the proposed method are encouraging.

show abstract

Bipolar Disorder Recognition via Multi-scale Discriminative Audio Temporal Representation

Cited by 27 publications

References 28 publications

Stochastic modelling of transition dynamic of mixed mood episodes in bipolar disorder

Stochastic modelling of transition dynamic of mixed mood episodes in bipolar disorder

Multi-instance Learning for Bipolar Disorder Diagnosis using Weakly Labelled Speech Data

Assessment of Bipolar Disorder Using Heterogeneous Data of Smartphone-Based Digital Phenotyping

Contact Info

Product

Resources

About