Automatic Depression Detection of Mobile-Based Text-dependent Speech Signals Using a Deep CNN Approach: A Prospective Cohort Study (Preprint)

2021 ◽  
Author(s):  
Ahyoung Kim ◽  
Eun Hye Jang ◽  
Seung-Hwan Lee ◽  
Kwang-Yeon Choi ◽  
Jeon Gyu Park ◽  
...  
Keyword(s):  
Depressive Disorder ◽  
Mental Health Treatment ◽  
Smart Phone ◽  
Acoustic Properties ◽  
Mobile Environment ◽  
Control Groups ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Depression Detection ◽  
Speech Data

BACKGROUND In the future, automatic diagnosis of depression based on speech could complement mental health treatment methods. Previous studies have reported that acoustic properties can be used to recognize depression, including mel-frequency cepstrum coefficients (MFCCs) applied to speech recognition. However, there are few studies in which these characteristics allow differential diagnosis of patients with depressive disorder. OBJECTIVE This paper proposes a framework to help with automatic depression detection in a mobile environment where speech data can be easily obtained. Specifically, we recorded speech data by performing a predefined text-based speech reading task on mobile, investigated whether the recorded data can screen for depression, and proposed a deep learning-based framework that helps in automatic depression detection. METHODS We recruited 125 patients who met the criteria for major depressive disorder (MDD) and 113 healthy controls without current or past mental illness. Participants' voices were recorded on smart-phone while performing the task of reading predefined text-based sentences. We investigated the differences in the voice characteristics between MDD and healthy control groups using statistical analysis. We also investigated the possibility of automatic depression detection using the proposed log mel (LM) spectrogram-based deep Convolutional Neural Networks (CNN) architectures and machine learning models. RESULTS We found that there were statistically discernable differences between MDD and control groups in the MFCC features extracted through the utterances of reading predefined text-based sentences. Moreover, the best accuracies achieved with LM spectrogram-based CNN and softmax classifier on the speech data are 80.00% accuracy. Our results show that the deep-learned acoustic characteristics lead to better performances of classifiers than those using the conventional approach. CONCLUSIONS Conclusions: In conclusion, this study suggests that the analysis of speech data recorded while reading text-dependent sentences could help predict depression status automatically by capturing characteristics of depression. Our method can contribute to an approach that allows individuals to easily and automatically assess their depressive state anytime, anywhere, without the need for experts to conduct psychological assessments on-site.

scholarly journals Understanding unconventional preprocessors in deep convolutional neural networks for face identification

2019 ◽  
Vol 1 (11) ◽  
Author(s):  
Chollette C. Olisah ◽  
Lyndon Smith
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Color Space ◽  
Back Propagation ◽  
Face Identification ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Deep Network

Abstract Deep convolutional neural networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessor’s module of the network. Therefore, in this paper, the network’s preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the deep network architecture, to investigate the contribution preprocessing makes to the network. Commonly used preprocessors are the data augmentation and normalization and are termed conventional preprocessors. Others are termed the unconventional preprocessors, they are: color space converters; grey-level resolution preprocessors; full-based and plane-based image quantization, Gaussian blur, illumination normalization and insensitive feature preprocessors. To achieve fixed network parameters, CNNs with transfer learning is employed. The aim is to transfer knowledge from the high-level feature vectors of the Inception-V3 network to offline preprocessed LFW target data; and features is trained using the SoftMax classifier for face identification. The experiments show that the discriminative capability of the deep networks can be improved by preprocessing RGB data with some of the unconventional preprocessors before feeding it to the CNNs. However, for best performance, the right setup of preprocessed data with augmentation and/or normalization is required. Summarily, preprocessing data before it is fed to the deep network is found to increase the homogeneity of neighborhood pixels even at reduced bit depth which serves for better storage efficiency.

scholarly journals Encryption Image using HiSea Algorithm Based on Android Operating System

2021 ◽  
pp. 222-228
Author(s):  
Zainab Khyioon Abdalrdha
Keyword(s):  
Mobile Phones ◽  
Smart Phone ◽  
Original Image ◽  
Mobile Environment ◽  
Limited Memory ◽  
Android Os ◽  
Different Types ◽  
Android Operating System ◽  
Computational Resources ◽  
Selection Of

The mobile phone environment represents one of the important environments in encryption various multimedia (audio, image, and video) , and this depends on the type of algorithm used in the encryption process, as phones have limited memory and computational resources, Therefore the selection of the algorithm must be compatible with the mobile environment in terms of speed, safety and flexibility in addition to choosing an algorithm that The simplicity and safety of the image encryption process was investigated with lightweight and efficient computing. In this paper, Hybrid Cube Encryption (HiSec) was used. When implementing this algorithm in a smart phone environment, the results showed the ease of encrypting images and retrieving the original image, in addition to that it only requires small computational resources, and the algorithm was very effective in encrypting images on mobile phones. This suggested method has been implemented in the mobile environment with android OS. The proposed method has been programmed in JAVA, and the method has been tried on different types of mobile phones (such as Huawei Nova 2, Huawei Nova 7, HTC, NOT 8, Galaxy S 20, and HONOR).

scholarly journals Evaluation of cognitive impairment in patients with major depressive disorder in remission

2021 ◽  
Vol 28 (1) ◽  
Author(s):  
Mustafa Ali ◽  
Magda Fahmy ◽  
Wafaa Haggag ◽  
Ashraf El-Tantawy ◽  
Haydy Hassan
Keyword(s):  
Major Depressive Disorder ◽  
Depressive Disorder ◽  
Cognitive Functions ◽  
Visual Memory ◽  
Wisconsin Card Sorting Test ◽  
Card Sorting ◽  
Control Groups ◽  
Major Depressive ◽  
Sorting Test ◽  
And Control

Abstract Background Cognitive symptoms are one of the core symptoms of depressive disorders with a bearing effect on functional outcomes. Cognitive symptoms, including poor concentration and difficulty making decisions, are one of the DSM-IV diagnostic criteria for major depressive disorder. This study was designed to evaluate cognitive deficits in a sample of adult patients with major depressive disorder (MDD) in remission. A cross-sectional study was done on 60 patients fulfilling the diagnostic criteria of MDD in remission state. In addition, 60 normal subjects with matched age, sex, and educational level were compared with the patients group. Participants in both patients and control groups were subjected to clinical assessment using Mini-International Neuropsychiatric Interview plus (MINI-plus), assessment of cognitive functions using Wechsler Memory Scale-Revised (WMS-R) short form, and Wisconsin Card Sorting Test (WCST). Results There were statistically significant differences between patients and control groups regarding cognitive function. The patients group scored less in visual memory, verbal memory, attention/concentration, and psychomotor speed. They also performed poorly regarding executive functions. But there was no statistically significant difference between the patients and control groups regarding sustained attention and visuospatial function. No significant correlations did exist between age at onset of MDD and the duration of illness with different domains of cognitive function except for figural memory of WMS-R and categories completed of Wisconsin card sorting test. Conclusion Patients with MDD in remission experienced deficits in several cognitive functions when compared to matched control subjects. The cognitive functions do not reach normal levels of performance, particularly in visual memory and executive functioning with remission of depressive symptoms.

scholarly journals Watermarking of Parkinson Disease Speech in Cloud-Based Healthcare Framework

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Musaed Alhussein ◽  
Ghulam Muhammad
Keyword(s):  
Additive White Gaussian Noise ◽  
Smart Phone ◽  
Singular Value ◽  
Discrete Wavelet ◽  
Speech Watermarking ◽  
Mobile Healthcare ◽  
Speech Data ◽  
Value Decomposition ◽  
Embed Watermark ◽  
Secure Transmission

Mobile healthcare in a cloud-based system increases the easiness and the ubiquitous nature of patient-doctor relationship. One of the major issues of this healthcare is secure transmission and data authenticity. If the data is not transmitted securely or not authenticated, the clients may face embarrassment. In this paper, we propose a cloud-based healthcare framework that will authenticate speech data from a patient suspected to have Parkinson’s disease. The patient sends his or her speech signal recorded via a smart phone through Internet to the cloud. A discrete wavelet transform- (DWT-) singular value decomposition (SVD) based speech watermarking module is run in the cloud to embed watermark to the signal. In case of authentication, watermark is extracted from the questioned signal and matched with the stored watermark. Experimental results indicate that the proposed DWT-SVD based watermarking system achieves imperceptibility and is robust against attacks such as additive white Gaussian noise and filtering.

scholarly journals SegCloud: a novel cloud image segmentation model using deep Convolutional Neural Network for ground-based all-sky-view camera observation

2019 ◽  
Author(s):  
Wanyi Xie ◽  
Dong Liu ◽  
Ming Yang ◽  
Shaoqing Chen ◽  
Benge Wang ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Cloud Cover ◽  
Weather Forecast ◽  
Cloud Detection ◽  
Feature Maps ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Discrimination Ability ◽  
Low Level ◽  
High Level

Abstract. Cloud detection and cloud properties have significant applications in weather forecast, signal attenuation analysis, and other cloud-related fields. Cloud image segmentation is the fundamental and important step to derive cloud cover. However, traditional segmentation methods rely on low-level visual features of clouds, and often fail to achieve satisfactory performance. Deep Convolutional Neural Networks (CNNs) are able to extract high-level feature information of object and have become the dominant methods in many image segmentation fields. Inspired by that, a novel deep CNN model named SegCloud is proposed and applied to accurate cloud segmentation based on ground-based observation. Architecturally, SegCloud possesses symmetric encoder-decoder structure. The encoder network combines low-level cloud features to form high-level cloud feature maps with low resolution, and the decoder network restores the obtained high-level cloud feature maps to the same resolution of input images. The softmax classifier finally achieves pixel-wise classification and outputs segmentation results. SegCloud has powerful cloud discrimination ability and can automatically segment the whole sky images obtained by a ground-based all-sky-view camera. Furthermore, a new database, which includes 400 whole sky images and manual-marked labels, is built to train and test the SegCloud model. The performance of SegCloud is validated by extensive experiments, which show that SegCloud is effective and accurate for ground-based cloud segmentation and achieves better results than traditional methods. Moreover, the accuracy and practicability of SegCloud is further proved by applying it to cloud cover estimation.

scholarly journals Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Er-Yang Huan ◽  
Gui-Hua Wen ◽  
Shi-Jun Zhang ◽  
Dan-Yang Li ◽  
Yang Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Chinese Medicine ◽  
Convolutional Neural Network ◽  
Recognition Algorithm ◽  
Face Image ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Core Content ◽  
Body Constitution ◽  
Proposed Model

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

scholarly journals Qigong-Based Therapy for Treating Adults with Major Depressive Disorder: A Meta-Analysis of Randomized Controlled Trials

2019 ◽  
Vol 16 (5) ◽  
pp. 826 ◽  
Author(s):  
Lijuan Guo ◽  
Zhaowei Kong ◽  
Yanjie Zhang
Keyword(s):  
Major Depressive Disorder ◽  
Depressive Disorder ◽  
Randomized Controlled Trials ◽  
Meta Analysis ◽  
Cochrane Library ◽  
Depression Symptoms ◽  
Controlled Trials ◽  
Control Groups ◽  
Major Depressive ◽  
Randomized Controlled

This current meta-analysis review was conducted to examine the effectiveness of Qigong-based therapy on individuals with major depressive disorder. Six electronic databases (PubMed, PsycINFO, Cochrane Library, and Web of Science, Chinese National Knowledge Infrastructure, and Wangfang) were employed to retrieve potential articles that were randomized controlled trials. The synthesized effect sizes (Hedges’ g) were computerized to explore the effectiveness of Qigong-based therapy. Additionally, a moderator analysis was performed based on the control type. The pooled results indicated that Qigong-based therapy has a significant benefit on depression severity (Hedges’ g = −0.64, 95% CI −0.92 to −0.35, p < 0. 001, I2 = 41.73%). Specifically, Qigong led to significantly reduced depression as compared to the active control groups (Hedges’ g = −0.47, 95% CI −0.81 to −0.12, p = 0.01, I2 = 22.75%) and the passive control groups (Hedges’ g = −0.80, 95% CI −1.23 to −0.37, p < 0.01, I2 = 48.07%), respectively. For studies which reported categorical outcomes, Qigong intervention showed significantly improved treatment response rates (OR = 4.38, 95% CI 1.26 to 15.23, p = 0.02) and remission rates (OR = 8.52, 95% CI 1.91 to 37.98, p = 0.005) in comparison to the waitlist control group. Conclusions: Qigong-based exercises may be effective for alleviating depression symptoms in individuals with major depressive disorder. Future well-designed, randomized, controlled trials with large sample sizes are needed to confirm these findings.

Sign in / Sign up

Export Citation Format

Share Document