COVID-19: Affect recognition through voice analysis during the winter lockdown in Scotland

The COVID-19 pandemic has led to unprecedented restrictions in people's lifestyle which have affected their psychological wellbeing. In this context, this paper investigates the use of social signal processing techniques for remote assessment of emotions. It presents a machine learning method for affect recognition applied to recordings taken during the COVID-19 winter lockdown in Scotland (UK). This method is exclusively based on acoustic features extracted from voice recordings collected through home and mobile devices (i.e. phones, tablets), thus providing insight into the feasibility of monitoring people's psychological wellbeing remotely, automatically and at scale. The proposed model is able to predict affect with a concordance correlation coefficient of 0.4230 (using Random Forest) and 0.3354 (using Decision Trees) for arousal and valence respectively. Clinical relevance: In 2018/2019, 12% and 14% of Scottish adults reported depression and anxiety symptoms. Remote emotion recognition through home devices would support the detection of these difficulties, which are often underdiagnosed and, if untreated, may lead to temporal or chronic disability.

Download Full-text

A Two-Stage Exon Recognition Model Based on Synergetic Neural Network

Computational and Mathematical Methods in Medicine ◽

10.1155/2014/503132 ◽

2014 ◽

Vol 2014 ◽

pp. 1-7 ◽

Cited By ~ 4

Author(s):

Zhehuang Huang ◽

Yidong Chen

Keyword(s):

Neural Network ◽

Digital Signal ◽

Two Stage ◽

Recognition Model ◽

Artificial Fish Swarm Algorithm ◽

Proposed Model ◽

Artificial Fish Swarm ◽

Recognition Efficiency ◽

Processing Techniques ◽

Signal Processing Techniques

Exon recognition is a fundamental task in bioinformatics to identify the exons of DNA sequence. Currently, exon recognition algorithms based on digital signal processing techniques have been widely used. Unfortunately, these methods require many calculations, resulting in low recognition efficiency. In order to overcome this limitation, a two-stage exon recognition model is proposed and implemented in this paper. There are three main works. Firstly, we use synergetic neural network to rapidly determine initial exon intervals. Secondly, adaptive sliding window is used to accurately discriminate the final exon intervals. Finally, parameter optimization based on artificial fish swarm algorithm is used to determine different species thresholds and corresponding adjustment parameters of adaptive windows. Experimental results show that the proposed model has better performance for exon recognition and provides a practical solution and a promising future for other recognition tasks.

Download Full-text

Recognition of Pashto Handwritten Characters Based on Deep Learning

Sensors ◽

10.3390/s20205884 ◽

2020 ◽

Vol 20 (20) ◽

pp. 5884

Author(s):

Muhammad Sadiq Amin ◽

Siddiqui Muhammad Yasir ◽

Hyunsik Ahn

Keyword(s):

Character Recognition ◽

Test Accuracy ◽

Forensic Evidence ◽

Handwritten Character Recognition ◽

Data Set ◽

Research Attention ◽

Handwritten Character ◽

Proposed Model ◽

Strong Candidate ◽

Processing Techniques

Handwritten character recognition is increasingly important in a variety of automation fields, for example, authentication of bank signatures, identification of ZIP codes on letter addresses, and forensic evidence. Despite improved object recognition technologies, Pashto’s hand-written character recognition (PHCR) remains largely unsolved due to the presence of many enigmatic hand-written characters, enormously cursive Pashto characters, and lack of research attention. We propose a convolutional neural network (CNN) model for recognition of Pashto hand-written characters for the first time in an unrestricted environment. Firstly, a novel Pashto handwritten character data set, “Poha”, for 44 characters is constructed. For preprocessing, deep fusion image processing techniques and noise reduction for text optimization are applied. A CNN model optimized in the number of convolutional layers and their parameters outperformed common deep models in terms of accuracy. Moreover, a set of benchmark popular CNN models applied to Poha is evaluated and compared with the proposed model. The obtained experimental results show that the proposed model is superior to other models with test accuracy of 99.64 percent for PHCR. The results indicate that our model may be a strong candidate for handwritten character recognition and automated PHCR applications.

Download Full-text

Measuring the outcomes of care in older people: a non-critical review of patient-based measures. II. Mental status, depression and psychological wellbeing instruments

Reviews in Clinical Gerontology ◽

10.1017/s0959259800000241 ◽

2000 ◽

Vol 10 (2) ◽

pp. 123-132 ◽

Cited By ~ 1

Author(s):

P. Kliempt ◽

D. Ruta ◽

M. McMurdo

Keyword(s):

Quality Of Life ◽

Health Status ◽

Cognitive Function ◽

Older People ◽

Mental Status ◽

Psychological Wellbeing ◽

Depression And Anxiety ◽

General Health Status ◽

Outcomes Of Care

This is the second in a series of three papers reviewing 69 patient-based outcome measures that have been developed specifically for use with older people, or that have been administered to populations that include older people. The first paper described how the measures were identified, and provided a brief description of 17 measures of general health status and quality of life. This paper reviews nine measures of mental status and cognitive function, 10 measures of depression and anxiety, and seven psychological wellbeing measures (see Tables 1-3).

Download Full-text

User Identity Protection in Automatic Emotion Recognition through Disguised Speech

AI ◽

10.3390/ai2040038 ◽

2021 ◽

Vol 2 (4) ◽

pp. 636-649

Author(s):

Fasih Haider ◽

Pierre Albert ◽

Saturnino Luz

Keyword(s):

Machine Learning ◽

Transfer Learning ◽

Assisted Living ◽

Speech Signal ◽

Low Cost ◽

Ambient Assisted Living ◽

Recognition Task ◽

Affect Recognition ◽

Acoustic Features ◽

Machine Learning Classification

Ambient Assisted Living (AAL) technologies are being developed which could assist elderly people to live healthy and active lives. These technologies have been used to monitor people’s daily exercises, consumption of calories and sleep patterns, and to provide coaching interventions to foster positive behaviour. Speech and audio processing can be used to complement such AAL technologies to inform interventions for healthy ageing by analyzing speech data captured in the user’s home. However, collection of data in home settings presents challenges. One of the most pressing challenges concerns how to manage privacy and data protection. To address this issue, we proposed a low cost system for recording disguised speech signals which can protect user identity by using pitch shifting. The disguised speech so recorded can then be used for training machine learning models for affective behaviour monitoring. Affective behaviour could provide an indicator of the onset of mental health issues such as depression and cognitive impairment, and help develop clinical tools for automatically detecting and monitoring disease progression. In this article, acoustic features extracted from the non-disguised and disguised speech are evaluated in an affect recognition task using six different machine learning classification methods. The results of transfer learning from non-disguised to disguised speech are also demonstrated. We have identified sets of acoustic features which are not affected by the pitch shifting algorithm and also evaluated them in affect recognition. We found that, while the non-disguised speech signal gives the best Unweighted Average Recall (UAR) of 80.01%, the disguised speech signal only causes a slight degradation of performance, reaching 76.29%. The transfer learning from non-disguised to disguised speech results in a reduction of UAR (65.13%). However, feature selection improves the UAR (68.32%). This approach forms part of a large project which includes health and wellbeing monitoring and coaching.

Download Full-text

Otitis media detection using tympanic membrane images with a novel multi-class machine learning algorithm

PeerJ Computer Science ◽

10.7717/peerj-cs.405 ◽

2021 ◽

Vol 7 ◽

pp. e405

Author(s):

Adi Alhudhaif ◽

Zafer Cömert ◽

Kemal Polat

Keyword(s):

Tympanic Membrane ◽

Otitis Media ◽

Visual Inspection ◽

Learning Algorithm ◽

Decision Support Model ◽

Image Processing Techniques ◽

Proposed Model ◽

Infection And Inflammation ◽

Decision Making Processes ◽

Processing Techniques

Background Otitis media (OM) is the infection and inflammation of the mucous membrane covering the Eustachian with the airy cavities of the middle ear and temporal bone. OM is also one of the most common ailments. In clinical practice, the diagnosis of OM is carried out by visual inspection of otoscope images. This vulnerable process is subjective and error-prone. Methods In this study, a novel computer-aided decision support model based on the convolutional neural network (CNN) has been developed. To improve the generalized ability of the proposed model, a combination of the channel and spatial model (CBAM), residual blocks, and hypercolumn technique is embedded into the proposed model. All experiments were performed on an open-access tympanic membrane dataset that consists of 956 otoscopes images collected into five classes. Results The proposed model yielded satisfactory classification achievement. The model ensured an overall accuracy of 98.26%, sensitivity of 97.68%, and specificity of 99.30%. The proposed model produced rather superior results compared to the pre-trained CNNs such as AlexNet, VGG-Nets, GoogLeNet, and ResNets. Consequently, this study points out that the CNN model equipped with the advanced image processing techniques is useful for OM diagnosis. The proposed model may help to field specialists in achieving objective and repeatable results, decreasing misdiagnosis rate, and supporting the decision-making processes.

Download Full-text

Experiences Using a Free Tool for Voice Therapy Based on Speech Technologies

Technologies for Inclusive Education - Advances in Educational Technologies and Instructional Design ◽

10.4018/978-1-4666-2530-3.ch002 ◽

2013 ◽

pp. 22-37

Author(s):

William R. Rodríguez ◽

Oscar Saz ◽

Eduardo Lleida

Keyword(s):

Speech Processing ◽

Speech Development ◽

Voice Therapy ◽

Educational Institutions ◽

Acoustic Features ◽

Formant Frequencies ◽

Visual Elements ◽

Computer Based ◽

Processing Techniques ◽

Visual Interface

This chapter reports the results after two years of deployment of PreLingua, a free computer-based tool for voice therapy, in different educational institutions. PreLingua gathers a set of activities that use speech processing techniques and an adapted interface to train patients who present speech development delays or special voice needs in the environment of special education. Its visual interface is especially designed for children with cognitive disabilities and maps relevant voice parameters like intensity, vocal onset, durations of sounds, fundamental frequency, and formant frequencies to visually attractive graphics. Reports of successful results of the use of PreLingua have been gathered in several countries by audiologists, speech therapists, and other professionals in the fields of voice therapy, and also, in other fields such as early stimulation, mutism, and attention-deficit disorders. This chapter brings together the experiences of these professionals on the use of the tool and how the use of an interface paradigm that maps acoustic features directly to visual elements in a screen can provide improvements in voice disorders in patients with cognitive and speech delays.

Download Full-text

Core beliefs in healthy youth and youth at ultra high-risk for psychosis: Dimensionality and links to depression, anxiety, and attenuated psychotic symptoms

Development and Psychopathology ◽

10.1017/s0954579417001912 ◽

2018 ◽

Vol 31 (1) ◽

pp. 379-392 ◽

Cited By ~ 7

Author(s):

Henry R. Cowan ◽

Dan P. McAdams ◽

Vijay A. Mittal

Keyword(s):

Cognitive Theory ◽

Active Role ◽

Psychotic Symptoms ◽

Core Beliefs ◽

Depression And Anxiety ◽

Symptoms Of Depression ◽

Negative Beliefs ◽

Proposed Model ◽

Exploratory Factor Analyses ◽

Ultra High Risk

AbstractCognitive theory posits that core beliefs play an active role in developing and maintaining symptoms of depression, anxiety, and psychosis. This study sought to comprehensively examine core beliefs, their dimensionality, and their relationships to depression, anxiety, and attenuated psychotic symptoms in two groups of community youth: a group at ultrahigh risk for psychosis (UHR; n = 73, M age = 18.7) and a matched healthy comparison group (HC; n = 73, M age = 18.1). UHR youth reported significantly more negative beliefs about self and others, and significantly less positive beliefs about self and others. HC youth rarely endorsed negative self-beliefs. Exploratory factor analyses found that HC negative self-beliefs did not cohere as a single factor. We hypothesized specific links between core beliefs and symptoms based on cognitive models of each disorder, and tested these links through regression analyses. The results in the HC group were consistent with the proposed models of depression and anxiety. The results in the UHR group were consistent with proposed models of depression and negative psychotic symptoms, somewhat consistent with a proposed model of positive psychotic symptoms, and not at all consistent with a proposed model of anxiety. These findings add to a growing developmental literature on core beliefs and psychopathology, with important clinical implications.

Download Full-text

Automatic Deception Detection using Multiple Speech and Language Communicative Descriptors in Dialogs

APSIPA Transactions on Signal and Information Processing ◽

10.1017/atsip.2021.6 ◽

2021 ◽

Vol 10 ◽

Author(s):

Huang-Cheng Chou ◽

Yi-Wen Liu ◽

Chi-Chun Lee

Keyword(s):

Domain Knowledge ◽

Deception Detection ◽

Temporal Dynamics ◽

Human Life ◽

Acoustic Features ◽

Textual Information ◽

Behavior Understanding ◽

Proposed Model ◽

Deceptive Behavior ◽

Textual Features

While deceptive behaviors are a natural part of human life, it is well known that human is generally bad at detecting deception. In this study, we present an automatic deception detection framework by comprehensively integrating prior domain knowledge in deceptive behavior understanding. Specifically, we compute acoustics, textual information, implicatures with non-verbal behaviors, and conversational temporal dynamics for improving automatic deception detection in dialogs. The proposed model reaches start-of-the-art performance on the Daily Deceptive Dialogues corpus of Mandarin (DDDM) database, 80.61% unweighted accuracy recall in deception recognition. In the further analyses, we reveal that (i) the deceivers’ deception behaviors can be observed from the interrogators’ behaviors in the conversational temporal dynamics features and (ii) some of the acoustic features (e.g. loudness and MFCC) and textual features are significant and effective indicators to detect deception behaviors.

Download Full-text

Lab Scale Model Experiment of Smart Hopper System to Remove Blockages Using Machine Vision and Collaborative Robot

Applied Sciences ◽

10.3390/app12020579 ◽

2022 ◽

Vol 12 (2) ◽

pp. 579

Author(s):

Heonmoo Kim ◽

Yosoon Choi

Keyword(s):

Machine Vision ◽

Recognition Accuracy ◽

Scale Model ◽

Robot Arm ◽

Mining Sites ◽

Image Processing Techniques ◽

Depth Images ◽

Proposed Model ◽

Processing Techniques ◽

Collaborative Robot

In this study, we propose a smart hopper system that automatically unblocks obstructions caused by rocks dropped into hoppers at mining sites. The proposed system captures RGB (red green blue) and D (depth) images of the upper surfaces of hopper models using an RGB-D camera and transmits them to a computer. Then, a virtual hopper system is used to identify rocks via machine vision-based image processing techniques, and an appropriate motion is simulated in a robot arm. Based on the simulation, the robot arm moves to the location of the rock in the real world and removes it from the actual hopper. The recognition accuracy of the proposed model is evaluated in terms of the quantity and location of rocks. The results confirm that rocks are accurately recognized at all positions in the hopper by the proposed system.

Download Full-text