Cry Recognition for Infant Incubator Monitoring System Based on Internet of Things using Machine Learning

Sutanto, Erwin; Fahmi, Fahmi; Shalannanda, Wervyan; Aridarma, Arga; Inovindo, Pt. Tesena

doi:10.22266/ijies2021.0228.41

Cited by 9 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The baby voices are classified using machine learning using the open voice database. The sensor-based incubator as proposed in the study [ 30 ] would help in reporting the infant's condition. The use of IoT technology would enhance the function of the actuators inside the incubator.…”

Section: Literature Reviewmentioning

confidence: 99%

An Efficient Classification of Neonates Cry Using Extreme Gradient Boosting-Assisted Grouped-Support-Vector Network

Chang

Bhattacharya

Vincent

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The cry is a loud, high pitched verbal communication of infants. The very high fundamental frequency and resonance frequency characterize a neonatal infant cry having certain sudden variations. Furthermore, in a tiny duration solitary utterance, the cry signal also possesses both voiced and unvoiced features. Mostly, infants communicate with their caretakers through cries, and sometimes, it becomes difficult for the caretakers to comprehend the reason behind the newborn infant cry. As a result, this research proposes a novel work for classifying the newborn infant cries under three groups such as hunger, sleep, and discomfort. For each crying frame, twelve features get extracted through acoustic feature engineering, and the variable selection using random forests was used for selecting the highly discriminative features among the twelve time and frequency domain features. Subsequently, the extreme gradient boosting-powered grouped-support-vector network is deployed for neonate cry classification. The empirical results show that the proposed method could effectively classify the neonate cries under three different groups. The finest experimental results showed a mean accuracy of around 91% for most scenarios, and this exhibits the potential of the proposed extreme gradient boosting-powered grouped-support-vector network in neonate cry classification. Also, the proposed method has a fast recognition rate of 27 seconds in the identification of these emotional cries.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Efficient Classification of Neonates Cry Using Extreme Gradient Boosting-Assisted Grouped-Support-Vector Network

Chang

Bhattacharya

Vincent

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…In their approach, they employed MFCC for feature extraction and convolutional and recurrent neural networks for the classification step; an accuracy of, respectively, 93.76% and 86.11% was obtained with each neural network. Sutanto et al (2020) [33] proposed the incorporation of crying decoders to infant incubators to assisting nurses to operate such devices according to the crying. For the training process, they employed the Dunstan Baby Language dataset and convolutional neural networks.…”

Section: Related Workmentioning

confidence: 99%

Granule-based fuzzy rules to assist in the infant-crying pattern recognition problem

2021

View full text Add to dashboard Cite

Crying is how babies express their needs eliciting care and providing information to parents and physicians about their health and physical status. Automatic crying-pattern analysis is performed to assist in the diagnosis of infant's emotional and physical conditions. Despite its usefulness, in this field, the use of such techniques requires machine learning approaches, besides specialists to tune the algorithms to get the best performance possible. To address the lack of knowledge or specialists, we propose a multi-class, auto-tuned classification algorithm based on fuzzy rules and the full model selection paradigm to discriminate among three different crying patterns through features extracted with Mel frequency cepstral coefficients. The obtained results showed an accuracy superior to 98% in all the experiments performed. Although the classification improvement is small its value lies in its automatic fine-tuning capacity, obtaining the best classifier for a given dataset releasing inexpert users from the complex trial-error configuration task.

show abstract

“…This makes it an effective instrument for investigating brain function and spotting irregularities coupled with depression. Moreover, EEG has a very high temporal resolution, meaning it can portray variations in brain activity in real-time with millisecond precision [23][24][25]. This is fundamental for sensing rapid fluctuations and dynamics of brain activity connected to emotional processing, which can be influential in understanding depression.…”

Section: Introductionmentioning

confidence: 99%

A machine learning based depression screening framework using temporal domain features of the electroencephalography signals

Khan,

Umar Saeed,

Frnda

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Depression is a serious mental health disorder affecting millions of individuals worldwide. Timely and precise recognition of depression is vital for appropriate mediation and effective treatment. Electroencephalography (EEG) has surfaced as a promising tool for inspecting the neural correlates of depression and therefore, has the potential to contribute to the diagnosis of depression effectively. This study presents an EEG-based mental depressive disorder detection mechanism using a publicly available EEG dataset called Multi-modal Open Dataset for Mental-disorder Analysis (MODMA). This study uses EEG data acquired from 55 participants using 3 electrodes in the resting-state condition. Twelve temporal domain features are extracted from the EEG data by creating a non-overlapping window of 10 seconds, which is presented to a novel feature selection mechanism. The feature selection algorithm selects the optimum chunk of attributes with the highest discriminative power to classify the mental depressive disorders patients and healthy controls. The selected EEG attributes are classified using three different classification algorithms i.e., Best- First (BF) Tree, k-nearest neighbor (KNN), and AdaBoost. The highest classification accuracy of 96.36% is achieved using BF-Tree using a feature vector length of 12. The proposed mental depressive classification scheme outperforms the existing state-of-the-art depression classification schemes in terms of the number of electrodes used for EEG recording, feature vector length, and the achieved classification accuracy. The proposed framework could be used in psychiatric settings, providing valuable support to psychiatrists.

show abstract

Cry Recognition for Infant Incubator Monitoring System Based on Internet of Things using Machine Learning

Cited by 9 publications

References 12 publications

An Efficient Classification of Neonates Cry Using Extreme Gradient Boosting-Assisted Grouped-Support-Vector Network

An Efficient Classification of Neonates Cry Using Extreme Gradient Boosting-Assisted Grouped-Support-Vector Network

Granule-based fuzzy rules to assist in the infant-crying pattern recognition problem

A machine learning based depression screening framework using temporal domain features of the electroencephalography signals

Contact Info

Product

Resources

About