Intelligent automatic sleep staging model based on CNN and LSTM

Liu, Zhuang; Dai, Minhui; Zhou, Yi; Sun, Lingyu

doi:10.3389/fpubh.2022.946833

Cited by 11 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sleep is not a uniform state but is composed of several cycles, each consisting of non-rapid eye movement (NREM) sleep and rapid eye movement (REM) sleep, which are fundamentally different in terms of brain activity and physiological functions (Figure 1 ) [ 4 - 6 ].…”

Section: Reviewmentioning

confidence: 99%

Exploring the Role of Circadian Rhythms in Sleep and Recovery: A Review Article

Desai,

Momin,

Hirpara

et al. 2024

Cureus

View full text Add to dashboard Cite

Sleep is essential for every living organism. Humans spend about one-third of their lives sleeping. Sleep has been studied extensively, and the role of sleep in psychological, mental, and physical well-being is established to be the best. The rhythm of the brain between wakefulness and sleep is called the circadian rhythm, which is mainly controlled by melatonin and the pineal gland. The imbalance of this rhythm can lead to devastating effects on health. Vigorous workouts close to bedtime can interfere with falling asleep. Meal timing and composition can significantly affect sleep quality. It is advised to avoid large meals, caffeine, and alcohol before bedtime. Heavy meals close to bedtime can lead to poor sleep and hormone disruption. By following these guidelines enumerated in the article, individuals can improve sleep quality and overall health. Sleep cycles, especially rapid eye movement sleep, have a profound influence on mental and physical health. Adhering to recommended sleep practices enhances bodily restoration, fortifies the immune system, and upholds metabolic equilibrium. Sleep hygiene aligned with circadian rhythms is crucial for disease prevention and well-being. Healthcare professionals should prioritize sleep optimization strategies for patient care and public health.

show abstract

Section: Reviewmentioning

confidence: 99%

Exploring the Role of Circadian Rhythms in Sleep and Recovery: A Review Article

Desai,

Momin,

Hirpara

et al. 2024

Cureus

View full text Add to dashboard Cite

show abstract

“…This approach ensures that the classifier accounts for both the spatial characteristics derived from individual frames and the temporal continuity inherent in the video, allowing for a comprehensive video classification strategy. The hybrid CNN-LSTM method has seen increasing application in fields such as online video categorization [ 35 ], behavior/activity recognition [ 36 ], natural language processing [ 37 ], weather broadcasting [ 38 ], auto-driving [ 39 ], lung sound diagnosis [ 40 ], and detecting wake-sleep patterns [ 41 ].…”

Section: Introductionmentioning

confidence: 99%

Schlieren imaging and video classification of alphabet pronunciations: exploiting phonetic flows for speech recognition and speech therapy

Talaat,

Barari,

et al. 2024

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

Speech is a highly coordinated process that requires precise control over vocal tract morphology/motion to produce intelligible sounds while simultaneously generating unique exhaled flow patterns. The schlieren imaging technique visualizes airflows with subtle density variations. It is hypothesized that speech flows captured by schlieren, when analyzed using a hybrid of convolutional neural network (CNN) and long short-term memory (LSTM) network, can recognize alphabet pronunciations, thus facilitating automatic speech recognition and speech disorder therapy. This study evaluates the feasibility of using a CNN-based video classification network to differentiate speech flows corresponding to the first four alphabets: /A/, /B/, /C/, and /D/. A schlieren optical system was developed, and the speech flows of alphabet pronunciations were recorded for two participants at an acquisition rate of 60 frames per second. A total of 640 video clips, each lasting 1 s, were utilized to train and test a hybrid CNN-LSTM network. Acoustic analyses of the recorded sounds were conducted to understand the phonetic differences among the four alphabets. The hybrid CNN-LSTM network was trained separately on four datasets of varying sizes (i.e., 20, 30, 40, 50 videos per alphabet), all achieving over 95% accuracy in classifying videos of the same participant. However, the network’s performance declined when tested on speech flows from a different participant, with accuracy dropping to around 44%, indicating significant inter-participant variability in alphabet pronunciation. Retraining the network with videos from both participants improved accuracy to 93% on the second participant. Analysis of misclassified videos indicated that factors such as low video quality and disproportional head size affected accuracy. These results highlight the potential of CNN-assisted speech recognition and speech therapy using articulation flows, although challenges remain in expanding the alphabet set and participant cohort.

show abstract

“…Deep Learning (DL) has been explored to automate SSC [ 8 ] [ 9 ]. Different DL architectures, such as Convolutional Neural Networks (CNNs) [ 10 ], Recurrent Neural Networks (RNNs) [ 11 ] and others have been experimented with in research. The DL-based models have achieved state of the art in terms of performance.…”

Section: Introductionmentioning

confidence: 99%

MorpheusNet: Resource Efficient Sleep Stage Classifier for Embedded On-Line Systems

Kavoosi,

Mitchell,

Kariyawasam

et al. 2023

2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

Sleep Stage Classification (SSC) is a labor-intensive task, requiring experts to examine hours of electrophysiological recordings for manual classification. This is a limiting factor when it comes to leveraging sleep stages for therapeutic purposes. With increasing affordability and expansion of wearable devices, automating SSC may enable deployment of sleep-based therapies at scale. Deep Learning has gained increasing attention as a potential method to automate this process. Previous research has shown accuracy comparable to manual expert scores. However, previous approaches require sizable amount of memory and computational resources. This constrains the ability to classify in real time and deploy models on the edge. To address this gap, we aim to provide a model capable of predicting sleep stages in real-time, without requiring access to external computational sources (e.g., mobile phone, cloud). The algorithm is power efficient to enable use on embedded battery powered systems. Our compact sleep stage classifier can be deployed on most off-the-shelf microcontrollers (MCU) with constrained hardware settings. This is due to the memory footprint of our approach requiring significantly fewer operations. The model was tested on three publicly available data bases and achieved performance comparable to the state of the art, whilst reducing model complexity by orders of magnitude (up to 280 times smaller compared to state of the art). We further optimized the model with quantization of parameters to 8 bits with only an average drop of 0.95% in accuracy. When implemented in firmware, the quantized model achieves a latency of 1.6 seconds on an Arm Cortex-M4 processor, allowing its use for on-line SSC-based therapies.

show abstract

Intelligent automatic sleep staging model based on CNN and LSTM

Cited by 11 publications

References 34 publications

Exploring the Role of Circadian Rhythms in Sleep and Recovery: A Review Article

Exploring the Role of Circadian Rhythms in Sleep and Recovery: A Review Article

Schlieren imaging and video classification of alphabet pronunciations: exploiting phonetic flows for speech recognition and speech therapy

MorpheusNet: Resource Efficient Sleep Stage Classifier for Embedded On-Line Systems

Contact Info

Product

Resources

About