In the current digital age, the ability to accurately classify large datasets has become of paramount importance across a myriad of fields, including computer vision (CV) [26, 37, 38, 11], natural language processing (NLP) [30, 33, 8, 4], bioinformatics [21], etc. The blossoming of artificial intelligence and deep learning has greatly facilitated the handling of complex classification tasks. Deep learning's capacity to sift through multitudes of variables, discern patterns, and extract key features has led to impressive breakthroughs in numerous applications, from image recognition and voice recognition to disease prediction [20]. The groundbreaking convolutional neural networks (ConvNets), such as ResNet[16] and EfficientNet[39], have emerged as dominant architectures in computer vision, with ResNet addressing the vanishing gradient issue through deep residual networks and enabling deeper models without performance loss, while EfficientNet introduced a compound scaling method that scales depth, width, and resolution, enhancing both efficiency and accuracy. These models have set new benchmarks across various datasets and have been pivotal in applications such as autonomous driving and advanced image recognition, reshaping how machines interpret visual data. Meanwhile, the success of pre-trained unsupervised Transformers [41] like ViT [11] for vision tasks and BERT [8] has shown that using primarily standard Transformer layers can achieve significant performance in downstream applications, reaching levels comparable to previous state-of-the-art neural networks and suggesting that Transformers may offer greater scalability across diverse domains. Transformers have demonstrated superior model capabilities but often suffer from poor generalization when compared to chain-like networks due to a lack of appropriate inductive bias [42]. Recent research has focused on hybrid methods that combine the structures of both to retain their respective advantages [10, 42, 7, 19].

Continuous monitoring and accurate detection of complex sleep patterns associated to different sleep-related conditions is essential, not only for enhancing sleep quality but also for preventing the risk of developing chronic illnesses associated to unhealthy sleep. Despite significant advances in research, achieving versatile recognition of various unhealthy and sub-healthy sleep patterns with simple wearable devices at home remains a significant challenge. Here, we report a robust and durable ultrasensitive strain sensor array printed on a smart garment, in its collar region. This solution allows detecting subtle vibrations associated with multiple sleep patterns at the extrinsic laryngeal muscles. Equipped with a deep learning neural network, it can precisely identify six sleep states-nasal breathing, mouth breathing, snoring, bruxism, central sleep apnea (CSA), and obstructive sleep apnea (OSA)-with an impressive accuracy of 98.6%, all without requiring specific positioning. We further demonstrate its explainability and generalization capabilities in practical applications. Explainable artificial intelligence (XAI) visualizations reflect comprehensive signal pattern analysis with low bias. Transfer learning tests show that the system can achieve high accuracy (overall accuracy of 95%) on new users with very few-shot learning (less than 15 samples per class). The scalable manufacturing process, robustness, high accuracy, and excellent generalization of the smart garment make it a promising tool for next-generation continuous sleep monitoring.

Sleep behavior significantly impacts health and acts as an indicator of physical and mental well-being. Monitoring and predicting sleep behavior with ubiquitous sensors may therefore assist in both sleep management and tracking of related health conditions. While sleep behavior depends on, and is reflected in the physiology of a person, it is also impacted by external factors such as digital media usage, social network contagion, and the surrounding weather. In this work, we propose SleepNet, a system that exploits social contagion in sleep behavior through graph networks and integrates it with physiological and phone data extracted from ubiquitous mobile and wearable devices for predicting next-day sleep labels about sleep duration. Our architecture overcomes the limitations of large-scale graphs containing connections irrelevant to sleep behavior by devising an attention mechanism. The extensive experimental evaluation highlights the improvement provided by incorporating social networks in the model. Additionally, we conduct robustness analysis to demonstrate the system's performance in real-life conditions. The outcomes affirm the stability of SleepNet against perturbations in input data. Further analyses emphasize the significance of network topology in prediction performance revealing that users with higher eigenvalue centrality are more vulnerable to data perturbations.

In this work, a dense recurrent convolutional neural network (DRCNN) was constructed to detect sleep disorders including arousal, apnea and hypopnea using available Polysomnography (PSG) measurement channels provided in the 2018 PhysioNet challenge database. Our model structure is composed of multiple dense convolutional units (DCU) followed by a bidirectional long-short term memory (LSTM) layer followed by a softmax output layer. The sleep events including sleep stages, arousal regions and multiple types of apnea and hypopnea are manually annotated by experts which enables us to train our proposed network using a multi-task learning mechanism. Three binary cross-entropy loss functions corresponding to sleep/wake, arousal presence/absence and apnea-hypopnea/normal detection tasks are summed up to generate our overall network loss function that is optimized using the Adam method. Our model performance was evaluated using two metrics: the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC). To measure our model generalization, 4-fold cross-validation was also performed. For training, our model was applied to full night recording data. Finally, the average AUPRC and AUROC values associated with the arousal detection task were 0.505 and 0.922, respectively on our testing dataset. An ensemble of four models trained on different data folds improved the AUPRC and AUROC to 0.543 and 0.931, respectively. Our proposed algorithm achieved the first place in the official stage of the 2018 PhysioNet challenge for detecting sleep arousals with AUPRC of $0.54$ on the blind testing dataset.