Sleep staging serves as a fundamental assessment for sleep quality measurement and sleep disorder diagnosis. Although current deep learning approaches have successfully integrated multimodal sleep signals, enhancing t...
详细信息
Sleep staging serves as a fundamental assessment for sleep quality measurement and sleep disorder diagnosis. Although current deep learning approaches have successfully integrated multimodal sleep signals, enhancing the accuracy of automatic sleep staging, certain challenges remain, as follows: 1) optimizing the utilization of multi-modal information complementarity, 2) effectively extracting both long- and short-range temporal features of sleep information, and 3) addressing the class imbalance problem in sleep data. To address these challenges, this paper proposes a two-stream encode-decoder network, named TSEDSleepNet, which is inspired by the depth sensitive attention and automatic multi-modal fusion (DSA2F) framework. In TSEDSleepNet, a two-stream encoder is used to extract the multiscale features of electrooculogram (EOG) and electroencephalogram (EEG) signals. And a self-attention mechanism is utilized to fuse the multiscale features, generating multi-modal saliency features. Subsequently, the coarser-scale construction module (CSCM) is adopted to extract and construct multi-resolution features from the multiscale features and the salient features. Thereafter, a Transformer module is applied to capture both long- and short-range temporal features from the multi-resolution features. Finally, the long- and short-range temporal features are restored with low-layer details and mapped to the predicted classification results. Additionally, the Lovász loss function is applied to alleviate the class imbalance problem in sleep datasets. Our proposed method was tested on the Sleep-EDF-39 and Sleep-EDF-153 datasets, and it achieved classification accuracies of 88.9% and 85.2% and Macro-F1 scores of 84.8% and 79.7%, respectively, thus outperforming conventional traditional baseline models. These results highlight the efficacy of the proposed method in fusing multi-modal information. This method has potential for application as an adjunct tool for diagnosing sleep disorde
作者：
Park, Seong-JoonKwak, Hee-YoulKim, Sang-HyoKim, SunghwanKim, YongjuneNo, Jong-Seon
Institute of Artificial Intelligence Pohang37673 Korea Republic of University of Ulsan
Department of Electrical Electronic and Computer Engineering Ulsan44610 Korea Republic of Sungkyunkwan University
Department of Electrical and Computer Engineering Suwon16419 Korea Republic of Kyonggi University
School of Electronic Engineering Suwon16227 Korea Republic of
Department of Electrical Engineering Pohang37673 Korea Republic of Yonsei University
Institute for Convergence Research and Education in Advanced Technology Seoul03722 Korea Republic of Seoul National University
Department of Electrical and Computer Engineering Seoul08826 Korea Republic of
With the broadening applications of deep learning, neural decoders have emerged as a key research focus, specifically aimed at improving the decoding performance of conventional decoding algorithms. In particular, err...
详细信息
Aortic aneurysms, characterized by local dilation of the aorta, often lead to catastrophic ruptures. Although aneurysm size is a well-established risk factor, smaller aneurysms can also rupture, indicating unclear rup...
详细信息
In the realm of smart healthcare, vast amounts of valuable patient data are generated worldwide. However, healthcare providers face challenges in data sharing due to privacy concerns. Federated learning (FL) offers a ...
详细信息
Accurately predicting the knee point cycle number,marking the onset of accelerated capacity degradation,is the first critical signal for managing lithium-ion battery life cycles in electric vehicles and stationary ene...
详细信息
Accurately predicting the knee point cycle number,marking the onset of accelerated capacity degradation,is the first critical signal for managing lithium-ion battery life cycles in electric vehicles and stationary energy storage ***,the inherent electrochemo-mechanical-thermal complexities of battery aging present significant challenges for physics-based models and machine-learning models,often leading to reduced predictive *** study developed a comprehensive dataset comprising 20 lithium nickel manganese cobalt oxide(NCM)/graphite cells(0.5-1 C) from our lab and 162 commercial lithium iron phosphate(LFP)/graphite cells(3-6 C) from the public database,with knee point observed between 100 and 1000 *** proposed a new strategy to extract novel features with strong physical context from early-cycle voltage curves,enabling precise knee point predictions across the chemistries without the need for extensive cycling *** model achieved a mean absolute percentage error(MAPE) of 7% for knee point prediction using five selected ***,the model yielded 8% MAPE with only one single feature across the initial 200 cycles,and 10% MAPE when applying five features across the initial 50 cycles,spanning different battery *** work highlights the potential of integrating multi-chemistry datasets with data-driven modeling to forecast aging patterns across diverse battery chemistries,advancing battery longevity and reliability.
In modern process industries, maintaining precise weight measurements is critical for ensuring product quality and operational efficiency. Accurate weight measurement systems not only aid in meeting regulatory standar...
详细信息
The sleep apnea is a disease in which there is the absence of airflow during respiration for at least 10 s. It may occur several times during the night sleep. This disease can lead to many types of cardiovascular...
详细信息
Objective and Impact *** use deep learning models to classify cervix images—collected with a low-cost,portable Pocket colposcope—with biopsy-confirmed high-grade precancer and *** boost classification performance on...
详细信息
Objective and Impact *** use deep learning models to classify cervix images—collected with a low-cost,portable Pocket colposcope—with biopsy-confirmed high-grade precancer and *** boost classification performance on a screened-positive population by using a class-balanced loss and incorporating green-light colposcopy image pairs,which come at no additional cost to the *** the majority of the 300,000 annual deaths due to cervical cancer occur in countries with low-or middle-Human Development Indices,an automated classification algorithm could overcome limitations caused by the low prevalence of trained professionals and diagnostic variability in provider visual *** dataset consists of cervical images(n=1,760)from 880 patient *** optimizing the network architecture and incorporating a weighted loss function,we explore two methods of incorporating green light image pairs into the network to boost the classification performance and sensitivity of our model on a test *** achieve an area under the receiver-operator characteristic curve,sensitivity,and specificity of 0.87,75%,and 88%,*** addition of the class-balanced loss and green light cervical contrast to a Resnet-18 backbone results in a 2.5 times improvement in *** methodology,which has already been tested on a prescreened population,can boost classification performance and,in the future,be coupled with Pap smear or HPV triaging,thereby broadening access to early detection of precursor lesions before they advance to cancer.
Polymer nanocomposites have been a topic of intensive research regarding High Voltage engineering since the nineties of the last century. They present an alternative to conventional polymers since the latter were diag...
详细信息
暂无评论