Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference最新文献_第3页

Robust Sequence-to-sequence Voice Conversion for Electrolaryngeal Speech Enhancement in Noisy and Reverberant Conditions. 嘈杂和混响条件下用于电喉音增强的稳健序列到序列语音转换

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10781979

Ding Ma, Yeonjong Choi, Fengji Li, Chao Xie, Kazuhiro Kobayashi, Tomoki Toda

{"title":"Robust Sequence-to-sequence Voice Conversion for Electrolaryngeal Speech Enhancement in Noisy and Reverberant Conditions.","authors":"Ding Ma, Yeonjong Choi, Fengji Li, Chao Xie, Kazuhiro Kobayashi, Tomoki Toda","doi":"10.1109/EMBC53108.2024.10781979","DOIUrl":"10.1109/EMBC53108.2024.10781979","url":null,"abstract":"Electrolaryngeal (EL) speech, an artificial speech produced by an electrolarynx for laryngectomees, lacks essential phonetic features, and differs in temporal structure from normal speech, resulting in poor naturalness and intelligibility. To address this deficiency, sequence-to-sequence (seq2seq) voice conversion (VC) models have been applied in converting EL speech to normal speech (EL2SP), showing some promising performances. However, previous studies mostly focus on converting clean EL speech, thereby restricting the further applicability in real-world scenarios, especially when the EL speech is inevitably interfered with background noise and reverberation. In light of this, we suggest novel training techniques based on seq2seq VC to enhance the robustness of real-world EL2SP. We first pretrain a normal-to-normal seq2seq VC model based on a text-to-speech model. Then, a two-stage fine-tuning is conducted by effectively using pseudo noisy and reverberant EL speech data artificially generated from only a small amount of original clean data available. Several design options are investigated to figure out the effectiveness of our method. The significant improvements presented in experimental results indicate that our method can non-trivially handle both clean and noisy-reverberant EL speech, enhancing the robustness of EL2SP in real-world scenarios.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143559989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identifying Canonical multi-scale Intrinsic Connectivity Networks in Infant resting-state fMRI and their Association with Age. 婴儿静息状态功能磁共振成像中典型多尺度内在连接网络的识别及其与年龄的关系。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782404

Prerana Bajracharya, Ashkan Faghiri, Zening Fu, Vince D Calhoun, Sarah Shultz, Armin Iraji

{"title":"Identifying Canonical multi-scale Intrinsic Connectivity Networks in Infant resting-state fMRI and their Association with Age.","authors":"Prerana Bajracharya, Ashkan Faghiri, Zening Fu, Vince D Calhoun, Sarah Shultz, Armin Iraji","doi":"10.1109/EMBC53108.2024.10782404","DOIUrl":"10.1109/EMBC53108.2024.10782404","url":null,"abstract":"Intrinsic Connectivity Networks (ICNs) reflect functional brain organization responsible for various cognitive processes, including sensory perception, motor control, memory, and attention. In this study, we used the Multivariate-Objective Optimization Independent Component Analysis with Reference (MOO-ICAR) and the NeuroMark 2.1 (adult) template to estimate subject-specific ICNs in resting-state functional magnetic resonance imaging (rsfMRI) data of infants. The NeuroMark 2.1 template contains 105 multi-scale canonical ICNs derived from 100k+ adults across multiple datasets. The multi-scale ICNs capture functional segregation across various levels of granularity across brain, revealing functional sources and their interactions. The results showed that the 105 ICNs in infants were spatially aligned with those in the template and revealed age-related distinctive patterns in static Functional Network Connectivity (sFNC), particularly in the sub-cortical and high-level cognitive domains. This study is the first to investigate the presence and development of these multi-scale ICNs in infant rsfMRI data. Our findings confirmed the presence of identifiable canonical ICNs in infants as young as six months, showcasing a strong association between these networks and age and suggesting potential biomarkers for early identification of neurodevelopmental disability.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143559559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Novel Direct Puncture Cannulation Blood Pump Support System: in Vivo Experimental Proof of Concept for a Therapeutic Approach with Cardiac Arrest. 一种新型直接穿刺插管血泵支持系统：心脏骤停治疗方法的体内实验证明。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782583

Yasuyuki Shiraishi, Francis Chikweto, Hanako Suzuki, Toshihiko Kijima, Aoi Fukaya, Hideyuki Horie, Kazushi Ishiyama, Tomoyuki Yambe

{"title":"A Novel Direct Puncture Cannulation Blood Pump Support System: in Vivo Experimental Proof of Concept for a Therapeutic Approach with Cardiac Arrest.","authors":"Yasuyuki Shiraishi, Francis Chikweto, Hanako Suzuki, Toshihiko Kijima, Aoi Fukaya, Hideyuki Horie, Kazushi Ishiyama, Tomoyuki Yambe","doi":"10.1109/EMBC53108.2024.10782583","DOIUrl":"10.1109/EMBC53108.2024.10782583","url":null,"abstract":"The rate of out-of-hospital cardiac arrest is increasing according to the changes in the proportion of ages in super-aged society. We developed a novel transcutaneous cannulation-type mechanical circulatory system for an alternative therapeutic approach to cardiac arrest using a small centrifugal blood pump. We proposed a transcutaneous mechanical circulatory support capable of rapid installation and quick start of circulatory support for recovery after cardiac arrest by left ventricular direct puncture using the Seldinger technique. The cannula consisted of three components as follows: a) a double-layered cylindrical blood pump housing, b) a centrifugal blood pump impeller primarily installed inside of the cannula, and c) an insertable actuator with magnet coupling. The special feature of the cannula inflow was a backflow resistive unit for adjusting backflow in the process of ventricular puncture. In this study, we performed an in vivo experiment to install the direct cannulation centrifugal blood pump on a goat after cardiac arrest induced by ventricular fibrillation as a proof of concept. As a primary result, the mechanical circulatory support could start in a short period by around one minute installation from the start of cannulation, which could be effective for the recovery after cardiac arrest under the assisted flow of 1.6 L/min at 13,000 rpm of the cannulation pump. Consequently, the novel approach may be useful for the prompt start of mechanical circulatory support.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143558954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Acute Pain Recognition from Facial Expression Videos using Vision Transformers. 用视觉变形器识别面部表情视频中的急性疼痛。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10781616

Ghazal Bargshady, Calvin Joseph, Niraj Hirachan, Roland Goecke, Raul Fernandez Rojas

{"title":"Acute Pain Recognition from Facial Expression Videos using Vision Transformers.","authors":"Ghazal Bargshady, Calvin Joseph, Niraj Hirachan, Roland Goecke, Raul Fernandez Rojas","doi":"10.1109/EMBC53108.2024.10781616","DOIUrl":"10.1109/EMBC53108.2024.10781616","url":null,"abstract":"Pain assessment is significant for patients and clinicians in diagnosis and treatment injuries and disease. It could facilitate a patient's treatment process by monitoring patients' pain levels in an accurate and regular manner. Automated detection of pain from facial expressions is a useful technique to assess pain of patients with communication disabilities. In this study, video vision transformers (ViViT) enhanced for pain recognition tasks are presented to capture spatio-temporal, facial information relevant to estimating the binary classification of pain and, thus, to provide valuable insights for automated estimation. The developed model has been trained and evaluated on two acute pain datasets, including 51 subjects using a newly collected pain intensity dataset designated as the AI4PAIN Challenge dataset, and 87 subjects from the BioVid Pain dataset. As an ablation study we used two baseline models, ResNet50 and a hybrid deep learning model based on the pretrained ResNet50+3DCNN. The results demonstrated that the proposed ViViT outperform the other models in pain detection by achieving accuracy = 66.96% for AI4PAIN dataset and accuracy = 79.95% for BioVid dataset.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143559012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Methodology for Measurement in Vivo Ankle Joint Kinematics after Two Different Types of Total Ankle Arthroplasty. 两种不同类型全踝关节置换术后踝关节运动学测量方法。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782043

Rea Ikeda, Hiroaki Kurokawa, Shinichi Kosugi, Yasuhito Tanaka, Masataka Yamamoto, Hiroshi Takemura

{"title":"Methodology for Measurement in Vivo Ankle Joint Kinematics after Two Different Types of Total Ankle Arthroplasty.","authors":"Rea Ikeda, Hiroaki Kurokawa, Shinichi Kosugi, Yasuhito Tanaka, Masataka Yamamoto, Hiroshi Takemura","doi":"10.1109/EMBC53108.2024.10782043","DOIUrl":"10.1109/EMBC53108.2024.10782043","url":null,"abstract":"Revision surgery due to relatively high rates of loosening and implant subsidence is one of critical problems after total ankle arthroplasty (TAA). In Japan, ahead of the world, two types of TAA with differently shaped alumina ceramic implants are being used in recently. For one type, Standard TAA, an analysis of ankle joint kinematics after replacement has been performed. However, the method is specific to its implant for standard TAA, and ankle joint kinematics after the other type, Combined TAA, has not been analyzed or compared in terms of kinematics. In addition, the previous method has critical issue of reproducibility because it includes manual processes. The purpose of this study is to develop in vivo kinematics analysis method of ankle joint after Standard TAA and Combined TAA that can be used to compare them. Definition of reference systems using common implant shapes features enabled kinematics analysis independent of its shape. Also, calculating ankle joint kinematics using iterative closest point (ICP) algorithm enabled a uniform analysis without any manual processes. The proposed method allows comparison of ankle joint kinematics after Standard TAA and Combined TAA with automatically and reproducibility. The analysis results may lead to the development of optimal implant shapes.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143559876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Separation of fascicles for motor unit separability in reinnervated muscles for neuroprosthesis application. 在神经假体应用的再神经肌肉中分离运动单元的束带。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782049

Lang Qin, Siyu Wang, Kiara N Quinn, Pierce Perkins, Sami Tuffaha, Nitish V Thakor

引用次数: 0

Sleep structure discriminates patients with isolated REM sleep behavior disorder: a deep learning approach. 睡眠结构区分孤立的快速眼动睡眠行为障碍患者：一种深度学习方法。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782600

Simon Feuerstein, Ambra Stefani, Raphael Angerbauer, Kristin Egger, Abubaker Ibrahim, Evi Holzknecht, Birgit Hogl, Antonio Rodriguez-Sanchez, Matteo Cesari

{"title":"Sleep structure discriminates patients with isolated REM sleep behavior disorder: a deep learning approach.","authors":"Simon Feuerstein, Ambra Stefani, Raphael Angerbauer, Kristin Egger, Abubaker Ibrahim, Evi Holzknecht, Birgit Hogl, Antonio Rodriguez-Sanchez, Matteo Cesari","doi":"10.1109/EMBC53108.2024.10782600","DOIUrl":"10.1109/EMBC53108.2024.10782600","url":null,"abstract":"Rapid eye movement (REM) sleep behavior disorder (RBD) is a disorder characterized by increased muscle tone and dream-enactment behaviors in REM sleep. In its isolated form (iRBD), it is a prodromal stage of neurodegenerative diseases. Currently, diagnosis of RBD requires time-consuming and subjective visual inspection of polysomnography (PSG). We propose a novel fast and objective deep learning model to identify patients with iRBD based on their sleep structure. A total of 86 iRBD and 81 controls, who underwent PSG, were included in the study. A validated algorithm was used to generate hypnodensity graphs (i.e., probabilistic representations of sleep structure). A ResNet-18 model was trained on five datasets consisting of whole night hypnodensities (with and without augmentation), and shorter segments (4 hours, 2 hours, and 30 minutes) to discriminate iRBD from controls. Using entire-night hypnodensity had notable benefits in terms of performance compared to shorter length segments, leading to a mean macro F1 score of 0.717 (per-segment), and of 0.784 (per-subject). Our findings show that sleep structure is important for iRBD classification and could potentially help clinicians.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143559803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Validation of the estimated Effect of Ankle Foot Orthoses on Spinal Cord Injury Gait Using Subject-Adjusted Musculoskeletal Models. 使用受试者调整的肌肉骨骼模型验证踝足矫形器对脊髓损伤步态的估计效果。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782279

Sergio Galindo-Leon, Inge Eriks-Hoogland, Kenji Suzuki, Diego Paez-Granados

{"title":"Validation of the estimated Effect of Ankle Foot Orthoses on Spinal Cord Injury Gait Using Subject-Adjusted Musculoskeletal Models.","authors":"Sergio Galindo-Leon, Inge Eriks-Hoogland, Kenji Suzuki, Diego Paez-Granados","doi":"10.1109/EMBC53108.2024.10782279","DOIUrl":"10.1109/EMBC53108.2024.10782279","url":null,"abstract":"Simulation of assistive devices on pathological gait through musculoskeletal models offers the potential and advantages of estimating the effect of the device in several biomechanical variables and the device characteristics ahead of manufacturing. In this study, we introduce a novel musculoskeletal modelling approach to simulate the biomechanical impact of ankle foot orthoses (AFO) on gait in individuals with spinal cord injury (SCI). Leveraging data from the Swiss Paraplegic Center, we constructed anatomically and muscularly scaled models for SCI-AFO users, aiming to predict changes in gait kinematics and kinetics. The importance of this work lies in its potential to enhance rehabilitation strategies and improve quality of life by enabling the pre-manufacturing assessment of assistive devices. Despite the application of musculoskeletal models in simulating walking aids effects in other conditions, no predictive model currently exists for SCI gait. Evaluation through RMSE showed similar results compared with other pathologies, simulation errors ranged between 0.23 to 2.3 degrees in kinematics. Moreover, the model was able to capture ankle joint muscular asymmetries and predict symmetry improvements with AFO use. However, the simulation did not reveal all the AFO effects, indicating a need for more personalized model parameters and optimized muscle activation to fully replicate orthosis effects on SCI gait.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synthetic ultrasound images to benchmark echocardiography-based biomechanics. 合成超声图像，为基于超声心动图的生物力学提供基准。

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782447

Tanmay Mukherjee, Sunder Neelakantan, Kyle Myers, Carl Tong, Reza Avazmohammadi

{"title":"Synthetic ultrasound images to benchmark echocardiography-based biomechanics.","authors":"Tanmay Mukherjee, Sunder Neelakantan, Kyle Myers, Carl Tong, Reza Avazmohammadi","doi":"10.1109/EMBC53108.2024.10782447","DOIUrl":"10.1109/EMBC53108.2024.10782447","url":null,"abstract":"Brightness mode (B-mode) ultrasound is a common imaging modality in the clinical assessment of several cardiovascular diseases. The utility of ultrasound-based functional indices such as the ejection fraction (EF) and stroke volume (SV) is widely described in diagnosing advanced-stage cardiovascular diseases. Additionally, structural indices obtained through the analysis of cardiac motion have been found to be important in the early-stage assessment of structural heart diseases, such as hypertrophic cardiomyopathy and myocardial infarction. Estimating heterogeneous variations in cardiac motion through B-mode ultrasound imaging is a crucial component of patient care. Despite the benefits of such imaging techniques, motion estimation algorithms are susceptible to variability between vendors due to the lack of benchmark motion quantities. In contrast, finite element (FE) simulations of cardiac biomechanics leverage well-established constitutive models of the myocardium to ensure reproducibility. In this study, we developed a methodology to create synthetic B-mode ultrasound images from FE simulations. The proposed methodology provides a detailed representation of displacements and strains under complex mouse-specific loading protocols of the LV. A comparison between the synthetic images and FE simulations revealed qualitative similarity in displacement patterns, thereby yielding benchmark quantities to improve the reproducibility of motion estimation algorithms. Thus, the study provides a methodology to create an extensive repository of images describing complex motion patterns to facilitate the enhanced reproducibility of cardiac motion analysis.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Impact of Cross-Validation Schemes for EEG-Based Auditory Attention Detection with Deep Neural Networks. 交叉验证方案对基于脑电图的深度神经网络听觉注意力检测的影响

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Pub Date : 2024-07-01 DOI: 10.1109/EMBC53108.2024.10782636

Gabriel Ivucic, Saurav Pahuja, Felix Putze, Siqi Cai, Haizhou Li, Tanja Schultz

{"title":"The Impact of Cross-Validation Schemes for EEG-Based Auditory Attention Detection with Deep Neural Networks.","authors":"Gabriel Ivucic, Saurav Pahuja, Felix Putze, Siqi Cai, Haizhou Li, Tanja Schultz","doi":"10.1109/EMBC53108.2024.10782636","DOIUrl":"10.1109/EMBC53108.2024.10782636","url":null,"abstract":"This study assesses the performance of different cross-validation splits for brain-signal-based Auditory Attention Decoding (AAD) using deep neural networks on three publicly available Electroencephalography datasets. We investigate the effect of trial-specific knowledge during training and assess adaptability to diverse scenarios with a trial-independent split. Introducing a causal time-series split, and simulating online decoding, our results demonstrate a consistent performance increase for auditory attention classification. These positive outcomes provide valuable insights for the development of future brain-signal-based AAD systems, emphasizing the potential for practical, person-dependent AAD applications. The results highlight the importance of diverse evaluation methodologies for enhancing generalizability in developing effective neurofeedback systems and assistive technologies for auditory processing disorders under more real-life conditions.","PeriodicalId":72237,"journal":{"name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","volume":"2024 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0