300 research outputs found
Explaining Network Decision Provides Insights on the Causal Interaction Between Brain Regions in a Motor Imagery Task
No full textNeural decoding widely exploits machine learning for classifying electroencephalographic (EEG) signals for brain-computer interface applications. Recent advancements in neural decoding regards the use of brain functional connectivity estimates as input features and the adoption of convolutional neural networks (CNNs) to realize decoders. Moreover, explainable artificial intelligence (XAI) approaches based on CNNs are growing interest in the neuroscience community, for validating the knowledge learned by networks and for using the decoder not only to classify the EEG but also to analyze it in a data-driven way, without a priori assumptions. However, the adoption of connectivity estimates for neural decoding is still in its infancy, as adopts non-directed connectivity measures, limits the analysis of few interactions/frequency ranges, and exploits classic machine learning approaches without exploring CNNs. Moreover, XAI approaches have never been applied to analyze EEG-based functional connectivity. To overcome these limitations, we design and apply a CNN for processing directed connectivity measures estimated via spectral Granger causality. The CNN automatically learns features in the frequency and spatial domains, and it is coupled with an explanation technique (DeepLIFT) for highlighting the most relevant connectivity inflow and outflow associated to each decoded brain state. Our approach is applied to motor imagery decoding, and achieves state-of-the-art performance compared to existing networks. DeepLIFT relevance representations match the directional interactions known occurring when imagining movements, validating the features related to the brain network, as learned by the CNN
Ruolo della Risonanza Magnetica nella staziazione e nel follow-up delle neoplasie laringee
No full textOrthoimage Generation by GÖKTÜRK-1: A Test Case in Rome
No full textThe paper presents a first evaluation of the potentialities of the imagery acquired by the GÖKTÜRK-1 satellite for the generation of orthoimages. Starting from a stereo pair captured over Rome (Italy), two orthoimages were generated with the Free and Open Source Software DATE developed at the Geodesy and Geomatics Division, Sapienza University of Rome. The two orthoimages were compared to a map of Rome at 1:2000 scale: only translations in the East and North directions were detected as geolocation errors, compliant with the expected geolocation accuracy of GÖKTÜRK-1 (CE90 of 10 m with no Ground Control Points). Specifically, an East bias of approximately -8 m was found for both the orthoimages, whereas a North bias of 1 m was detected for the quasi nadiral image and a much higher North bias of -7 m was observed for the second image, displaying an off-nadir angle of about 25 degrees. These geolocation errors can be in principle corrected using just one Ground Control Point, enabling the production of orthophoto maps at 1:5000 scale from GÖKTÜRK-1 pseudo-nadiral imagery
Multi-modal Decoding of Reach-to-Grasping from EEG and EMG via Neural Networks
No full textConvolutional neural networks (CNNs) have revolutionized motor decoding from electroencephalographic (EEG) signals, showcasing their ability to outperform traditional machine learning, especially for Brain-Computer Interface (BCI) applications. By processing also other recording modalities (e.g., electromyography, EMG) together with EEG signals, motor decoding improved. However, multi-modal algorithms for decoding hand movements are mainly applied to simple movements (e.g., wrist flexion/extension), while their adoption for decoding complex movements (e.g., different grip types) is still under-investigated. In this study, we recorded EEG and EMG signals from 12 participants while they performed a delayed reach-to-grasping task towards one out of four possible objects (a handle, a pin, a card, and a ball), and we addressed multi-modal EEG+EMG decoding with a dual-branch CNN. Each branch of the CNN was based on EEGNet. The performance of the multi-modal approach was compared to mono-modal baselines (based on EEG or EMG only). The multi-modal EEG+EMG pipeline outperformed the EEG-based pipeline during movement initiation, while it outperformed the EMG-based pipeline in motor preparation. Finally, the multi-modal approach was capable of accurately discriminating between grip types widely during the task, especially from movement initiation. Our results further validate multi-modal decoding for potential future BCI applications, aiming at achieving a more natural user experience
SWOT Level 2 Lake Single-Pass Product: The L2_HR_LakeSP Data Preliminary Analysis for Water Level Monitoring
No full textThe Surface Water and Ocean Topography (SWOT) mission, launched in December 2022, aims to address the crucial environmental goal of water monitoring to support preparedness for extreme events and facilitate adaptation to climate change on global and local scales. This mission will provide a comprehensive inventory of worldwide water resources, lakes, reservoir storage, and river dynamics. In this work, we carried out a preliminary assessment of SWOT’s Lake product Level 2 version 1.1, also known as “L2_HR_LakeSP”. The analysis was performed across six diverse lakes on three continents, revealing an average median bias of 0.08 m with respect to the considered reference, after suitable outlier removal. An overall precision of 0.22 m was found, combined with an average correlation of 68% between SWOT and reference time series. Moreover, the accuracy varied in the considered six lakes, since biases up to some decimeters were found for some of them; they could be due to residual inconsistencies between the vertical reference frame of SWOT and that of the considered reference. In summary, the first analysis of the “L2_HR_LakeSP” product, Version 1.1, demonstrated the promising potential of SWOT for monitoring seasonal variations in water levels. Nevertheless, notable anomalies were found in the water masks, particularly in higher latitudes, suggesting potential difficulties in accurately delineating water bodies in those regions. Additionally, a discernible reduction in accuracy was observed towards the end of the monitoring period. These preliminary findings indicate some issues that should be addressed in future investigations about the quality and potential of SWOT’s lake products for advancing our understanding of global water dynamics
SpeechBrain-MOABB: An open-source Python library for benchmarking deep neural networks applied to EEG signals
No full textDeep learning has revolutionized EEG decoding, showcasing its ability to outperform traditional machine learning models. However, unlike other fields, EEG decoding lacks comprehensive open-source libraries dedicated to neural networks. Existing tools (MOABB and braindecode) prevent the creation of robust and complete decoding pipelines, as they lack support for hyperparameter search across the entire pipeline, and are sensitive to fluctuations in results due to network random initialization. Furthermore, the absence of a standardized experimental protocol exacerbates the reproducibility crisis in the field. To address these limitations, we introduce SpeechBrain-MOABB, a novel open-source toolkit carefully designed to facilitate the development of a comprehensive EEG decoding pipeline based on deep learning. SpeechBrain-MOABB incorporates a complete experimental protocol that standardizes critical phases, such as hyperparameter search and model evaluation. It natively supports multi-step hyperparameter search for finding the optimal hyperparameters in a high-dimensional space defined by the entire pipeline, and multi-seed training and evaluation for obtaining performance estimates robust to the variability caused by random initialization. SpeechBrain-MOABB outperforms other libraries, including MOABB and braindecode, with accuracy improvements of 14.9% and 25.2% (on average), respectively. By enabling easy-to-use and easy-to-share decoding pipelines, our toolkit can be exploited by neuroscientists for decoding EEG with neural networks in a replicable and trustworthy way
Brain metastasis in head and neck squamous cell carcinoma after immune check point inhibitors treatment
No full text
- …
