Vishal Jain, M. Forssell, Derya Z. Tansel, Chaitanya Goswami, G. Fedder, P. Grover, M. Chamanzar
{"title":"High resolution focused non-invasive electrical stimulation of motor cortex in rodent model","authors":"Vishal Jain, M. Forssell, Derya Z. Tansel, Chaitanya Goswami, G. Fedder, P. Grover, M. Chamanzar","doi":"10.1109/NER52421.2023.10123813","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123813","url":null,"abstract":"Transcranial electrical stimulation (TES), a technique for stimulating the brain without surgical intervention, has potential applications for therapeutic interventions as well as brain-computer interfaces. One of the known limitations of conventional TES is that the stimulation volume is very large, due to the size and placement of electrodes typically used, which does not allow accurate targeting and results in large off-target activation. This work demonstrates a novel method for high resolution transcranial stimulation of motor cortex in mouse models using a flexible ultra-high-density electrode array. An electrode array was designed with ring-shaped electrodes having a hole in the middle, allowing simultaneous transcranial stimulation and intracortical recording using a commercial silicon neural probe. Intracortical recordings performed during transcranial stimulation, at both the stimulation target and at adjacent locations spaced at a 650 μm pitch, demonstrate the spatial localization of the evoked neural activity. Significant multi-unit activity was recorded at the center of the stimulation zone in the 15ms following stimulation, while low off-target activity is measured 650 μm away from the center. The locus of the stimulation was moved at four different locations in the cortex, with similar localized intracortical response obtained at all locations. Simultaneous stimulation of multiple sites was also demonstrated.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115722068","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}
{"title":"Semi-supervised adaptation of upper-limb myoelectric pattern recognition prosthesis control through virtual gameplay","authors":"Andru Liu, Matthew L. Elwin, Zachary A. Wright","doi":"10.1109/NER52421.2023.10123898","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123898","url":null,"abstract":"Advanced machine learning algorithms can adapt to variation in new data inputs. Such adaptive algorithms have been employed on myoelectric pattern recognition control systems to improve upper-limb prosthesis performance. When training their control system, prosthesis users typically attempt to make consistent and repeatable muscle contractions. However, minimizing input data variation does not always resemble realistic usage scenarios as several factors (muscle fatigue, limb position, electrode shift, etc.) can contribute to changes in the characteristics of the muscle signals that could lead to poor controller performance. While it may be difficult to account for all the possible variation, prosthesis users may benefit from training that better mimics real-life prosthesis use. This paper investigates the use of virtual games, developed for practicing specific aspects of myoelectric prosthesis control, to adapt a linear discriminant analysis (LDA) model in a semi-supervised manner. Results from offline analysis of virtual game data collected across two weeks showed that classification error rates were better for 7 out of 10 prosthesis users when applying an adaptive LDA model compared to a traditional non-adaptive LDA model. We also compare these results to an alternative model in which we apply a heuristic set of rules to identify and relabel “misclassified” predicted outputs during virtual game play before evaluating the classification performance of an adaptive LDA classifier with re-labeled inputs. Virtual games are a promising clinical tool which can be applied to better learn the user's control preferences under simulated use conditions. Further development of this work could impact daily prosthesis use and performance for those who use myoelectric pattern recognition-controlled prostheses.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123054185","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}
Ruofan Liu, Satyam Kumar, Hussein Alawieh, E. Carnahan, J. Millán
{"title":"On Transfer Learning for Naive Brain Computer Interface Users","authors":"Ruofan Liu, Satyam Kumar, Hussein Alawieh, E. Carnahan, J. Millán","doi":"10.1109/NER52421.2023.10123866","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123866","url":null,"abstract":"Motor Imagery (MI) based Brain-Computer Interfaces (BCI) typically require the collection of subject-specific calibration data to build a classifier of motor intent. The BCI users are then trained over multiple online sessions with real-time feedback using the calibrated decoder to acquire MI skills. The subject-specific calibration session is thought to be necessary for accurate MI decoding due to the wide variability in electroencephalogram (EEG) signals across the population. The process of acquiring calibration data is long and tedious and includes training individualized decoding models for each subject. Transfer Learning setups can help circumvent this individualized calibration and decoder training phase by using data acquired from previous subjects. This paper first proposes a geometry-aware deep learning architecture that exploits the spatial similarity of MI neural activity between BCI users. We show the efficacy of the proposed approach by classifying the motor intentions of 18 naive BCI subjects. In a subject-specific setting, our proposed method significantly outperforms classical decoding algorithms. Next, we train the proposed network and skip the subject-specific calibration data to mimic a transfer learning setting. We show that our model architecture achieves similar performance to subject-specific decoders in the transfer learning setting. This finding opens the door to robust BCIs that are readily transferable across subjects without the need for subject-specific calibration and individualized decoding models.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122033203","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}
Naser Sharatfhani, John M. Long, S. Adams, Abbas Z. Kouzani
{"title":"Novel Neural Microprobe with Adjustable Stiffness","authors":"Naser Sharatfhani, John M. Long, S. Adams, Abbas Z. Kouzani","doi":"10.1109/NER52421.2023.10123721","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123721","url":null,"abstract":"To successfully insert a microprobe into the brain and record/stimulate the target neural tissue, it must meet two opposing requirements. Firstly, it must be stiff enough to tolerate the penetration force during insertion. Secondly, it must be compliant enough to withstand brain micromotion during operation, since a mechanical mismatch between the stiff microprobe and soft surrounding neural tissue leads to neural tissue damage and, ultimately, the failure of the microprobe within a few weeks/months of implantation. The design proposed in this study enables the creation of a neural microprobe whose elastic modulus varies from 4.2 GPa during insertion to 149 kPa during operation, as a function of the applied motion. The proposed mechanism for changing the stiffness works independently of the microprobe fabrication material and the surrounding environment's conditions. The microprobe and surrounding neural tissue are simulated to calculate the elastic modulus of the microprobe based on the finite element method and investigate the induced strain on the tissue by the brain longitudinal and lateral micromotions, simultaneously. The obtained results show that the maximum strain on the tissue surrounding the proposed microprobe is ~59 % less than that of the classic cylindrical microprobe with the same material, diameter, and length. The microprobe is fabricated based on two-photon polymerization technology.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129949624","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}
{"title":"Optimizing Neuromorphic Spike Encoding of Dynamic Stimulus Signals Using Information Theory","authors":"Ahmad El Ferdaoussi, J. Rouat, É. Plourde","doi":"10.1109/NER52421.2023.10123854","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123854","url":null,"abstract":"Neuromorphic systems use spike representations of stimuli as inputs. These systems should ensure that the spikes carry a maximum amount of information on the signals that they encode. There is a pressing need to better understand how to maximize the information encoded into spikes, as it can have important implications for the outcome of the applications in which the spike representations are used. This work proposes the use of information theory, specifically the information rate, to maximize the information that a spike train carries on the signal that is encoded. The method consists of varying the encoding parameters to produce spike trains of different densities, and then estimating the information rate between the signal and the spike train over the entire range of spike densities. This allows to find an estimate of the spike density that maximizes the information rate, and therefore the optimal encoding parameters. The method is applied to the encoding of two stimuli (Brownian motion and speech) with a Leaky Integrate-and-Fire neuron. The proposed approach is fast and general, as it can be used with any dynamic stimulus input and any spike encoding technique. It offers a rigorous solution to the problem of spike encoding optimization and allows the separation of the encoding stage from task-specific applications that use spikes as inputs.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128675717","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}
Kai Yuan, Chun Hang Eden Ti, Chengpeng Hu, Raymond K. Tong
{"title":"The Effects of Anodal Oscillatory Transcranial Direct Current Stimulation on Top-Down Cortico-Muscular Control: A Pilot Study","authors":"Kai Yuan, Chun Hang Eden Ti, Chengpeng Hu, Raymond K. Tong","doi":"10.1109/NER52421.2023.10123900","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123900","url":null,"abstract":"Oscillatory transcranial direct current stimulation (otDCS) is a novel non-invasive stimulation protocol that combines the characteristics of both transcranial direct current and alternating current stimulation. Therefore, it has the ability to simultaneously modulate the potential and oscillatory activities of neuronal membranes. In this pilot study, anodal otDCS in different frequencies (20 Hz, 25 Hz, and 30 Hz) in the beta band were applied to 4 healthy subjects. High-density EEG and EMG were collected during a simple isometric finger contraction task. The modulation effects of otDCS on the top-down motor control were explored using generalized partial directed coherence (GPDC), which is a directed measurement of cortico-muscular interactions in both top-down and bottom-up directions. The individual peak frequencies for top-down GPDC was $20.25pm 2.06$. There was a trend toward an increase in top-down GPDC after 20 Hz anodal otDCS, but not after 25 Hz or 30 Hz otDCS. The findings in this pilot study imply the effect of 20 Hz otDCS on top-down motor control, which can be applied to patients with impairment in motor control, such as stroke survivors. Our results also suggest the potential effectiveness of otDCS in the individual peak frequency in the beta band, which might be investigated in future studies.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126812436","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}
G. Gagliardi, A. L. Alfeo, V. Catrambone, M. G. Cimino, Marina De Vos, G. Valenza
{"title":"Fine-Grained Emotion Recognition Using Brain-Heart Interplay Measurements and eXplainable Convolutional Neural Networks","authors":"G. Gagliardi, A. L. Alfeo, V. Catrambone, M. G. Cimino, Marina De Vos, G. Valenza","doi":"10.1109/NER52421.2023.10123758","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123758","url":null,"abstract":"Emotion recognition from electro-physiological signals is an important research topic in multiple scientific domains. While a multimodal input may lead to additional information that increases emotion recognition performance, an optimal processing pipeline for such a vectorial input is yet undefined. Moreover, the algorithm performance often compromises between the ability to generalize over an emotional dimension and the explainability associated with its recognition accuracy. This study proposes a novel explainable artificial intelligence architecture for a 9-level valence recognition from electroencephalographic (EEG) and electrocardiographic (ECG) signals. Synchronous EEG-ECG information are combined to derive vectorial brain-heart interplay features, which are rearranged in a sparse matrix (image) and then classified through an explainable convolutional neural network. The proposed architecture is tested on the publicly available MAHNOB dataset also against the use of vectorial EEG input. Results, also expressed in terms of confusion matrices, outperform the current state of the art, especially in terms of recognition accuracy. In conclusion, we demonstrate the effectiveness of the proposed approach embedding multimodal brain-heart dynamics in an explainable fashion.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127019199","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}
John M. Rattray, Maxwell Ujhazy, Robert Stevens, Ralph Etienne-Cummings
{"title":"Assistive Multimodal Wearable for Open Air Digit Recognition Using Machine Learning","authors":"John M. Rattray, Maxwell Ujhazy, Robert Stevens, Ralph Etienne-Cummings","doi":"10.1109/NER52421.2023.10123870","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123870","url":null,"abstract":"To increase access to digital systems for populations suffering from upper limb motor impairment we present an assistive wearable device to capture gestures performed in air. These open air gestures provide an interface for users who are unable to exhibit the fine motor control needed for standardized human computer interfaces utilizing miniature button input such as keyboards and keypads. By capturing the motion performed at the wrist by an accelerometer as well as the muscle activation signatures using surface electromyography, we improve the classification accuracy as compared to using either modality alone. Twelve features were extracted from the multimodal time series data in both the time and frequency domain and used as input to a collection 4 machine learning models for classification, Fine Tree, K-Nearest Neighbor, Support Vector Machine, and Artificial Neural Network. One subject performed the task of writing single digits in free space and after post-processing and feature extraction we achieved a classification accuracy of 96.2% for binary discrimination of digits zero and one using a support vector machine model and an accuracy of 71% when classifying all 10 digits using an artificial neural network. Our findings indicate the feasibility of a wearable multimodal human computer interface to relieve the burden conventional interfaces present to motor impaired users.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"23 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124529640","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}
{"title":"Wireless Sensors with Edge Deep Learning for Detecting and Alerting the Freezing of Gait Symptoms in Parkinson's Patients*","authors":"Ourong Lin, Tian Yu, Yuhan Hou, Yi Zhu, Xilin Liu","doi":"10.1109/NER52421.2023.10123828","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123828","url":null,"abstract":"This paper presents the design of a wireless sensor network for detecting and alerting the freezing of gait (FoG) symptoms in patients with Parkinson's disease. A novel button pin type sensor node design was developed for easy attachment. Three sensor nodes, each integrating a 3-axis accelerometer, can be placed on a patient at their ankle, thigh, and truck. Each sensor node can independently detect FoG using an on-device deep learning (DL) model, featuring a convolutional neural network (CNN). The DL model outputs from the three sensor nodes are processed in a central node using a majority voting algorithm. In a validation using a public dataset, the prototype developed achieved an FoG detection sensitivity of 88.8% and an F1 score of 85.34%, using less than 20k trainable parameters per sensor node. Once FoG is detected, an auditory signal will be generated to alert users, and the alarm signal will also be sent to mobile phones for further actions if needed. The sensor node can be easily recharged wirelessly by inductive coupling. The system is self-contained and processes all user data locally without streaming data to external devices or the cloud, thus eliminating the cybersecurity risks and power penalty associated with wireless data transmission. The developed methodology can be used in a wide range of applications.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127670035","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}
Adam Fitchett, J. Fabbri, Yaoxing Hu, J. Cange, Karolina Kozeniauskaite, K. Shepard, D. Holder, K. Aristovich
{"title":"Imaging Circuit Activity in the Rat Brain with Fast Neural EIT and Depth Arrays","authors":"Adam Fitchett, J. Fabbri, Yaoxing Hu, J. Cange, Karolina Kozeniauskaite, K. Shepard, D. Holder, K. Aristovich","doi":"10.1109/NER52421.2023.10123878","DOIUrl":"https://doi.org/10.1109/NER52421.2023.10123878","url":null,"abstract":"Few techniques are specialized for neuroscience at the “mesoscopic” level of neural circuits. Fast neural electrical impedance tomography (fnEIT) is a novel imaging technique that offers affordability, portability, and high spatial $(sim 100 mu mathrm{m})$ and temporal (~1 ms) resolution. fnEIT with depth arrays offers the opportunity to study the dynamics of circuits in the brains of animal models. However, current depth array geometries are not optimized for this imaging modality. They feature small, closely packed electrodes with high impedance that do not provide sufficient SNR for high resolution EIT image reconstruction. They also have a highly limited range. It is necessary to develop depth arrays suitable for fnEIT and evaluate their performance in a representative setting for circuit neuroscience. In this study, we optimized the geometry of depth arrays for fnEIT, and then investigated the prospects of imaging thalamocortical circuit activity in the rat brain. Optimization was consistent with the hypothesis that small, closely spaced electrodes were not suitable for fnEIT. In vivo experiments with the optimized geometry then showed that fnEIT can image thalamocortical circuit activity at a high enough resolution to see the activity propagating from specific thalamic nuclei to specific regions of the somatosensory cortex. This bodes well for fnEIT's potential as a technique for circuit neuroscience.","PeriodicalId":201841,"journal":{"name":"2023 11th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127965070","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}