eyeSay: Brain Visual Dynamics Decoding With Deep Learning &amp; Edge Computing

Zou, Jiadao; Zhang, Qingxue

doi:10.1109/tnsre.2022.3193714

Cited by 7 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It will be promising to further enhance the system with more effective pattern extraction [ 37 , 38 , 39 , 40 ] studies. The proposed approaches could also be generalized to other applications or signals [ 41 , 42 , 43 , 44 ] for event detection, template signal learning, and signal quality purification.…”

Section: Resultsmentioning

confidence: 99%

Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction

Zhang

Zhou

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Background: Internet-of-things technologies are reshaping healthcare applications. We take a special interest in long-term, out-of-clinic, electrocardiogram (ECG)-based heart health management and propose a machine learning framework to extract crucial patterns from noisy mobile ECG signals. Methods: A three-stage hybrid machine learning framework is proposed for estimating heart-disease-related ECG QRS duration. First, raw heartbeats are recognized from the mobile ECG using a support vector machine (SVM). Then, the QRS boundaries are located using a novel pattern recognition approach, multiview dynamic time warping (MV-DTW). To enhance robustness with motion artifacts in the signal, the MV-DTW path distance is also used to quantize heartbeat-specific distortion conditions. Finally, a regression model is trained to transform the mobile ECG QRS duration into the commonly used standard chest ECG QRS durations. Results: With the proposed framework, the performance of ECG QRS duration estimation is very encouraging, and the correlation coefficient, mean error/standard deviation, mean absolute error, and root mean absolute error are 91.2%, 0.4 ± 2.6, 1.7, and 2.6 ms, respectively, compared with the traditional chest ECG-based measurements. Conclusions: Promising experimental results are demonstrated to indicate the effectiveness of the framework. This study will greatly advance machine-learning-enabled ECG data mining towards smart medical decision support.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction

Zhang

Zhou

2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The prediction output from the softmax layer was utilized in the classification layer to recognize the eye-writing characters using cross-entropy loss (CE). The final output of the TCN is given in equation ( 8) where P 𝑖 and q 𝑖 represent the ground truth of a character among all other eye-writing characters and probabilities generated, respectively [55].…”

Section: Temporal Convolutional Networkmentioning

confidence: 99%

Translated Pattern-Based Eye-Writing Recognition Using Dilated Causal Convolution Network

Bature,

Abdullahi,

Chiracharit

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Recently, eye-writing has been used as a novel language communication method, in which the paths of eye movement are detected for character recognition. However, instability of the eyes causes gaze points to form a character with a non-uniform shape and distinct writing style across participants. The non-uniformity affected the performance of the recognition algorithms and set back the applicability of eyewriting. In this paper root translation and dilated causal convolutional (DCC) layers are utilized to model the non-uniformity in eye-writing patterns. The root translation shifted the pattern to have uniform root gaze points by obtaining the difference between the initial gaze points and subsequent gaze points. The translated patterns were used to train the temporal convolution network (TCN) having three stacked DCC layers with different filter and dilation factors. The DCC layers extract temporal dependencies in the pattern by convolving a particular gaze point with a certain previous gaze point within its receptive field. To evaluate the performance of the proposed method, a dataset of 36 eye-writing characters including 26 English and 10 Arabic numerals was recorded from 20 participants using Tobii eye tracker. The evaluation results depicted that our proposed method achieved an accuracy of 96.20% on our newly designed English and Arabic numeral datasets. The proposed method outperform conventional methods by achieving 98.81%, 97.76%, and 93.51% on HideMyGaze, Complex gaze gesture, and Isolated Japanese Katakana datasets, respectively.

show abstract

“…We here model the . → B relationship with a Bayesian linear regression function [27] as (4), where U(.) is the loss prediction function, X is the noise, and B is the actual loss corresponding to the AE configuration .…”

Section: Ibbd: Iomt Big-data Bayesian-backward Deep-encoder Learningmentioning

confidence: 99%

“…ITH advancements of electronics, wireless, and intelligent algorithms [1,2], Internet of Medical Things (IoMT) [3,4], with high efficiency, intelligence, reliability, connectivity, and more features, is attracting intensive interests for smart health applications [5][6][7][8]. With the potential to continuously stream human bio-dynamics to the cloud, it is expected that IoMT can greatly boost the big data-driven precision health practices.…”

Section: Introductionmentioning

confidence: 99%

Efficient IoT Big Data Streaming With Deep-Learning-Enabled Dynamics

Wong

Piuri

Scotti

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

Internet of Medical Things (IoMT) is igniting many emerging smart health applications, by continuously streaming the big data for data-driven innovations. One critical obstacle in IoMT big data is the power hungriness of long-term data transmission. Targeting this challenge, we propose a novel framework called, IoMT Big-data Bayesian-backward Deepencoder learning (IBBD), which mines deep autoencoder (AE) configurations for data sparsification and determines optimal trade-offs between information loss and power overhead. More specifically, the IBBD framework leverages an additional external Bayesian-backward loop that recommends AE configurations, on top of a traditional deep learning loop that executes and evaluate the AE quality. The IBBD recommendation is based on confidence to further minimize the regularized metrics that quantify the quality of AE configurations, and it further leverages regularization techniques to allow adjusting error-power tradeoffs in the mining process. We have conducted thorough experiments on a cardiac data streaming application and demonstrated the superiority of IBBD over the common practices like Discrete Wavelet Transform, and we have further generalized IBBD through validating the optimal AE configurations determined on one user to other users. This study is expected to greatly advance IoMT big data streaming practices towards precision medicine.

show abstract

eyeSay: Brain Visual Dynamics Decoding With Deep Learning & Edge Computing

Cited by 7 publications

References 40 publications

Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction

Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction

Translated Pattern-Based Eye-Writing Recognition Using Dilated Causal Convolution Network

Efficient IoT Big Data Streaming With Deep-Learning-Enabled Dynamics

Contact Info

Product

Resources

About