IP Library › Granted Patent US 12,333,443
Granted Patent B2
US 12,333,443 · App. 17/356,342 · Granted Jun 17, 2025

Systems and methods for using federated learning for training centralized seizure detection and prediction models on decentralized datasets

Inventors: Sharanya Arcot Desai (Sunnyvale, CA); Thomas K. Tcheng (Pleasant Hill, CA)
Assignee: NeuroPace, Inc
G06N3/098G06F8/65G16H50/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,333,443
App. No.
17/356,342
Granted
Jun 17, 2025
Kind
B2
Abstract

A server for updating a current version of a machine learning model resident in implanted medical devices includes an interface, a memory, and a processor. The interface is configured to receive a plurality of updated versions of the machine learning model from a plurality of remote sources remote from the server. The remote source may be, e.g., implanted medical devices and/or subservers. The processor is coupled to the memory and the interface and is configured to aggregate the plurality of updated versions to derive a server-updated version of the machine learning model, and to transmit the server-updated version of the machine learning model to one or more of the plurality of remote sources as a replacement for the current version of the machine learning model.

Claims (93)

1. A method of replacing a first machine learning model of a first architecture resident in a plurality of implanted medical devices, wherein the first machine learning model is generated using a first dataset and is configured to detect a neurological event in electrical activity of a brain, the method comprising:

providing, from a server to each of a plurality of remote sources remote from the server, information on a second dataset for generating a second machine learning model of a second architecture different than the first architecture, which second dataset includes at least one type of data that is not included in the first dataset and comprises records of electrical activity collected in response to detections of neurological events by the first machine learning model;

generating, at each of the plurality of remote sources, a version of the second machine learning model based on a corresponding second dataset;

receiving, at a server, a plurality of versions of the second machine learning model from the plurality of remote sources;

aggregating, at the server, the plurality of versions of the second machine learning model to derive a server-generated version of the second machine learning model; and

transmitting, at the server, the server-generated version of the second machine learning model to one or more of the plurality of remote sources as a replacement for the first machine learning model.

2. The method of claim 1 , wherein:

the second machine learning model comprises a neural network architecture having a plurality of nodes, and is characterized by a plurality of biases, each of the plurality of biases being associated with a corresponding node of the plurality of nodes, and

aggregating the plurality of versions of the second machine learning model comprises:

for at least one node of the plurality of nodes included in the plurality of versions of the second machine learning model, calculating an average of the biases associated with the at least one node, and

assigning the average to the at least one node.

3. The method of claim 2 , wherein aggregating the plurality of versions of the second machine learning model further comprises:

prior to calculating an average of the biases, applying a weight factor to each of the biases associated with the at least one node, wherein each weight factor is based on an amount of data included in the second dataset on which the version of the second machine learning model was trained.

4. The method of claim 1 , wherein:

the second machine learning model comprises a neural network architecture having a plurality of nodes and a plurality of interconnections between pair of nodes of the plurality of nodes, and is characterized by a plurality of weights, each weight of the plurality of weights being associated with a corresponding one of the plurality of interconnections, and

aggregating the plurality of versions of the second machine learning model comprises:

for at least one interconnection of the plurality of interconnections included in the plurality of versions of the second machine learning model, calculating an average of the weights associated with the at least one interconnection, and

assigning the average to the at least one interconnection.

5. The method of claim 4 , wherein aggregating the plurality of versions of the second machine learning model further comprises:

prior to calculating an average of the weights, applying a weight factor to each of the weights associated with the at least one interconnection, wherein each weight factor is based on an amount of data included in the second dataset on which the version of the second machine learning model was trained.

6. The method of claim 1 , wherein:

the second machine learning model comprises a neural network architecture having a plurality of nodes, and is characterized by a plurality of biases, each of the plurality of biases being associated with a corresponding node of the plurality of nodes, and

aggregating the plurality of versions of the second machine learning model comprises:

grouping the plurality of nodes into one or more sets of nodes based on one of probabilistic federated neural matching or federated matched averaging;

for at least one of the sets of nodes, calculating an average of the biases associated with the nodes in the at least one set of nodes; and

assigning the average to the nodes included in the at least one set of nodes.

7. The method of claim 1 , wherein:

the first machine learning model comprises a logistic regression having one or more parameters; and

the second machine learning model comprises one of a convolutional neural network (CNN); an autoencoder; and a recurrent neural network (RNN).

8. The method of claim 1 , wherein:

the plurality of remote sources comprises at least two of the plurality of implanted medical devices (IMD), and

the version of the second machine learning model generated by the at least two of the plurality of implanted medical devices is based on a second dataset stored in the respective implanted medical device.

9. The method of claim 8 , wherein generating a version of the second machine learning model comprises:

extracting features from a plurality of physiological records included in the second dataset; and

training the version of the second machine learning model on the extracted features.

10. The method of claim 9 , wherein each of the plurality of physiological records comprises:

electrical activity of a brain, and

at least one of neural tissue motion, heart rate, blood profusion, blood oxygenation, neurotransmitter concentrations, blood glucose, sweat hormones, body motion, and pH level.

11. The method of claim 9 , wherein each of the plurality of physiological records has a same tag, which identifies a common aspect among the plurality of physiological records, the common aspect corresponding to one of:

an occurrence of a neurological event;

absence of a neurological event; and

patient state.

12. The method of claim 8 , further comprising transmitting, at the at least two of the plurality of implanted medical devices, the IMD-generated version of the second machine learning model to the server.

13. The method of claim 8 , further comprising:

transmitting, at the at least two of the plurality of implanted medical devices, the IMD-generated version of the second machine learning model to a subserver remote from the server;

aggregating, at the subserver, the IMD-generated versions to derive a subserver-generated version of the second machine learning model; and

transmitting, at the one or more subservers, the subserver-generated version of the second machine learning model to the server, wherein the subserver-generated version corresponds to one of the plurality of versions of the second machine learning model aggregated at the server.

14. The method of claim 1 , wherein:

the plurality of remote sources comprises one or more subservers remote from the server,

the version of the second machine learning model generated by the one or more subservers is based on a second dataset received by the respective subserver from one or more of the plurality of implanted medical devices; and

and further comprising, transmitting, at the one or more subservers, the subserver-generated version of the second machine learning model to the server, wherein the subserver-generated version corresponds to one of the plurality of versions of the second machine learning model aggregated at the server.

15. The method of claim 14 , wherein generating a subserver-generated version comprises:

pooling, at the one or more subservers, a plurality of second datasets received from the one or more of the plurality of implanted medical devices to create a dataset pool; and

training, at the one or more subservers, the version of the second machine learning model on the dataset pool.

16. The method of claim 15 , wherein training comprises:

extracting, at the one or more subservers, features from a plurality of physiological records; and

training the version of the second machine learning model on the extracted features.

17. The method of claim 14 , wherein generating a subserver-generated version comprises:

for one or more of the implanted medical devices from which the one or more subservers receives a second dataset:

training, at the one or more subservers, the version of the second machine learning model on the second dataset to derive a version of the second machine learning model; and

aggregating, at the one or more subservers, the versions of the second machine learning model to derive the subserver-generated version of the second machine learning model.

18. The method of claim 14 , further comprising, at one or more of the plurality of implanted medical devices:

refraining from generating an IMD-generated version of the second machine learning model; and

refraining from receiving the subserver-generated version of the second machine learning model.

19. The method of claim 1 , further comprising:

testing the subserver-generated version of the second machine learning model prior to transmitting the subserver-generated version of the second machine learning model to one or more of the plurality of remote sources.

20. The method of claim 1 , wherein the plurality of versions of the second machine learning model is received at the server synchronously.

21. The method of claim 1 , wherein the plurality of versions of the second machine learning model is received at the server asynchronously.

22. A server for replacing a first machine learning model of a first architecture resident in a plurality of implanted medical devices, wherein the first machine learning model is generated using a first dataset and is configured to detect a neurological event in electrical activity of a brain, the server comprising:

an interface configured to receive a plurality of versions of a second machine learning model from a plurality of remote sources remote from the server;

a memory; and

a processor coupled to the memory and the interface and configured to:

provide to each of the plurality of remote sources remote from the server, information on a second dataset for generating a second machine learning model of a second architecture different than the first architecture, which second dataset includes at least one type of data that is not included in the first dataset and comprises records of electrical activity collected in response to detections of neurological events by the first machine learning model;

aggregate the plurality of versions of the second machine learning model to derive a server-generated version of the second machine learning model; and

transmit the server-generated version of the second machine learning model to one or more of the plurality of remote sources as a replacement for the first machine learning model.

23. The method of claim 1 , wherein the at least one type of data that is included in the second dataset but not in the first dataset comprises at least one of spectral power, an autocorrelation feature, a cross correlation feature, and a specified duration of a record of electrical activity.

24. An implantable medical device, comprising:

a first machine learning model of a first architecture, wherein the first machine learning model is generated using a first dataset and is configured to detect a neurological event in electrical activity of a brain;

an interface configured to:

receive information on a second dataset, which second dataset includes at least one type of data that is not included in the first dataset and comprises records of electrical activity collected in response to detections of neurological events by the first machine learning model, and

provide to a server, a version of a second machine learning model;

a memory storing data; and

a processor coupled to the memory and the interface and configured to:

extract the second dataset from the data stored i memory, and

generate the version of the second machine learning model based on the second dataset, wherein the second machine learning model is of a second architecture different than the first architecture.

25. The implantable medical device of claim 24 , wherein the processor is configured to generate the version of the second machine learning model by being further configured to train the second machine learning model on the second dataset.

26. The implantable medical device of claim 25 , wherein the processor is configured to train the second machine learning model on the second dataset by being further configured to:

extract features from a plurality of physiological records included in the second dataset; and

train the second machine learning model on the extracted features.

27. The implantable medical device of claim 26 , wherein each of the plurality of physiological records is of a same type.

28. The implantable medical device of claim 27 , wherein the same type comprises any one of:

electrical activity of a brain, neural tissue motion, heart rate, blood profusion, blood oxygenation, neurotransmitter concentrations, blood glucose, sweat hormones, body motion, and pH level.

29. The implantable medical device of claim 24 , wherein the processor is further configured to transmit the version of the second machine learning model to the server through the interface.

Assignments (2)
SECURITY INTEREST Recorded Jun 25, 2025
From: NEUROPACE, INC.
To: MIDCAP FUNDING IV TRUST
Reel/Frame 071712/0422 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 22, 2021
From: ARCOT DESAI, SHARANYA; TCHENG, THOMAS K.
To: NEUROPACE, INC.
Reel/Frame 057557/0586 →
Continuity (2)
Provisional Application 63043514 · Jun 24, 2020
Related Publication 20210407678A1 · Dec 30, 2021
References Cited (148)
US 6016449A · Fischell et al. · 2000 [cited by applicant]
US 6480743B1 · Kirkpatrick et al. · 2002 [cited by applicant]
US 6594524B2 · Esteller et al. · 2003 [cited by applicant]
US 6810285B2 · Pless et al. · 2004 [cited by applicant]
US 7209787B2 · Dilorenzo · 2007 [cited by applicant]
US 7231254B2 · Dilorenzo · 2007 [cited by applicant]
US 7242984B2 · Dilorenzo · 2007 [cited by applicant]
US 7277758B2 · Dilorenzo · 2007 [cited by applicant]
US 7280867B2 · Frei et al. · 2007 [cited by applicant]
US 7324851B1 · Dilorenzo · 2008 [cited by applicant]
US 7403820B2 · Dilorenzo · 2008 [cited by applicant]
US 7529582B1 · Dilorenzo · 2009 [cited by applicant]
US 7542803B2 · Heruth et al. · 2009 [cited by applicant]
US 7599736B2 · Dilorenzo · 2009 [cited by applicant]
US 7623928B2 · Dilorenzo · 2009 [cited by applicant]
US 7676273B2 · Goetz et al. · 2010 [cited by applicant]
US 7747325B2 · Dilorenzo · 2010 [cited by applicant]
US 7822481B2 · Gerber et al. · 2010 [cited by applicant]
US 7853322B2 · Bourget et al. · 2010 [cited by applicant]
US 7853329B2 · Dilorenzo · 2010 [cited by applicant]
US 7894903B2 · John · 2011 [cited by applicant]
US 7899545B2 · John · 2011 [cited by applicant]
US 7930035B2 · Dilorenzo · 2011 [cited by applicant]
US 7957797B2 · Bourget et al. · 2011 [cited by applicant]
US 7957809B2 · Bourget et al. · 2011 [cited by applicant]
US 7966073B2 · Pless et al. · 2011 [cited by applicant]
US 7974696B1 · Dilorenzo · 2011 [cited by applicant]
US 8027730B2 · John · 2011 [cited by applicant]
US 8126567B2 · Gerber et al. · 2012 [cited by applicant]
US 8543214B2 · Osorio et al. · 2013 [cited by applicant]
US 8543217B2 · Stone et al. · 2013 [cited by applicant]
US 8694115B2 · Goetz et al. · 2014 [cited by applicant]
US 8706237B2 · Giftakis et al. · 2014 [cited by applicant]
US 8731656B2 · Bourget et al. · 2014 [cited by applicant]
US 8903486B2 · Bourget et al. · 2014 [cited by applicant]
US 9931508B2 · Burdick et al. · 2018 [cited by applicant]
US 9955921B2 · Esteller et al. · 2018 [cited by applicant]
US 10123717B2 · Tcheng · 2018 [cited by applicant]
US 10252056B2 · Mogul · 2019 [cited by applicant]
US 10729907B2 · Desai et al. · 2020 [cited by applicant]
US 20030018367A1 · Dilorenzo · 2003 [cited by applicant]
US 20030171789A1 · Malek et al. · 2003 [cited by applicant]
US 20040199217A1 · Lee et al. · 2004 [cited by applicant]
US 20040199218A1 · Lee et al. · 2004 [cited by applicant]
US 20040215286A1 · Stypulkowski · 2004 [cited by applicant]
US 20040267330A1 · Lee et al. · 2004 [cited by applicant]
US 20050021103A1 · Dilorenzo · 2005 [cited by applicant]
US 20050021104A1 · Dilorenzo · 2005 [cited by applicant]
US 20050060007A1 · Goetz · 2005 [cited by applicant]
US 20050060008A1 · Goetz · 2005 [cited by applicant]
US 20060265022A1 · John et al. · 2006 [cited by applicant]
US 20070073355A1 · Dilorenzo · 2007 [cited by applicant]
US 20070142862A1 · Dilorenzo · 2007 [cited by applicant]
US 20070142874A1 · John · 2007 [cited by applicant]
US 20070162086A1 · Dilorenzo · 2007 [cited by applicant]
US 20070167991A1 · Dilorenzo · 2007 [cited by applicant]
US 20070208212A1 · Dilorenzo · 2007 [cited by applicant]
US 20070287931A1 · Dilorenzo · 2007 [cited by applicant]
US 20080058773A1 · John · 2008 [cited by applicant]
US 20080061961A1 · John · 2008 [cited by applicant]
US 20080071314A1 · John · 2008 [cited by applicant]
US 20080109005A1 · Trudeau et al. · 2008 [cited by applicant]
US 20080119900A1 · Dilorenzo · 2008 [cited by applicant]
US 20090018609A1 · Dilorenzo · 2009 [cited by applicant]
US 20100023089A1 · Dilorenzo · 2010 [cited by applicant]
US 20100217348A1 · Dilorenzo · 2010 [cited by applicant]
US 20100241183A1 · Dilorenzo · 2010 [cited by applicant]
US 20100249859A1 · Dilorenzo · 2010 [cited by applicant]
US 20110040353A1 · Gerber et al. · 2011 [cited by applicant]
US 20110307030A1 · John · 2011 [cited by applicant]
US 20160228705A1 · Crowder et al. · 2016 [cited by applicant]
US 20190117978A1 · Desai et al. · 2019 [cited by applicant]
US 20200272857A1 · Desai et al. · 2020 [cited by applicant]
WO 2016154298 · 2016 [cited by applicant]
Hard, A., Federated Learning for Mobile Keyboard Prediction, Retrieved from Internet:<https://arxiv.org/abs/1811.03604> (Year: 2019). [cited by examiner]
Dumpelmann, M., Early seizure detection for closed loop direct neurostimulation devices in epilepsy, Retrieved from Internet:<https://iopscience.iop.org/article/10.1088/1741-2552/ab094a/meta> (Year: 2019). [cited by examiner]
Smith, V., et al, Federated Multi-Task Learning, Retrieved from Internet:<https://proceedings.neurips.cc/paper/2017/hash/6211080fa89981f66b1a0c9d55c61d0f-Abstract.html> (Year: 2017). [cited by examiner]
Brown, J., Identification of novel DNA repair proteins via primary sequence, secondary structure, and homology, Retrieved from Internet:<https://link.springer.com/article/10.1186/1471-2105-10-25> (Year: 2009). [cited by examiner]
Camara, et al, Resting tremor classification and detection in Parkinson's disease patients, Retrieved from Internet:<https://www.sciencedirect.com/science/article/pii/S1746809414001414> (Year: 2015). [cited by examiner]
Eirich, T., Beam: A Tool for Flexible Software Update, Retrieved from Internet:<https://scholar.google.com/scholar?cluster=2104970323893850914&hl=en&as_sdt=0,47> (Year: 1994). [cited by examiner]
Kusonmano, et al, Effects of Pooling Samples on the Performance of Classification Algorithms: A Comparative Study, Retrieved from Internet:<https://onlinelibrary.wiley.com/doi/full/10.1100/2012/278352> (Year: 2012). [cited by examiner]
McMahan, et al, Communication-Efficient Learning of Deep Networks from Decentralized Data, Retrieved from Internet:<https://proceedings.mlr.press/v54/mcmahan17a?ref=https://githubhelp.com> (Year: 2017). [cited by examiner]
Thalij, et al, Multiobjective Glowworm Swarm Optimization-Based Dynamic Replication Algorithm for Real-Time Distributed Databases, Retrieved from Internet:<https://onlinelibrary.wiley.com/doi/full/10.1155/2018/2724692> … [cited by examiner]
Wang, et al, Federated Learning with Matched Averaging, Retrieved from Internet:<https://arxiv.org/abs/2002.06440> (Year: 2020). [cited by examiner]
Baud et al., “Multi-day rhythms modulate seizure risk in epilepsy.” Nat Commun 9, 88, (2018). [cited by applicant]
Brinkmann et al., “Forecasting Seizures Using Intracranial EEG Measures and SVM in Naturally Occurring Canine Epilepsy,” G. A. PLoS.One.,10:e0133900 (2015). [cited by applicant]
Cantero et al., “Sleep-dependent theta oscillations in the human hippocampus and neocortex,”, J Neurosci,23:10897-10903 (2003). [cited by applicant]
Carrington et al.,“Effect of focal low-frequency stimulation on amygdala-kindled afterdischarge thresholds and seizure profiles in fast- and slow-kindling rat strains,” Epilepsia, 48:1604-1613 (2007). [cited by applicant]
Chan et al., “Automated seizure onset detection for accurate onset time determination in intracranial EEG,” Clin. Neurophysiol.,119:2687-2696 (2008). [cited by applicant]
Colom, “Septal networks: relevance to theta rhythm, epilepsy and Alzheimer's disease,” J Neurochem., 96:609-623 (2006). [cited by applicant]
Crespel et al., “Sleep influence on seizures and epilepsy effects on sleep in partial frontal and temporal lobe epilepsies,” M. Clin.Neurophysiol.,111 Suppl 2:S54-S59 (2000). [cited by applicant]
Desai et al., “Quantitative electrocorticographic biomarkers of clinical outcomes in mesial temporal lobe epileptic patients treated with the RNS system”, Clinical Neurophysiology 130, 1364-1374, (2019). [cited by applicant]
García-Hernández et al., “Septo-hippocampal networks in chronic epilepsy”, EAT Neurol. Mar. 2010; 222(1):86-92. [cited by applicant]
Goodman et al., “Preemptive low-frequency stimulation decreases the incidence of amygdala-kindled seizures,” Epilepsia,46:1-7 (2005). [cited by applicant]
Herman et al., “Distribution of partial seizures during the sleep-wake cycle: differences by seizure onset site,” Neurology,56:1453-1459 (2001). [cited by applicant]
Karoly et al., “The circadian profile of epilepsy improves seizure forecasting.” Brain 140, 2169-2182, (2017). [cited by applicant]
Karoly et al., “Forecasting cycles of seizure likelihood”. Epilepsia 61, 776-786, (Dec. 19, 2019). [cited by applicant]
Kisilev et al., “Medical Image Description Using Multi-task-loss CNN.” Deep Learning and Data Labeling for Medical Applications. DLMIA Labels 2016 2016. Lecture Notes in Computer Science(), vol. 10008. Springer, Cham. h… [cited by applicant]
Litt et al., “Epileptic Seizures May Begin Hours in Advance of Clinical Onset: A Report of Five Patients”, Neuron, vol. 30, 51-64, Apr. 2001. [cited by applicant]
Logesparan et al., “Optimal features for online seizure detection”, Medical & Biological Engineering & Computing, 50.7 (2012): 659-669, and Supplementary Material relating to article. [cited by applicant]
Lysyansky et al., “Optimal No. of stimulation contacts for coordinated reset neuromodulation,” Front Neuroeng.,6:5 (2013). [cited by applicant]
Malow, “The interaction between sleep and epilepsy,” Epilepsia,48 Suppl 9:36-38 (2007). [cited by applicant]
Maturana et al., “Critical slowing down as a biomarker for seizure susceptibility”. Nat Commun 11, 2172, (2020). [cited by applicant]
Meisel et al., “Intrinsic excitability measures track antiepileptic drug action and uncover increasing/ decreasing excitability over the wake/sleep cycle”. Proc Natl Acad Sci U S A 112, 14694-14699, (Nov. 6, 2015). [cited by applicant]
Miller et al., “Anticonvulsant effects of the experimental induction of hippocampal theta activity,” Epilepsy Res., 18:195-204 (1994). [cited by applicant]
Minecan et al., “Relationship of epileptic seizures to sleep stage and sleep depth,” Sleep,25:899-904 (2002). [cited by applicant]
Ng et al., “Why are seizures rare in rapid eye movement sleep? Review of the frequency of seizures in different sleep stages,” M. Epilepsy Res.Treat.,2013:932790 (2013). [cited by applicant]
Ogren et al., “Three-dimensional hippocampal atrophy maps distinguish two common temporal lobe seizure-onset patterns,” Epilepsia, 50(6):1361-1370 (2009). [cited by applicant]
Osorio et al., “Real-Time Automated Detection and Quantitative Analysis of Seizures and Short-Term Prediction of Clinical Onset”, Epilepsia, 39(6):615-627 (1998). [cited by applicant]
Perucca et al., “Intracranial electroencephalographic seizure-onset patterns: effect of underlying pathology,” J. Brain: 137:183-196 (2014). [cited by applicant]
Popovych et al., “Desynchronizing electrical and sensory coordinated reset neuromodulation”, Frontiers in Human Neuroscience, Mar. 20, 2012, vol. 6, Article 58. [cited by applicant]
Quigg et al., Electrocorticographic events from long-term ambulatory brain recordings can potentially supplement seizure diaries. Epilepsy Res 161, 106302, (2020). [cited by applicant]
Schiller et al., “Characterization and comparison of local onset and remote propagated electrographic seizures recorded with intracranial electrodes,” Epilepsia,39:380-388 (1998). [cited by applicant]
Skarpaas et al., “Clinical and electrocorticographic response to antiepileptic drugs in patients treated with responsive stimulation”, Epilepsy & Behavior 83, 192-200, (2018). [cited by applicant]
Tass et al., “Long-lasting desynchronization in rat hippocampal slice induced by coordinated reset stimulation”, Physical Review F 80, 011902 (2009). [cited by applicant]
Tass et al., “Coordinated reset has sustained aftereffects in Parkinsonian monkeys,” Ann.Neurol,72:816-820 (2012). [cited by applicant]
Uriguen et al., “Comparison of background EEG activity of different groups of patients with idiopathic epilepsy using Shannon spectral entropy and cluster-based permutation statistical testing”. PLoS One 12, (Sep. 18, 2… [cited by applicant]
Van Putten et al., “Detecting temporal lobe seizures from scalp EEG recordings: a comparison of various features,” Clin. Neurophysiol.,116:2480-2489 (2005). [cited by applicant]
Vaswani et al., “Attention is all you need”. Advances in Neural Information Processing Systems 30 (2017). [cited by applicant]
Wackermann, “Beyond mapping: estimating complexity of multichannel EEG recordings,” Acta Neurobiol.Exp.(Wars.),56:197-208 (1996). [cited by applicant]
Welsh et al., “A circadian rhythm of hippocampal theta activity in the mouse,” Physiol.Behav,35:533-538 (1985). [cited by applicant]
Zeiler et al., “Visualizing and Understanding Convolutional Networks”, ArXiv:1311.2901v3, Nov. 28, 2013, pp. 1-11. [cited by applicant]
Ali Hossam Shoeb, and John Guttag: “Application of Machine Learning to Epileptic Seizure Detection”, Appearing in the Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel 2010, Copyright 2… [cited by applicant]
Spencer, S. S., Guimaraes, P., Katz, A., Kim, J., and Spencer, D. Epilepsia: “Morphological patterns of seizures recorded intracranially,” 33:537-545 (1992). [cited by applicant]
Lee, S. A., Spencer, D. D., and Spencer, S. S. Epilepsia: “Intracranial EEG seizure-onset patterns in neocortical epilepsy,” 41:297-307 (2000). [cited by applicant]
Langan, Y., Nashef, L., and Sander, J. W.: “Case-control study of SUDEP,” Neurology,64:1131-1133 (2005). [cited by applicant]
Bateman, L. M., Li, C. S., Lin, T. C., and Seyal, M. Epilepsia: “Serotonin reuptake inhibitors are associated with reduced severity of ictal hypoxemia in medically refractory partial epilepsy,” 51:2211-2214 (2010). [cited by applicant]
Ali Hossam Shoeb: Thesis “Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment”, Submitted to Harvard-MIT Div. of Health Sciences re Dr. of Philosophy in EE and Med Engineering at MIT, Sep.… [cited by applicant]
Maryann D'Alessandro, George Vachtsevanos, Rosana Esteller, Javier Echauz, Stephen Cranstoun, Greg Worrell, Landi Parish and Brian Litt: “A multi-feature and multi-channel univariate selection process for seizure predic… [cited by applicant]
Isa Conradsen, Student Member; IEEE, Sándor Beniczky, Karsten Hoppe, Peter Wolf and Helge B. D. Sorensen Member, IEEE: “Automated algorithm for generalised tonic-clonic epileptic seizure onset detection based on sEMG ze… [cited by applicant]
Alaa Kharbouch, Ali Shoeb, John Guttag, and Sydney S. Cash: “An algorithm for seizure onset detection using intracranial EEG,” Epilepsy Balmy. Dec. 2011; 22(01): S29-S35. [cited by applicant]
Yusuf U Khan, Omar Farooq and Priyanka Sharma: “Automatic Detection of Seizure Onset in Pediatric EEG”, International Journal of Embedded Systems and Applications (IJESA) vol. 2, No. 3, Sep. 2012. [cited by applicant]
Yizhuo Zhang, Guanghua Xu, Jing Wang, Lin Liang: “An automatic patient-specific seizure onset detection method in intracranial EEG based on incremental nonlinear dimensionality reduction, Computers in Biology and Medici… [cited by applicant]
A.J. Gabor, R.R. Leach, and F.U. Dowla: “Automated Seizure Detection Using a Self-Organizing Neural Network”, Dept. of Neurology, University of CA, Davis Medical Center, Jan. 5, 1996; Published Apr. 15, 1996, Electroenc… [cited by applicant]
A.J. Gabor: “Automated Seizure Detection Using a Self-Organizing Neural Network, Validation and Comparison with Other Detection Strategies”, Dept. of Neurology, University of CA, Davis Medical Center, Accepted for Publi… [cited by applicant]
Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge”, International Journal of Computer Vision, available online Apr. 11, 2015, published Dec. 2015; vol. 115, Issue 3, DOI 10.1007/s11263-015-0816-; pp… [cited by applicant]
Lecun et al., “Deep Learning”, Nature, May 27, 2015, vol. 521; DOI:10.1038/nature14539; pp. 436-444. [cited by applicant]
Xu et al., “Survey of Clustering Algorithms”, IEEE Transactions on Neural Networks, vol. 16, No. 3, May 1, 2005; 35 pages. [cited by applicant]
Krizhevsky et al., “ImageNet Classification with Deep Convolutional Neural Networks”, NIPS'12 Proceedings of the 25th International Conference on Neural Information Processing Systems—vol. 1, pp. 1097-1105, Dec. 3, 2012. [cited by applicant]
Desai, Sharanya, “Insights from mining large-scale human EcoG data”, ICTAL2017, The Penumbra Conference, presented Aug. 21, 2017; 9 pages. [cited by applicant]
Esteva et al. “Dermatologist level classification of skin cancer with deep neural networks”, Nature, vol. 542, published Feb. 2, 2017, pp. 115-118. [cited by applicant]
Desai et al., “Transfer-learning for differentiating epileptic patients who respond to treatment based on chronic ambulatory ECoG data,” in 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), 2019: … [cited by applicant]
Hussein, Ramy et al. “Epileptic Seizure Detection: A Deep Learning Approach”, ArXiv:1803.09848v1, Mar. 27, 2018, pp. 1-12; 2018. [cited by applicant]
Tsiouris, Kostas M. et al. “A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals”, Computers in Biology and Medicine, vol. 99, Aug. 1, 2018, pp. 24-37. [cited by applicant]
Thodoroff, M. et al. “Learning Robust Features using Deep Learning for Automatic Seizure Detection”, ArXiv:1608.00220, Jul. 31, 2016, pp. 1-12. [cited by applicant]
Pailla , Tejaswy et al. “Autoencoders for learning template spectrograms in electrocorticographic signals”, Journal of Neural Engineering, vol. 16, No. 1, Jan. 14, 2019. [cited by applicant]
Ling, Zhen-Huia et al. “Waveform Modeling and Generation Using Hierarchical Recurrent Neural Networks for Speech Bandwidth Extension”, IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, No. 5, pp.… [cited by applicant]
Zeiler, Matthew D. et al. “Visualizing and Understanding Convolutional Networks”, ArXiv:1311.2901v3, Nov. 28, 2013, pp. 1-11. [cited by applicant]