scholarly journals Reservoir computing with biocompatible organic electrochemical networks for brain-inspired biosignal classification

2021 ◽  
Vol 7 (34) ◽  
pp. eabh0693
Author(s):  
Matteo Cucchi ◽  
Christopher Gruener ◽  
Lautaro Petrauskas ◽  
Peter Steiner ◽  
Hsin Tseng ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Biological Tissues ◽  
Reservoir Computing ◽  
Biosignal Analysis ◽  
Steady Improvement ◽  
Electrochemical Devices ◽  
Classification Tasks ◽  
Biosignal Classification ◽  
Potential Use ◽  
Computing Approach

Early detection of malign patterns in patients’ biological signals can save millions of lives. Despite the steady improvement of artificial intelligence–based techniques, the practical clinical application of these methods is mostly constrained to an offline evaluation of the patients’ data. Previous studies have identified organic electrochemical devices as ideal candidates for biosignal monitoring. However, their use for pattern recognition in real time was never demonstrated. Here, we produce and characterize brain-inspired networks composed of organic electrochemical transistors and use them for time-series predictions and classification tasks using the reservoir computing approach. To show their potential use for biofluid monitoring and biosignal analysis, we classify four classes of arrhythmic heartbeats with an accuracy of 88%. The results of this study introduce a previously unexplored paradigm for biocompatible computational platforms and may enable development of ultralow–power consumption hardware-based artificial neural networks capable of interacting with body fluids and biological tissues.

Multi-target ranging using optical reservoir computing approach in the laterally coupled semiconductor lasers with self-feedback

2021 ◽  
Author(s):  
Dong-Zhou Zhong ◽  
Zhe Xu ◽  
Ya-Lan Hu ◽  
Ke-Ke Zhao ◽  
Jin-Bo Zhang ◽  
...  
Keyword(s):  
Semiconductor Lasers ◽  
Hilbert Transform ◽  
Optical Feedback ◽  
Optical Injection ◽  
Reservoir Computing ◽  
Probe Signal ◽  
Laser Array ◽  
Target Ranging ◽  
Relative Errors ◽  
Computing Approach

Abstract In this work, we utilize three parallel reservoir computers using semiconductor lasers with optical feedback and light injection to model radar probe signals with delays. Three radar probe signals are generated by driving lasers constructed by a three-element lase array with self-feedback. The response lasers are implemented also by a three-element lase array with both delay-time feedback and optical injection, which are utilized as nonlinear nodes to realize the reservoirs. We show that each delayed radar probe signal can well be predicted and to synchronize with its corresponding trained reservoir, even when there exist parameter mismatches between the response laser array and the driving laser array. Based on this, the three synchronous probe signals are utilized for ranging to three targets, respectively, using Hilbert transform. It is demonstrated that the relative errors for ranging can be very small and less than 0.6%. Our findings show that optical reservoir computing provides an effective way for applications of target ranging.

Potential Use of Artificial Intelligence for Regulatory Intelligence: Biopharmaceutical Industry’s Views

2019 ◽  
Vol 53 (6) ◽  
pp. 759-766
Author(s):  
Mark Mayer ◽  
Angelica Canedo ◽  
Tam Dinh ◽  
Madelyn Low ◽  
Ariel Ortiz ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Potential Use

Cost-effectiveness of AI in medicine from a clinical, technical, and economic perspective: A scoping review and a framework of analysis (Preprint)

2021 ◽  
Author(s):  
Jesus Gomez Rossi ◽  
Ben Feldberg ◽  
Joachim Krois ◽  
Falk Schwendicke
Keyword(s):  
Artificial Intelligence ◽  
Cost Effectiveness ◽  
Scientific Literature ◽  
Economic Aspects ◽  
Inclusion Criteria ◽  
Economic Perspective ◽  
Health Policy Analysis ◽  
The Cost ◽  
The Relationship ◽  
Potential Use

BACKGROUND Research and Development (R&D) of Artificial Intelligence (AI) in medicine involve clinical, technical and economic aspects. Better understanding the relationship between these dimensions seems necessary to coordinate efforts of R&D among stakeholders. OBJECTIVE To assess systematically existing literature on the cost-effectiveness of Artificial Intelligence (AI) from a clinical, technical and economic perspective. METHODS A systematic literature review was conducted to study the cost-effectiveness of AI solutions and summarised within a scoping framework of health policy analysis developed to study clinical, technical and economic dimensions. RESULTS Of the 4820 eligible studies, 13 met the inclusion criteria. Internal medicine and emergency medicine were the most studied clinical disciplines. Technical R&D aspects have not been uniformly disclosed in the studies we analysed. Monetisation aspects such as payment models assumed have not been reported in the majority of cases. CONCLUSIONS Existing scientific literature on the cost-effectiveness of AI currently does not allow to draw conclusive recommendations. Further research and improved reporting on technical and economic aspects seem necessary to assess potential use-cases of this technology, as well as to secure reproducibility of results. CLINICALTRIAL Not applicable

Compliance Problems and Digitizing Case Management in England and Wales

2020 ◽  
pp. 153-178
Author(s):  
John Sorabji
Keyword(s):  
Artificial Intelligence ◽  
Case Management ◽  
Civil Procedure ◽  
Civil Justice ◽  
Reform Programme ◽  
Effective Operation ◽  
Compliance Problem ◽  
Civil Justice System ◽  
Civil Courts ◽  
Potential Use

Compliance with case management orders has been a hidden problem undermining the effective operation of the Civil Procedure Rules. The focus of academic critique has, however, been on the adverse consequences to their effective operation of non-compliance with such orders. This chapter considers this unexamined problem of case management: the compliance problem. It first examines the nature of the compliance problem, placing it within the context of the wider and substantially explored problem of non-compliance; the latter having formed a major limb of Zuckerman’s critique of English civil procedure. It then explores how current and potential future reforms to the English civil justice system arising from HMCTS reform programme, the Civil Courts Structure review, digitization and the potential use of artificial intelligence (AI) could overcome this unexplored problem.

scholarly journals Evolutionary aspects of reservoir computing

2019 ◽  
Vol 374 (1774) ◽  
pp. 20180377 ◽  
Author(s):  
Luís F. Seoane
Keyword(s):  
Artificial Intelligence ◽  
Fine Tuning ◽  
Test Model ◽  
Reservoir Computing ◽  
Cognitive Architectures ◽  
Computing Paradigm ◽  
Highly Nonlinear ◽  
Input Signals ◽  
Speculative Discussion ◽  
Evolutionary Aspects

Reservoir computing (RC) is a powerful computational paradigm that allows high versatility with cheap learning. While other artificial intelligence approaches need exhaustive resources to specify their inner workings, RC is based on a reservoir with highly nonlinear dynamics that does not require a fine tuning of its parts. These dynamics project input signals into high-dimensional spaces, where training linear readouts to extract input features is vastly simplified. Thus, inexpensive learning provides very powerful tools for decision-making, controlling dynamical systems, classification, etc. RC also facilitates solving multiple tasks in parallel, resulting in a high throughput. Existing literature focuses on applications in artificial intelligence and neuroscience. We review this literature from an evolutionary perspective. RC’s versatility makes it a great candidate to solve outstanding problems in biology, which raises relevant questions. Is RC as abundant in nature as its advantages should imply? Has it evolved? Once evolved, can it be easily sustained? Under what circumstances? (In other words, is RC an evolutionarily stable computing paradigm?) To tackle these issues, we introduce a conceptual morphospace that would map computational selective pressures that could select for or against RC and other computing paradigms. This guides a speculative discussion about the questions above and allows us to propose a solid research line that brings together computation and evolution with RC as test model of the proposed hypotheses. This article is part of the theme issue ‘Liquid brains, solid brains: How distributed cognitive architectures process information’.

scholarly journals Artificial intelligence neuropathologist for glioma classification using deep learning on hematoxylin and eosin stained slide images and molecular markers

2020 ◽  
Author(s):  
Lei Jin ◽  
Feng Shi ◽  
Qiuping Chun ◽  
Hong Chen ◽  
Yixin Ma ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Molecular Markers ◽  
Diagnostic Testing ◽  
Deep Convolutional Neural Networks ◽  
Multiple Classification ◽  
Neuropathological Diagnosis ◽  
Hematoxylin And Eosin ◽  
Classification Tasks ◽  
Glioma Classification

Abstract Background Pathological diagnosis of glioma subtypes is essential for treatment planning and prognosis. Standard histological diagnosis of glioma is based on postoperative hematoxylin and eosin stained slides by neuropathologists. With advancing artificial intelligence (AI), the aim of this study was to determine whether deep learning can be applied to glioma classification. Methods A neuropathological diagnostic platform is designed comprising a slide scanner and deep convolutional neural networks (CNNs) to classify 5 major histological subtypes of glioma to assist pathologists. The CNNs were trained and verified on over 79 990 histological patch images from 267 patients. A logical algorithm is used when molecular profiles are available. Results A new model of the squeeze-and-excitation block DenseNet with weighted cross-entropy (named SD-Net_WCE) is developed for the glioma classification task, which learns the recognizable features of glioma histology CNN-based independent diagnostic testing on data from 56 patients with 17 262 histological patch images demonstrated patch level accuracy of 86.5% and patient level accuracy of 87.5%. Histopathological classifications could be further amplified to integrated neuropathological diagnosis by 2 molecular markers (isocitrate dehydrogenase and 1p/19q). Conclusion The model is capable of solving multiple classification tasks and can satisfactorily classify glioma subtypes. The system provides a novel aid for the integrated neuropathological diagnostic workflow of glioma.

scholarly journals Numerical simulation of miniature antennas applicators of microwave radiometry for diagnostics of the functional state of the brain

2019 ◽  
Vol 30 ◽  
pp. 13005
Author(s):  
Vitaly Leushin ◽  
Sergey Chizhikov ◽  
Sergey Vesnin ◽  
Mikhail Sedankin ◽  
Igor Porokhov ◽  
...  
Keyword(s):  
Finite Difference Time Domain ◽  
Biological Tissues ◽  
Microwave Radiometry ◽  
Spiral Antenna ◽  
Functional Diagnostics ◽  
Miniature Antennas ◽  
New Sensors ◽  
Difference Time ◽  
The Brain ◽  
Potential Use

This paper describes the use of Finite Difference Time Domain technique of numerical modeling for development and simulation symmetrical dipole with triangular shoulders placed in a cylindrical housing and a spiral antenna placed in a cylindrical housing for use in microwave radiometry. The new sensors have been tested and validated on different phantoms and biological tissues. Results suggest sufficient characteristics of broadband antennas for potential use in brain functional diagnostics.

Sign in / Sign up

Export Citation Format

Share Document