Leveraging long short-term memory (LSTM)-based neural networks for modeling structure-property relationships of metamaterials from electromagnetic responses.
Ontology highlight
ABSTRACT:
SUBMITTER: Pillai P
PROVIDER: S-EPMC8452651 | biostudies-literature | 2021 Sep
REPOSITORIES: biostudies-literature
Publications
Leveraging long short-term memory (LSTM)-based neural networks for modeling structure-property relationships of metamaterials from electromagnetic responses.
Pillai Prajith P Pal Parama P Chacko Rinu R Jain Deepak D Rai Beena B
Scientific reports 20210920 1
We report a neural network model for predicting the electromagnetic response of mesoscale metamaterials as well as generate design parameters for a desired spectral behavior. Our approach entails treating spectral data as time-varying sequences and the inverse problem as a single-input multiple output model, thereby compelling the network architecture to learn the geometry of the metamaterial designs from the spectral data in lieu of abstract features. ...[more]
Similar Datasets
Project description:BackgroundRecent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data.ResultsWe propose a new model to detect and classify relations in text, BO-LSTM, that takes advantage of domain-specific ontologies, by representing each entity as the sequence of its ancestors in the ontology. We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using open biomedical ontologies, specifically Chemical Entities of Biological Interest (ChEBI), Human Phenotype, and Gene Ontology. We assessed the performance of BO-LSTM with drug-drug interactions mentioned in a publicly available corpus from an international challenge, composed of 792 drug descriptions and 233 scientific abstracts. By using the domain-specific ontology in addition to word embeddings and WordNet, BO-LSTM improved the F1-score of both the detection and classification of drug-drug interactions, particularly in a document set with a limited number of annotations. We adapted an existing DDI extraction model with our ontology-based method, obtaining a higher F1 score than the original model. Furthermore, we developed and made available a corpus of 228 abstracts annotated with relations between genes and phenotypes, and demonstrated how BO-LSTM can be applied to other types of relations.ConclusionsOur findings demonstrate that besides the high performance of current deep learning techniques, domain-specific ontologies can still be useful to mitigate the lack of labeled data.
| S-EPMC6323831 | biostudies-literature
Project description:Seizure prediction could improve quality of life for patients through removing uncertainty and providing an opportunity for acute treatments. Most seizure prediction models use feature engineering to process the EEG recordings. Long-Short Term Memory (LSTM) neural networks are a recurrent neural network architecture that can display temporal dynamics and, therefore, potentially analyze EEG signals without performing feature engineering. In this study, we tested if LSTMs could classify unprocessed EEG recordings to make seizure predictions. Long-term intracranial EEG data was used from 10 patients. 10-s segments of EEG were input to LSTM models that were trained to classify the EEG signal. The final seizure prediction was generated from 5 outputs of the LSTM model over 50 s and combined with time information to account for seizure cycles. The LSTM models could make predictions significantly better than a random predictor. When compared to other publications using the same dataset, our model performed better than several others and was comparable to the best models published to date. Furthermore, this framework could still produce predictions significantly better than chance when the experimental paradigm design was altered, without the need to reperform feature engineering. Removing the need to perform feature engineering is an advancement on previously published models. This framework can be applied to many different patients' needs and a variety of acute interventions. Also, it opens the possibility of personalized seizure predictions that can be altered to meet daily needs.
| S-EPMC11604808 | biostudies-literature
Project description:Polymer networks built out of dynamic covalent bonds offer the potential to translate the control and tunability of chemical reactions to macroscopic physical properties. Under conditions at which these reactions occur, the topology of covalent adaptable networks (CANs) can rearrange, meaning that they can flow, self-heal, be remolded, and respond to stimuli. Materials with these properties are necessary to fields ranging from sustainability to tissue engineering; thus the conditions and time scale of network rearrangement must be compatible with the intended use. The mechanical properties of CANs are based on the thermodynamics and kinetics of their constituent bonds. Therefore, strategies are needed that connect the molecular and macroscopic worlds. In this Perspective, we analyze structure-reactivity-property relationships for several classes of CANs, illustrating both general design principles and the predictive potential of linear free energy relationships (LFERs) applied to CANs. We discuss opportunities in the field to develop quantitative structure-reactivity-property relationships and open challenges.
| S-EPMC9812368 | biostudies-literature
Project description:Modeling metal additive manufacturing processes is of great importance because it allows for the production of objects that are closer to the desired geometry and mechanical properties. Over-deposition often takes place during laser metal deposition, especially when the deposition head changes its direction and results in more material being melted onto the substrate. Modeling over-deposition is one of the necessary steps toward online process control, as a good model can be used in a closed-loop system to adjust the deposition parameters in real-time to reduce this phenomenon. In this study, we present a long-short memory neural network to model over-deposition. The model has been trained on simple geometries such as straight tracks, spiral and V-tracks made of Inconel 718. The model shows good generalization capabilities and can predict the height of more complex and previously unseen random tracks with limited performance loss. After the addition to the training dataset of a small amount of data coming from the random tracks, the performance of the model for such additional shapes improves significantly, making this approach feasible for more general applications as well.
| S-EPMC10320393 | biostudies-literature
Project description:Response to environmental thermomechanical inputs in applications that range from wearable electronics to aerospace structures necessitates agile communication systems driven by reconfigurable electromagnetic structures. Antennas in these systems must dynamically preserve acceptable radiation characteristics while enabling on-demand performance reconfiguration. However, existing reconfiguration mechanisms through stretchable conductors rely on high-strain behavior in soft substrates, which limits their applicability. Herein, this work demonstrates the use of mechanical metamaterials for stretchable conductors and dielectrics in antennas. Metamaterials allow conductor stretching up to 30% with substrate base material tensile moduli ranging from 26 MPa to 44 GPa. It is shown, through several antenna designs, that mechanical metamaterials enable similar frequency reduction upon stretching as monolithic conductors, while simultaneously providing a miniaturization effect. The conductor patterning, furthermore, provides control over coupling between mechanical stretching and electromagnetic reconfiguration. This approach enables designing reconfigurable antenna functionality through metamaterial geometry in response to arising needs in applications ranging from body-adapted electronics to space vehicles.
| S-EPMC9951316 | biostudies-literature
Project description:We present the theory of electromagnetic energy propagation through a dispersive and absorbing hyperbolic metamaterial (HMM). In this way, the permittivity tensor components of HMM (especially, nanowire HMM) may appear to be hopeless, but as a non-trivial step, we find that they can be cast into more transparent forms. We find under the influence of an electromagnetic wave, the responses of nanowire HMM (multilayer HMM) in the directions perpendicular to and parallel to the optical axis are similar to those of Lorentz (Drude) and Drude (Lorentz) media, respectively. We obtain simple expressions for the electromagnetic energy density formula of both typical structures of HMMs, i.e., nanowire and multilayer HMMs. Numerical examples reveal the general characteristics of the direction-dependent energy storage capacity of both nanowire and multilayer HMMs. The results of this study may shed more physical insight into the optical characteristics of HMMs.
| S-EPMC9232634 | biostudies-literature
Project description:BackgroundThe accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.MethodsFirst, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager-Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis.ResultsThe proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR.ConclusionsThe presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/distinction of muscle activity from background noise in sEMG signals.
| S-EPMC8532313 | biostudies-literature
Project description:Current practice of building QSAR models usually involves computing a set of descriptors for the training set compounds, applying a descriptor selection algorithm and finally using a statistical fitting method to build the model. In this study, we explored the prospects of building good quality interpretable QSARs for big and diverse datasets, without using any pre-calculated descriptors. We have used different forms of Long Short-Term Memory (LSTM) neural networks to achieve this, trained directly using either traditional SMILES codes or a new linear molecular notation developed as part of this work. Three endpoints were modeled: Ames mutagenicity, inhibition of P. falciparum Dd2 and inhibition of Hepatitis C Virus, with training sets ranging from 7,866 to 31,919 compounds. To boost the interpretability of the prediction results, attention-based machine learning mechanism, jointly with a bidirectional LSTM was used to detect structural alerts for the mutagenicity data set. Traditional fragment descriptor-based models were used for comparison. As per the results of the external and cross-validation experiments, overall prediction accuracies of the LSTM models were close to the fragment-based models. However, LSTM models were superior in predicting test chemicals that are dissimilar to the training set compounds, a coveted quality of QSAR models in real world applications. In summary, it is possible to build QSAR models using LSTMs without using pre-computed traditional descriptors, and models are far from being "black box." We wish that this study will be helpful in bringing large, descriptor-less QSARs to mainstream use.
| S-EPMC7861338 | biostudies-literature
Project description:The definition of a precise illumination region is essential in many applications where the electromagnetic field should be confined in some specific volume. By using conventional structures, it is difficult to achieve an adequate confinement distance (or volume) with negligible levels of radiation leakage beyond it. Although metamaterial structures and metasurfaces are well-known to provide high controllability of their electromagnetic properties, this feature has not yet been applied to solve this problem. We present a method of electromagnetic field confinement based on the generation of evanescent waves by means of metamaterial structures. With this method, the confinement volume can be controlled, namely, it is possible to define a large area with an intense field without radiation leakage. A prototype working in the microwave region has been implemented, and very good agreement between the measurements and the theoretical prediction of field distribution has been obtained.
| S-EPMC5123569 | biostudies-literature
Project description:Long short-term memory (LSTM) networks, widely used for financial time series forecasting, face challenges in arbitrage spread prediction, especially in hyperparameter tuning for large datasets. These issues affect model complexity and adaptability to market dynamics. Existing heuristic algorithms for LSTM often struggle to capture the complex dynamics of futures spread data, limiting prediction accuracy. We propose an integrated Cuckoo and Zebra Algorithms-optimised LSTM (ICS-LSTM) network for arbitrage spread prediction. This method replaces the Lévy flight in the Cuckoo algorithm with the Zebra algorithm search, improving convergence speed and solution optimization. Experimental results showed a mean absolute percentage error (MAPE) of 0.011, mean square error (MSE) of 3.326, mean absolute error (MAE) of 1.267, and coefficient of determination (R2) of 0.996. The proposed model improved performance by reducing MAPE by 8.3-50.0%, MSE by 10.2-77.8%, and MAE by 9.3-63.0% compared to existing methods. These improvements translate to more accurate spread predictions, enhancing arbitrage opportunities and trading strategy profitability.
| S-EPMC11784865 | biostudies-literature