Neural network-based anomalous diffusion parameter estimation approaches for Gaussian processes

Szarek, Dawid

doi:10.1007/s12572-021-00298-6

Cited by 6 publications

(5 citation statements)

References 53 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For Task 1 1D, we trained 12 models, each model corresponding to a batch of trajectory lengths: [10,20], [21,30], [31,40], [41,50] [36] generates trajectories with anomalous exponent α ∈ [0.05, 2) in intervals of 0.05. This means that 39 different alpha values can be generated, and there are five diffusion models for a total of 195 different kinds of trajectories.…”

Section: Model Trainingmentioning

confidence: 99%

“…When regressing the anomalous diffusion exponent, the sensitivity of ML models to added noise in SBM trajectories warrants further study. Recently, Szarek [40] has encountered a similar lack in resiliency to noise using an RNN-based model, like UPV-Mat, HNU, and eduN models. It appears that the difficulty in working with SBM is an inherent characteristic of SBM trajectories, as opposed to the neural network architecture used for inference of α.…”

Section: Regression Of the Anomalous Diffusion Exponent (Task 1 1d)mentioning

confidence: 99%

See 1 more Smart Citation

Characterization of anomalous diffusion through convolutional transformers

Firbas¹,

Garibo‐i‐Orts²,

García-March³

et al. 2023

J. Phys. A: Math. Theor.

View full text Add to dashboard Cite

The results of the Anomalous Diffusion Challenge (AnDi Challenge) (Muñoz-Gil et al, 2021) have shown that machine learning methods can outperform classical statistical methodology at the characterizing of anomalous diffusion in both the inference of the anomalous diffusion exponent $\alpha$ associated with each trajectory (Task 1), and the determination of the underlying diffusive regime which produced such trajectories (Task 2). Furthermore, of the five teams that finished in the top three across both tasks of the AnDi challenge, three of those teams used \textit{recurrent neural networks} (RNNs). While RNNs, like the \textit{long short-term memory} (LSTM) network, are effective at learning long-term dependencies in sequential data, their key disadvantage is that they must be trained sequentially. In order to facilitate training with larger data sets, by training in parallel, we propose a new \textit{transformer} based neural network architecture for the characterization of anomalous diffusion. Our new architecture, the \textit{Convolutional Transformer} (ConvTransformer) uses a bi-layered convolutional neural network to extract features from our diffusive trajectories that can be thought of as being words in a sentence. These features are then fed to two transformer encoding blocks that perform either regression (Task 1) or classification (Task 2). To our knowledge, this is the first time transformers have been used for characterizing anomalous diffusion. Moreover, this may be the first time that a transformer encoding block has been used with a convolutional neural network and without the need for a transformer decoding block or positional encoding. Apart from being able to train in parallel, we show that the ConvTransformer is able to outperform the previous state-of-the-art at determining the underlying diffusive regime (Task2) in short trajectories (length 10-50 steps), which are the most important for experimental researchers.

show abstract

Section: Model Trainingmentioning

confidence: 99%

Section: Regression Of the Anomalous Diffusion Exponent (Task 1 1d)mentioning

confidence: 99%

Characterization of anomalous diffusion through convolutional transformers

Firbas¹,

Garibo‐i‐Orts²,

García-March³

et al. 2023

J. Phys. A: Math. Theor.

View full text Add to dashboard Cite

show abstract

“…Recurrent neural networks (RNN) have been used for inference of the anomalous diffusion exponent and for the classification of anomalous diffusion models [191][192][193][194] and changes between diffusion models [195]. Although questions exist with regard to their accuracy in handling long-time correlations.…”

Section: Neural Network For Time Series Analysismentioning

confidence: 99%

Heterogeneous anomalous transport in cellular and molecular biology

Waigh,

Korabel

2023

Rep. Prog. Phys.

View full text Add to dashboard Cite

It is well established that a wide variety of phenomena in cellular and molecular biology involve anomalous transport e.g. the statistics for the motility of cells and molecules are fractional and do not conform to the archetypes of simple diffusion or ballistic transport. Recent research demonstrates that the anomalous transport is in many cases heterogeneous in both time and space. Thus single anomalous exponents and single generalized diffusion coefficients are unable to satisfactorily describe many crucial phenomena in cellular and molecular biology. We consider advances in the field of heterogeneous anomalous transport (HAT) highlighting: experimental techniques (single molecule methods, microscopy, image analysis, fluorescence correlation spectroscopy, inelastic neutron scattering and NMR), theoretical tools for data analysis (robust statistical methods such as first passage probabilities, survival analysis, different varieties of mean square displacements etc), analytic theory and generative theoretical models based on simulations. Special emphasis is made on high throughput analysis techniques based on machine learning and neural networks. Furthermore, we consider anomalous transport in the context of microrheology and the heterogeneous viscoelasticity of complex fluids. HAT in the wavefronts of reaction-diffusion systems is also considered, since it plays an important role in morphogenesis and signalling. In addition we present specific examples from cellular biology including: embryonic cells, leukocytes, cancer cells, bacterial cells, bacterial biofilms and eukaryotic microorganisms. Case studies from molecular biology include: DNA, membranes, endosomal transport, endoplasmic reticulum, mucins, globular proteins and amyloids.

show abstract

“…Szarek proposed a novel hybrid convolutional neural network model that uses a 1-to-1 method to predict the occurrence of four types of solar flares within 24 hours. The results showed that the prediction effect of this model was better than that of the traditional model [9]. Chea and Nam propose an optimal residual deep neural network and an efficient image preprocessing technique and apply the method to three eye disease classifications in currently available public datasets.…”

Section: Related Workmentioning

confidence: 99%

“…The algorithm has good recommendation performance Szarek [9] and Zheng et al [11] A new hybrid convolutional neural network model…”

Section: Multipopulation Collaborative Genetic Algorithm Based On Col...mentioning

confidence: 99%

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

Shang

2023

Journal of Applied Mathematics

View full text Add to dashboard Cite

Flexible job-shop scheduling problem (FJSP) is a new research hotspot in the field of production scheduling. To solve the multiobjective FJSP problem, the production of flexible job shop can run normally and quickly. This research takes into account various characteristics of FJSP problems, such as the need to ensure the continuity and stability of processing, the existence of multiple objectives in the whole process, and the constant complexity of changes. It starts with deep learning neural networks and genetic algorithms. Long short-term memory (LSTM) and convolutional neural networks (CNN) are combined in deep learning neural networks. The new improved algorithm is based on the combination of deep learning neural networks LSTM and CNN with genetic algorithm (GA), namely, CNN-LSTM-GA algorithm. Simulation results showed that the accuracy of the CNN-LSTM-GA algorithm was between 85.2% and 95.3% in the test set. In the verification set, the minimum accuracy of the CNN-LSTM-GA algorithm was 84.6%, both of which were higher than the maximum accuracy of the other two algorithms. In the FJSP simulation experiment, the AUC value of the CNN-LSTM-GA algorithm was 0.92. After 40 iterations, the F1 value of the CNN-LSTM-GA algorithm remained above 0.8, which was significantly higher than the other two algorithms. CNN-LSTM-GA is superior to the other two algorithms in terms of prediction accuracy and overall performance of FJSP. It is more suitable for solving the discrete manufacturing job scheduling problem with FJSP characteristics. This study significantly raises the utilisation rate of the assembly shop’s equipment, optimises the scheduling of FJSP, and fully utilises each processing device’s versatile characteristics, which are quite useful for the production processes of domestic vehicle manufacturing companies.

show abstract

Neural network-based anomalous diffusion parameter estimation approaches for Gaussian processes

Cited by 6 publications

References 53 publications

Characterization of anomalous diffusion through convolutional transformers

Characterization of anomalous diffusion through convolutional transformers

Heterogeneous anomalous transport in cellular and molecular biology

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

Contact Info

Product

Resources

About