Method For Prediction Of Response Research Articles

Rotor dynamic response prediction using physics-informed multi-LSTM networks

The deep learning method provides an effective alternative to numerical simulations for establishing the nonlinear input-output relationship and calculating dynamic responses of rotor systems. To overcome the low generalization capability of pure data-driven long short-term memory (LSTM) networks when predicting dynamic responses to out-of-distribution inputs, a dynamic response prediction method using physics-informed multi-LSTM networks is proposed. This approach incorporates required physical constraints into the deep LSTM network, allowing the model training process to optimize the network parameters within the feasible solution space that adheres to physical laws. Consequently, this enhances the physical interpretability of the deep learning model. Specifically, two physics-informed multi-LSTM network architectures are introduced, and physical laws of equation of motion, state dependency and hysteretic constitutive relationship are considered to construct the physics loss. The feasibility of the proposed method is verified by a Bouc-Wen hysteresis model and a simulated gas generator rotor. The response prediction performance of the two networks is validated on a constructed fault rotor dataset with significant sample differences, along with cross-speed and cross-node prediction validation for the rotor system. The results demonstrate that the trained networks exhibit strong robustness and generalization capabilities, making them suitable as surrogate models for rotor systems.

Seismic response prediction method of train-bridge coupled system based on convolutional neural network-bidirectional long short-term memory-attention modeling

Seismic response prediction is crucial for the safety analysis of train-bridge coupled systems. However, due to the complexity, suddenness, and high-risk nature of earthquakes, there are strong nonlinear relationships among different parts of bridges, making it challenging to express their spatial correlations using analytical models and traditional neural networks. To address this, this paper establishes a ballast track shaker scaling model and employs the grating monitoring measurement method to construct a spatial quasi-distributed monitoring system for the ballast track, thereby collecting seismic strain responses of the train-bridge coupled system under various seismic conditions. A hybrid neural network method is proposed for predicting the seismic responses of the train-bridge coupled system. This hybrid neural network integrates the features of a Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory Neural Network (BiLSTM), and the attention mechanism, thereby termed the CNN-BiLSTM-attention hybrid neural network. The model was validated using strain responses from 54 seismic scenarios. The results indicate that the model has a Mean Absolute Error (MAE) of 0.2349 and a coefficient of determination (R2) of 0.9446. Comparing the prediction results with those from RNN and LSTM models, it was found that the CNN effectively extracts features under various seismic parameters, while the BiLSTM better captures the temporal information of the strain responses, ensuring effective prediction regardless of the magnitude of strain responses. Therefore, the CNN-BiLSTM-attention hybrid neural network model is recommended for predicting seismic response.

E-PINN: A fast physics-informed neural network based on explicit time-domain method for dynamic response prediction of nonlinear structures

The physics-informed neural networks (PINNs), serving as the surrogate models, have emerged in the dynamic response prediction of nonlinear systems. However, in the conventional PINN model, the global differential equation of motion of the nonlinear system is directly integrated into the loss function, which requires the network to capture the intricate global dynamic evolution mechanism of the system and thus poses significant challenges for network learning. In this study, inspired by the explicit time-domain method (ETDM), a novel PINN based on ETDM, called E-PINN, is proposed to address the challenges arising from the network learning of the existing PINNs. A lightweight long short-term memory (LSTM) module is trained to learn the nonlinear evolution mechanism of restoring forces, while a single convolutional layer (SCL) module is utilized to reflect the linear evolution mechanism of the primary structure under the combined action of the external excitations and the nonlinear restoring forces. The weights of the SCL module can be directly retrieved from the discrete convolutional formulation of ETDM, and only the parameters in the LSTM module need to be optimized through a loss function solely based on the nonlinear restoring forces, thereby enabling easy network learning of the proposed E-PINN by decoupling the linear and nonlinear evolution mechanisms embedded in the nonlinear system. Three numerical examples are investigated by the present approach, and the results demonstrate the superior training efficiency and prediction accuracy of E-PINN in dynamic response prediction of nonlinear systems.

A nonlinear structural pulse-like seismic response prediction method based on pulse-like identification and decomposition learning

Abstract Accurate prediction of structural responses under seismic action is important for the performance evaluation of structures. However, depending on the differences in the characteristics of ground motions, particularly whether they contain impulses, the seismic-response characteristics of structures may differ significantly. Hence, a new method, i.e., WD–AttDL, is proposed in this study to predict structural response under pulse-like ground motions. This method innovatively combines a wavelet decomposition-based velocity pulse-identification method with decomposition learning, where decomposed pulses and high-frequency features are used as inputs to the neural-network model, thus simplifying the identification of pulse features for the model. The decomposition learning module integrates different types of submodules, such as CNN feature-extraction, LSTM temporal-learning, and self-attention mechanism submodules. To reduce the nonlinear time-range analysis calculations required to generate training data, a screening method for impulsive ground motions based on time-series feature clustering is proposed. The accuracy and applicability of the proposed method are verified by numerically simulating three different cycles of reinforced-concrete frame structures and a three-dimensional masonry structure. Compared with existing structural seismic-response models, WD–AttDL synergistically integrates different modules and thus offers a higher prediction accuracy. In particular, it reduces the peak error of the predicted response, which is important for the evaluation of structural performance. Additionally, based on the response predicted by WD–AttDL, a vulnerability analysis of the structure under pulse-like seismic effects can be performed rapidly and accurately.

Established a therapeutic response prediction model in metastatic gastric cancer by liquid biopsy

AbstractThis study by Okuno et al. successfully identified eight exo‐miRNAs through exosome‐based discovery and established an exo‐miRNA‐based liquid biopsy assay for predicting therapeutic response in metastatic gastric cancer (mGC). Exosomes, a subpopulation of extracellular vesicles originating from endosomes, play a crucial role in this context. Liquid biopsy, analyzing blood for circulating tumor cells, extracellular vesicles, or cell‐free nucleic acid, has revolutionized cancer diagnosis and monitoring. It significantly contributes to early detection, staging, and relapse detection in various cancers. Numerous studies have highlighted the clinical significance of miRNA and lncRNA within extracellular vesicles. The authors developed a response‐prediction model for chemo‐responsiveness in mGC patients. This study's model predicts responses robustly, demonstrating its potential efficacy in clinical practice. It offers a non‐invasive and accessible method for therapeutic response prediction, crucial for precision medicine in mGC. Successful translation of these findings into clinical applications promises substantial benefits for patient care.

Machine Learning based Seismic Response Prediction Methods for Steel Frame Structures

Machine Learning based Seismic Response Prediction Methods for Steel Frame Structures

DAPM-CDR: A domain adaptation prompting model for drug response prediction

The rising incidence and mortality rates of cancer present significant challenges to global health. Variations in tumor growth rates and treatment responses have revealed the limitations of traditional therapies, highlighting the urgent need for predictive models for cancer drug responses based on computational methods. Current drug response prediction methods often fall short in accurately predicting responses for rare cancers with limited data. To address these issues, we propose a domain adaptation prompting model for drug response prediction, DAPM-CDR. DAPM-CDR is trained with cancer types with rich response data of cancer cell lines, integrating both common and specific information into prompts through contrastive learning, to transfer knowledge to target tasks that with sparse data on cancer cell line responses, thereby enhancing the generalization capabilities across various cancer types. The experiment results demonstrate that DAPM-CDR outperforms several competitive methods in predicting drug responses of cell lines, particularly excelling with data from rare cancers and showing significant performance enhancements.

Time history response prediction of stochastic SDOF structures through Kriging-NARX modeling and adaptive real-time hybrid simulation

Emulating time history response is a critical benchmark for evaluating the seismic resilience of structures and assessing their reliability in the face of uncertainties. Traditional computational simulations, while commonly favored, often fall short in accurately describing the behavior of intricate structural components. Real-time hybrid simulation (RTHS) offers an effective and efficient experimental technique for replicating the responses of deterministic systems in a cyber-physical manner but encounters challenges when dealing with stochastic systems. This study proposes an innovative application of RTHS for time history response prediction of nonlinear stochastic structures. A cross-validation (CV)-Voronoi sampling strategy is applied to sequentially select uncertain parameter samples for RTHS. Nonlinear autoregressive with exogenous input (NARX) model is identified and updated from RTHS results in a sequential manner. Coefficients of final NARX model are surrogated using the Kriging meta-models to account for given uncertainties. Laboratory tests on single-degree-of-freedom (SDOF) structures with self-centering viscous dampers (SC-VD) were conducted to demonstrate the effectiveness of the proposed approach. Predicted time history responses from the final Kriging-NARX model are further compared and validated. It is demonstrated that the proposed approach provides an effective and efficient method for time history response prediction of stochastic systems especially when accurate numerical models are not available.

A multisource data‐driven monitoring model for assessing concrete dam behavior

AbstractThe pivotal role of dam infrastructure necessitates continuous health monitoring, which results in extensive sets of data. Most monitoring data‐based models in dam engineering concentrate on predicting dam behavior. However, little attention has been systematically paid to the processing of extensive monitoring data, modeling of comprehensive dam behavior, and assessment of overall dam operation status. Here, we propose a novel monitoring model comprising three main aspects: a multidimensional data mining method, a multipoint response prediction method, and a multilayer data fusion‐based assessment method. Utilizing monitoring data from a mega concrete arch dam, we evaluate and discuss the effects of data mining, modeling accuracy for dam behavior, robustness against data pollution, and sensitivity to anomalies. Comparisons with classical benchmarks demonstrate the performance of the proposed model for the dam.

Stability prediction for robotic milling based on tool tip frequency response prediction by considering the interface stiffness of spindle-tool system

The change of tool tip frequency response caused by the posture dependence of robot dynamic is one of the key problems that make it difficult to accurately predict the milling stability of robot. In this paper, a tool tip frequency response prediction method considering the interface stiffness characteristics of spindle-tool system is proposed for stability prediction of robotic milling under the condition of posture variation. Firstly, the interface stiffness models of spindle-toolholder, toolholder-spring clip and spring clip-tool are established based on Yoshimura's unit area method. Then, The dynamics model for the robot body and the interface stiffness models for spindle-tool system are imported into the finite element analysis model of the spindle system, so that the prediction of the tool tip frequency response is realized by harmonic response analysis. Compared with the experimental results, the maximum error of the natural frequency was not more than 2 %, and the maximum error of the amplitude was not more than 12 %. Finally, the 2 DOF robot milling stability prediction model is established. Then the robot milling chatter is predicted considering redundant degrees of freedom from the perspective of regenerative chatter prediction theory, and the accuracy of prediction results is verified by milling experiment.

Abstract LB434: Rapid and reproducible expansion of rare tumor cells: The R3CE platform for personalized medicine

Abstract We have developed a novel single-cell derived 3D organoid culture platform, Rapid, Reproducible, Rare Cell 3D Expansion (R3CE), capable of generating 3D organoids from solid tumors and normal tissues obtained via surgical tissues and needle biopsies within one week. This method demonstrates over 90% success in banking for at least two passages with over 106 cells across various cancer types, including breast cancer, colorectal cancer, hepatoma cancer, and ovarian cancer. The organoids maintain high fidelity to original tissues, as evidenced by H&E staining, WES, and protein marker analysis across generations. Notably, the R3CE platform can also cultivate circulating tumor cells (CTCs) from peripheral blood. The drug sensitivity profiles of RCE-cultured CTCs closely mirrored clinical outcomes in breast cancer patients. For a patient with stage IV HER2-positive breast cancer, our real-time assay results led to an adjustment in treatment from lapatinib/5-FU to lapatinib/Trastuzumab emtansine (TDM-1), which resulted in substantial clinical improvement. To our knowledge, the R3CE platform is the first 3D organoid system that does not require aggregation or 3D scaffold such as matrigel system. These advancements position the R3CE platform as a promising tool for personalized medicine, offering a rapid and accurate method for drug screening and therapeutic response prediction to guide clinical decision-making in cancer treatment. Citation Format: Wen-Hung Kuo, Yen-Jang Huang, Jia-Yang Chen, Yi-Chun Wu, Chia-Chun Chen, Mark D. Pegram, Ying-Chih Chang. Rapid and reproducible expansion of rare tumor cells: The R3CE platform for personalized medicine [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB434.

DBDNMF: A Dual Branch Deep Neural Matrix Factorization method for drug response prediction.

Anti-cancer response of cell lines to drugs is in urgent need for individualized precision medical decision-making in the era of precision medicine. Measurements with wet-experiments is time-consuming and expensive and it is almost impossible for wide ranges of application. The design of computational models that can precisely predict the responses between drugs and cell lines could provide a credible reference for further research. Existing methods of response prediction based on matrix factorization or neural networks have revealed that both linear or nonlinear latent characteristics are applicable and effective for the precise prediction of drug responses. However, the majority of them consider only linear or nonlinear relationships for drug response prediction. Herein, we propose a Dual Branch Deep Neural Matrix Factorization (DBDNMF) method to address the above-mentioned issues. DBDNMF learns the latent representation of drugs and cell lines through flexible inputs and reconstructs the partially observed matrix through a series of hidden neural network layers. Experimental results on the datasets of Cancer Cell Line Encyclopedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC) show that the accuracy of drug prediction exceeds state-of-the-art drug response prediction algorithms, demonstrating its reliability and stability. The hierarchical clustering results show that drugs with similar response levels tend to target similar signaling pathway, and cell lines coming from the same tissue subtype tend to share the same pattern of response, which are consistent with previously published studies.

Optimized models and deep learning methods for drug response prediction in cancer treatments: a review.

Recent advancements in deep learning (DL) have played a crucial role in aiding experts to develop personalized healthcare services, particularly in drug response prediction (DRP) for cancer patients. The DL's techniques contribution to this field is significant, and they have proven indispensable in the medical field. This review aims to analyze the diverse effectiveness of various DL models in making these predictions, drawing on research published from 2017 to 2023. We utilized the VOS-Viewer 1.6.18 software to create a word cloud from the titles and abstracts of the selected studies. This study offers insights into the focus areas within DL models used for drug response. The word cloud revealed a strong link between certain keywords and grouped themes, highlighting terms such as deep learning, machine learning, precision medicine, precision oncology, drug response prediction, and personalized medicine. In order to achieve an advance in DRP using DL, the researchers need to work on enhancing the models' generalizability and interoperability. It is also crucial to develop models that not only accurately represent various architectures but also simplify these architectures, balancing the complexity with the predictive capabilities. In the future, researchers should try to combine methods that make DL models easier to understand; this will make DRP reviews more open and help doctors trust the decisions made by DL models in cancer DRP.

Abstract 3660: Plasma cell free DNA hydroxymethylation profiling reveals anti-PD1 treatment response and resistance biology in non-small cell lung cancer

Abstract Background: Treatment with immune checkpoint inhibitors (ICIs) targeting programmed death-1 (PD-1) can yield durable anti-tumor responses, yet not all patients respond to ICIs. Current approaches to select patients who may benefit from anti-PD-1 treatment are insufficient. 5-hydroxymethylation (5hmC) analysis of plasma-derived cell free DNA (cfDNA) presents a novel non-invasive approach for identification of therapy response biomarkers which can tackle challenges associated with tumor biopsies such as tumor heterogeneity and serial sample collection. Methods: 151 blood samples were collected from 31 non-small cell lung cancer (NSCLC) patients before therapy start and at multiple timepoints whilst on therapy. Blood samples were processed to obtain plasma-derived cfDNA, followed by enrichment of 5hmC-containing cfDNA fragments through biotinylation via a two-step chemistry and binding to streptavidin coated beads. 5hmC-enriched cfDNA and whole genome libraries were prepared in parallel and sequenced to obtain whole hydroxymethylome and whole genome plasma profiles, respectively. Results: Comparison of on-treatment timepoint to matched pre-treatment samples from same patients revealed that anti-PD-1 treatment induced distinct changes in plasma cfDNA 5hmC profiles of responders, as judged by RECIST, relative to non-responders. In responders, 5hmC accumulated over genes involved in immune activation such as IFNγ and IFNα response, inflammatory response, and TNFα signaling, whereas in non-responders 5hmC increased over epithelial to mesenchymal transition genes. The Molecular Response to anti-PD-1 treatment, as measured by 5hmC changes in plasma cfDNA profiles were observed early, starting with the first cycle of treatment. Comparison of pre-treatment plasma samples revealed that anti-PD-1 treatment response- and resistance-associated genes can be captured by 5hmC profiling of plasma-derived cfDNA. Conclusions: These results demonstrate that 5hmC profiling can identify response and resistance associated biological pathways in plasma samples, offering a novel method for non-invasive prediction and monitoring of immunotherapy response in NSCLC. Citation Format: Gulfem D. Guler, Yuhong Ning, Ceyda Coruh, Tierney Phillips, Maryam Nabiyouni, Kyle Hazen, Aaron Scott, Wayne Volkmuth, Samuel Levy. Plasma cell free DNA hydroxymethylation profiling reveals anti-PD1 treatment response and resistance biology in non-small cell lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3660.

Vibration response prediction and vibration safety assessment method for building structures around viaducts under the action of high-speed railway trains

Concerning the cumulative damage of building structures caused by the long-term effects from high-speed railway train loads and various environmental impacts, and to ensure the service safety of building structures around viaducts, this paper establishes a vibration safety assessment method for the entire life cycle of building structures with less workload and good applicability, while ensuring the accuracy and effectiveness of the prediction of vibration response of building structures. Firstly, the vibration source function is formed based on the mechanical model of the mobile vibration source of high-speed railway trains, and the vibration wave of high-speed railway trains is numerically simulated. Then the time and frequency characteristics of the simulated high-speed railway train vibration waves are verified through on-site monitoring tests. In addition, the peak particle vibration velocity attenuation formula for the foundation site of the viaduct is derived by the dimension analysis method, and it is used to correct the attenuation characteristics of the simulated high-speed railway train vibration waves. Finally, based on the response spectrum method to realize the prediction and assessment of the overall vibration response of the building structures, and using the cumulative damage coefficient to reflect the cumulative degree of the service damage of the building structure, a vibration safety assessment method for the whole lifecycle of the building structure is proposed. The method overcomes the shortcoming that vibration velocity does not reflect the impact of service damage on the vibration safety of building structures, and avoids neglecting localized vibration damage, and is therefore useful for the rapid, overall vibration safety assessment of any long-term service building structure in a viaduct site.

A seismic response prediction method based on a self-optimized Bayesian Bi-LSTM mixed network for high-speed railway track-bridge system

A seismic response prediction method based on a self-optimized Bayesian Bi-LSTM mixed network for high-speed railway track-bridge system

A candidate method for prediction of the non-stationary response of strongly nonlinear systems under wide-band noise excitation

This paper expands the application of the RBFNN method to the prediction of non-stationary responses in strongly nonlinear systems subjected to wide-band noises (WBNs) excitation. Specifically, the SAM is initially employed to deduce the averaged Fokker–Planck–Kolmogorov (FPK) equation. The non-stationary responses of the energy of the system under WBNs are modeled as a one-dimensional Markov diffusion process. This yields a one-dimensional FPK equation that governs the NSRs of the system subject to WBNs. Subsequently, solving the corresponding FPK equation and obtaining the system’s NSRs are accomplished with the RBFNN method. Furthermore, four indicative cases exposed to WBNs are studied to verify the proposed scheme. Comparisons with simulations demonstrate the accuracy and efficiency of the developed technique.

Seismic response prediction of a damped structure based on data-driven machine learning methods

Damping technology has been widely used because of its good vibration control effect. However, due to the strong nonlinearity of the added dampers, accurately predicting the seismic response of damped structures remains a challenge. This study investigates the application of interpretable machine learning (ML)-based and deep learning-based approaches to the prediction of the maximum inter-storey displacement of a damped structure. A comprehensive database consisting of 13,855 structural responses to ground motions was collected. Seven traditional interpretable ML algorithms including random forest and extreme gradient boosting (XGBoost), a convolutional neural network based on large receptive field, and seismic wave transformer (SWT) model based on a transformer network were developed. The predictions show that the error of the SWT based on unsupervised feature extraction is reduced by 50.90% compared with that of the optimal XGBoost in ensemble learning. Although the SWT has the highest global accuracy, XGBoost is found to have a smaller error when the structure is in a linear state with peak ground acceleration as partition index, so an aggregation model (AM)-based structural response prediction method was also proposed. The accuracy of the AM improved by 27.95% compared with that of the SWT. In contrast with other ML models, the proposed AM is more advantageous in terms of computational efficiency and accuracy.

GPDRP: a multimodal framework for drug response prediction with graph transformer

BackgroundIn the field of computational personalized medicine, drug response prediction (DRP) is a critical issue. However, existing studies often characterize drugs as strings, a representation that does not align with the natural description of molecules. Additionally, they ignore gene pathway-specific combinatorial implication.ResultsIn this study, we propose drug Graph and gene Pathway based Drug response prediction method (GPDRP), a new multimodal deep learning model for predicting drug responses based on drug molecular graphs and gene pathway activity. In GPDRP, drugs are represented by molecular graphs, while cell lines are described by gene pathway activity scores. The model separately learns these two types of data using Graph Neural Networks (GNN) with Graph Transformers and deep neural networks. Predictions are subsequently made through fully connected layers.ConclusionsOur results indicate that Graph Transformer-based model delivers superior performance. We apply GPDRP on hundreds of cancer cell lines’ bulk RNA-sequencing data, and it outperforms some recently published models. Furthermore, the generalizability and applicability of GPDRP are demonstrated through its predictions on unknown drug-cell line pairs and xenografts. This underscores the interpretability achieved by incorporating gene pathways.

Chronicle knowledge-based multi-level response prediction for predictive control by forest models in process industry

The control output response prediction is confirmed to be crucial for predictive control in process industries. The data-driven approaches that adopt system-independent predictors for output response predictions of multiple controlled variables are promising due to their easy implementation using available open-source models. However, the intrinsic knowledge among controlled variables is ignored, for it cannot be fed into the data-driven models directly, including control events, control antecedents, and temporal constraint information, which inevitably limits the predictive performance. This study proposes a hybrid control output response prediction method embedded with chronicle knowledge and a data-driven model for predictive control. It starts from the knowledge discovery and instance pool establishment by symbolic techniques. Control intrinsic knowledge extracted from the instance pool will be integrated into the modeling of forest model-based predictors, where the knowledge will be leveraged for predictor structure designing and temporal constraints estimation. In this way, tailored predictors with multi-level structures will be devised to capture the intrinsic correlation of controlled variables with different working levels. The control output response predictors will finally be introduced into the design of predictive controllers to make multi-output response predictions. The experimental results show the superiority of the proposed method over baselines in the prediction accuracy as well as the capability of set-point tracking and disturbance rejection.