Intelligent Prediction Research Articles

Building information modeling-based production process optimization model

In the current manufacturing process of enterprises, there are some problems such as poor predictability and low level of intelligence, which lead to high product error rate and affect production efficiency. Therefore, this paper introduces the building information model in the field of engineering construction, and proposes a big data predictive manufacturing model based on the building information model, which divides the production process into production service system, resource planning system, production control system and after-sales service system, and realizes the overall process optimization of planning-production-sales on the basis of the close combination of each system and virtual model system. Finally, the application of error correction process in production line is verified from an empirical point of view, which provides a reference method and path for reducing production error rate and improving work efficiency.

Reversible data hiding in encrypted images based on additive secret sharing and additive joint coding using an intelligent predictor

Reversible data hiding in encrypted images based on additive secret sharing and additive joint coding using an intelligent predictor

Intelligent optimization prediction of screw conveyor speed for earth pressure balance shield machine based on complete ensemble empirical mode decomposition of adaptive noise and deep learning

The excavation stratum of the earth pressure balance (EPB) shield machine is complex and changeable. For ensuring the excavated interface stabilization, the rotational speed of screw conveyor must be precisely controlled to maintain the balance of earth pressure in sealed cabin and to avoid accidents such as ground collapse or upliftment. A data-driven intelligent optimal model is presented by the paper, which organically integrates the complete ensemble empirical mode decomposition of adaptive noise (CEEMDAN), sparrow search algorithm (SSA) and long short-term memory (LSTM) network to achieve accurate prediction of screw conveyor rotation speed. Firstly, Pearson correlation analysis method is used to analyze the historical data of shield tunneling, and the tunneling parameters strongly related to the change of screw conveyor rotation speed are obtained as model input. Secondly, the CEEMDAN is used to decompose the obtained parameter data set into several modal components, and then the denoised data is reorganized to capture the changing characteristics of the original data and reduce the complexity of the data. Then, the parameters such as the learning rate of the LSTM network are optimized by using the strong global search ability of SSA to enhance the prediction precision further in the model. Finally, based on decomposed and reorganized data, SSA-LSTM is used to establish a rotation speed intelligent prediction model realize precise controlling of screw conveyor rotation speed. The simulation experiment is carried out by using the construction data of a section of Beijing Metro Line 10, and the results of three evaluation indexes of the model are given: Mean Absolute Error (MAE) is 0.02878, Mean Absolute Percentage Error (MAPE) is 0.00882 and R2 is 0.99909, which shows that the model has good prediction performance. The control effect of the method on the earth pressure balance of the sealed cabin is tested, and the maximum error value is 0.25%, which verifies the engineering applicability of the method.

Intelligent Prediction of Stability Bearing Capacity of New-Type Modular Assembled Latticed Shells with Flange Connections

Intelligent Prediction of Stability Bearing Capacity of New-Type Modular Assembled Latticed Shells with Flange Connections

Development of an Operating System Supporting Intelligent Predictions and Recommendations

This Study discusses the development of an intelligent operating system feature that supports smart prediction and recommendations using artificial intelligence (AI) capabilities within the Linux operating system. The study aims to integrate AI-driven features into Linux to enhance user productivity and efficiency by providing relevant application recommendations based on user behavior patterns. The implementation involves data collection of application usage, training machine learning models for application recommendations, and integrating these features into the Linux environment. The project utilizes Python for scripting, employing libraries such as psutil, pandas, scikit-learn, and joblib for data handling and machine learning tasks. The results demonstrate successful implementation of the AI-driven recommendation system, enhancing user interaction and productivity within the Linux operating system

Artificial Intelligence to Predict the Risk of Lymph Node Metastasis in T2 Colorectal Cancer.

To develop and externally validate an updated artificial intelligence (AI) prediction system for stratifying the risk of lymph node metastasis (LNM) in T2 colorectal cancer (CRC). Recent technical advances allow complete local excision of T2 CRC, traditionally treated with surgical resection. Yet, the widespread adoption of this approach is hampered by the inability to stratify the risk of LNM. Data from pT2 CRC patients undergoing surgical resection between April 2000 and May 2022 at one Japanese and one Italian center were analyzed. Primary goal was AI system development for accurate LNM prediction. Predictors encompassed seven variables: age, sex, tumor size and location, lympho-vascular invasion, histological differentiation, and carcinoembryonic antigen level. The tool's discriminating power was assessed via Area Under the Curve (AUC), sensitivity, and specificity. Out of 735 initial patients, 692 were eligible. Training and validation cohorts comprised of 492 and 200 patients, respectively. The AI model displayed an AUC of 0.75 in the combined validation dataset. Sensitivity for LNM prediction was 97.8% and specificity was 15.6%. The Positive and the Negative Predictive Value were 25.7% and 96% respectively. The False Negative (FN) rate was 2.2%, the False Positive was 84.4%. Our AI model, based on easily accessible clinical and pathological variables, moderately predicts LNM in T2 CRC. However, the risk of FN needs to be considered. The training of the model including more patients across Western and Eastern centers -differentiating between colon and rectal cancers- may improve its performance and accuracy.

Experimental study on shear mechanical characteristics and its size effect of concrete joints based on BP neural network method

In order to study the shear mechanical characteristics and its size effect on concrete joints, this paper uses the RDS-200 shear test system developed by GCTS company to carry out the indoor direct shear tests on concrete joint specimens with five kinds of JRC and five grades of joint surface size under five normal stress conditions. The results show that the pre-peak shear stiffness of concrete joints is not significantly affected by JRC and normal stress, but is significantly affected by the joint surface size. The pre-peak shear stiffness decreases with the increase of joint surface size, when the joint surface size increases from 35 mm to 95 mm, the pre-peak shear stiffness of specimens with JRC being 0 ∼ 2, 4 ∼ 6, 8 ∼ 10, 12 ∼ 14 and 16 ∼ 18 decreased by 66.96 %, 63.87 %, 71.67 %, 64.57 % and 66.32 %, respectively, with an average of 66.68 %. Moreover, with the increase of joint surface size, the decrease rate of pre-peak shear stiffness decreases gradually, which is basically exponential, that is because the pre-peak shear stiffness has negative size effect. In addition, the peak shear strength of concrete joints increases with the increase of normal stress and JRC, and the relationship between peak shear strength and normal stress conforms to the Mohr-Coulomb criterion. Furthermore, there is no obvious size effect on the peak shear strength of concrete joints in the range of 35–95 mm. An intelligent prediction method for predicting the peak shear strength and pre-peak shear stiffness of concrete joints considering JRC, joint surface size and normal stress was established. The prediction results show that the BP Neural Network optimized by genetic algorithm can effectively predict the peak shear strength and pre-peak shear stiffness of concrete joints, the average error of peak shear strength is about 4.91 %, and the average error of pre-peak shear stiffness is 9.37 %. The conclusions can provide some reference for the evaluation of shear instability of rock joints in surface and underground rock engineering.

Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU

Abstract Realizing automatic control of shield machine tunneling attitude is a challenging problem. Realizing multi-step intelligent prediction for attitude and position is an important prerequisite for solving this problem in the tunneling process with complex and varied geological environments. In this paper, a multi-step intelligent predictive scheme based on beluga whale optimization-convolutional neural network-Long Short-term memory-gated recurrent unit (BWO-CNN-LSTM-GRU) is proposed for shield machine position attitude. First, Pearson correlation analysis is utilized to determine the input feature variables from the construction data and temporalize the input features. Subsequently, CNN-LSTM-GRU predictive models are established for the six positional parameters, separately. Among them, CNN performs feature extraction on the input variables, and LSTM-GRU realizes the predictions for the target positional parameters. In the end, the optimization of the convolutional layer dimension, the number of convolutional layers, iterations, the learning rate, the number of neurons in the LSTM layer and GRU layer of each position predictive model is performed on the basis of BWO, separately, and the best hyperparameters found are built into a BWO-CNN-LSTM-GRU position predictive model, which realizes the multi-step intelligent predictions for the shield machine’s position. The proposed approach is examined by utilizing the Beijing Metro Line 10. The results show that the predictive deviation of the position predictive model is within 3 mm, and the positional trajectory points obtained on the basis of the predicted values and the 3D coordinate system are highly coincident with the actual trajectory points. Therefore, the approach provides a more accurate predictive result for shield attitude and position and can provide a decision-making scheme for further realizing the coordinated autonomous control of shield machine.

CT-based artificial intelligence prediction model for ocular motility score of thyroid eye disease.

Thyroid eye disease (TED) is the most common orbital disease in adults. Ocular motility restriction is the primary complaint of patients, while its evaluation is quite difficult. The present study aimed to introduce an artificial intelligence (AI) model based on orbital computed tomography (CT) images for ocular motility score. A total of 410 sets of CT images and clinical data were obtained from the hospital. To build a triple classification predictive model for ocular motility score, multiple deep learning models were employed to extract features of images and clinical data. Subgroup analyses based on pertinent clinical features were performed to test the efficacy of models. The ResNet-34 network outperformed Alex-Net and VGG16-Net in prediction of ocular motility score, with the optimal accuracy (ACC) of 0.907, 0.870, and 0.890, respectively. Subgroup analyses indicated no significant difference in ACC between active or inactive phase, functional visual field diplopia or peripheral visual field diplopia (p > 0.05). However, in the gender subgroup, the prediction model performed more accurately in female patients than males (p = 0.02). In conclusion, the AI model based on CT images and clinical data successfully realized automatic scoring of ocular motility in TED patients. This approach potentially enhanced the efficiency and accuracy of ocular motility evaluation, thus facilitating clinical application.

Presenting a new deep learning-based method with the incorporation of error effects to predict certain cryptocurrencies

In recent years, with the emergence of blockchain technology, we have witnessed a remarkable increase in the use of digital currencies. However, investing in the digital currency market carries a high level of risk due to the market's erratic behavior and high price fluctuations. Consequently, the need for an appropriate model for intelligent prediction and risk management is perceived. Motivated by the above subject, we propose a novel approach based on a deep neural network with a focus on error patterns. The proposed approach is based on the theory of non-random walks and assumes that there are predictable components in the price movements of cryptocurrencies. This new approach attempts to improve prediction results by modeling residual values and incorporating their impact on the main predictions. The time scope of this research is from October 31, 2018, to December 30, 2023, on a daily basis, spanning Five years. In this study, we utilized Long Short-Term Memory (LSTM) as the main prediction model and Vector Autoregression (VAR) for forecasting noise in three well-known cryptocurrencies: Bitcoin, Ethereum, and Binance Coin (BNB). The results indicate that the proposed approach has been able to enhance the predictions.

Building Dual AI Models and Nomograms Using Noninvasive Parameters for Aiding Male Bladder Outlet Obstruction Diagnosis and Minimizing the Need for Invasive Video-Urodynamic Studies: Development and Validation Study.

Diagnosing underlying causes of nonneurogenic male lower urinary tract symptoms associated with bladder outlet obstruction (BOO) is challenging. Video-urodynamic studies (VUDS) and pressure-flow studies (PFS) are both invasive diagnostic methods for BOO. VUDS can more precisely differentiate etiologies of male BOO, such as benign prostatic obstruction, primary bladder neck obstruction, and dysfunctional voiding, potentially outperforming PFS. These examinations' invasive nature highlights the need for developing noninvasive predictive models to facilitate BOO diagnosis and reduce the necessity for invasive procedures. We conducted a retrospective study with a cohort of men with medication-refractory, nonneurogenic lower urinary tract symptoms suspected of BOO who underwent VUDS from 2001 to 2022. In total, 2 BOO predictive models were developed-1 based on the International Continence Society's definition (International Continence Society-defined bladder outlet obstruction; ICS-BOO) and the other on video-urodynamic studies-diagnosed bladder outlet obstruction (VBOO). The patient cohort was randomly split into training and test sets for analysis. A total of 6 machine learning algorithms, including logistic regression, were used for model development. During model development, we first performed development validation using repeated 5-fold cross-validation on the training set and then test validation to assess the model's performance on an independent test set. Both models were implemented as paper-based nomograms and integrated into a web-based artificial intelligence prediction tool to aid clinical decision-making. Among 307 patients, 26.7% (n=82) met the ICS-BOO criteria, while 82.1% (n=252) were diagnosed with VBOO. The ICS-BOO prediction model had a mean area under the receiver operating characteristic curve (AUC) of 0.74 (SD 0.09) and mean accuracy of 0.76 (SD 0.04) in development validation and AUC and accuracy of 0.86 and 0.77, respectively, in test validation. The VBOO prediction model yielded a mean AUC of 0.71 (SD 0.06) and mean accuracy of 0.77 (SD 0.06) internally, with AUC and accuracy of 0.72 and 0.76, respectively, externally. When both models' predictions are applied to the same patient, their combined insights can significantly enhance clinical decision-making and simplify the diagnostic pathway. By the dual-model prediction approach, if both models positively predict BOO, suggesting all cases actually resulted from medication-refractory primary bladder neck obstruction or benign prostatic obstruction, surgical intervention may be considered. Thus, VUDS might be unnecessary for 100 (32.6%) patients. Conversely, when ICS-BOO predictions are negative but VBOO predictions are positive, indicating varied etiology, VUDS rather than PFS is advised for precise diagnosis and guiding subsequent therapy, accurately identifying 51.1% (47/92) of patients for VUDS. The 2 machine learning models predicting ICS-BOO and VBOO, based on 6 noninvasive clinical parameters, demonstrate commendable discrimination performance. Using the dual-model prediction approach, when both models predict positively, VUDS may be avoided, assisting in male BOO diagnosis and reducing the need for such invasive procedures.

Intelligent Prediction and Application Research on Soft Rock Tunnel Deformation Based on the ICPO-LSTM Model

In tunnel construction, the prediction of the surrounding rock deformation is related to the construction safety and stability of the tunnel structure. In order to achieve an accurate prediction of the surrounding rock deformation in soft rock tunnel construction, a Long Short-Term Memory (LSTM) neural network is used to construct a prediction model of the vault settlement and the horizontal convergence of the upper conductor in soft rock tunnels. The crested porcupine optimisation (CPO) algorithm is used to realise the hyper-parameter optimisation of the LSTM model and to construct the framework of the calculation process of the CPO-LSTM model. Taking the soft rock section of the Baoshishan Tunnel as an example, the large deformation of the surrounding rock is measured and analysed in situ, and the monitoring data of arch settlement and superconducting level convergence are obtained, which are substituted into the CPO-LSTM model for calculation, and compared and analysed with traditional machine learning and optimisation algorithms. The results show that the CPO-LSTM model has an R2 of 0.9982, a MAPE of 0.8595% and an RMSE of 0.1922, which are the best among all the models. In order to further improve the optimisation capability of the CPO, some improvements were made to the CPO and an Improved Crested Porcupine Optimiser (ICPO) was proposed. The ICPO-LSTM prediction model was established, and the ZK6 + 834 section was selected as a research object for comparison and analysis with the CPO-LSTM model. The results of the error analysis show that the prediction accuracy of the improved ICPO-LSTM model has been further improved, and the prediction accuracy of the model meets the requirements of guiding construction.

Meaning in Life As a Predictor of Personal Growth Initiative and Emotional Intelligence for Adolescents

ABSTRACT Meaning in life is the process in which individuals make sense of their lived experiences and the world around them. In adolescence, youth face developmental challenges and stressors that can threaten their well-being. Knowledge of the mechanisms and contributors to protective factors, such as meaning in life, can enhance counselors’ and school counselors’ delivery of services to adolescents and support their optimal growth. In this study, we conducted multiple regression analyses to examine the relationship between participants’ meaning in life, emotional intelligence, and personal growth initiative in a youth sample (n = 203). Our findings indicated that meaning in life was related to students’ personal growth initiative and emotional intelligence. Specifically, we identified that meaning in life predicted personal growth initiative and emotional intelligence for participants in this study. Based on our findings, we offer practical implications for school counselors and counselors working with youth. Implications for research are also provided.

Research on Intelligent Prediction of Surface Roughness in Cutting 42CrMo Steel by using Particle Swarm Optimization-based Support Vector Machine

Research on Intelligent Prediction of Surface Roughness in Cutting 42CrMo Steel by using Particle Swarm Optimization-based Support Vector Machine

Mapping model of ribbon contour and tool influence function based on distributed parallel neural networks in magneto-rheological finishing

Magnetorheological finishing (MRF) stands out as a notable polishing technology, characterized by high precision and minimal damage. However, establishing an accurate and practical model for the tool influence function (TIF) of MRF poses a significant challenge. In this paper, a TIF modeling method of MRF based on distributed parallel neural networks is proposed for the first time. Assessment of the viability of this approach through multiple sets of robot-assisted MRF experiments is detailed. The experimental results conclusively demonstrate the successful intelligent prediction of TIF, with key indicators such as volume removal rate and peak removal rate achieving an average prediction accuracy exceeding 95%. This method can remarkably advance the intelligence of the TIF model in MRF and serve as a valuable reference for other optical fabrication methods.

Explainable artificial intelligence prediction of defect characterization in composite materials

Non-destructive evaluation (NDE) techniques are integral across diverse applications for void detection within composites. Infrared (IR) thermography (IRT) is a prevalent NDE technique that utilizes reverse heat transfer principles to infer defect characteristics by analyzing temperature distribution. Although the forward heat transfer problem is well-posed, its inverse counterpart lacks uniqueness, posing non-unique solutions. The present study performs simulations using finite element analysis (FEA) in defective (a penny-shaped defect) composites through which the heat transfer flux is modeled. A total of 2100 simulations with various defect positions and sizes (depth, size, and thickness) are executed, and the corresponding surface temperature vs. time and vs. distance diagrams are extracted. The FEA outputs provide ample input data for developing an explainable artificial intelligence (XAI) model to estimate the defect characteristics. A detailed feature engineering task is performed to select the representative information from the diagrams. Explainable decision tree-based machine learning (ML) models with transparent decision paths based on derived features are developed to predict the defect depth, size, and thickness. The ML models’ results suggest superb accuracy (R2 = 0.92 to 0.99) across all three defect characteristics. The provided workflow sets a benchmark applicable to a range of fields, including health monitoring.

Artificial Intelligence Predictions of Biomass Power of an Installed Waste Water Treatment Plant

In the current study, the power generations obtained from gas turbines of an installed waste water treatment plant were predicted, utilizing artificial intelligence method consisting of artificial neural network (ANN). In this regards, a cumulative of 445 data, found in the power generation data cluster and found in the physical and chemical data clusters has been used in the predictions based on the artificial intelligence association method. Each instant data of these total 445 data corresponds to daily average power generation (P) obtained from gas turbines of the facility and corresponds to physical and chemical parameters including the temperature (T), degree of acidity (pH), conductivity (σ), as well as the daily total volumetric flow of the waste gas to be burned at the gas generator (Q). Accordingly, the best prediction obtained by ANN approach was concluded to generate the statistical accuracy results corresponding to 6.1279% mean absolute percentage error (MAPE), 2.1540 MWh/day root mean square error (RMSE), and 0.9730 correlation coefficient (R) for power generation parameter.

Multilingual non-intrusive binaural intelligibility prediction based on phone classification

Speech intelligibility (SI) prediction models are a valuable tool for the development of speech processing algorithms for hearing aids or consumer electronics. For the use in realistic environments it is desirable that the SI model is non-intrusive (does not require separate input of original and degraded speech, transcripts or a-priori knowledge about the signals) and does a binaural processing of the audio signals. Most of the existing SI models do not fulfill all of these criteria. In this study, we propose an SI model based on phone probabilities obtained from a deep neural net. The model comprises a binaural enhancement stage for prediction of the speech recognition threshold (SRT) in realistic acoustic scenes. In the first part of the study, SRT predictions in different spatial configurations are compared to the results from normal-hearing listeners. On average, our approach produces lower errors and higher correlations compared to three intrusive baseline models. In the second part, we explore if measures relevant in spatial hearing, i.e., the intelligibility level difference (ILD) and the binaural ILD (BILD), can be predicted with our modeling approach. We also investigate if a language mismatch between training and testing the model plays a role when predicting ILD and BILD. This point is especially important for low-resource languages, where not thousands of hours of language material are available for training. Binaural benefits are predicted by our model with an error of 1.5 dB. This is slightly higher than the error with a competitive baseline MBSTOI (1.1 dB), but does not require separate input of original and degraded speech. We also find that good binaural predictions can be obtained with models that are not specifically trained with the target language.

P-252 Non-invasive artificial intelligence (AI) prediction of blastocyst development from mature oocytes unveils correlation with blastocyst ploidy for enhanced reproductive insight at earliest stage of development

Abstract Study question Can MAGENTA identify mature oocytes more likely to develop into a blastocyst of euploid status? Summary answer Although built to predict blastocyst development, MAGENTA analysis of mature oocytes additionally displays the ability to highlight those with higher potential to become euploid embryos. What is known already MAGENTA (AI image-analysis tool) has been trained to assess and predict blastocyst stage embryo development from mature, denuded oocytes. MAGENTA scores consistently identify oocytes of better quality – more likely to develop into a blastocyst, including blastocysts of higher morphological quality. However, in addition to achieving a blastocyst, the ploidy status of that embryo is crucial in dictating overall chances of implantation and cycle success. Although MAGENTA was not trained to predict blastocyst ploidy from oocytes, most chromosomal errors are of maternal meiotic origin. A correlation between MAGENTA and ploidy status would ignite research possibilities and provide valuable insights. Study design, size, duration A retrospective dataset of 1,324 blastocyst embryos that underwent PGT-A via NGS sequencing, between the years 2021-2023, was assessed. All embryos that were tested for ploidy from a patient cohort were included. Embryos reported as mosaic or ‘no diagnosis’ were excluded from analysis (N = 169). All embryos were cultured in a time-lapse incubator immediately post-ICSI. Of the biopsied blastocysts, 81% were of good morphological quality (expansion grade 1-6, ICM and TE grade A/B). Participants/materials, setting, methods The data includes 292 patients with a mean age of 38.5 (range 19-46) and an average number of tested blastocysts of 4 (range 1-14). Of the 1173 blastocysts, 847 were aneuploid (72.2%) and 326 were euploid (27.8%). 83% of the blastocysts were from patients of advanced maternal age (AMA, ≥38years old). The first time-lapse image, capturing the mature oocyte stage, was extracted, and scored by MAGENTA (scale 0-10). MAGENTA scores were compared by Welch’s t-tests. Main results and the role of chance Impressively, oocytes that developed into euploid blastocysts (n = 326) were identified by MAGENTA with a higher average score of 6.8 compared to those that developed into aneuploid blastocysts (n = 847) with a score of 6.4; a statistically significant differentiation (p < 0.05). 80% of the dataset were high quality blastocysts (expansion 4-6, ICM and TE grade A/B) with an imbalance of euploid (n = 295; mean score 6.8) and aneuploid (n = 643; mean score 6.6) blastocysts—likely a result of AMA. Therefore, subgroup analysis was focused on assessing the ploidy status relationships amongst several patient age groups within these AMA cases. Due to our clinic’s indication for PGT-A, the smallest subset of oocytes was from patients <38 years of age (N = 373, 48% euploid). In this age group there was no significant difference in MAGENTA scores between the oocytes of euploid and aneuploid embryo status (6.9 vs 6.7; p = 0.522). However, in oocytes from patients aged ≥38 (N = 800, 19% euploid), the distinction between those that became euploid and aneuploid blastocysts is evident with a statistically significant difference in MAGENTA scores (6.8 vs 6.3; p < 0.05). This relationship with ploidy status additionally remains with further stratification into the ≥41 age group (N = 467 oocytes, 13% euploid; 6.7 vs 5.9; p < 0.01). Limitations, reasons for caution Majority of the patients in this dataset underwent PGT-A due to AMA, further research is required to include a wider age demographic, particularly in patients <35 years old. Greater representation of varying blastocyst qualities is required to further assess MAGENTA correlation to ploidy outcomes amongst quality groups. Wider implications of the findings This study presents the first non-invasive assessment of mature oocyte quality that indicates oocytes with greater potential for euploid blastocyst development. This application of MAGENTA provides a novel method of gaining ploidy status potential at the mature oocyte stage, which is invaluable to both IVF and cryopreservation cycles. Trial registration number NOT APPLICABLE

Time-series traction prediction of surrounding rock deformation in tunnel construction based on mechanical parameter inversion

The deformation of the surrounding rock serves as a macroscopic representation of the stability status of the tunnel, and is also an important indicator for stability evaluation. To address the difficulty of accurately predicting long-term deformation in tunnel surrounding rock with limited monitoring data, a time-series traction prediction method based on the inversion of mechanical parameters was proposed. Employing the adaptive vigilance chaotic sparrow search algorithm (ACSSA) to optimize initial parameters in extreme learning machines (ELM) and long short-term memory (LSTM) neural networks. It then constructed two deformation time-series prediction models and a rock mechanics parameter inversion model based on the ACSSA-ELM and ACSSA-AMLSTM algorithms. Based on the mechanical parameter inversion model and numerical simulation, the value of the surrounding rock deformation at the key construction nodes of the tunnel was calculated as the traction point, and the traction interval and traction control equation were defined. Cubic spline interpolation and wavelet decomposition were employed to preprocess the measured deformation data of the surrounding rock. Subsequently, the proposed time-series prediction model was utilized for prediction. The predicted results within the traction interval undergo correction based on the traction points, thereby achieving a more precise and intelligent prediction of the tunnel surrounding rock deformation. Based on literature cases and data from the Huayang Tunnel project in Chongqing, the proposed method was validated and applied. The model's accuracy has been validated and successfully guided construction and production. Finally, the impact of different methods on traction effectiveness and the distribution pattern of traction points on model performance was discussed.