Multilayer Perceptron Neural Network Research Articles

Coral bionic e-skin for motion monitoring and intelligent recognition of underwater communication commands assisted by deep learning

Continuous and dependable underwater motion monitoring and communication are crucial for ensuring the safety of swimming, divers and underwater workers. We have developed a coral-inspired piezoresistive electronic skin (Melamine sponge-poly(pyrrole)-polydimethylsiloxane, MS-ppy-PDMS e-skin) for motion monitoring and underwater communication. The microstructure of the coral-like poly(pyrrole) and the PDMS acting as “limestone” make MS-ppy-PDMS e-skin superhydrophobic, stable (up to 80,000 cycles and acid and alkali resistance), and sensitive over a wide pressure sensing range (1–2,000 kPa). Moreover, MS-ppy-PDMS e-skin exhibits remarkable breathability, photothermal antibacterial efficacy, and biocompatibility, thereby increasing the comfort of wear while maintaining its outstanding sensing functionality. MS-ppy-PDMS e-skin exhibited dependable electrical signals output in motion monitoring tests on land and underwater. Most crucially, the combination of underwater communication commands captured by MS-ppy-PDMS e-skin with a multilayer perceptron (MLP) neural network allows for rapid and precise analysis and recognition, achieving a 99.38% accuracy rate in identifying underwater communication commands. This enables the realization of intelligent perception function, and is expected to further advance the development of human brain-like cognitive systems. Overall, the coral bionic MS-ppy-PDMS e-skin demonstrates tremendous application potential in the fields of motion monitoring and underwater communication.

Comparative analysis of cement grade and cement strength as input features for machine learning-based concrete strength prediction

Machine learning (ML) has gained recognition as a valuable tool for predicting concrete properties. This study investigated the influence of input features related to cement strength on the performance of ML models. Four datasets with various features were prepared, and for each dataset, cement grade and cement strength were alternately applied as input features. ML models such as Random Forest, Extreme Gradient Boosting, and Multilayer Perceptron Neural Network were utilized to predict concrete strength for each dataset. The results showed a tendency for the prediction performance to improve when cement properties were used as input features, with the extent of improvement varying across the datasets. Permutation importance analysis indicated that cement strength often had a greater influence on the ML models than cement grade, positively enhancing prediction performance. Therefore, considering cement strength as an input feature is expected to be beneficial for constructing more accurate ML models.

Multiscale analysis of carbon nanotube-reinforced curved beams: A finite element approach coupled with multilayer perceptron neural network

This paper presents a comprehensive investigation into the structural response of curved composite beams enhanced with carbon nanotube (CNT). Employing a multiscale framework, our analysis leverages the finite element method (FEM) to account for both bending and shear deformations across six degrees of freedom. The inquiry encompasses diverse mechanical, geometrical, and boundary configurations to assess these composite beams' natural vibration features. Moreover, we introduce a multilayer perceptron (MLP) neural network architecture designed to forecast such beams' dimensionless first natural frequency. Trained on a meticulously curated dataset derived from FEM simulations, the neural network model exhibits promising predictive capabilities concerning the free vibration frequency. To ascertain the efficacy and precision of our proposed methodology, we conduct a comparative analysis between FEM results and employ statistical metrics to evaluate the neural network's predictive performance. The findings of this study reveal an impressive predictive accuracy of over 95 % with regards to the initial natural frequency of the composite beams, thereby emphasizing the potential effectiveness of neural network methodologies in engineering analyses. This study significantly contributes to advancing our comprehension of the vibrational dynamics inherent in carbon nanotube-reinforced composite beams, while concurrently underscoring the potential efficacy of neural networks in forecasting their dynamic attributes.

Mitigating risks in central line-associated bloodstream infection: a comprehensive insight into critical care nurses’ knowledge, attitudes, barriers, and compliance

BackgroundCentral venous catheter-related bloodstream infections (CLABSIs) are a significant concern in intensive care units (ICUs) as they lead to increased morbidity, mortality, and healthcare costs. Fortunately, these infections are largely preventable through strict adherence to CLABSI prevention guidelines. Nurses play a critical role in preventing CLABSIs.AimThis study aimed to investigate factors affecting critical care nurses' knowledge, attitudes, and perceived barriers related to implementing CLABSI prevention guidelines, and to predict factors influencing compliance with these guidelines.MethodsThis cross-sectional study was conducted from April to May 30, 2023, with a convenience sample of 470 critical care nurses from ICUs across eight hospitals in Sana’a, Yemen. Data were collected using an observational checklist and self-administered questionnaire. Descriptive statistics, Independent Student’s t-test, one-way ANOVA, Pearson’s correlation coefficient, multiple linear regression, and multilayer perceptron neural networks were performed.ResultsCritical care nurses exhibited low knowledge of CLABSI prevention guidelines, with compliance reaching an acceptable level. Despite the higher perceived barriers, the nurses demonstrated a positive attitude. Nurses with greater knowledge and positive attitudes displayed higher compliance levels. However, perceived barriers were negatively associated with knowledge and compliance. Notably, multilayer neural network analysis identified knowledge and perceived barriers as the strongest predictors of nurses' compliance.ConclusionThe current findings emphasize the need for multifaceted strategies to implement the CLABSI prevention guidelines. These strategies should address knowledge gaps, support positive attitudes, and address practical barriers faced by nurses to ensure successful implementation of CLABSI prevention.

Predicting air quality index and fine particulate matter levels in Bagdad city using advanced machine learning and deep learning techniques

Particulate matter pollution is recognized globally as one of the most hazardous forms of air pollution, profoundly impacting environmental integrity and public health. Key metrics for assessing this pollution include the Air Quality Index (AQI) and fine particulate matter with diameters ≤2.5 μm (PM2.5). These indicators are closely associated with severe health consequences, such as premature death from chronic exposure. While traditional statistical methods have been employed in some studies to evaluate AQI and PM2.5, the application of advanced machine learning techniques has been limited. This research employs deep learning and artificial neural networks (ANN) to forecast AQI and PM2.5 levels in Baghdad, Iraq. The study utilizes an extensive dataset from July 1, 2016, to December 12, 2021, comprising over 48,000 data points for AQI and PM2.5. Time serves as an independent input variable influencing these dependent variables. The analysis employs a diverse set of machine learning algorithms, including random forest, decision tree, K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), and Long Short-Term Memory networks (LSTM). The findings demonstrate that MLP and LSTM models outperform other methods, providing the most accurate predictions. The correlation coefficients were 0.977 and 0.983 for the prediction of AQI and 0.973 and 0.985 for the prediction of PM2.5 using MLP and LSTM, respectively. In addition, the outcomes showed that both AQI and PM2.5 were within the moderate to unhealthy ranges, and their distribution levels pointed to the need for addressing air quality in Baghdad city. Furthermore, this study contributes to the burgeoning field of machine learning applications in environmental science by establishing a robust and nuanced predictive framework for evaluating air quality. It highlights the potential of deep learning in public health applications and offers actionable insights for policymaking to mitigate air pollution and its adverse effects.

Buckle propagation failure of subsea pipelines; experimental, analytical, and numerical simulations

This research program investigates buckle propagation in subsea pipeline systems, The study aims to understand and predict propagation pressure (PP ), essential for ensuring the structural integrity and safe operation of these pipelines, hypothesizing that incorporating strain hardening effects into the strain energy approach can significantly enhance the prediction of propagation pressure (PP ) and that geometric parameters, particularly the diameter-to-thickness (D/t) ratio, play a major role in PP prediction. Accurate PP prediction is essential for ensuring the structural integrity and safe operation of these pipelines. The investigation is conducted through analytical, experimental, numerical, and machine learning approaches. A new analytical solution for PP is proposed, incorporating strain hardening effects using a strain energy approach. Experimental tests conducted using a hyperbaric chamber cover a wide range of pipeline configurations and materials, including steel, aluminum, and stainless steel. Complementing experimental data, numerical simulations using finite element methods facilitate parametric dependence analysis and the visualization of results through 3D charts. More than 600 FE models were simulated to investigate the influence of geometric and material parameters on PP . The findings from both experimental and numerical analyses indicated that the geometric and material properties have a significant impact on PP , specifically, the diameter-to-thickness (D/t) ratio, yield stress (σy ), and tangent modulus (E′). Furthermore, Machine Learning (ML) techniques have been used to predict the PP value and have concluded that the Random Forest (RF) technique outperformed the K-Nearest Neighbors (KNN), and Multi-layer Perceptron (MLP) neural network techniques. Overall, this study concludes that analytical, numerical, and machine learning approaches offer valuable insights into buckle propagation in subsea pipelines, contributing to improved safety and reliability in offshore oil and gas operations.

Development of a machine learning approach for prediction of red blood cell transfusion in patients undergoing Cesarean section at a single institution

Despite recent advances in surgical techniques and perinatal management in obstetrics for reducing intraoperative bleeding, blood transfusion may occur during a cesarean section (CS). This study aims to identify machine learning models with an optimal diagnostic performance for intraoperative transfusion prediction in parturients undergoing a CS. Additionally, to address model performance degradation due to data imbalance, this study further investigated the variation in predictive model performance depending on the ratio of event to non-event data (1:1, 1:2, 1:3, and 1:4 model datasets and raw data).The area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) were evaluated to compare the predictive accuracy of different machine learning algorithms, including XGBoost, K-nearest neighbor, decision tree, support vector machine, multilayer perceptron, logistic regression, random forest, and deep neural network. We compared the predictive performance of eight prediction algorithms that were applied to five types of datasets. The intraoperative transfusion in maternal CS was 7.2% (1020/14,254). XGBoost showed the highest AUROC (0.8257) and AUPRC (0.4825) among the models. The most significant predictors for transfusion in maternal CS as per machine learning models were placenta previa totalis, haemoglobin, placenta previa partialis, and platelets. In all eight prediction algorithms, the change in predictive performance based on the AUROC and AUPRC according to the resampling ratio was insignificant. The XGBoost algorithm exhibited optimal performance for predicting intraoperative transfusion. Data balancing techniques employed to alter the event data composition ratio of the training data failed to improve the performance of the prediction model.

Enhancing left ventricular segmentation in echocardiography with a modified mixed attention mechanism in SegFormer architecture

Echocardiography is a key tool for the diagnosis of cardiac diseases, and accurate left ventricular (LV) segmentation in echocardiographic videos is crucial for the assessment of cardiac function. However, since semantic segmentation of video needs to take into account the temporal correlation between frames, this makes the task very challenging. This article introduces an innovative method that incorporates a modified mixed attention mechanism into the SegFormer architecture, enabling it to effectively grasp the temporal correlation present in video data. The proposed method processes each time series by encoding the image input into the encoder to obtain the current time feature map. This map, along with the historical time feature map, is then fed into a time-sensitive mixed attention mechanism type of convolution block attention module (TCBAM). Its output can serve as the historical time feature map for the subsequent sequence, and a combination of the current time feature map and historical time feature map for the current sequence. The processed feature map is then input into the Multilayer Perceptron (MLP) and subsequent networks to generate the final segmented image. Through extensive experiments conducted on two different datasets: Hamad Medical Corporation, Tampere University, and Qatar University (HMC-QU), Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) and Sunnybrook Cardiac Data (SCD), achieving a Dice coefficient of 97.92 % on the SCD dataset and an F1 score of 0.9263 on the CAMUS dataset, outperforming all other models. This research provides a promising solution to the temporal modeling challenge in video semantic segmentation tasks using transformer-based models and points out a promising direction for future research in this field.

Predictive modelling of freeway space utilising clinical history, normalised muscle activity, dental occlusion, and mandibular movement analysis

This study aimed to predict dental freeway space by examining the clinical history, habits, occlusal parameters, mandibular hard tissue movement, soft tissue motion, muscle activity, and temporomandibular joint function of 66 participants. Data collection involved video-based facial landmark tracking, mandibular electrognathography, surface electromyography of mandibular range of motion, freeway space, chewing tasks, phonetic expressions, joint vibration analysis, and 3D jaw scans of occlusion. This resulted in a dataset of 121 predictor features, with freeway space as the target variable. Six models were trained on synthetic data ranging from 500 to 25,000 observations, with 65 original observations reserved for testing: Linear Regression, Random Forest, CatBoost Regressor, XGBoost Regressor, Multilayer Perceptron Neural Network (MPNN), and TabNet. Explainable AI indicated that key predictors of freeway space included phonetics, resting temporalis muscle activity, mandibular muscle activity during clenching, body weight, mandibular hard tissue lateral displacements, and dental arch parameters. CatBoost excelled with a test error of 0.65 mm using 5000 synthetic data points, while a refined MPNN achieved the best performance with 25,000 synthetic data points and 121 unique predictors, yielding an absolute error of 0.43 mm on the 65 original observations.

Exploring deep fully convolutional neural networks for surface defect detection in complex geometries

In this paper, we propose a machine learning approach for detecting superficial defects in metal surfaces using point cloud data. We compare the performance of two popular deep learning architectures, multilayer perceptron networks (MLPs) and fully convolutional networks (FCNs), with varying feature sets. Our results show that FCNs (F1=0.94) outperformed MLPs (F1=0.52) in terms of precision, recall, and F1-score. We found that transfer learning with pre-trained models can improve performance when the amount of available data is limited. Our study highlights the importance of considering the amount and quality of training data in developing machine learning models for defect detection in industrial settings with 3D images.

India-Vietnam Bilateral Trade and Investment Relations: An Empirical Analysis

The relations between India and Vietnam have been strengthening in both social and economic aspects. The bilateral trade and investment relations between the two countries are on an upward trend. In this context, the present paper analyzes the trade intensity between India and Vietnam and provides an overview of the investment relations. The study also examines the impact of the host country's GDP and exchange rate on the home country's export level for both India and Vietnam using the Multilayer Perceptron Neural Network technique of Artificial Neural Network. The main findings of the study show that before 2017, India's exports are more intensive than imports with Vietnam and Vietnam's imports are more intensive than exports with India. However, since 2017, this trend is slightly reversed and Vietnam's exports are more intense than imports with India. Furthermore, it is found that the host country's GDP and exchange rate have a significant impact on India and Vietnam's bilateral exports.

Unsupervised heterogeneous domain adaptation for EEG classification

Objective. Domain adaptation has been recognized as a potent solution to the challenge of limited training data for electroencephalography (EEG) classification tasks. Existing studies primarily focus on homogeneous environments, however, the heterogeneous properties of EEG data arising from device diversity cannot be overlooked. This motivates the development of heterogeneous domain adaptation methods that can fully exploit the knowledge from an auxiliary heterogeneous domain for EEG classification. Approach. In this article, we propose a novel model named informative representation fusion (IRF) to tackle the problem of unsupervised heterogeneous domain adaptation in the context of EEG data. In IRF, we consider different perspectives of data, i.e. independent identically distributed (iid) and non-iid, to learn different representations. Specifically, from the non-iid perspective, IRF models high-order correlations among data by hypergraphs and develops hypergraph encoders to obtain data representations of each domain. From the non-iid perspective, by applying multi-layer perceptron networks to the source and target domain data, we achieve another type of representation for both domains. Subsequently, an attention mechanism is used to fuse these two types of representations to yield informative features. To learn transferable representations, the maximum mean discrepancy is utilized to align the distributions of the source and target domains based on the fused features. Main results. Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model. Significance. This article handles an EEG classification situation where the source and target EEG data lie in different spaces, and what’s more, under an unsupervised learning setting. This situation is practical in the real world but barely studied in the literature. The proposed model achieves high classification accuracy, and this study is important for the commercial applications of EEG-based BCIs.

Impact of various DIII-D diagnostics on the accuracy of neural network surrogates for kinetic EFIT reconstructions

Kinetic equilibrium reconstructions make use of profile information such as particle density and temperature measurements in addition to magnetics data to compute a self-consistent equilibrium. They are used in a multitude of physics-based modeling. This work develops a multi-layer perceptron (MLP) neural network (NN) model as a surrogate for kinetic Equilibrium Fitting (EFITs) and trains on the 2019 DIII-D discharge campaign database of kinetic equilibrium reconstructions. We investigate the impact of including various diagnostic data and machine actuator controls as input into the NN. When giving various categories of data as input into NN models that have been trained using those same categories of data, the predictions on multiple equilibrium reconstruction solutions (poloidal magnetic flux, global scalars, pressure profile, current profile) are highly accurate. When comparing different models with different diagnostics as input, the magnetics-only model outputs accurate kinetic profiles and the inclusion of additional data does not significantly impact the accuracy. When the NN is tasked with inferring only a single target such as the EFIT pressure profile or EFIT current profile, we see a large increase in the accuracy of the prediction of the kinetic profiles as more data is included. These results indicate that certain MLP NN configurations can be reasonably robust to different burning-plasma-relevant diagnostics depending on the accuracy requirements for equilibrium reconstruction tasks.

A comprehensive approach utilizing quantum machine learning in the study of corrosion inhibition on quinoxaline compounds

In this investigation, a quantitative structure-property relationship (QSPR) model coupled with a quantum neural network (QNN) was used to explore the corrosion inhibition efficiency (CIE) of quinoxaline compounds. Integrating quantum chemical properties (QCP) features reduced computational burden by strategically reducing the features from 11 to 4 while maintaining prediction accuracy. QNN models outperform traditional methods like artificial neural networks (ANN) and multilayer perceptron neural networks (MLPNN), with a coefficient of determination (R2) value of 0.987, coupled with diminished root mean square error (RMSE), mean absolute error (MAE), and mean absolute deviation (MAD) values of 0.97, 0.92, and 1.10, respectively. Predictions for six newly synthesized quinoxaline derivatives: quinoxaline-6-carboxylic acid (Q1), methyl quinoxaline-6-carboxylate (Q2), (2E,3E)-2,3-dihydrazono-1,2,3,4-tetrahydroquinoxaline (Q3), (2E,3E) 2,3-dihydrazono-6-methyl-1,2,3,4-tetrahydroquinoxaline (Q4), (E)-3-(4-methoxyethyl)-7-methylquinoxalin-2(1 H)-one (Q5), and 2-(4-methoxyphenyl)-7-methylthieno[3,2-b] quinoxaline (Q6), show remarkable CIE values of 95.12, 96.72, 91.02, 92.43, 89.58, and 93.63 %, respectively. This breakthrough technique simplifies testing and production procedures for new anti-corrosion materials.

Research on a Multidimensional Digital Printing Image Quality Evaluation Method Based on MLP Neural Network Regression

High-quality printing is a longstanding objective in the printing and replication industry. However, the methods used to evaluate print quality suffer from subjectivity and multidimensionality, relying on personal preferences and subjective perceptions to assess the quality of printed images, which poses significant limitations. To address these issues, a set of evaluation metrics aimed at assessing the quality of digital printing products is proposed to achieve evaluation results consistent with human visual perception. Given the differing imaging principles of pre-press digital images and post-scan images, these images are first preprocessed to standardize them for comparison. Next, features are extracted in both spatial and frequency domains, and similarity metrics are used to quantify the differences in features between pre-press digital images and post-scan images. Finally, a multilayer perceptron (MLP) neural network regression model is trained to predict the final objective quality scores. Experimental results on two standard databases demonstrate that this metric exhibits high consistency in both subjective and objective quality evaluation metrics for printed image quality assessment and outperforms other metrics in terms of accuracy.

An algorithm for two-dimensional pattern detection by combining Echo State Network-based weak classifiers

Pattern detection is one of the essential technologies in computer vision. To solve pattern detection problems, the system needs a vast amount of computational resources. To train a multilayer perceptron or convolutional neural network, the gradient descent method is commonly used. The method consumes computational resources. To reduce the amount of computation, we propose a two-dimensional pattern detection algorithm based on Echo State Network (ESN). The training rule of ESN is based on one-shot ridge regression, which enables us to avoid the gradient descent. ESN is a kind of recurrent neural network (RNN), which is often used to embed temporal signals inside the network, rarely used for the embedding of static patterns. In our prior work (Kage, 2023), we found that static patterns can be embedded in an ESN network by associating the training patterns with its stable states, or attractors. By using the same training procedure as our prior work, we made sure that we can associate each training patch image with the desired output vector. The resulting performance of a single ESN classifier is, however, relatively poor. To overcome this poor performance, we introduced an ensemble learning framework by combining multiple ESN weak classifiers. To evaluate the performance, we used CMU-MIT frontal face images (CMU DB). We trained eleven ESN-based classifiers by using six CMU DB training images and evaluated the performance by using a CMU DB test image. We succeeded in reducing false positives in the CMU DB test image down to 0.0515 %.

Forecasting Robot Movement with Sensor Readings and Multi-Layer Perceptron Models

Classification of sensor data plays a crucial role in different fields, aiding in important tasks like detecting faults, recognizing events and predicting maintenance needs. This research paper thoroughly explores the use of machine learning methods, in specific Multi-Layer Perceptron (MLP) networks, to classify sensor data. The dataset used in this study includes raw measurements from all 24 ultrasound sensors alongside their corresponding class labels indicating the robots actions (such as moving or turning left). The study tackles challenges like imbalanced classes, noisy signals, and striving for classification through a case study employing MLP models. Through conducting experiments and analysis, we fine-tuned the MLP models setup to achieve a 93.04% accuracy on the test dataset. Additionally evaluation metrics like precision, recall and F1 score highlighted the models effectiveness across different classes. A comparison with Support Vector Machines (SVM) and Logistic Regression models highlighted the performance of the MLP model. These results not only show the effectiveness of MLP networks but also provide valuable insights into best practices, for classifying sensor data. Through examining the intricacies of sensor data analysis and classification this study contributes to enhancing our knowledge of applying machine learning to real world challenges.

Analyzing speed-difference impact on freeway joint injury severities of Leading-Following vehicles using statistical and data-driven models

Rear-end (RE) crashes are notably prevalent and pose a substantial risk on freeways. This paper explores the correlation between speed difference among the following and leading vehicles (Δν) and RE crash risk. Three joint models, comprising both uncorrelated and correlated joint random-parameters bivariate probit (RPBP) approaches (statistical methods) and a cross-stitch multilayer perceptron (CS-MLP) network (a data-driven method), were estimated and compared against three separate models: Support Vector Machines (SVM), eXtreme Gradient Boosting (XGBoost), and MLP networks (all data-driven methods). Data on 15,980 two-vehicle RE crashes were collected over a two-year period, from January 1, 2021, to December 31, 2022, considering two possible levels of injury severity: no injury and injury/fatality for both drivers of following and leading vehicles. The comparative performance analysis demonstrates the superior predictive capability of the CS-MLP network over the uncorrelated/correlated joint RPBP model, SVM, XGBoost, and MLP networks in terms of recall, F-1 Score, and AUC. Significantly, numerous shared variables influence the injury severity outcomes for the following and leading vehicles across both statistical and data-driven approaches. Among these factors, the following vehicle (a truck) and the leading vehicle (a passenger car) demonstrate contrasting effects on the injury severity outcomes for both vehicles. Furthermore, the SHapley Additive exPlanations (SHAP) values from the CS-MLP network visually show the relationship between Δν and injury severity, revealing non-linear trends unlike the average effects shown by statistical methods. They indicate that the least injury outcomes for both following and leading vehicles occurs at a Δν of 0 to 10 mph, matching observed patterns in RE crash data. Additionally, a marked variation in the trend of SHAP values for the two vehicles is noted as the speed difference increases. Therefore, the findings affirm the superior performance of joint model development and substantiate the non-linear impacts of speed difference on injury outcomes. The adoption of dynamic speed control measures is recommended to mitigate the injury outcomes involved in two-vehicle RE crashes.

A study on the application of artificial neural network to predict k-eff and peaking factor of a small modular PWR

Machine learning (ML) using artificial neural network (ANN) methods is being applied to predict required parameters for nuclear reactors based on learning from big data sets. The ML models usually give faster calculation speed while the accuracy is good agreement with physical simulators. In this work, a multi-layer perceptron network was built and trained to predict k-eff and peaking factor of a small modular pressurized water reactor (PWR). The results are compared with those obtained by using a reactor physics code system, i.e. SRAC2006. The comparison shows good agreement accuracy and higher performance of the ML models.

Designing three-dimensional lattice structures with anticipated properties through a deep learning method

Lattice structures have been a hot topic recently owing to their superior mechanical properties, which are significantly influenced by the unit cell structure. By leveraging the power of deep learning, inverse design can be conducted on the unit cell structure based on the mechanical properties of its lattice structure. Assisted by deep learning, this study introduces a novel data-driven approach to design three-dimensional (3D) unit cells for lattice structures with anticipated properties. The approach can be efficiently and accurately applied to various unit cell structures. An auto-encoder is trained to extract the geometric features from unit cell point clouds. The effective mechanical properties of the lattice structures are calculated by combining the homogenization method and the finite element method. Subsequently, a mapping relationship between mechanical properties and geometric features is established through the multi-layer perceptron neural network. The models are ultimately employed to design 3D unit cells given anticipated properties of lattice structures. The results show that the mechanical properties of the generated unit cells satisfy the anticipated values. The applications of proposed method are demonstrated in orthopedic implants, new hybrid unit cells, and functionally gradient structures. Furthermore, the method can be extended to unit cell design across diverse domains.