Perceptron Research Articles

Development of an atmospheric boundary layer detection system based on a rotary-wing unmanned aerial vehicle.

To enhance meteorological detection methods, an atmospheric boundary layer detection system based on a rotary-wing unmanned aerial vehicle (UAV) was proposed. Computational fluid dynamics (CFD) was employed to model the surrounding airflow distribution during UAV hovering, thereby determining the optimal positions for sensor installation. A novel radiation shield was designed for the temperature sensor, offering both excellent radiation shielding and superior ventilation. To further improve temperature measurement accuracy, an error correction model based on CFD and neural network algorithms was designed. CFD was used to quantify the temperature measurement errors of the sensor under different environmental conditions. Subsequently, random forest and multilayer perceptron algorithms were employed to train and learn from the simulated temperature errors, resulting in the development of the error correction model. To validate the accuracy of the detection system, comparative experiments were conducted using the measurement values from the 076B temperature observation instrument as a reference. The experimental results indicate that the mean absolute error, root mean square error, and correlation coefficient between the experimental temperature errors and the algorithm-predicted errors are 0.055, 0.066, and 0.971 °C, respectively. The average error of the corrected temperature data is 0.05 °C, which shows substantial agreement with the reference temperature data. During UAV hovering, the average discrepancies between the temperature, humidity, and air pressure data of the detection system and the ground-based reference data are 0.6 °C, 1.6% RH, and 0.77 hPa, respectively.

Investigation and application of data balancing and combined discriminant model in rock burst severity prediction

In the development of intelligent rock burst prediction models, issues such as incomplete data coverage and data imbalance are frequently encountered. These issues may lead to risks of overfitting in predictive models, poor generalization capabilities, and increased bias, which in turn may result in misjudgments and unpredictable losses. To accurately predict rock burst disasters and mitigate or eliminate related threats, this paper proposes a composite prediction model that integrates Density-Based Nonlinear Resampling (DBNR)-Tomek Link data balancing algorithms with Bayesian Optimization (BO)-Multilayer Perceptron (MLP)-Random Forest (RF). Initially, this study collected and organized a total of 301 recorded rock burst disaster field observation data, covering various tectonic plates, engineering types, rock origins, rock textures, and rock burst types. Subsequently, from a data analysis perspective, we employed the PCA-SSA-K-means unsupervised clustering algorithm to delve into the underlying information contained within the data, thereby validating the rationality of categorizing rock bursts into four grades. Then, using the L2 norm to optimize the dimensionality of the indicators and supplementing with indicator importance ranking and hypothesis testing, we selected the maximum tangential stress of the surrounding rock, the ratio of the maximum tangential stress of the surrounding rock to the uniaxial compressive strength of the rock (stress coefficient), and the elastic energy index as the criteria for rock burst intensity grading. Following that, the DBNR-Tomek Link sampling method was applied to balance the sample data, optimizing the data sample ratio and ultimately expanding the sample size to 396, improving the proportion of data samples from 2:3:4:1 to 1:1:2:1, thereby enhancing the model’s generalization performance. Ultimately, a BO-MLP-RF composite prediction model was constructed based on Bayesian Optimization (BO), Multilayer Perceptron (MLP), and Random Forest (RF) algorithms, with the Bayesian Optimization method ensuring that the model fits the training data well and generalizes to the test data. The results of tenfold cross-validation demonstrated that the model’s accuracy is consistently around 92.5%, combining the training results of rock burst models with imbalanced datasets, proving that the MLP model, adept at modeling nonlinear data, and the RF model, skilled in modeling large-scale data, serve as basic classifiers. This demonstrates that the application of data balancing and combined discriminative model schemes have enhanced the model’s predictive performance and stability. The model is capable of providing high-accuracy, high-efficiency early warning monitoring services for rock burst phenomena in rock engineering, thereby ensuring engineering safety.

Retrieval of cloud fraction using machine learning algorithms based on FY-4A AGRI observations

Abstract. Cloud fraction as a vital component of meteorological satellite products plays an essential role in environmental monitoring, disaster detection, climate analysis and other research areas. Random forest (RF) and multilayer perceptron (MLP) algorithms were used in this paper to retrieve the cloud fraction of AGRI (Advanced Geosynchronous Radiation Imager) on board the Fengyun-4A (FY-4A) satellite based on its full-disk level-1 radiance observation. Corrections have been made subsequently to the retrieved cloud fraction in areas where solar glint occurs using a correction curve fitted with sunglint angle as weight. The algorithm includes two steps: the cloud detection is conducted firstly for each AGRI field of view to identify whether it is clear sky, partly cloudy or overcast within the observation field. Then, the cloud fraction is retrieved for the scene identified as partly cloudy. The 2B-CLDCLASS-lidar cloud fraction product from the CloudSat and CALIPSO active remote sensing satellite is employed as the truth to assess the accuracy of the retrieval algorithm. Comparison with the operational AGRI level-2 cloud fraction product is also conducted at the same time. The results indicate that both the RF and MLP cloud detection models achieved high accuracy, surpassing that of operational products. However, both algorithms demonstrated weaker discrimination capabilities for partly cloudy conditions compared to clear-sky and overcast situations. Specifically, they tended to misclassify fields of view with low cloud fractions (e.g., cloud fraction = 0.16) as clear sky and those with higher cloud fractions (e.g., cloud fraction = 0.83) as overcast. Between the two models, RF exhibited higher overall accuracy. Both RF and MLP models performed well in cloud fraction retrieval, showing lower mean error (ME), mean absolute error (MAE) and root mean square error (RMSE) compared to operational products. The ME for both RF and MLP cloud fraction retrieval models was close to zero, while RF had slightly lower MAE and RMSE than MLP. During daytime, the high reflectance in sunglint areas led to larger retrieval errors for both RF and MLP algorithms. However, after correction, the retrieval accuracy in these regions improved significantly. At night, the absence of visible light observations from the AGRI instrument resulted in lower classification accuracy compared to daytime, leading to higher cloud fraction retrieval errors during nighttime.

Cyanogel-Transformed Porous Palladium and Iron Framework Intermixed with rGO for Wearable Hydrogen Sensing.

Wearable hydrogen (H2) sensing is necessary to monitor the H2 leakage in its transportation and storage, of which ppm-concentration detection limit and fast response at room temperature are highly desired. Here, a wearable H2 sensing working at room temperature is developed with palladium and iron framework intermixed with reduced graphene oxide (rGO//Pd-Fe FW), which is synthesized by combined Pd-Fe cyanogel immobilized with graphene oxide as precursor and in situ reduction. As-prepared rGO//Pd-Fe FW is observed with porous FW structure composed of interconnected Pd-Fe nanoparticles, in which rGO is evenly intermixed. Beneficially, rGO//Pd-Fe FW exhibits 2ppm low detection limit and 2 s fast response (1 v/v% H2) at room temperature. Such excellent H2 sensing performance may be attributed to the synergistic effect of the optimized Pd-Fe FW's catalytic activity, boosted electron transfers between Pd hydride and rGO, and enriched adsorption sites over porous FW's surface. Practically, the perceptron learning algorithm combined with principal component analysis is conducted to identify the H2 leakage, and the wearable H2 sensing devices are built by integrating rGO//Pd-Fe FW over the paper and flexible printed circuit board with reliable sensing responses.

L2R-MLP: A Multilabel Classification Scheme for the Detection of DNS Tunneling

Domain name system (DNS) tunneling attacks can bypass firewalls, which typically "trust" DNS transmissions by concealing malicious traffic in the packets trusted to convey legitimate ones, thereby making detection using conventional security techniques challenging. To address this issue, we propose a Lebesgue-2 regularized multilayer perceptron (L2R-MLP) algorithm for detecting DNS tunneling attacks. The DNS dataset was carefully curated from a publicly available repository, and relevant features, such as packet size and count, were selected using the recursive feature elimination technique. L2 regularization in the MLP classifier's hidden layers enhances pattern recognition during training, effectively countering the risk of overfitting. When evaluated against a benchmark MLP model, L2R-MLP demonstrated superior performance with 99.46% accuracy, 97.00% precision, a 97.00 F1-score, 99.95% recall, and an AUC of 89.00%. In comparison, the benchmark MLP achieved 92.53% accuracy, 96.00% precision, a 97.00 F1-score, 99.95% recall, and an AUC of 87.00%. This highlights the effectiveness of L2 regularization in improving predictive capabilities and model generalization for unseen instances.

Efficient Productivity-Aware Control Parameter Optimization in Cutter Suction Dredger Construction Using Machine Learning with Parallel Global Search

This paper proposes an efficient productivity-aware optimization framework that utilizes hybrid machine learning with parallel global search to timely and appropriately adjust the critical control parameters (CCPs) of a cutter suction dredger (CSD) during construction. This optimization framework consists of three main parts. First, a hybrid Jaya–multilayer perceptron (MLP) algorithm was developed to rapidly construct a model that captures the interaction between construction parameters and slurry concentration. Next, the preliminary coarse results for the CCPs are determined through multi-parameter sensitivity analysis. Finally, the proposed resilient-zone parallel global search algorithm was employed to further optimize the CCPs, yielding more precise optimization results. To validate the proposed optimization framework and implement the in-situ service, it is applied to a real-world case study involving “Tianda” CSD construction. The results demonstrated that the average optimization duration is 6.7 s, which is shorter than the data acquisition interval of 8 s. Our approach improves the computational efficiency by 9.4 times compared with traditional optimization control methods. Additionally, there is a significant increase in the slurry concentration, with the maximum growth rate reaching 81.64%.

An Effective Analysis of the Machine Learning Algorithms for the Early Diagnosis of Liver Failure

In the recent years Deep learning algorithms have emerged as a potential means for the diagnosis of medical diseases owing to their capability to extract composite features and patterns from huge datasets. The results of the proposed work demonstrate the efficiency of the Single Layer Perceptron, Multi-Layer Perceptron and auto encoder algorithms through extensive validation in precisely detecting the early signs of liver failure. The efficacy of the algorithms are compared based on performance metrics such as accuracy, F1 score, and recall. The comparative analysis shows that the performance of Multi-Layer Perceptron is superior. The highest accuracy is obtained by MLP as it has True Positive of 1.0, True Negative of 0.975, False Positive of 0.024 and False Negative of 0.0 leading to the accuracy 99.41 and f1 score is obtained as 99.61 and has Precision of 99.23 and Recall of 99.41.

Vibration Analysis of a Centrifugal Pump with Healthy and Defective Impellers and Fault Detection Using Multi-Layer Perceptron

Centrifugal pumps (CPs) are widely utilized in many different industries, and their operations are maintained by their reliable performance. CPs’ most common faults can be categorized as mechanical or flow-related faults: the first ones are often associated with damage at the impeller, while the second ones are associated with cavitation. It is possible to use computational algorithms to monitor both failures in CPs. In this study, two different problems in pumps, the defective impeller and cavitation, have been considered. When a CP is working in a faulty condition, it generates vibrations that can be measured using piezoelectric sensors. Collected data can be analyzed to extract time- and frequency-domain data. Interpreting the time-domain data showed that distinguishing the type of defect is not possible. However, indicators like kurtosis, skewness, mean, and variance can be used as input for the multi-layer perceptron (MLP) algorithm to classify pump faults. This study presents a detailed discussion of the vibration-based method outcomes, emphasizing the benefits and drawbacks of the multi-layer perceptron method. The results show that the suggested algorithm can identify the occurrence of different faults and quantify their severity during pump operation in real time.

Advancing source reactor-type discrimination using machine learning techniques and SFCOMPO-2.0 experimental database

In recent years, nuclear forensic analysis has become crucial due to the growing global threat of nuclear terrorism and smuggling. Since 2005, extensive research has been conducted on identifying the origin of spent nuclear fuel, focusing on the source reactor-type discrimination, 235U enrichment of the fresh fuel, and the fuel exposure in the reactor (known as burnup). However, the majority of research relies on computed databases, which may lead to tracing discrepancies compared with actual situations. The present study employs the isotopic measurements from the experimental SFCOMPO-2.0 database to predict nuclear reactor types using Factor Analysis (FA) and various machine learning classification algorithms. The results reveal that FA is an effective method for dimension reduction and visualization. The FA-KNN, Random Forest (RF), and Multilayer Perceptron (MLP) algorithms are applied using a consistent dataset partition to ensure unbiased comparisons. The prediction results based on 10-fold stratified cross-validation are quite promising and the Receiver Operating Characteristic (ROC) curves for multi-class classification confirm the excellent generalization ability of models. Therefore, the application of machine learning techniques is highly effective for reactor-type forensics analysis, especially for RF and MLP.

Using a Grey Wolf Optimization and Multilayer Perceptron Algorithms for an Anomaly-Based Intrusion Detection System

Using a Grey Wolf Optimization and Multilayer Perceptron Algorithms for an Anomaly-Based Intrusion Detection System

Carbon dot unravels accumulation of triterpenoid in Evolvulus alsinoides hairy roots culture by stimulating growth, redox reactions and ANN machine learning model prediction of metabolic stress response

Evolvulus alsinoides, a therapeutically valuable shrub can provide consistent supply of secondary metabolites (SM) with pharmaceutical significance. Nonetheless, because of its short life cycle, fresh plant material for research and medicinal diagnostics is severely scarce throughout the year. The effects of exogenous carbon quantum dot (CD) application on metabolic profiles, machine learning (ML) prediction of metabolic stress response, and SM yields in hairy root cultures of E. alsinoides were investigated and quantified. The range of the particle size distribution of the CDs was between 3 and 7 nm. The CDs EPR signal and spin trapping experiments demonstrated the formation of O2-•spin-adducts at (g = 2.0023). Carbon dot treatment increased the levels of hydrogen peroxide and malondialdehyde concentrations as well as increased antioxidant enzyme activity. CD treatments (6 μg mL-1) significantly enhanced the accumulation of squalene and stigmasterol (7 and 5-fold respectively). The multilayer perceptron (MLP) algorithm demonstrated remarkable prediction accuracy (MSE value = 1.99E-03 and R2 = 0.99939) in both the training and testing sets for modelling. Based on the prediction, the maximum oxidative stress index and enzymatic activities were highest in the medium supplemented with 10 μg mL-1 CDs. The outcome of this study indicated that, for the first time, using CD could serve as a novel elicitor for the production of valuable SM. MLP may also be used as a forward-thinking tool to optimize and predict SM with high pharmaceutical significance. This study would be a touchstone for understanding the use of ML and luminescent nanomaterials in the production and commercialization of important SM.

Utilizing IoT-Enhanced Multilayer Perceptron and Run Length Encoding for Classifying Plant Suitability Based on pH and Soil Humidity Parameters

This research proposes an IoT-based system for classifying plant suitability using pH data and soil humidity parameters. The system utilizes Run-Length Encoding (RLE) to compress sensor data, which is transmitted to a database server via the Esp8266 module. A Multilayer Perceptron (MLP) algorithm is employed to classify the data, achieving an accuracy of 0.82 with only two parameters. The classification results are displayed on a website, providing real-time recommendations for farmers. The system's performance is evaluated using a dataset from Kaggle. The Kaggle dataset contains 2200 instances for 22 different plants and the results show that the proposed system can effectively classify plant suitability based on environmental factors. This research contributes to the development of IoT-based recommendation systems for precision agriculture, and future studies can build upon this work to improve accuracy and quality.

Comparing logistic regression and neural networks for predicting skewed credit score: a LIME-based explainability approach

Over the past years, machine learning emerged as a powerful tool for credit scoring, producing high-quality results compared to traditional statistical methods. However, literature shows that statistical methods are still being used because they still perform and can be interpretable compared to neural network models, considered to be black boxes. This study compares the predictive power of logistic regression and multilayer perceptron algorithms on two credit-risk datasets by applying the Local Interpretable Model-Agnostic Explanations (LIME) explainability technique. Our results show that multilayer perceptron outperforms logistic regression in terms of balanced accuracy, Matthews Correlation Coefficient, and F1 score. Based on our findings from LIME, building models on imbalanced datasets results in biased predictions towards the majority class. Model developers in the field of finance could consider explanation methods such as LIME to extend the use of deep learning models to help them make well-informed decisions.

Predicting non-suicidal self-injury among Chinese adolescents: The application of ten algorithms of machine learning

Background and aimsHigh non-suicidal self-injury (NSSI) prevalence among adolescents is a global health issue. However, current prediction models for adolescent NSSI rely on a limited set of algorithms, resulting in biased predictions. Therefore, the aim of this study is to develop multiple machine learning models to enhance prediction accuracy and mitigate biases among Chinese adolescents. MethodsA total of 4487 junior and senior high school students in China were recruited. Multiple algorithms were included, such as logistic regression, decision tree, support vector machine, Naive Bayes, multi-layer perceptron, K-nearest neighbors, and ensemble learning algorithm like random forest, bagging, AdaBoost, and stacking to build predictive models. Data processing techniques, including standardization and the synthetic minority oversampling technique, were employed to optimize the predictive model. The model was trained on 70 % of the data, reserving 30 % for testing. ResultsThe ten prediction models achieved a good performance, with area under the receiver operating characteristic curve (AUC) scores above 0.700 in the test set. The stacking and random forest models achieved AUC scores of 0.904 and 0.898, respectively. The prediction performance of the Naive Bayes model was relatively poor. The top five important variables were resilience, bully, suicidal ideation, internet addiction, and depression. ConclusionsThe ensemble machine learning algorithm showed promising results predicting NSSI among adolescents. Such algorithms should be recommended for future NSSI research to enhance predictive accuracy. Identification of important features in NSSI prediction can help develop screening protocols and lay a foundation for clinical diagnosis and intervention in adolescent populations.

Enhancing stroke prediction using the waikato environment for knowledge analysis

<p>State-of-the-art data mining tools incorporate advanced machine learning (ML) and artificial intelligence (AI) models, and it is widely used in classification, association rules, clustering, prediction, and sequential models. Data mining is important for the process of diagnosing and predicting diseases in the early stages, and this contributes greatly to the development of the health services sector. This study utilized classification to predict the stroke of a sample of the patient dataset that was taken from Kaggle. The classification model was created using the data mining program waikato environment for knowledge analysis (WEKA). This data mining tool helped identify individuals most at risk of stroke based on analysis of features extracted from the patient’s dataset. These features were used in classification processes according to the naive Bayes (NB), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) algorithms. Analysis of the classification results of the previous algorithms showed that the SVM outperformed other algorithms in terms of accuracy (94.4%), sensitivity (100%), and F-measure (97.1%). However, the NB algorithm had the best performance in terms of precision (95.7%).</p>

Formation of Bachelor`s Skills in the Field of Machine Learning and Intelligent Data Analysis

The article presents the content of the educational disciplines “Workshop on Python Programming” and “Fundamentals of Artificial Intelligence”, included in the module “Data Analysis. Machine learning. Artificial Intelligence”, implemented in Ural universities. Modern teachers note that when preparing the next generation of teachers, the priority should be their acquisition of experience in using artificial intelligence tools in teaching. The objectives of mastering the module are developing students’ skills in the field of neural network mathematical modeling, developing knowledge about basic data analysis algorithms, development of skills in visualization and interpretation of data to solve applied problems using object-oriented programming technologies and artificial neural network technologies. As part of project activities, students gain experience in data mining by completing research projects (for example, a project on comparative assessment of the effectiveness of multilayer perceptron learning algorithms) and applied projects (for example, on the development of a neural network system for predicting the success of schoolchildren’s research work; on the development of a neural network system for predicting student attendance training sessions). At USPU, software systems have been developed in Python that implement the presented neural network prognostic systems. Educational and methodological materials for the disciplines of the module include video lectures and presentations for them, laboratory work (including those based on GoogleColab notebooks), datasets, test sets, theory questions and practical tasks for exams and tests. The effectiveness of the developed teaching methodology is confirmed by the results of a pedagogical experiment. Keywords: neural network technologies, data mining, predictive systems, machine learning, content of the academic discipline

Optimization of Non-Linear Problems Using Salp Swarm Algorithm and Solving the Energy Efficiency Problem of Buildings with Salp Swarm Algorithm-based Multi-Layer Perceptron Algorithm

Optimization of Non-Linear Problems Using Salp Swarm Algorithm and Solving the Energy Efficiency Problem of Buildings with Salp Swarm Algorithm-based Multi-Layer Perceptron Algorithm

Supervised classification and circuit parameter analysis of electrical bioimpedance spectroscopy data of water stress in tomato plants

Drought poses a significant challenge by inducing water stress in crops, urgently calling for effective monitoring and early intervention. In this work, we conducted a comprehensive 38-day investigation of the bioimpedance of water stressed tomato stems under controlled environmental conditions. A total of 8000 measurements were meticulously collected across a frequency spectrum spanning from 100 Hz to 10 MHz. The collected data was categorized into control, early stress, and late stress groups, corresponding to distinct phases of water stress treatment. To analyze the data, we employed established equivalent circuit models, including Cole, Randles, and double Cole. Subsequently, we evaluated the performance of eight machine learning algorithms widely-used in predicting the water stress stages of the plants. Remarkably, the Cole model, in conjunction with a multi-layer perceptron (MLP) algorithm, demonstrated robust performance, achieving an impressive F1 score of 0.89. In fact, in the control group, 378 out of 388 instances were accurately identified. However, misclassifications were observed in the early and late stress groups, with 31 out of 179 and 14 out of 208 instances mislabeled, respectively. Furthermore, we scrutinized the Cole model’s circuit parameters over time, providing insights aligned with the plant physiological behavior documented in the literature. Our findings suggest that MLP models trained on stem bioimpedance data hold promise as a valuable technique for estimating water stress in tomato plants, offering an essential tool for proactive management by farmers.

Research on Machine Learning-Based Method for Predicting Industrial Park Electric Vehicle Charging Load

To achieve global sustainability goals and meet the urgent demands of carbon neutrality, China is continuously transforming its energy structure. In this process, electric vehicles (EVs) are playing an increasingly important role in energy transition and have become one of the primary user groups in the electricity market. Traditional load prediction algorithms have difficulty in constructing mathematical models for predicting the charging load of electric vehicles, which is characterized by high randomness, high volatility, and high spatial heterogeneity. Moreover, the predicted results often exhibit a certain degree of lag. Therefore, this study approaches the analysis from two perspectives: the overall industrial park and individual charging stations. By analyzing specific load data, the overall framework for the training dataset was established. Additionally, based on the evaluation system proposed in this study and utilizing both Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) algorithms, a framework for machine learning-based load prediction methods was constructed to forecast electric vehicle charging loads in industrial parks. Through a case analysis, it was found that the proposed solution for the short-term prediction of the charging load in industrial park electric vehicles can achieve accurate and stable forecasting results. Specifically, in terms of data prediction for normal working days and statutory holidays, the Long Short-Term Memory (LSTM) algorithm demonstrated high accuracy, with R2 coefficients of 0.9283 and 0.9154, respectively, indicating the good interpretability of the model. In terms of weekend holiday data prediction, the Multilayer Perceptron (MLP) algorithm achieved an R2 coefficient of as high as 0.9586, significantly surpassing the LSTM algorithm’s value of 0.9415, demonstrating superior performance.

Accelerometers-based position and time interval comparisons for predicting the behaviors of young bulls housed in a feedlot system

Animal behavior monitoring is an important tool for animal production. This behavior monitoring strategy can indicate the well-being and health of animals, which can lead to better productive performance. This study aimed to assess the most effective accelerometer attachment position (on either the halter or a neck collar) and data transmission time intervals (ranging from 6 to 600 s) for predicting behavioral patterns, including water and food intake frequencies, as well as other activities in young beef cattle bulls within a feedlot system. A range of machine learning algorithms were applied to satisfy the aims of the study, including the random forest, support vector machine, multilayer perceptron, and naive Bayes classifier algorithms. All studied models produced high performance metrics (above 0.90) when using both attachment positions, except for the models built using the naive Bayes classifier. Therefore, coupling accelerometers with collars is a more viable alternative for use on animals, as doing so is easier than applying accelerometers to halters. Utilizing a dataset with more observations (i.e., shorter time intervals) did not result in considerable improvements in the performance metrics of the trained models. Therefore, using datasets with fewer observations is more advantageous, as it can lead to decreased computational and temporal demands for model training, in addition to saving the battery of the device considered in this study.