Multilayer Perceptron Neural Network Research Articles

A multi-task fusion model based on a residual–Multi-layer perceptron network for mammographic breast cancer screening

Background and objectiveDeep learning approaches are being increasingly applied for medical computer-aided diagnosis (CAD). However, these methods generally target only specific image-processing tasks, such as lesion segmentation or benign state prediction. For the breast cancer screening task, single feature extraction models are generally used, which directly extract only those potential features from the input mammogram that are relevant to the target task. This can lead to the neglect of other important morphological features of the lesion as well as other auxiliary information from the internal breast tissue. To obtain more comprehensive and objective diagnostic results, in this study, we developed a multi-task fusion model that combines multiple specific tasks for CAD of mammograms. MethodsWe first trained a set of separate, task-specific models, including a density classification model, a mass segmentation model, and a lesion benignity–malignancy classification model, and then developed a multi-task fusion model that incorporates all of the mammographic features from these different tasks to yield comprehensive and refined prediction results for breast cancer diagnosis. ResultsThe experimental results showed that our proposed multi-task fusion model outperformed other related state-of-the-art models in both breast cancer screening tasks in the publicly available datasets CBIS-DDSM and INbreast, achieving a competitive screening performance with area-under-the-curve scores of 0.92 and 0.95, respectively. ConclusionsOur model not only allows an overall assessment of lesion types in mammography but also provides intermediate results related to radiological features and potential cancer risk factors, indicating its potential to offer comprehensive workflow support to radiologists.

Improved Wildlife Recognition through Fusing Camera Trap Images and Temporal Metadata

Camera traps play an important role in biodiversity monitoring. An increasing number of studies have been conducted to automatically recognize wildlife in camera trap images through deep learning. However, wildlife recognition by camera trap images alone is often limited by the size and quality of the dataset. To address the above issues, we propose the Temporal-SE-ResNet50 network, which aims to improve wildlife recognition accuracy by exploiting the temporal information attached to camera trap images. First, we constructed the SE-ResNet50 network to extract image features. Second, we obtained temporal metadata from camera trap images, and after cyclical encoding, we used a residual multilayer perceptron (MLP) network to obtain temporal features. Finally, the image features and temporal features were fused in wildlife identification by a dynamic MLP module. The experimental results on the Camdeboo dataset show that the accuracy of wildlife recognition after fusing the image and temporal information is about 93.10%, which is an improvement of 0.53%, 0.94%, 1.35%, 2.93%, and 5.98%, respectively, compared with the ResNet50, VGG19, ShuffleNetV2-2.0x, MobileNetV3-L, and ConvNeXt-B models. Furthermore, we demonstrate the effectiveness of the proposed method on different national park camera trap datasets. Our method provides a new idea for fusing animal domain knowledge to further improve the accuracy of wildlife recognition, which can better serve wildlife conservation and ecological research.

Climate and disease: tackling coffee brown-eye spot with advanced forecasting models.

Climate influences the interaction between pathogens and their hosts significantly. This is particularly evident in the coffee industry, where fungal diseases like Cercospora coffeicola, causing brown-eye spot, can reduce yields drastically. This study focuses on forecasting coffee brown-eye spot using various models that incorporate agrometeorological data, allowing for predictions at least 1 week prior to the occurrence of disease. Data were gathered from eight locations across São Paulo and Minas Gerais, encompassing the South and Cerrado regions of Minas Gerais state. In the initial phase, various machine learning (ML) models and topologies were calibrated to forecast brown-eye spot, identifying one with potential for advanced decision-making. The top-performing models were then employed in the next stage to forecast and spatially project the severity of brown-eye spot across 2681 key Brazilian coffee-producing municipalities. Meteorological data were sourced from NASA's Prediction of Worldwide Energy Resources platform, and the Penman-Monteith method was used to estimate reference evapotranspiration, leading to a Thornthwaite and Mather water-balance calculation. Six ML models - K-nearest neighbors (KNN), artificial neural network multilayer perceptron (MLP), support vector machine (SVM), random forests (RF), extreme gradient boosting (XGBoost), and gradient boosting regression (GradBOOSTING) - were employed, considering disease latency to time define input variables. These models utilized climatic elements such as average air temperature, relative humidity, leaf wetness duration, rainfall, evapotranspiration, water deficit, and surplus. The XGBoost model proved most effective in high-yielding conditions, demonstrating high precision and accuracy. Conversely, the SVM model excelled in low-yielding scenarios. The incidence of brown-eye spot varied noticeably between high- and low-yield conditions, with significant regional differences observed. The accuracy of predicting brown-eye spot severity in coffee plantations depended on the biennial production cycle. High-yielding trees showed superior results with the XGBoost model (R2 = 0.77, root mean squared error, RMSE = 10.53), whereas the SVM model performed better under low-yielding conditions (precision 0.76, RMSE = 12.82). The study's application of agrometeorological variables and ML models successfully predicted the incidence of brown-eye spot in coffee plantations with a 7 day lead time, illustrating that they were valuable tools for managing this significant agricultural challenge. © 2024 Society of Chemical Industry.

Dual fusion network for semantic segmentation of point clouds

The current networks for point cloud segmentation fail to fully consider the connections between points in each neighborhood, which makes the final segmentation capability underperform. To obtain richer local relationships between points, this paper proposes a network called GDFNet (Graph Convolution-based Dual Fusion Network), which dynamically mines the correlations between points in each layer of the network. GDFNet is divided into two parts: a density-sensitive assignment module and a spatial dynamic convolution module. The density-sensitive assignment module treats the traditional convolution kernel as a nonlinear function consisting of a weight and a density function applicable to the local coordinates of 3D points. For a given point, the weight function is learned by a multilayer perceptron network, and the density function is learned by kernel density estimation. In this way, the density features of each point are fitted, thus improving the inherent defect of the original point cloud with non-uniform density. The spatial dynamic convolution module groups the original feature channels and then uses gated processing units to enrich the feature representation of the input points. At the same time, dynamic convolution is embedded in the Euclidean space to obtain the structural information of each point and further supplement the local detail features. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS and ScanNetv2 datasets.

Application of a reconfigurable all-optical activation unit based on optical injection into a bistable Fabry-Perot laser in multilayer perceptron neural networks.

In this Letter, we theoretically investigate the application of a bistable Fabry-Perot semiconductor laser under optical injection as an all-optical activation unit for multilayer perceptron optical neural networks. The proposed device is programmed to provide reconfigurable sigmoid-like activation functions with adjustable thresholds and saturation points and benchmarked on machine learning image recognition problems. Due to the reconfigurability of the activation unit, the accuracy can be increased by up to 2% simply by adjusting the control parameter of the activation unit to suit the specific problem. For a simple two-layer perceptron neural network, we achieve inference accuracies of up to 95% and 85%, for the MNIST and Fashion-MNIST datasets, respectively.

Can Machine Learning Predict Running Kinematics Based on Upper Trunk GPS-Based IMU Acceleration? A Novel Method of Conducting Biomechanical Analysis in the Field Using Artificial Neural Networks

This study aimed to investigate whether running kinematics can be accurately estimated through an artificial neural network (ANN) model containing GPS-based accelerometer variables and anthropometric data. Thirteen male participants with extensive running experience completed treadmill running trials at several speeds. Participants wore a GPS device containing a triaxial accelerometer, and running kinematics were captured by an 18-camera motion capture system for each trial. Multiple multilayer perceptron neural network models were constructed to estimate participants’ 3D running kinematics. The models consisted of the following input variables: 3D peak accelerometer acceleration during foot stance (g), stance time (s), running speed (km/h), participant height (cm), leg length (cm), and mass (kg). Pearson’s correlation coefficient (r), root mean squared error (RMSE), and relative root mean squared error (rRMSE) showed that ANN models provide accurate estimations of joint/segment angles (mean rRMSE = 13.0 ± 4.3%) and peak segment velocities (mean rRMSE = 22.1 ± 14.7%) at key gait phases across foot stance. The highest accuracies were achieved for flexion/extension angles of the thorax, pelvis, and hip, and peak thigh flexion/extension and vertical velocities (rRMSE < 10%). The current findings offer sports science and medical practitioners working with this data a method of conducting field-based analyses of running kinematics using a single IMU.

Intelligent control strategy for industrial furnaces based on yield classification prediction using a gray relative correlation-convolutional neural network-multilayer perceptron (GCM) machine learning model

Industrial furnaces still play an important role in national economic growth. Owing to the complexity of the production process, the product yield fluctuates, and cannot be executed in real time, which has not kept pace with the development of the intelligent technologies in Industry 4.0. In this study, based on the deep learning theory and operational data collected from more than one year of actual production of a lime kiln, we proposed a hybrid deep network model combining a gray relative correlation, a convolutional neural network and a multilayer perceptron model (GCM) to categorize production processes and predict yield classifications. The results show that the loss and calculation time of the model based on the screened set of variables are significantly reduced, and the accuracy is almost unaffected; the GCM model has the best performance in predicting the yield classification of lime kilns. The intelligent control strategy for non-fault state is then set according to the predicted yield classification. Operating parameters are adjusted in a timely manner according to different priority control sequences to achieve higher yield, ensure high production efficiency, reduce unnecessary waste, and save energy.

Thermomechanical behavior of a novel hybrid epoxy/ZnO nanocomposite adhesive in structural bonding: Experimental analysis and ANN modeling

ObjectivesEpoxy adhesives are advanced materials, but suffer from high brittleness and low toughness due to their high crosslinking degree, which limits their service life in structural applications. The lack of appropriate thermal stability at high temperatures is another constraint of epoxy adhesives. The main aim of this research was to increase the thermal stability and toughness of epoxy adhesives using phenolic resin, zinc oxide (ZnO) nanoparticles, and poly (butyl acrylate-block-styrene) copolymer as a toughening agent. Furthermore, the mechanical properties of epoxy adhesives were predicted by designing two feed-forward multilayer perceptron (MLP) networks. MethodsEpoxy adhesives with different contents of phenolic resin (10, 20, and 30 phr), copolymer (1.25, 2.5, and 3.75 phr), and ZnO (0.5, 1, 2, and 5 phr) nanoparticles were synthesized under mechanical mixing by using xylene as solvent. Then, the epoxy adhesive samples for tensile and lap shear tests were cured at room temperature for 7 and 2 days, respectively. The mechanical properties of adhesive samples were measured by tensile and lap shear tests. The thermal stability of the epoxy adhesive samples was investigated by thermogravimetric analysis (TGA). The kinetics of the curing reaction of the optimum epoxy adhesive samples was also studied by differential scanning calorimetry (DSC). ResultsThe toughness of epoxy adhesive containing 10 phr phenolic, 2.5 phr block copolymer, and 2 phr ZnO nanoparticles increased by 20%, and shear strength by 99% compared to pure epoxy adhesive, notifying a significant synergistic effect. The TGA results showed that all three mentioned additives have increased the thermal stability of pure epoxy. The highest thermal stability was observed for epoxy adhesive containing 2.5 phr block copolymer and 2 phr ZnO nanoparticles. In addition, DSC analysis proved the positive effect of ZnO nanoparticles incorporation and block copolymer on the curing kinetics of epoxy adhesive. Moreover, the predicted tensile strength, tensile modulus, toughness, and shear strength of epoxy adhesives by MLP networks showed a very good consistency between the experimental data and the model predictions (e.g., MRE < 1.1 for lap shear). SignificanceIn the current study, the artificial neural networks (ANN) results showed that there was very good consistency between the ANN predictions and the experimental data.

Machine learning of the chemical elements for enhanced interpretation of depositional environments: Upper Jurassic strata case study in central Saudi Arabia

To explore how machine learning (ML) techniques can enhance the interpretation of depositional environments using chemical elemental data, this study analyzes data from 156 shallow marine strata samples. Several advanced machine learning (ML) techniques were integrated to predict lithofacies and stratigraphic units of shallow marine carbonate strata, focusing on the Arab-D reservoir equivalent outcrops in Central Saudi Arabia. Utilizing a detailed geochemical dataset comprising major, trace, and rare earth elements, we aimed to determine the feasibility of using chemical elemental data in sedimentary geology for predictive modeling. The studied strata are categorized into two lithological units based on depositional settings: one unit comprises rocks that dominantly deposited below the storm wave base with a single lithofacies association, whereas the other includes rocks dominantly deposited above the storm wave base, and consists of two lithofacies associations. The study demonstrates the efficacy of ML algorithms in distinguishing these two lithological units, with a minimum prediction accuracy of 76%. Four ML techniques, including K-nearest neighbors (KNN); random forest classifier (RFC); gradient boosting classifier (GBC); and multi-layer perceptron neural network (MLP-NN) were used, two of them (RFC and GBC) achieved 89% and 92% prediction accuracy. However, a slightly poorer performance was observed in predicting fine-scale lithofacies associations of these lithological units, especially for the lithofacies association representing a transitional interval between the two lithofacies units. Expanding the scope of the study, we tested the ML models against geochemically similar strata from the Oligocene shallow marine reef carbonates. These strata are globally comparable and provide an external validation for the predictive models developed from the Saudi Arabian dataset. GBC and RFC maintained a higher accuracy level than KNN and MLP, demonstrating their robustness and transferability across diverse geological settings. Based on these results, the study underscores the significance of specific oxides and elements as distinctive geochemical markers, elucidating the environmental conditions of the depositional environments and their deposits. This research advances the application of ML in interpreting the depositional environments of shallow marine strata using elemental data, as the majority of the existing researches focus on employing unsupervised machine learning for cluster analysis.

PET/CT-Based Radiogenomics Supports KEAP1/NFE2L2 Pathway Targeting for Non-Small Cell Lung Cancer Treated with Curative Radiotherapy.

In lung cancer patients, radiotherapy is associated with a increased risk of local relapse (LR) when compared with surgery but with a preferable toxicity profile. The KEAP1/NFE2L2 mutational status (MutKEAP1/NFE2L2) is significantly correlated with LR in patients treated with radiotherapy but is rarely available. Prediction of MutKEAP1/NFE2L2 with noninvasive modalities could help to further personalize each therapeutic strategy. Methods: Based on a public cohort of 770 patients, model RNA (M-RNA) was first developed using continuous gene expression levels to predict MutKEAP1/NFE2L2, resulting in a binary output. The model PET/CT (M-PET/CT) was then built to predict M-RNA binary output using PET/CT-extracted radiomics features. M-PET/CT was validated on an external cohort of 151 patients treated with curative volumetric modulated arc radiotherapy. Each model was built, internally validated, and evaluated on a separate cohort using a multilayer perceptron network approach. Results: The M-RNA resulted in a C statistic of 0.82 in the testing cohort. With a training cohort of 101 patients, the retained M-PET/CT resulted in an area under the curve of 0.90 (P < 0.001). With a probability threshold of 20% applied to the testing cohort, M-PET/CT achieved a C statistic of 0.7. The same radiomics model was validated on the volumetric modulated arc radiotherapy cohort as patients were significantly stratified on the basis of their risk of LR with a hazard ratio of 2.61 (P = 0.02). Conclusion: Our approach enables the prediction of MutKEAP1/NFE2L2 using PET/CT-extracted radiomics features and efficiently classifies patients at risk of LR in an external cohort treated with radiotherapy.

Tunnel boring machine performance assessment and prediction applying hybrid artificial intelligence

A machine for tunnel boring machine (TBM) is recognized as productive equipment for tunnel construction. A dependable and precise tunnel boring machine’s performance (such as penetration rate (ROP)) prediction could reduce the cost and help choose the suitable construction method. Hence, this research develops new integrated artificial intelligence methods, i.e., biogeography-based multilayer perceptron neural network (BMLP) and biogeography-based support vector regression (BSVR), to forecast TBMPR. Using the biogeography-based optimization (BBO) algorithm aims to improve the developed model’s performance by determining the optimized neuron number of hidden layers for MLP models and the ideal values of the essential variables of SVR method. The results show that advanced methods can productively make a nonlinear relation among the ROP and its forecasters to obtain a satisfying forecast. Amongst the BMLP models with several hidden substrates, BM5L with five hidden substrates could attain the total ranking score (TRS) greatest rate, with root mean squared error (RMSE) and coefficient of determination (R2) equal to 0.017 and 0.9969. Simultaneously, the BSVR was the supreme model because of the fewer RMSE (0.00497 m/hr) and a larger R2 (0.999) compared with BMLP models. Overall, the acquired TRSs show that the BSVR outperforms the BMLP in terms of performance. As a consequence, the BSVR model may have been chosen as the suggested model if it had been able to accurately forecast the observed value even better than BM5L.

Quantitative Detection of Pipeline Cracks Based on Ultrasonic Guided Waves and Convolutional Neural Network.

In this study, a quantitative detection method of pipeline cracks based on a one-dimensional convolutional neural network (1D-CNN) was developed using the time-domain signal of ultrasonic guided waves and the crack size of the pipeline as the input and output, respectively. Pipeline ultrasonic guided wave detection signals under different crack defect conditions were obtained via numerical simulations and experiments, and these signals were input as features into a multi-layer perceptron and one-dimensional convolutional neural network (1D-CNN) for training. The results revealed that the 1D-CNN performed better in the quantitative analysis of pipeline crack defects, with an error of less than 2% in the simulated and experimental data, and it could effectively evaluate the size of crack defects from the echo signals under different frequency excitations. Thus, by combining the ultrasonic guided wave detection technology and CNN, a quantitative analysis of pipeline crack defects can be effectively realized.

Toxicity source apportionment of fugitive dust PM2.5-bound polycyclic aromatic hydrocarbons using multilayer perceptron neural network analysis in Guanzhong Plain urban agglomeration, China

Polycyclic aromatic hydrocarbons (PAHs) in urban fugitive dust, known for their toxicity and ability to generate reactive oxygen species (ROS), are a major public health concern. This study assessed the spatial distribution and health risks of 15 PAHs in construction dust (CD) and road dust (RD) samples collected from June to November 2021 over the cities of Tongchuan (TC), Baoji (BJ), Xianyang (XY), and Xi'an (XA) in the Guanzhong Plain, China. The average concentration of ΣPAHs in RD was 39.5 ± 20.0 μg g−1, approximately twice as much as in CD. Four-ring PAHs from fossil fuels combustion accounted for the highest proportion of ΣPAHs in fugitive dust over all four cities. Health-related indicators including benzo(a)pyrene toxic equivalency factors (BAPTEQ), oxidative potential (OP), and incremental lifetime cancer risk (ILCR) all presented higher risk in RD than those in CD. The multilayer perceptron neural network algorithm quantified that vehicular and industrial emissions contributed 86 % and 61 % to RD and CD BAPTEQ, respectively. For OP, the sources of biomass and coal combustion were the key generator which accounted for 31–54 %. These findings provide scientific evidence for the direct efforts toward decreasing the health risks of fugitive dust in Guanzhong Plain urban agglomeration, China.

A multilayer perceptron neural network approach for optimizing solar irradiance forecasting in Central Africa with meteorological insights

Promoting renewable energy sources, particularly in the solar industry, has the potential to address the energy shortfall in Central Africa. Nevertheless, a difficulty occurs due to the erratic characteristics of solar irradiance data, which is influenced by climatic fluctuations and challenging to regulate. The current investigation focuses on predicting solar irradiance on an inclined surface, taking into consideration the impact of climatic variables such as temperature, wind speed, humidity, and air pressure. The used methodology for this objective is Artificial Neural Network (ANN), and the inquiry is carried out in the metropolitan region of Douala. The data collection device used in this research is the meteorological station located at the IUT of Douala. This station was built as a component of the Douala sustainable city effort, in partnership with the CUD and the IRD. Data was collected at 30-min intervals for a duration of around 2 years, namely from January 17, 2019, to October 30, 2020. The aforementioned data has been saved in a database that underwent pre-processing in Excel and later employed MATLAB for the creation of the artificial neural network model. 80% of the available data was utilized for training the network, 15% was allotted for validation, and the remaining 5% was used for testing. Different combinations of input data were evaluated to ascertain their individual degrees of accuracy. The logistic Sigmoid function, with 50 hidden layer neurons, yielded a correlation coefficient of 98.883% between the observed and estimated sun irradiation. This function is suggested for evaluating the intensities of solar radiation at the place being researched and at other sites that have similar climatic conditions.

Forecasting Sauter mean droplet size and examining the range of droplet sizes in a Tenova liquid–liquid extraction column

A new type of Tenova pulsed extraction column was introduced in 2017. It is the newest generation of pulsed columns. Due to the internal equipment of this column and the lack of moving parts and the simplicity and speed of repairs and maintenance, it has been the focus of researchers in recent years. No correlations for predicting the mean drop size and drop size distribution of the Tenova column have been reported. The Sauter mean drop diameter and drop size distribution are investigated for a Tenova pulsed column with a diameter and an active height of 7.4 and 73 cm, respectively. Three standard chemical systems of isobutyl acetate-water, isobutanol-water, and toluene-water have been used. The effects of pulse intensity, dispersed and continuous phase flow rates have been taken into account. In each experiment, 200–300 drops have been analyzed in a total of 10,000 drops. The investigation covered a spectrum of physical properties, notably surface tension (within a range of 1.75–36 mN/m). Operating conditions including pulse intensity (in the range of 0.2–2 cm/s) and the flow rate of continuous and dispersed phases (in the range of 8–30 L/h) have been investigated. Methods based on artificial intelligence (AI) such as multilayer perceptron neural networks and gene expression programming were combined with a dimensional analysis approach to provide a new approach to estimating the mean drop diameter (d32). Experimental results have been compared with the equations found by other researchers in similar columns. The variation of drop size distribution has also been experimentally obtained.Methods based on artificial intelligence (AI) such as multilayer perceptron neural networks and gene expression programming were combined with a dimensional analysis approach to provide a new approach to estimating the mean drop diameter (d32). Experimental results have been compared with the equations found by other researchers in similar columns. The variation of drop size distribution has also been experimentally obtained.

Neural-network-based end-to-end learning for adaptive optimization of two-dimensional signal generation in UVLC systems.

Visible light communication (VLC) benefits from the underwater blue-green window and holds immense potential for underwater wireless communication. In order to address the limitations of various equipment and harsh channel conditions in the underwater visible light communication (UVLC) system, the researchers proposed to use the method of autoencoder (AE) to tap the potential of the system. However, traditional AE schemes involve replacing the transmitting and receiving components of a communication system with a large multilayer perceptron (MLP) network, and they have significant drawbacks due to their reliance on a single network structure. In this paper, a novel 2D adaptive optimization autoencoder (2D-AOAE) framework is proposed to realize adaptive modulation and demodulation of two-dimensional signals. By implementing this scheme, we experimentally achieved a transmission rate of 2.85 Gbps over a 1.2-meter underwater VLC link. Compared to the traditional 32QAM UVLC system, the 2D-AOAE scheme demonstrated a 15.4% data rate increase. Moreover, the 2D-AOAE scheme exhibited a remarkable 73% improvement when compared to the UVLC system utilizing the traditional AE scheme. This significant enhancement highlights the superior performance and capabilities of the 2D-AOAE scheme in terms of transmission rate.

Fast hybrid methods for modeling landslide susceptibility in Ardal County

Recently, machine learning models have received huge attention for environmental risk modeling. One of these applications is landslide susceptibility mapping which is a necessary primary step for dealing with the landslide risk in prone areas. In this study, a conventional machine learning model called multi-layer perceptron (MLP) neural network is built upon advanced optimization algorithms to achieve a firm prediction of landslide susceptibility in Ardal County, West of Iran. The used geospatial dataset consists of fourteen conditioning factors and 170 landslide events. The used optimizers are electromagnetic field optimization (EFO), symbiotic organisms search (SOS), shuffled complex evolution (SCE), and electrostatic discharge algorithm (ESDA) that contribute to tuning MLP’s internal parameters. The competency of the models is evaluated using several statistical methods to provide a comparison among them. It was discovered that the EFO-MLP and SCE-MLP enjoy much quicker training than SOS-MLP and ESDA-MLP. Further, relying on both accuracy and time criteria, the EFO-MLP was found to be the most efficient model (time = 1161 s, AUC = 0.879, MSE = 0.153, and R = 0.657). Hence, the landslide susceptibility map of this model is recommended to be used by authorities to provide real-world protective measures within Ardal County. For helping this, a random forest-based model showed that Elevation, Lithology, and Land Use are the most important factors within the studied area. Lastly, the solution discovered in this study is converted into an equation for convenient landslide susceptibility prediction.

Analyzing predictors of pearl millet supply chain using an artificial neural network

PurposeThe internal (farmer-controlled) and external (non-farmer-controlled) factors affect crop yield. However, not a single study has identified and analyzed yield predictors in India using effective predictive models. Thus, this study aims to investigate how internal and external predictors impact pearl millet yield and Stover yield.Design/methodology/approachDescriptive analytics and artificial neural network are used to investigate the impact of predictors on pearl millet yield and Stover yield. From descriptive analytics, 473 valid responses were collected from semi-arid zone, and the predictors were categorized into internal and external factors. Multi-layer perceptron-neural network (MLP-NN) model was used in Statistical Package for the Social Sciences version 25 to model them.FindingsThe MLP-NN model reveals that rainfall has the highest normalized importance, followed by irrigation frequency, crop rotation frequency, fertilizers type and temperature. The model has an acceptable goodness of fit because the training and testing methods have average root mean square errors of 0.25 and 0.28, respectively. Also, the model has R2 values of 0.863 and 0.704, respectively, for both pearl millet and Stover yield.Research limitations/implicationsTo the best of the authors’ knowledge, the current study is first of its kind related to impact of predictors of both internal and external factors on pearl millet yield and Stover yield.Originality/valueThe literature reveals that most studies have estimated crop yield using limited parameters and forecasting approaches. However, this research will examine the impact of various predictors such as internal and external of both yields. The outcomes of the study will help policymakers in developing strategies for stakeholders. The current work will improve pearl millet yield literature.

Multilayer Perceptron Neural Network Approach to Classifying Learning Modalities Under the New Normal

Because of community quarantines and lockdowns during COVID–19 times, the Philippine’s Department of Education (DepEd) implemented blended learning (BL) both online and offline distance learning modalities (LM) among basic educational institutions in the hope of continuing learners’ learning experiences amidst the pandemic. Learners’ LM are classified through the use of an Algorithm for Learning Delivery Modality as recommended by DepEd. Based on initial investigation, mismatches in learners’ LM were, however, observed, resulting in learners’ massive shifting from one LM to another in the middle of the school year. In this study, we introduced an approach to classifying learner’s LM using machine learning (ML) techniques. We compared the effectiveness of five ML classifiers, namely the random forest (RF), multilayer perceptron neural network (MLP NN), K-nearest neighbor (KNN), support vector machine (SVM), and Naïve Bayes (NB). Learner’s enrolment and survey form (LESF) data from the repository of a local private high school in the Philippines is used in model formulation. We also compared three existing feature selection (FS) algorithms (recursive feature elimination (RFE), Boruta algorithm (BA), and ReliefF)–integrated into the five ML classifiers as data feature reduction techniques. Results show that the combination of MLP NN and BA yielded a considerably high performance among the rest of the formulated models. Sensitivity analysis revealed that asynchronous LM is most sensitive to “existing health condition” feature, modified asynchronously, is highly characterized by low educational attainment and unstable employment status of parents or guardians, while synchronous learners have high socio–economic status as compared to other LM.

Zero crossing detection algorithm based on an MLP neural network for differential confocal microscopy

Differential confocal microscopy is widely used because of its ultra-high axial resolution. The surface gradient results in light loss, which decreases the slope of the differential response signal at zero crossing. At this point, when the signal-to-noise ratio is fixed, the traditional linear fitting method to determine the position of zero crossing is subject to significant error influence. To solve these issues, this paper proposes a zero crossing detection algorithm based on a multilayer perceptron (MLP) neural network. Experimental results reveal that the proposed algorithm is more robust and capable of better zero crossing extraction. When numerical aperture (NA)=0.4, the average error is 16.9 nm, which is 55.4 % higher than that of the traditional linear fitting algorithm. The proposed algorithm has a high potential for use with the differential confocal sensor to measure unknown steep surfaces.