MLP-based Model Research Articles

How to Learn More? Exploring Kolmogorov–Arnold Networks for Hyperspectral Image Classification

Convolutional neural networks (CNNs) and vision transformers (ViTs) have shown excellent capability in complex hyperspectral image (HSI) classification. However, these models require a significant number of training data and are computational resources. On the other hand, modern Multi-Layer Perceptrons (MLPs) have demonstrated a great classification capability. These modern MLP-based models require significantly less training data compared with CNNs and ViTs, achieving state-of-the-art classification accuracy. Recently, Kolmogorov–Arnold networks (KANs) were proposed as viable alternatives for MLPs. Because of their internal similarity to splines and their external similarity to MLPs, KANs are able to optimize learned features with remarkable accuracy, in addition to being able to learn new features. Thus, in this study, we assessed the effectiveness of KANs for complex HSI data classification. Moreover, to enhance the HSI classification accuracy obtained by the KANs, we developed and proposed a hybrid architecture utilizing 1D, 2D, and 3D KANs. To demonstrate the effectiveness of the proposed KAN architecture, we conducted extensive experiments on three newly created HSI benchmark datasets: QUH-Pingan, QUH-Tangdaowan, and QUH-Qingyun. The results underscored the competitive or better capability of the developed hybrid KAN-based model across these benchmark datasets over several other CNN- and ViT-based algorithms, including 1D-CNN, 2DCNN, 3D CNN, VGG-16, ResNet-50, EfficientNet, RNN, and ViT.

TriMLP : A Foundational MLP-Like Architecture for Sequential Recommendation

In this work, we present TriMLP as a foundational MLP-like architecture for the sequential recommendation, simultaneously achieving computational efficiency and promising performance. First, we empirically study the incompatibility between existing purely MLP-based models and sequential recommendation, that the inherent fully-connective structure endows historical user–item interactions (referred as tokens) with unrestricted communications and overlooks the essential chronological order in sequences. Then, we propose the MLP-based Triangular Mixer to establish ordered contact among tokens and excavate the primary sequential modeling capability under the standard auto-regressive training fashion. It contains (1) a global mixing layer that drops the lower-triangle neurons in MLP to block the anti-chronological connections from future tokens and (2) a local mixing layer that further disables specific upper-triangle neurons to split the sequence as multiple independent sessions. The mixer serially alternates these two layers to support fine-grained preferences modeling, where the global one focuses on the long-range dependency in the whole sequence, and the local one calls for the short-term patterns in sessions. Experimental results on 12 datasets of different scales from 4 benchmarks elucidate that TriMLP consistently attains favorable accuracy/efficiency tradeoff over all validated datasets, where the average performance boost against several state-of-the-art baselines achieves up to 14.88%, and the maximum reduction of inference time reaches 23.73%. The intriguing properties render TriMLP a strong contender to the well-established RNN-, CNN-, and Transformer-based sequential recommenders. Code is available at https://github.com/jiangyiheng1/TriMLP .

Sunspot number-based neural network model for global solar radiation estimation in Ghardaïa

In this investigation, the estimation of global solar radiation was meticulously carried out within Ghardaïa city, a region situated in Southern Algeria, utilizing a sophisticated multilayer perceptron (MLP) neural network architecture. This research primarily concentrated on developing a predictive model based on a singular input parameter, specifically, the sunspot numbers, to forecast global solar radiation levels. The model's formulation was rooted in empirical data collected over an extensive period from 1984 to 2000, which was used for training the neural network. To assess the model's predictive accuracy and robustness, data from the years 2001 to 2004 were employed for validation purposes. The outcomes of this study were highly satisfactory, indicating that the MLP-based model possesses a significant predictive capability for Diffuse Global Solar Radiation (DGSR). This is substantiated by robust statistical metrics, including a normalized Root Mean Square Error (nRMSE) of 0.076, reflecting the model's accuracy in prediction, and a correlation coefficient (R) of 93.16%, denoting a strong correlation between the predicted and observed values. These results underscore the model's efficacy and potential application in accurately estimating global solar radiation in the specified region.

Effect of applying serpentine channels and hybrid nanofluid for thermal management of photovoltaic cell: Numerical simulation, ANN and sensitivity analysis

Regarding the importance of thermal management of solar PV cells to achieve higher efficiency and electricity output, a novel configuration by use of serpentine channels for cooling is proposed and numerically investigated in the present article. Moreover, a hybrid nanofluid, (MWCNT)-Fe3O4/water, is employed as the coolant to investigate its potential in further improvement of thermal management. Computational Fluid Dynamics (CFD) is applied to numerically simulate the systems and investigate the impacts of different factors. Performance of the proposed configuration is compared with cooling channels with simple structure without nanofluids. Simulations results revealed that the employment of serpentine channels leads to modification in the thermal management of the cell compared with the simple channel. The maximum improvement rate in this condition compared with simple channels is around 9.63 % that is obtained in case of maximum mass flow rate of coolant and solar radiation intensity. Despite increment in pressure loss by using the serpentine channel compared with the simple channel, 2.6 ×10−3 W and 9.3 ×10−4 W, respectively, in mass flow rate of 0.003 kg/s for water, increase in the generated electricity is much more in this case. Furthermore, numerical results show that applying the hybrid nanofluid with 0.1 % concentration can cause slight reduction in the temperature compared with using water. Moreover, Group Method of Data Handling (GMDH) and Multilayer Perceptron (MLP) neural network as intelligent methods used for estimation of the cell temperature and the maximum error for the developed model is approximately 1.1 % and 0.098 % for the GMDH- and MLP-based models, respectively. Finally, sensitivity analysis is implemented and it is shown that solar radiation intensity is the most influential factor on the cell temperature in condition of using serpentine channels while mass flow rate of the coolant has the minimum relevancy factor and consequently effect on the temperature of the solar cell.

Application of improved glomerular filtration rate estimation by a neural network model in patients with neurogenic lower urinary tract dysfunction.

Previous studies have indicated that creatinine (Cr)-based glomerular filtration rate (GFR) estimating equations - including the new Chronic Kidney Disease Epidemiology creatinine (CKD-EPIcr) equation without race and the estimated glomerular filtration rate (eGFR) equation developed for the Chinese population - displayed suboptimal performance in patients with neurogenic lower urinary tract dysfunction (NLUTD), which limited their clinical application for detecting changes in GFR levels in all cohorts. To develop a neural network model based on multilayer perceptron (MLP) for evaluating GFR in Chinese NLUTD patients, and compare the diagnostic performance with Cr-based multiple linear regression equations for Chinese and the CKD-EPIcr equation without race. Single-center, cross-sectional study of GFR estimation from serum Cr, demographic data, and clinical characteristics in Chinese patients with NLUTD. A total of 204 NLUTD patients, from 27 different geographic regions of China, were selected. A random sample of 141 of these subjects was included in the training sample set, and the remaining 63 patients were included in the testing sample set. The reference GFR (rGFR) was assessed by the technetium-99m-labeled diethylenetriaminepentaacetic acid (99mTc-DTPA) double plasma sample method. A neural network model based on MLP was developed to evaluate GFR in the training sample set, which was then validated in the testing sample set and compared with Cr-based GFR equations. The MLP-based model showed significant performance improvement in evaluating the difference, absolute difference, precision, and accuracy of GFR estimation compared with the Cr-based GFR equations. Additionally, compared with the rGFR, we found that the MLP-based model provided an acceptable level of accuracy (greater than 85%, which was within a 30% deviation from the rGFR). The MLP-based model offered significant advantages in estimating GFR in Chinese NLUTD patients, and its application could be suggested in clinical practice.

S[formula omitted]WaveNet: A novel spectral–spatial wave network for hyperspectral image classification

Deep learning has made significant progress in hyperspectral image (HSI) classification, and its powerful ability to automatically learn abstract features is well recognized. Recently, the simple architecture of multi-layer perceptron (MLP) has been extensively employed to extract long-range dependencies of HSI and achieved impressive results. However, existing MLP-based models exhibit insufficient representation of spectral–spatial information in HSI and generally aggregate features with fixed weights, which limits their ability to capture semantic differences. To tackle these challenges, this paper proposes a novel spectral–spatial wave network (S2WaveNet) for HSI classification tasks to enhance the representation capability of spectral–spatial features in ground objects. Specifically, the spectral–spatial wave mixer (S2WaveMixer) block is designed as a key component to represent each HSI input as a wave function with amplitude and phase parts. Thus, it enables a deeper dynamic perception and facilitates the extraction of spectral–spatial feature variations of ground objects. The amplitude represents the original features and the phase term is a complex value changing based on the semantic contents of the input images. Furthermore, the inception unit is introduced into the S2WaveMixer block to consider spectral–spatial information at multiple granularity levels. Experiments conducted on five public datasets demonstrate the superiority of S2WaveNet in classification performance and generalization compared to competitors.

Deciphering the Efficacy of No-Attention Architectures in Computed Tomography Image Classification: A Paradigm Shift

The burgeoning domain of medical imaging has witnessed a paradigm shift with the integration of AI, particularly deep learning, enhancing diagnostic precision and expediting the analysis of Computed Tomography (CT) images. This study introduces an innovative Multilayer Perceptron-driven model, DiagnosticMLP, which sidesteps the computational intensity of attention-based mechanisms, favoring a no-attention architecture that leverages Fourier Transforms for global information capture and spatial gating units for local feature emphasis. This study’s methodology encompasses a sophisticated augmentation and patching strategy at the input level, followed by a series of MLP blocks designed to extract hierarchical features and spatial relationships, culminating in a global average pooling layer before classification. Evaluated against state-of-the-art MLP-based models including MLP-Mixer, FNet, gMLP, and ResMLP across diverse and extensive CT datasets, including abdominal, and chest scans, DiagnosticMLP demonstrated a remarkable ability to converge efficiently, with competitive accuracy, F1 scores, and AUC metrics. Notably, in datasets featuring kidney and abdomen disorders, the model showcased superior generalization capabilities, underpinned by its unique design that addresses the complexity inherent in CT imaging. The findings in terms of accuracy and precision-recall balance posit DiagnosticMLP as an exceptional outperforming alternative to attention-reliant models, paving the way for streamlined, efficient, and scalable AI tools in medical diagnostics, reinforcing the potential for AI-augmented precision medicine without the dependency on attention-based architectures.

CSSNet: Cascaded spatial shift network for multi-organ segmentation

Multi-organ segmentation is vital for clinical diagnosis and treatment. Although CNN and its extensions are popular in organ segmentation, they suffer from the local receptive field. In contrast, MultiLayer-Perceptron-based models (e.g., MLP-Mixer) have a global receptive field. However, these MLP-based models employ fully connected layers with many parameters and tend to overfit on sample-deficient medical image datasets. Therefore, we propose a Cascaded Spatial Shift Network, CSSNet, for multi-organ segmentation. Specifically, we design a novel cascaded spatial shift block to reduce the number of model parameters and aggregate feature segments in a cascaded way for efficient and effective feature extraction. Then, we propose a feature refinement network to aggregate multi-scale features with location information, and enhance the multi-scale features along the channel and spatial axis to obtain a high-quality feature map. Finally, we employ a self-attention-based fusion strategy to focus on the discriminative feature information for better multi-organ segmentation performance. Experimental results on the Synapse (multiply organs) and LiTS (liver & tumor) datasets demonstrate that our CSSNet achieves promising segmentation performance compared with CNN, MLP, and Transformer models. The source code will be available at https://github.com/zkyseu/CSSNet.

MSS-UNet: A Multi-Spatial-Shift MLP-based UNet for skin lesion segmentation

Multilayer perceptron (MLP) networks have become a popular alternative to convolutional neural networks and transformers because of fewer parameters. However, existing MLP-based models improve performance by increasing model depth, which adds computational complexity when processing local features of images. To meet this challenge, we propose MSS-UNet, a lightweight convolutional neural network (CNN) and MLP model for the automated segmentation of skin lesions from dermoscopic images. Specifically, MSS-UNet first uses the convolutional module to extract local information, which is essential for precisely segmenting the skin lesion. We propose an efficient double-spatial-shift MLP module, named DSS-MLP, which enhances the vanilla MLP by enabling communication between different spatial locations through double spatial shifts. We also propose a module named MSSEA with multiple spatial shifts of different strides and lighter external attention to enlarge the local receptive field and capture the boundary continuity of skin lesions. We extensively evaluated the MSS-UNet on ISIC 2017, 2018, and PH2 skin lesion datasets. On three datasets, the method achieves IoU metrics of 85.01%±0.65, 83.65%±1.05, and 92.71%±1.03, with a parameter size and computational complexity of 0.33M and 15.98G, respectively, outperforming most state-of-the-art methods.The code is publicly available at https://github.com/AirZWH/MSS-UNet.

Machine learning-based prediction of symptomatic intracerebral hemorrhage after intravenous thrombolysis for stroke: a large multicenter study.

This study aimed to compare the performance of different machine learning models in predicting symptomatic intracranial hemorrhage (sICH) after thrombolysis treatment for ischemic stroke. This multicenter study utilized the Shenyang Stroke Emergency Map database, comprising 8,924 acute ischemic stroke patients from 29 comprehensive hospitals who underwent thrombolysis between January 2019 and December 2021. An independent testing cohort was further established, including 1,921 patients from the First People's Hospital of Shenyang. The structured dataset encompassed 15 variables, including clinical and therapeutic metrics. The primary outcome was the sICH occurrence post-thrombolysis. Models were developed using an 80/20 split for training and internal validation. Performance was assessed using machine learning classifiers, including logistic regression with lasso regularization, support vector machine (SVM), random forest, gradient-boosted decision tree (GBDT), and multilayer perceptron (MLP). The model boasting the highest area under the curve (AUC) was specifically employed to highlight feature importance. Baseline characteristics were compared between the training cohort (n = 6,369) and the external validation cohort (n = 1,921), with the sICH incidence being slightly higher in the training cohort (1.6%) compared to the validation cohort (1.1%). Among the evaluated models, the logistic regression with lasso regularization achieved the highest AUC of 0.87 (95% confidence interval [CI]: 0.79-0.95; p < 0.001), followed by the MLP model with an AUC of 0.766 (95% CI: 0.637-0.894; p = 0.04). The reference model and SVM showed AUCs of 0.575 and 0.582, respectively, while the random forest and GBDT models performed less optimally with AUCs of 0.536 and 0.436, respectively. Decision curve analysis revealed net benefits primarily for the SVM and MLP models. Feature importance from the logistic regression model emphasized anticoagulation therapy as the most significant negative predictor (coefficient: -2.0833) and recombinant tissue plasminogen activator as the principal positive predictor (coefficient: 0.5082). After a comprehensive evaluation, the MLP model is recommended due to its superior ability to predict the risk of symptomatic hemorrhage post-thrombolysis in ischemic stroke patients. Based on decision curve analysis, the MLP-based model was chosen and demonstrated enhanced discriminative ability compared to the reference. This model serves as a valuable tool for clinicians, aiding in treatment planning and ensuring more precise forecasting of patient outcomes.

A Hierarchical Three-Dimensional MLP-Based Model for EEG Emotion Recognition

A Hierarchical Three-Dimensional MLP-Based Model for EEG Emotion Recognition

Retrieval of surface solar irradiance from satellite imagery using machine learning: pitfalls and perspectives

Abstract. Knowledge of the spatial and temporal characteristics of solar surface irradiance (SSI) is critical in many domains. While meteorological ground stations can provide accurate measurements of SSI locally, they are sparsely distributed worldwide. SSI estimations derived from satellite imagery are thus crucial to gain a finer understanding of the solar resource. Inferring SSI from satellite images is, however, not straightforward, and it has been the focus of many researchers in the past 30 to 40 years. For long, the emphasis has been on models grounded in physical laws with, in some cases, simple statistical parametrizations. Recently, new satellite SSI retrieval methods have been emerging, which directly infer the SSI from the satellite images using machine learning. Although only a few such works have been published, their practical efficiency has already been questioned. The objective of this paper is to better understand the potential and the pitfalls of this new family of methods. To do so, simple multi-layer-perceptron (MLP) models are constructed with different training datasets of satellite-based radiance measurements from Meteosat Second Generation (MSG) with collocated SSI ground measurements from Météo-France. The performance of the models is evaluated on a test dataset independent from the training set in both space and time and compared to that of a state-of-the-art physical retrieval model from the Copernicus Atmosphere Monitoring Service (CAMS). We found that the data-driven model's performance is very dependent on the training set. Provided the training set is sufficiently large and similar enough to the test set, even a simple MLP has a root mean square error (RMSE) that is 19 % lower than CAMS and outperforms the physical retrieval model at 96 % of the test stations. On the other hand, in certain configurations, the data-driven model can dramatically underperform even in stations located close to the training set: when geographical separation was enforced between the training and test set, the MLP-based model exhibited an RMSE that was 50 % to 100 % higher than that of CAMS in several locations.

Use of Synthetic Data in Maritime Applications for the Problem of Steam Turbine Exergy Analysis

Machine learning applications have demonstrated the potential to generate precise models in a wide variety of fields, including marine applications. Still, the main issue with ML-based methods is the need for large amounts of data, which may be impractical to come by. To assure the quality of the models and their robustness to different inputs, synthetic data may be generated using other ML-based methods, such as Triplet Encoded Variable Autoencoder (TVAE), copulas, or a Conditional Tabular Generative Adversarial Network (CTGAN). With this approach, a dataset can be trained using ML methods such as Multilayer Perceptron (MLP) or Extreme Gradient Boosting (XGB) to improve the general performance. The methods are applied to the dataset containing mass flow, temperature, and pressure measurements in seven points of a marine steam turbine as inputs, along with the exergy efficiency (η) and destruction (Ex) of the whole turbine (WT), low-pressure cylinder (LPC) and high-pressure cylinder (HPC) as outputs. The achieved results show that models trained on synthetic data achieve slightly worse results than the models trained on original data in previous research, but allow for the use of as little as two-thirds of the dataset to achieve these results. Using R2 as the main evaluation metric, the best results achieved are 0.99 for ηWT using 100 data points and MLP, 0.93 for ηLPC using 100 data points and an MLP-based model, 0.91 for ηHPC with the same method, and 0.97 for ExWT, 0.96 for ExLPC, and 0.98 for ExHPC using a the XGB trained model with 100 data points.

Learning-Based Longitudinal Prediction Models for Mortality Risk in Very-Low-Birth-Weight Infants: A Nationwide Cohort Study

Introduction: Prediction models assessing the mortality of very-low-birth-weight (VLBW) infants were confined to models using only pre- and perinatal variables. We aimed to construct a prediction model comprising multifactorial clinical events with data obtainable at various time points. Methods: We included 15,790 (including 2,045 in-hospital deaths) VLBW infants born between 2013 and 2020 who were enrolled in the Korean Neonatal Network, a nationwide registry. In total, 53 prenatal and postnatal variables were sequentially added into the three discrete models stratified by hospital days: (1) within 24 h (TL-1d), (2) from day 2 to day 7 after birth (TL-7d), (3) from day 8 after birth to discharge from the neonatal intensive care unit (TL-dc). Each model predicted the mortality of VLBW infants within the affected period. Multilayer perception (MLP)-based network analysis was used for modeling, and ensemble analysis with traditional machine learning (ML) analysis was additionally applied. The performance of models was compared using the area under the receiver operating characteristic curve (AUROC) values. The Shapley method was applied to reveal the contribution of each variable. Results: Overall, the in-hospital mortality was 13.0% (1.2% in TL-1d, 4.1% in TL-7d, and 7.7% in TL-dc). Our MLP-based mortality prediction model combined with ML ensemble analysis had AUROC values of 0.932 (TL-1d), 0.973 (TL-7d), and 0.950 (TL-dc), respectively, outperforming traditional ML analysis in each timeline. Birth weight and gestational age were constant and significant risk factors, whereas the impact of the other variables varied. Conclusion: The findings of the study suggest that our MLP-based models could be applied in predicting in-hospital mortality for high-risk VLBW infants. We highlight that mortality prediction should be customized according to the timing of occurrence.

Optimising Airport Ground Resource Allocation for Multiple Aircraft Using Machine Learning-Based Arrival Time Prediction

Managing aircraft turnaround is a complex process due to various factors, including passenger handling. Airport ground handling, resource planning, optimal manpower, and equipment utilisation are some cost-cutting strategies, particularly for airlines and ground handling service teams. Scheduled aircraft arrival and departure times are critical aspects of the entire ground management and passenger handling process. This research aimed to optimise airport ground resource allocation for multiple aircraft using machine learning-based prediction methodologies to enhance the prediction of aircraft arrival time, an uncontrollable variable. Our proposed models include a multiple linear regression (MLR) model and a multilayer perceptron (MLP)-based model, both of which are used for predicting round-trip arrival times. Additionally, we developed a MLP-based model for multiclass classification of arrival delays based on departure time and delay from the same airport. Under normal weather conditions and operational scenarios, the models were able to predict round-trip arrival times with a root mean squared error of 8 min for each origin–destination pair and classify arrival delays with an average accuracy of 93.5%. Our findings suggest that machine learning-based approaches can be used to predict round-trip arrival times based on the departure time from the same airport, and thereby accurately estimate the number of actual flight movements per hour well in advance. This predictability enables optimised ground resource planning for multiple aircraft based on constrained airport resource deployment and utilisation.

Pay attention to the hidden semanteme

With the capability of modeling lighter, MLP-based models like the pNLP-Mixer and the HyperMixer demonstrate the potential for diverse tasks in NLP. However, these linguistic models are not optimized for the regularity of textual hierarchical abstraction. Here, this paper proposes the hidden bias attention (HBA), a novel attention mechanism that is lighter than self-attention and focuses on extracting hidden (topic) semanteme. Additionally, this paper introduces a series of lightweight deep learning architectures, HBA-Mixer based on HBA and MHBA-Mixers based on multi-head HBA, which both outperforms pNLP-Mixer and HyperMixer in accuracy with fewer parameters on 3 tasks, including text classification, natural language inference, and sentiment analysis. Compared with large pre-trained models, MHBA-Mixers achieve over 90% of their accuracy with one-thousandth of the parameters.

RMMLP:Rolling MLP and matrix decomposition for skin lesion segmentation

Accurate skin lesion segmentation is of great significance for improving the quantitative analysis of skin cancer. However, due to the irregular shapes and ambiguous boundaries of lesions, automatic segmentation is still very difficult. Although the emergence of CNN and Transformer hybrid models recently complements their respective shortcomings, the use of transformer results in heavy parameters, and the complex structure requires a lot of data and resources for training. In contrast, Multi-Layer Perceptron (MLP) is a cost-effective alternative to complex self-attention. To this end, we propose an MLP-based model using matrix decomposition and rolling tensors for skin lesion segmentation. Specifically, we can dynamically calculate the correlation matrix according to the size of the input image and use it as the weight to guide the segmentation. The way of rolling tensors can fully mix the feature information and sequentially extract the information under different receptive fields. We also employ a two-layer decoding structure using matrix decomposition to fuse the feature extracted in the parallel MLP encoders. Extensive experiments are conducted on the public skin disease datasets ISIC2016, ISIC2017, ISIC2018 and PH2. After comparison, we found that although the addition of Transformer makes up for the lack of global information on CNN, the complex structure of Transformer itself will lead to huge parameters and is difficult to train. The experimental results show that we achieved higher results with fewer parameters compared to other state-of-the-art models which mean that the self-attention mechanism of Transformer is not irreplaceable. Our code is released at https://github.com/Lingglesymphony/RMMLP.

Polyp-Mixer: An Efficient Context-Aware MLP-Based Paradigm for Polyp Segmentation

Precise and efficient polyp segmentation plays a crucial role in colonoscopy, which is important for the prevention of colorectal cancer. Despite CNN-based methods have achieved great progress in the polyp segmentation task, they are incapable of modeling long-range dependencies. Transformer-based models utilize self-attention mechanism to overcome this problem while suffering from heavy computing cost. Benefiting from simple structures, MLP-based models seem to be an alternative. However, they struggle with dealing with flexible input scales and modeling long-term dependencies. Both of these two factors are important for image segmentation, which could explain why the MLP architecture performs poorly compared to the Transformer. To remedy this issue, we propose a novel Polyp-Mixer, which utilizes MLP-based structures in both encoder and decoder. In particular, we use CycleMLP as the encoder to overcome the fixed input scale issue. Besides, we propose a Multi-head Mixer by converting the current CycleMLP into a Multi-head fashion, allowing our model to explore rich context information from various subspaces. In addition, we build a powerful Contextual Bridger Module between the encoder and decoder, which can capture semantics from larger receptive fields and combine them with various decoder layers. Experiments demonstrate the proposed method with fewer parameters ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim 16\text{M}$ </tex-math></inline-formula> ) achieves SOTA on 4 public benchmarks. Our code will be released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/shijinghuihub/Polyp-Mixer</uri>

Reliability estimation for drone communications by using an MLP-based model

Unmanned aerial vehicles (UAVs) or drones have been widely employed in both military and civilian tasks due to their reliability and low cost. UAVs ad hoc networks also acknowledged as flying ad-hoc networks (FANETs), are multi-UAV systems arranged in an ad hoc manner. In order to maintain consistent and effective communication, reliability is a prime concern in FANETs. This paper presents an analytical framework to estimate the reliability of drones’ communication in FANETs. The proposed system takes into account the reliability of communications in FANETs, including channel fading. The suggested analytical investigation is used to generate a dataset, then an artificial neural network (ANN) based multi-layer perceptron (MLP) model is used to estimate the reliability of drones’ communication. Moreover, to define the best MLP model with hidden layers, the correlation coefficient (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are obtained. Moreover, numerical results are presented which verify analytical studies.

Prediction of landslide tsunami run-up on a plane beach through feature selected MLP-based model

We proposed new prediction models based on multilayer perceptron (MLP) which successfully predict the maximum run-up of landslide-generated tsunami waves and assess the role of parameters affecting it. The input is approximately 55,000 rows of data generated through an analytical solution employing slide’s cross section, initial submergence, vertical thickness, horizontal length, beach slope angle and the maximum run-up itself, along with its occurrence time. The parameters are first ranked through a feature selection algorithm and six models are constructed for a 9,000-row randomly sampled dataset. These MLP-based models led predictions with a minimum Mean Absolute Percentage Error of 1.1% and revealed that vertical slide thickness has the largest impact on the maximum tsunami run-up, whereas beach slope angle has minimal effect. Comparison with existing literature showed the reliability and applicability of the offered models. The methodology introduced here can be suggested as fast and flexible method for prediction of landslide-induced tsunami run-up.