Search

With the rapid progress of the integrated nanophotonics technology, the optical neural network architecture has been widely investigated. Since the optical neural network can complete the inference processing just by propagating the optical signal in the network, it is expected more than one order of magnitude faster than the electronics-only implementation of artificial neural networks (ANN). In this paper, we first propose an optical vector-matrix multiplication (VMM) circuit using wavelength division multiplexing, which enables inference processing at the speed of light with ultra-wideband. This paper next proposes optoelectronic circuit implementation for batch normalization and activation function, which significantly improves the accuracy of the inference processing without sacrificing the speed performance. Finally, using a virtual environment for machine learning and an optoelectronic circuit simulator, we demonstrate the ultra-fast and accurate operation of the optical-electronic ANN circuit.

The Grey Wolf Optimizer (GWO) is a very recently developed and emerging swarm-intelligent algorithm. The GWO algorithm was inspired by the social dominance hierarchy and hunting strategy of the grey wolves that has been successfully tailored to tackle various discrete and continuous optimization problems. During its practical implementation, however, it may be stuck in sub-optimal solutions (stagnation in local optima) due to its less exploration in the early stages that show the main drawback of this algorithm. Therefore, this research work enhances the hunting and attacking mechanism in order to modify the corresponding position updated equation and exploitation equation, respectively, to propose a novel algorithm, called Weighted Grey Wolf Optimizer with Improved Convergence Rate (WGWOIC). The effectiveness of the proposed algorithm (WGWOIC) is investigated by testing it an 33 different and fairly popular numerical benchmark functions. Although, these test functions are considered from two different benchmark datasets to assess the strength and robustness of the proposed algorithm regarding the unknown search space of the problem. In order to carry out performance analysis, moreover, the WGWOIC’s results are compared against many other state-of-the-art meta-heuristic algorithms, such as Particle Swarm Optimization (PSO), Moth-Flame Optimization (MFO), Whale Optimization Algorithm (WOA), Grey Wolf Optimizer (GWO) and very recent variants of GWO. The comparative study for WGWOIC concludes that the proposed algorithm provides very competitive results against other studied meta-heuristic algorithms. Furthermore, the hybridization of the WGWOIC meta-heuristic optimization algorithm with a Multi- Layer Perceptron (MLP) neural network is employed to improve the accuracy of the classification problem. WGWOIC trainer provides the optimal values for weight and biases to the MLP network. Further, the performance is tested in terms of classification accuracy on five popular classification datasets and assesses the efficiency of the WGWOIC trainer is assessed against many other meta-heuristics trainers. The results show that the proposed algorithm eventually provides very competitive outcomes, implying that the WGWOIC algorithm offers a better exploitation, explores the search space and effectively solves several different classification problems.

The most extensive urban growths in the next 30 years are expected to occur in developing countries. Lagos, Nigeria - Africa’s second most populous megacity- is a prime example. To achieve more sustainable and resilient cities, there is a need for modeling the urban growth patterns of major cities and analyzing their implications. In this study, the urban growth of Lagos state was modeled using the Multi-Layer Perceptron (MLP) neural network for the transition modeling and the Markov Chain analysis for the change prediction, achieving a model accuracy of 81.8%. An innovative visual validation of the model results using the ArcGIS was combined with kappa correlation statistics. The results show that by 2031, built-up areas will be the most spatially extensive LULC class in the study area with percentage coverage of 34.1% as opposed to 9% in 1986. The coverage of bare areas is also expected to increase by 53% between 2016 and 2031. Conversely, 24.9% and 68.3% loss of forestlands and wetlands respectively, are expected between 2016 and 2031. In view of the 11th goal of SDGs which focuses on achieving sustainable cities and communities, the objectives of African Union’s Agenda 2063, and based on the urban growth trends observed, the study recommends a prioritization of vertical expansion as opposed to the current horizontal urban growth trends in the study area.

Feature extraction is an integral part in speech emotion recognition. Some emotions become indistinguishable from others due to high resemblance in their features, which results in low prediction accuracy. This paper analyses the impact of spectral contrast feature in increasing the accuracy for such emotions. The RAVDESS dataset has been chosen for this study. The SAVEE dataset, CREMA-D dataset and JL corpus dataset were also used to test its performance over different English accents. In addition to that, EmoDB dataset has been used to study its performance in the German language. The use of spectral contrast feature has increased the prediction accuracy in speech emotion recognition systems to a good degree as it performs well in distinguishing emotions with significant differences in arousal levels, and it has been discussed in detail.

This research aims to develop the analysis model for diseases in water buffalo towards the application of the feature selection technique along with the Multi-Layer Perceptron neural network. The data used for analysis was collected from books and documents related to diseases in water buffalo and the official website of the Department of Livestock Development. The data consists of the characteristics of six diseases in water buffalo, including Anthrax disease, Hemorrhagic Septicemia, Brucellosis, Foot and Mouth disease, Parasitic disease, and Mastitis. Since the amount of the collected data was limited, the Synthetic Minority Over-sampling Technique was also employed to adjust the imbalance dataset. Afterward, the adjusted dataset was used to select the disease characteristics towards the application of two feature selection techniques, including Correlation-based Feature Selection and Information Gain. Subsequently, the selected features were then used for developing the analysis model for diseases in water buffalo towards the use of Multi-Layer Perceptron neural network. The evaluation results of the model’s effectiveness, given by the 10-fold cross-validation, showed that the analysis model for diseases in water buffalo developed by Correlation-based Feature Selection and Multi-Layer Perceptron neural network provided the highest level of effectiveness with the accuracy of 99.71%, the precision of 99.70%, and the recall of 99.72%. This implies that the analysis model is effectively applicable.

The evolution of machine learning (ML) algorithms provides researchers and engineers with state-of-the-art tools to dynamically model complex relationships. The design and operation of municipal solid waste (MSW) management systems require accurate estimation of generation rates. In this study, we applied rapid, non-linear and non-parametric data driven ML algorithms independently, multi-layer perceptron artificial neural network (MLP-ANN) and support vector regression (SVR) models to predict annual MSW generation rates in Bahrain. Models were trained and tested with MSW generation data for period of 1997–2019. The population, gross domestic product, annual tourist numbers, annual electricity consumption and total annual CO2 emissions were selected as explanatory variables and incorporated into developed models. The zero score normalization (ZSN) and minimum maximum normalization (MMN) methods were utilized to improve the quality of data and subsequently enhances the performance of ML algorithms. Statistical metrics were employed to discriminate performance of MLP-ANN and SVR models. The linear, polynomial, radial basis function (RBF) and sigmoid kernel functions were investigated to find the optimal SVR model. Results showed that RBF-SVR model with R2 value of 0.97% and 4.82% and absolute forecasting error (AFE) for the period of 2008 and 2019 exhibits superior prediction and robustness in comparison to MLP-ANN. The efficacy of MLP-ANN model was also reasonably successful with R2 value of 0.94. It was shown that MMN pre-processing generated optimal MLP-ANN model while ZSN pre-processing produced optimal RBF-SVR model. This work also highlights the importance of application of ML modelling approaches to plan and implement their roadmap for waste management systems by policymakers.

Knowledge of pore-water pressure (PWP) variation is fundamental for slope stability. A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability. To explore the applicability and advantages of recurrent neural networks (RNNs) on PWP prediction, three variants of RNNs, i.e., standard RNN, long short-term memory (LSTM) and gated recurrent unit (GRU) are adopted and compared with a traditional static artificial neural network (ANN), i.e., multi-layer perceptron (MLP). Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models. The coefficient of determination (R2) and root mean square error (RMSE) are used for model evaluations. The influence of input time series length on the model performance is investigated. The results reveal that MLP can provide acceptable performance but is not robust. The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 kPa for the selected two piezometers. The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall. The GRU and LSTM models can provide more precise and robust predictions than the standard RNN. The effects of the hidden layer structure and the dropout technique are investigated. The single-layer GRU is accurate enough for PWP prediction, whereas a double-layer GRU brings extra time cost with little accuracy improvement. The dropout technique is essential to overfitting prevention and improvement of accuracy.

This study examines rainfall forecasting for the Perfume (Huong) River basin using the machine learning method. To be precise, statistical measurement indicators are deployed to evaluate the reliability of the actual accumulated data. At the same time, this study applied and compared two popular models of multi-layer perceptron and the k-nearest neighbors (k-NN) with different configurations. The calculated rainfall data are obtained from the Hue, Aluoi, and Namdong hydrological stations, where the rainfall demonstrated a giant impact on the downstream from 1980 to 2018. This study result shows that both models, once fine-tuned properly, enjoyed the performance with standard metrics of R_squared, mean absolute error, Nash–Sutcliffe efficiency, and root-mean-square error. In particular, once Adam stochastic is deployed, the implementation of the MLP model is significantly improving. The promising forecast results encourage us to consider applying these models with future data to help natural disaster non-stop mitigation in the Perfume River basin.

Matrix completion has been widely used in image recovery and recommendation. The conventional matrix completion models based on multi-layer perceptron (MLP) only has local constraints on the observation data so that the completed matrix contains a lot of noise. Therefore, this paper proposes a novel matrix completion model based on the MLP integrating kernel regularization (MCKR). The proposed model uses the MLP to extract feature, which can automatically extract interaction feature of missing data and observational data. Moreover, through a non-linear mapping of low-dimensional latent subspace and schatten p-norm, a novel kernel regularization is derived to provide a global constraint for reducing the noise of the completed matrix. Finally, the validity and practicability of the proposed model is verified on three publicly available datasets. Compared with baselines including matrix factorization (MF), Logistic matrix factorization (LMF), expertise matrix factorization (EMF) and multi-layer perceptron (MLP), the proposed model achieves state-of-the-art result.

This paper proposed a grape drying machine using computer vision and Multi-layer Perceptron (MLP) method. Computer vision is for taking grapes’ image on conveyor, whereas MLP is for controlling grape drying machine and classifying its output. To evaluate the proposed, a kind of grapes are put on conveyor of the machine and their images are taken every two min. Some parameters of MLP to control the drying machine includes dried grape, temperature, grape area, motor position, and motion speed. Those parameters are to adjust an appropriate MLP’s output, including motion control and heater control. Two different temperatures are employed on the machine, including 60 and 75°C. The results showed that the grape could be dried with similar area 3800 pixel at the 770th min using temperature 60°C and at the 410th min using temperature 75°C. Comparing between them, the similar ratio could also be achieved at 0.64 with different time 360 min. Indeed, the temperature setting at 75°C resulted faster drying performance.

Accurate localization of radioactive materials is crucial in homeland security and radiological emergencies. Coded-aperture gamma camera is an interesting solution for such applications and can be developed into portable real-time imaging devices. However, traditional reconstruction methods cannot effectively deal with signal-independent noise, thereby hindering low-noise real-time imaging. In this study, a novel reconstruction method with excellent noise-suppression capability based on a multi-layer perceptron (MLP) is proposed. A coded-aperture gamma camera based on pixel detector and coded-aperture mask was constructed, and the process of radioactive source imaging was simulated. Results showed that the MLP method performs better in noise suppression than the traditional correlation analysis method. When the Co-57 source with an activity of 1 MBq was at 289 different positions within the field of view which correspond to 289 different pixels in the reconstructed image, the average contrast-to-noise ratio (CNR) obtained by the MLP method was 21.82, whereas that obtained by the correlation analysis method was 5.85. The variance in CNR of the MLP method is larger than that of correlation analysis, which means the MLP method has some instability in certain conditions.

As stated by World Health Organization (WHO) report, 246 million individuals have suffered with diabetes disease over worldwide and it is anticipated that by 2025 this estimation can cross 380 million. So, the proper and quick diagnosis of this disease is turned into a significant challenge for the machine learning researchers. This paper aims to design a robust model for diagnosis of diabetes using a hybrid approach of Chaotic-Jaya (CJaya) algorithm with Extreme Learning Machine (ELM), which is named as CJaya-ELM. In this paper, Jaya algorithm with Chaotic learning approach is used to optimize the random parameters of ELM classifier. Here, to assess the efficacy of the designed model, Pima Indian diabetes dataset is considered. Here, the designed model CJaya-ELM, has been compared with basic ELM, Teaching Learning Based Optimization algorithm (TLBO) optimized ELM (TLBO-ELM), Multi-Layer Perceptron (MLP), Jaya algorithm optimized MLP (Jaya-MLP), TLBO algorithm optimized MLP (TLBO-MLP) and CJaya algorithm optimized MLP models. CJaya-ELM model resulted in the highest testing accuracy of 0.9687, sensitivity of 1, specificity of 0.9688 with 0.9782 area under curve (AUC) value. Results reveal that CJaya-ELM model effectively classifies both the positive and negative samples of Pima and outperforms the competitors.

In recent years, there has been tremendous growth in the amount of natural language text through various sources. Computational analysis of this text has got considerable attention among the NLP researchers. Automatic analysis and representation of natural language text is a step by step procedure. Deep level tagging is one of such steps applied over the text. In this paper, we demonstrate a methodology for deep level tagging of Malayalam text. Deep level tagging is the process of assigning deeper level information to every noun and verb in the text along with normal POS tags. In this study, we move towards a direction that is not much explored in the case of Malayalam language. Malayalam is a morphologically rich and agglutinative language. The morphological features of the language are effectively utilized for the computational analysis of Malayalam text. The language level details required for the study are provided by Thunjath Ezhuthachan Malayalam University, Tirur.

Zontul, Metin (Arel Author), Karateke, Seda (Arel Author), Reliable prediction of municipal solid waste (MSW) generation rates is a significant element of planning and implementation of sustainable solid waste management strategies. In this study, the multi-layer perceptron artificial neural network (MLP-ANN) is applied to verify the prediction of annual generation rates of domestic, commercial and construction and demolition (C&D) wastes from the year 1997 to 2016 in Askar Landfill site in the Kingdom of Bahrain. The proposed robust predictive models incorporated selected explanatory variables to reflect the influence of social, demographical, economic, geographical and touristic factors upon waste generation rates (WGRs). The Mean Squared Error (MSE) and coefficient of determination (R-2) are used as performance indicators to evaluate effectiveness of the developed models. MLP-ANN models exhibited strong accuracy in predictions with highR(2)and low MSE values. TheR(2)values for domestic, commercial and C&D wastes are 0.95, 0.99 and 0.91, respectively. Our results show that the developed MLP-ANN models are effective for the prediction of WGRs from different sources and could be considered as a cost-effective approach for planning integrated MSW management systems.

The traditional RSS-based fingerprint localization algorithm needs RSS values from all access points (AP) at each reference point (RP). In the large-scale indoor environment, the increasing of the number of APs will lead to establish a large-scale fingerprint database, which occupies a lot of storage space. In this paper, we propose a new reliable localization algorithm, which firstly utilizes quantized RSS to encode the monitoring region which has been divided into grids, so as to specify the grids that the interested target appears roughly. Then, we utilize Multi-Layer Perceptron (MLP) to train the grid regions in which the beacons deployment is non-isomorphic and obtain the accurate localization result. Due to the same deployment of isomorphic regions, it is imperative to train only one model to replace the others, which greatly reduces the computation of neural network. It can be concluded from the experimental results that compared with the traditional MLP-based fingerprint localization algorithm, the proposed algorithm reduces the size of fingerprint database over 80% with guarantee of localization accuracy. Moreover, our algorithm can obtain better localization accuracy compared with the other latest quantization based localization algorithm.

One of the challenges in the successful implementation of deep neural networks (DNN) lies on the determination of its architecture, in terms of the number of hidden layers and neurons for each hidden layer. In this research, a new approach is proposed to determine the neural networks architecture especially in the form of Multi-layer Perceptron (MLP) which will later be used as a machine learning method to classify data with large number of attribute. The new approach is proposed since the previous approaches are no longer applicable as general guidelines to determine the architecture of neural networks. Thus, the proposed approach aims to determine the number of hidden layers by using principal component analysis (PCA), while the number of neurons for each hidden layer is determined by using K-Means clustering. The determined neural network architecture is utilized to classify data with large number of attribute, such as the Gas Sensor Array Drift dataset which has 128 input attributes and six output classes and the Parkinson’s Disease Classification dataset which has 754 output attributes and two output classes. The results indicate that the best-performing architecture for the first dataset is the one that uses one hidden layer, with a PCA cumulative variance of 69.7%, while for the second dataset is the one that uses three hidden layers, with a PCA cumulative variance of 38.9%. Increasing the number of hidden layers does not always improve the performance of neural networks. Therefore, it is essential to determine the number of hidden layers and neurons that are appropriate to achieve good performance in neural networks. The use of PCA and K-Means clustering is expected to provide guidelines in determining neural networks architectures with good performance.

Stock prices forecasting is a topic research in the fields of investment and national policy, which has been a challenging problem owing to the multi-noise, nonlinearity, high-frequency, and chaos of stocks. These characteristics of stocks impede most forecasting models from extracting valuable information from stocks data. Herein, a novel hybrid deep learning model integrating attention mechanism, multi-layer perceptron, and bidirectional long-short term memory neural network is proposed. First, the raw data including four types of datasets (historical prices of stocks, technical indicators of stocks closing prices, natural resources prices, and historical data of the Google index) are transformed into a knowledge base with reduced dimensions using principal component analysis. Subsequently, multi-layer perceptron is used for the fast transformation of feature space and rapid gradient descent, bidirectional long-short term memory neural network for extracting temporal features of stock time series data, and attention mechanism for making the neural network focus more on crucial temporal information by assigning higher weights. Finally, a comprehensive model evaluation method is used to compare the proposed model with seven related baseline models. After extensive experiments, the proposed model demonstrated its good forecasting performance.

In this paper, a Supervised Extreme Learning Machine-based Auto-Encoder (SELM-AE) is proposed for discriminative Feature Learning. Different from traditional ELM-AE (designed based on data information X only), SELM-AE is designed based on both data information X and label information T. In detail, SELM-AE not only minimizes the reconstruction error of input data but also minimizes the intra-class distance and maximizes the inter-class distance in the new feature space. Under this way, the new data representation extracted by proposed SELM-AE is more discriminative than traditional ELM-AE for further classification. Then multiple SELM-AEs are stacked layer by layer to develop a new multi-layer perceptron (MLP) network called ML-SAE-ELM. Benefit from SELM-AE, the proposed ML-SAE-ELM is highly effective on classification than ELM-AE based MLP. Moreover, different from ELM-AE based MLP that requires large number of hidden nodes to achieve satisfactory accuracy, ML-SAE-ELM usually takes very small number of hidden nodes on both feature learning and classification stages to achieve better accuracy, which highly lightens the network memory requirement. The proposed method has been evaluated over 13 benchmark binary and multi-class datasets and one complicated image dataset. As shown in the experimental results, through the visualization of data representation, the proposed SELM-AE extracts more discriminative data representation than ELM-AE. Moreover, the shallow ML-SAE-ELM with smaller hidden nodes achieves higher classification accuracy than hierarchical ELM (a commonly used effective ELM-AE based MLP) on most evaluated datasets.

By increasing the complexity of the Internet of Things (IoT) applications, fault prediction become an important challenge in interactions between human, and smart devices. Fault prediction is one of the key factors to achieve better arranging the IoT applications. Most of the current research studies evaluated the fault prediction methods using simulation environments. However, formal verification of the correctness of a fault prediction method has not been reported yet. This paper presents a behavioral modeling and formal verification of a hybrid machine learning-based fault prediction model with Multi-Layer Perceptron (MLP) and Particle Swarm Optimization (PSO) algorithms. In particular, the PSO is used for feature selection. Then, the fault prediction is considered as a behavior to be verified formally. The fault prediction behavior is divided into two types of behaviors: dimension reduction behavior and prediction behavior. For each of the behaviors, one formal model is designed. The behavioral models designed are mapped into the Labeled Transition System (LTS). The Process Analysis Toolkit (PAT) model checker is employed to evaluate the behavioral models. The accuracy of the fault prediction method is done by some existing specifications such as deadlock-free and reachability properties in terms of linear temporal logic formulas. Also, the verification of the fault prediction behaviors is used to detect the defect metrics of information-centric IoT applications. Experimental results showed that our proposed verification method has minimum verification time and memory usage for evaluating critical specification rules than other research studies.

This study evaluated the axial capacity of cold-formed racking upright sections strengthened with an innovative reinforcement method by finite element modelling and artificial intelligence techniques. At the first stage, several specimens with different lengths, thicknesses and reinforcement spacings were modelled in ABAQUS. The finite element method (FEM) was employed to increase the available datasets and evaluate the proposed reinforcement method in different geometrical types of sections. The most influential factors on the axial strength were investigated using a feature-selection (FS) method within a multi-layer perceptron (MLP) algorithm. The MLP algorithm was developed by particle swarm optimization (PSO) and FEM results as input. In terms of accuracy evaluation, some of the rolling criteria including results showed that geometrical parameters have almost the same contribution in compression capacity and displacement of the specimens. According to the performance evaluation indexes, the best model was detected and specified in the paper and optimised by tuning other parameters of the algorithm. As a result, the normalised ultimate load and displacement were predicted successfully.

Background The origin is the starting site of DNA replication, an extremely vital part of the informational inheritance between parents and children. More importantly, accurately identifying the origin of replication has great application value in the diagnosis and treatment of diseases related to genetic information errors, while the traditional biological experimental methods are time-consuming and laborious. Results We carried out research on the origin of replication in a variety of eukaryotes and proposed a unique prediction method for each species. Throughout the experiment, we collected data from 7 species, including Homo sapiens, Mus musculus, Drosophila melanogaster, Arabidopsis thaliana, Kluyveromyces lactis, Pichia pastoris and Schizosaccharomyces pombe. In addition to the commonly used sequence feature extraction methods PseKNC-II and Base-content, we designed a feature extraction method based on TF-IDF. Then the two-step method was utilized for feature selection. After comparing a variety of traditional machine learning classification models, the multi-layer perceptron was employed as the classification algorithm. Ultimately, the data and codes involved in the experiment are available at https://github.com/Sarahyouzi/EukOriginPredict. Conclusions The prediction accuracy of the training set of the above-mentioned seven species after 100 times fivefold cross validation reach 92.60%, 90.80%, 91.22%, 96.15%, 96.72%, 99.86%, 96.72%, respectively. It denotes that compared with other methods, the methods we designed could accomplish superior performance. In addition, our experiments reveals that the models of multiple species could predict each other with high accuracy, and the results of STREME shows that they have a certain common motif.

With the proliferation of mobile devices, the popularity of Android applications (apps) has increased exponentially. Efficient power consumption in a device is essential from the perspective of the user because users want their devices to work all day. Developers must properly utilize the application programming interfaces (APIs) provided by Android software development kit to optimize the power consumption of their app. Occasionally, developers fail to relinquish the resources required by their app, resulting in a resource leak. Wake lock APIs are used in apps to manage the power state of the Android smartphone, and they frequently consume more power than necessary if not used appropriately (also called energy leak). In this study, we use a multi-layer perceptron (MLP) to detect wake lock leaks in Android apps because the MLP can solve complex problems and determine similarities in graphs. To detect wake lock leaks, we extract the call graph as features from the APK and embed the instruction and neighbor information in the node’s label of the call graph. Then, the encoded data are input to an MLP model for training and testing. We demonstrate that our model can identify wake lock leaks in apps with 99% accuracy.

Purpose: Glioblastoma Multiform (GBM) is one of the most common and deadly malignant brain tumors. Surgery is the primary treatment, and careful surgery can minimize recurrence odds. Magnetic Resonance Imaging (MRI) imaging with Magnetic Resonance Spectroscopy (MRS) is used to diagnose various types of tumors in the Central Nervous System (CNS). In this study, several classification methods were used to separate tumor and healthy tissue. Materials and Methods: This study examined the MRI and MRS results of seven people enrolled in this study in 2018. The data was obtained with a prescription from a neurologist and neurosurgeon. Choline (Cho) and N-Acetylaspartate (NAA) metabolite signals were selected as the reference signal after preprocessing and removing the water signal. With the support of 3 radiologists, each tumor and healthy vesicles were identified for every patient. Then, tumor and healthy voxels were separated based on Multilayer Perceptron (MLP), linear Support Vector Machine (SVM), Gaussian SVM, and Fuzzy system using the obtained values and four different methods. Results: Data extracted from Cho and NAA metabolites were fed into MLP, linear SVM, Gaussian and Fuzzy SVM as input, and the amounts of accuracy, sensitivity, and specificity were determined for each method. The maximum accuracy for training mode and test mode was equal to 89.7% and 87%, respectively, specific to classification using Gaussian SVM. The results also showed that the classification accuracy can be significantly increased by increasing the number of fuzzy membership functions from 2 to 6. Conclusion: The results of this study suggested that a more complex classification system, such as SVM with a Gaussian kernel and fuzzy system can be more efficient and reliable when it comes to separating tumor tissue from healthy tissues from MRS data.

Recently, many convolutional neural network (CNN)-based methods have been proposed to tackle the classification task of hyperspectral images (HSI). In fact, CNN has become the de-facto standard for HSI classification. It seems that the traditional neural networks such as multi-layer perceptron (MLP) are not competitive for HSI classification. However, in this study, we try to prove that the MLP can achieve good classification performance of HSI if it is properly designed and improved. The proposed Modified-MLP for HSI classification contains two special parts: spectral–spatial feature mapping and spectral–spatial information mixing. Specifically, for spectral–spatial feature mapping, each input sample of HSI is divided into a sequence of 3D patches with fixed length and then a linear layer is used to map the 3D patches to spectral–spatial features. For spectral–spatial information mixing, all the spectral–spatial features within a single sample are feed into the solely MLP architecture to model the spectral–spatial information across patches for following HSI classification. Furthermore, to obtain the abundant spectral–spatial information with different scales, Multiscale-MLP is proposed to aggregate neighboring patches with multiscale shapes for acquiring abundant spectral–spatial information. In addition, the Soft-MLP is proposed to further enhance the classification performance by applying soft split operation, which flexibly capture the global relations of patches at different positions in the input HSI sample. Finally, label smoothing is introduced to mitigate the overfitting problem in the Soft-MLP (Soft-MLP-L), which greatly improves the classification performance of MLP-based method. The proposed Modified-MLP, Multiscale-MLP, Soft-MLP, and Soft-MLP-L are tested on the three widely used hyperspectral datasets. The proposed Soft-MLP-L leads to the highest OA, which outperforms CNN by 5.76%, 2.55%, and 2.5% on the Salinas, Pavia, and Indian Pines datasets, respectively. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods, which shows that the MLP-based methods are still competitive for HSI classification.

Traditional techniques to identify macromolecular targets for drugs utilize solely the information on a query drug and a putative target. Nonetheless, the mechanisms of action of many drugs depend not only on their binding affinity toward a single protein, but also on the signal transduction through cascades of molecular interactions leading to certain phenotypes. Although using protein-protein interaction networks and drug-perturbed gene expression profiles can facilitate system-level investigations of drug-target interactions, utilizing such large and heterogeneous data poses notable challenges. To improve the state-of-the-art in drug target identification, we developed GraphDTI, a robust machine learning framework integrating the molecular-level information on drugs, proteins, and binding sites with the system-level information on gene expression and protein-protein interactions. In order to properly evaluate the performance of GraphDTI, we compiled a high-quality benchmarking dataset and devised a new cluster-based cross-validation protocol. Encouragingly, GraphDTI not only yields an AUC of 0.996 against the validation dataset, but it also generalizes well to unseen data with an AUC of 0.939, significantly outperforming other predictors. Finally, selected examples of identified drugtarget interactions are validated against the biomedical literature. Numerous applications of GraphDTI include the investigation of drug polypharmacological effects, side effects through offtarget binding, and repositioning opportunities.

Pelagic chlorophyll-a concentrations are key for evaluation of the environmental status and productivity of marine systems, and data can be provided by in situ measurements, remote sensing and modelling. However, modelling chlorophyll-a is not trivial due to its nonlinear dynamics and complexity. In this study, chlorophyll-a concentrations for the Helgoland Roads time series were modeled using a number of measured water and environmental parameters. We chose three common machine learning algorithms from the literature: the support vector machine regressor, neural networks multi-layer perceptron regressor and random forest regressor. Results showed that the support vector machine regressor slightly outperformed other models. The evaluation with a test dataset and verification with an independent validation dataset for chlorophyll-a concentrations showed a good generalization capacity, evaluated by the root mean squared errors of less than 1 µg L−1. Feature selection and engineering are important and improved the models significantly, as measured in performance, improving the adjusted R2 by a minimum of 48%. We tested SARIMA in comparison and found that the univariate nature of SARIMA does not allow for better results than the machine learning models. Additionally, the computer processing time needed was much higher (prohibitive) for SARIMA. Keywords: time series regression; artificial intelligence; Helgoland Roads time series; support vector machine; multi-layer perceptron; random forest; productivity; SARIMA

Real-time river flood forecasting models can be useful for issuing flood alerts and reducing or preventing inundations. To this end, machine-learning (ML) methods are becoming increasingly popular thanks to their low computational requirements and to their reliance on observed data only. This work aimed to evaluate the ML models’ capability of predicting flood stages at a critical gauge station, using mainly upstream stage observations, though downstream levels should also be included to consider backwater, if present. The case study selected for this analysis was the lower stretch of the Parma River (Italy), and the forecast horizon was extended up to 9 h. The performances of three ML algorithms, namely Support Vector Regression (SVR), MultiLayer Perceptron (MLP), and Long Short-term Memory (LSTM), were compared herein in terms of accuracy and computational time. Up to 6 h ahead, all models provided sufficiently accurate predictions for practical purposes (e.g., Root Mean Square Error &lt, 15 cm, and Nash-Sutcliffe Efficiency coefficient &gt, 0.99), while peak levels were poorly predicted for longer lead times. Moreover, the results suggest that the LSTM model, despite requiring the longest training time, is the most robust and accurate in predicting peak values, and it should be preferred for setting up an operational forecasting system.

This study evaluates an innovative reinforcement method for cold-formed steel (CFS) upright sections through finite element assessment as well as prediction of the normalized ultimate load and deflection of the profiles by artificial intelligence (AI) and machine learning (ML) techniques. Following the previous experimental studies, several CFS upright profiles with different lengths, thicknesses and reinforcement spacings are modeled and analyzed under flexural loading. The finite element method (FEM) is employed to evaluate the proposed reinforcement method in different upright sections and to provide a valid database for the analytical study. To detect the most influential factor on flexural strength, the “feature selection” method is performed on the FEM results. Then, by using the feature selection method, a hybrid neural network (a combination of multi-layer perceptron algorithm and particle swarm optimization method) is developed for the prediction of normalized ultimate load. The correlation coefficient (R), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), mean absolute error (MAE) and Wilmot’s index of agreement (WI) are used as the measure of precision. The results show that the geometrical parameters have almost the same contribution in the flexural capacity and deflection of the specimens. According to the performance evaluation indexes, the best model is detected and optimized by tuning other algorithm parameters. The results indicate that the hybrid neural network can successfully predict the normalized ultimate load and deflection.

Diabetes is one of the chronic diseases in the world, 246 million people are inflicted by this disease and according to a World Health Organisation (WHO) report, this figure will increase to 380 million sufferers by 2025. Many other debilitating and critical health issues may further develop if this disease is not diagnosed or remain unidentified. Machine Learning (ML) techniques are now being used in various fields like education, healthcare, business, recommendation system, etc. Healthcare data is complex and high in dimensionality and contains irrelevant information - due to this, the prediction accuracy is low. The Pima Indians Diabetes Dataset was used in this research, it consisted of 768 records. Firstly, the missing values are replaced by the median followed by Linear Discriminant Analysis. Using the Python programming language, feature selection techniques is applied in combination with five classification algorithms: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Logistic Regression, Random Forest and Decision Tree. The aim of this paper is to compare the different classification algorithms in order to predict diabetes in patients more accurately. K-fold cross-validation is applied, considering k to be 2, 4, 5 and 10. The performance parameters taken are the: accuracy, precision, recall, F Score and area under the curve. Our study found that the MLP classifier gave the highest accuracy of 78.7% with a recall of 61.26%, precision of 72.45% and F1 Score of 65.97% for k = 4.

Translational compensation is one of the key problems in parameter estimation of moving targets and radar imaging, and envelope correction is the basis of translation compensation. However, in inverse synthetic aperture imaging, the traditional translation compensation algorithms cannot be applied to micro-motion targets. Based on the characteristics of micro-motion targets and the advantages of the terahertz radar, a new method of envelope correction for micro-motion targets based on the multi-layer perceptron is proposed in this paper, which is verified by a radar system with a carrier frequency of 330 GHz. The experimental targets adopted in this paper are rotating corner reflectors and precession warhead. Finally, this paper proposes a measure based on inverse Radon transform and compares the performance of the proposed algorithm with that of the previous one, which fully verifies the effectiveness of the proposed method.

Cuneiform language is an old language that was invented by the people of Sumerian nation. It is an essential language for many archeologists. Especially who are interested in studying and investigating the old nations of Iraq. Dealing with this type of language usually requires specialist to translate its symbols, which are basically forms of nail shapes. This study presents a new approach to translate the cuneiform writing by employing artificial neural network (ANN) technique. Effectively, multi-layer perceptron (MLP) neural network has been adapted for translating the Sumerian cuneiform symbol images to their corresponding English letters. This work has been successfully established and it attained 100%. &nbsp

Of late, Network Security Research is taking center stage given the vulnerability of computing ecosystem with networking systems increasingly falling to hackers. On the network security canvas, Intrusion detection system (IDS) is an essential tool used for timely detection of cyber-attacks. A designated set of reliable safety has been put in place to check any severe damage to the network and the user base. Machine learning (ML) is being frequently used to detect intrusion owing to their understanding of intrusion detection systems in minimizing security threats. However, several single classifiers have their limitation and pose challenges to the development of effective IDS. In this backdrop, an ensemble approach has been proposed in current work to tackle the issues of single classifiers and accordingly, a highly scalable and constructive majority voting-based ensemble model was proposed which can be employed in real-time for successfully scrutinizing the network traffic to proactively warn about the possibility of attacks. By taking into consideration the properties of existing machine learning algorithms, an effective model was developed and accordingly, an accuracy of 99%, 97.2%, 97.2%, and 93.2% were obtained for DoS, Probe, R2L, and U2R attacks and thus, the proposed model is effective for identifying intrusion. &nbsp

Wildfires are becoming more frequent in different parts of the globe, and the ability to predict when and where they will occur is a complex process. Identifying wildfire events with high probability of becoming a large wildfire is an important task for supporting initial attack planning. Different methods, including those that are physics-based, statistical, and based on machine learning (ML) are used in wildfire analysis. Among the whole, those based on machine learning are relatively novel. In addition, because the number of wildfires is much greater than the number of large wildfires, the dataset to be used in a ML model is imbalanced, resulting in overfitting or underfitting the results. In this manuscript, we propose to generate synthetic data from variables of interest together with ML models for the prediction of large wildfires. Specifically, five synthetic data generation methods have been evaluated, and their results are analyzed with four ML methods. The results yield an improvement in the prediction power when synthetic data are used, offering a new method to be taken into account in Decision Support Systems (DSS) when managing wildfires.

With the latest advances in information and communication technologies, greater amounts of sensitive user and corporate information are shared continuously across the network, making it susceptible to an attack that can compromise data confidentiality, integrity, and availability. Intrusion Detection Systems (IDS) are important security mechanisms that can perform the timely detection of malicious events through the inspection of network traffic or host-based logs. Many machine learning techniques have proven to be successful at conducting anomaly detection throughout the years, but only a few considered the sequential nature of data. This work proposes a sequential approach and evaluates the performance of a Random Forest (RF), a Multi-Layer Perceptron (MLP), and a Long-Short Term Memory (LSTM) on the CIDDS-001 dataset. The resulting performance measures of this particular approach are compared with the ones obtained from a more traditional one, which only considers individual flow information, in order to determine which methodology best suits the concerned scenario. The experimental outcomes suggest that anomaly detection can be better addressed from a sequential perspective. The LSTM is a highly reliable model for acquiring sequential patterns in network traffic data, achieving an accuracy of 99.94% and an f1-score of 91.66%.

Shipborne gravity can be used to refine altimeter-derived gravity whose accuracy is low in shallow waters and areas with complex submarine topography. As altimeter-derived gravity only within a small radius around the shipborne data can be corrected by traditional methods, a new method based on multi-layer perceptron (MLP) neural network is proposed to refine the altimeter-derived gravity. Input variables of MLP include the positional information at observation points and geophysical information (from our own South China Sea gravity anomaly model (SCSGA) V1.0 and bathymetry model ETOPO1) at grid points around observation points. Output variables of MLP are the refined residual gravity anomalies at observation points. Training shipborne data are classified into four cases to train four MLP models, which are used to predict the refined gravity anomaly model SCSGA V1.1. Then all of the training shipborne data are used for training an MLP model to predict the refined gravity anomaly model SCSGA V1.2. Assessed by testing shipborne data, the accuracy of SCSGA V1.2 is 0.14 mGal higher than that of SCSGA V1.0, and similar to that of SCSGA V1.1. Compared with the original gravity anomaly model (SCSGA V1.0), the accuracy of the refined gravity anomaly model (SCSGA V1.2) by MLP is improved by 4.4% in areas where the training data are concentrated, and also improved by 2.2% in other areas. Therefore, the method of MLP can be used to refine the altimeter-derived gravity model by shipborne gravity, overcoming the problem of limited correction radius for traditional methods.

et al.;IEEE Circuits and Systems Society (CAS) Visual Signal Processing and Communications Technical Committee;IEEE Communications Society (ComSoc);IEEE Council on Electronic Design Automation (CEDA);IEEE Reliability Society;IEEE Signal Processing Society, 7th IEEE World Forum on Internet of Things, WF-IoT 2021 -- 14 June 2021 through 31 July 2021 -- -- 173945, We develop a Multi-Layer Perceptron (MLP) Decomposition architecture for mobile Internet Things (IoT) indoor positioning. We demonstrate the performance of our architecture on an indoor system that utilizes ultra-wideband (UWB) positioning. Our architecture outperforms the following benchmark processing techniques on the same data: MLP, Linear Regression, Ridge Regression, Support Vector Regression, and the Least Squares Method for indoor positioning. The results show that our architecture can significantly advance the positioning accuracy of indoor positioning systems and enable indoor applications such as navigation, proximity marketing, asset tracking, collision avoidance, and social distancing. © 2021 IEEE., Türkiye Bilimsel ve Teknolojik Araştirma Kurumu, TÜBITAK: 1139B411901516, The industry sponsor for the TUBITAK 2209-B grant that funded this work was SADELABS (SADE Teknoloji, Inc.), Izmir, Turkey., This work was funded by TUBITAK (Scientific and Technological Research Council of Turkey) under the 2209-B Grant #1139B411901516.

In order to study the multiple restricted factors and parameters of the eddy current loss of generator end structures, both the multi-layer perceptron (MLP) and support vector regression (SVR) are used to study and predict the mechanism of the synergistic effect of metal shield conductivity, relative permeability of clamping plates and structural characteristics of eddy current losses. Based on the eddy current losses of generator end structures under different metal shielding thicknesses and electromagnetic properties, the calculation accuracy of the MLP and SVR is compared. The prediction method gives an effective means for the complex design of the end region of the generator, which reduces the effort of the designers. It also promotes the design efficiency of the electrical generator.

In this study, hardware-in-the-loop based real-time state of charge estimation was performed in Li-Ion batteries, which are widely used in hybrid and battery electric vehicles. The state of charge is estimated on the Li-Ion battery cell that forms the electric vehicle battery system. Multi-layer perceptron approach has been preferred as a method for estimating the battery state of charge. Discharge experiments based on different electrical loads were applied to the Li-Ion battery cell to be used in multilayer perceptron learning processes. An experimental setup has been prepared to perform the discharge process under different electrical loads. In each discharge experiment, battery open circuit voltage, battery discharge current and battery cell temperature parameters were measured and were recorded. By using the data obtained from the experiments on the battery cell, a multilayer perceptron model was created in MATLAB environment. After creating the multilayer perceptron model, the real-time battery state of charge the was estimated at different discharge currents in the experimental setup and the results obtained were evaluated. © 2020, Ismail Saritas. All rights reserved. 2-s2.0-85100221415

Reconfigurable Intelligent Surfaces (RISs) are recently gaining remarkable attention as a low-cost, hardware-efficient, and highly scalable technology capable of offering dynamic control of electro-magnetic wave propagation. Their envisioned dense deployment over various obstacles of the, otherwise passive, wireless communication environment has been considered as a revolutionary means to transform them into network entities with reconfigurable properties, providing increased environmental intelligence for diverse communication objectives. One of the major challenges with RIS-empowered wireless communications is the low-overhead dynamic configuration of multiple RISs, which according to the current hardware designs have very limited computing and storage capabilities. In this paper, we consider a typical communication pair between two nodes that is assisted by a plurality of RISs, and devise low-complexity supervised learning approaches for the RISs' phase configurations. By assuming common tunable phases in groups of each RIS's unit elements, we present multi-layer perceptron Neural Network (NN) architectures that can be trained either with positioning values or the instantaneous channel coefficients. We investigate centralized and individual training of the RISs, as well as their federation, and assess their computational requirements. Our simulation results, including comparisons with the optimal phase configuration scheme, showcase the benefits of adopting individual NNs at RISs for the link budget performance boosting., 6 pages, 6 figures, accepted to IEEE GLOBECOM 2020

Despite yielding considerable degrees of accuracy in landslide predictions, the outcomes of different landslide susceptibility models are prone to spatial disagreement; and therefore, uncertainties. Uncertainties in the results of various landslide susceptibility models create challenges in selecting the most suitable method to manage this complex natural phenomenon. This study aimed to propose an approach to reduce uncertainties in landslide prediction, diagnosing spatial agreement in machine learning-based landslide susceptibility maps. It first developed landslide susceptibility maps of Cox’s Bazar district of Bangladesh, applying four machine learning algorithms: K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM), featuring hyperparameter optimization of 12 landslide conditioning factors. The results of all the four models yielded very high prediction accuracy, with the area under the curve (AUC) values range between 0.93 to 0.96. The assessment of spatial agreement of landslide predictions showed that the pixel-wise correlation coefficients of landslide probability between various models range from 0.69 to 0.85, indicating the uncertainty in predicted landslides by various models, despite their considerable prediction accuracy. The uncertainty was addressed by establishing a Logistic Regression (LR) model, incorporating the binary landslide inventory data as the dependent variable and the results of the four landslide susceptibility models as independent variables. The outcomes indicated that the RF model had the highest influence in predicting the observed landslide locations, followed by the MLP, SVM, and KNN models. Finally, a combined landslide susceptibility map was developed by integrating the results of the four machine learning-based landslide predictions. The combined map resulted in better spatial agreement (correlation coefficients range between 0.88 and 0.92) and greater prediction accuracy (0.97) compared to the individual models. The modelling approach followed in this study would be useful in minimizing uncertainties of various methods and improving landslide predictions.

Background: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an imaging technique which helps in visualizing and quantifying perfusion&mdash, one of the most important indicators of an organ&rsquo, s state. This paper focuses on perfusion and filtration in the kidney, whose performance directly influences versatile functions of the body. In clinical practice, kidney function is assessed by measuring glomerular filtration rate (GFR). Estimating GFR based on DCE-MRI data requires the application of an organ-specific pharmacokinetic (PK) model. However, determination of the model parameters, and thus the characterization of GFR, is sensitive to determination of the arterial input function (AIF) and the initial choice of parameter values. Methods: This paper proposes a multi-layer perceptron network for PK model parameter determination, in order to overcome the limitations of the traditional model&rsquo, s optimization techniques based on non-linear least-squares curve-fitting. As a reference method, we applied the trust-region reflective algorithm to numerically optimize the model. The effectiveness of the proposed approach was tested for 20 data sets, collected for 10 healthy volunteers whose image-derived GFR scores were compared with ground-truth blood test values. Results: The achieved mean difference between the image-derived and ground-truth GFR values was 2.35 mL/min/1.73 m2, which is comparable to the result obtained for the reference estimation method (&minus, 5.80 mL/min/1.73 m2). Conclusions: Neural networks are a feasible alternative to the least-squares curve-fitting algorithm, ensuring agreement with ground-truth measurements at a comparable level. The advantages of using a neural network are twofold. Firstly, it can estimate a GFR value without the need to determine the AIF for each individual patient. Secondly, a reliable estimate can be obtained, without the need to manually set up either the initial parameter values or the constraints thereof.

Dementia has a large negative impact on the global healthcare and society. Diagnosis is rather challenging as there is no standardised test. The purpose of this paper is to conduct an analysis on ADNI data and determine its effectiveness for building classification models to differentiate the categories Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Dementia (DEM), based on tuning three Deep Learning models: two Multi-Layer Perceptron (MLP1 and MLP2) models and a Convolutional Bidirectional Long Short-Term Memory (ConvBLSTM) model. The results show that the MLP1 and MLP2 models accurately distinguish the DEM, MCI and CN classes, with accuracies as high as 0.86 (SD 0.01). The ConvBLSTM model was slightly less accurate but was explored in view of comparisons with the MLP models, and for future extensions of this work that will take advantage of time-related information. Although the performance of ConvBLSTM model was negatively impacted by a lack of visit code data, opportunities were identified for improvement, particularly in terms of pre-processing.

Landslide susceptibility mapping is well recognized as an essential element in supporting decision-making activities for preventing and mitigating landslide hazards as it provides information regarding locations where landslides are most likely to occur. The main purpose of this study is to produce a landslide susceptibility map of Mt. Umyeon in Korea using an artificial neural network (ANN) involving the factor selection method and various non-linear activation functions. A total of 151 historical landslide events and 20 predisposing factors consisting of Geographic Information System (GIS)-based morphological, hydrological, geological, and land cover datasets were constructed with a resolution of 5 x 5 m. The collected datasets were applied to information gain ratio analysis to confirm the predictive power and multicollinearity diagnosis to ensure the correlation of independence among the landslide predisposing factors. The best 11 predisposing factors that were selected in this study were randomly divided into a 70:30 ratio for training and validation datasets, which were used to produce ANN-based landslide susceptibility models. The ANN model used in this study had a multi-layer perceptron (MLP) structure consisting of an input layer, one hidden layer, and an output layer. In the output layer, the logistic sigmoid function was used to represent the result value within the range of 0 to 1, and six non-linear activation functions were used for the hidden layer. The performance of the landslide susceptibility models was evaluated using the receiver operating characteristic curve, Kappa index, and five statistical indices (sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV)) with the training dataset. In addition, the landslide susceptibility models were validated using the aforementioned measures with the validation dataset and were compared using the Friedman test to check the significant differences among the six developed models. The optimal number of neurons was determined based on the aforementioned performance evaluation and validation results. Overall, the model with the best performance was the MLP model with the logistic sigmoid activation function in the output layer and the hyperbolic tangent sigmoid activation function with five neurons in the hidden layer. The validation results of the best model showed a sensitivity of 82.61%, specificity of 78.26%, accuracy of 80.43%, PPV of 79.17%, NPV of 81.82%, a Kappa index of 0.609, and AUC of 0.879. The results of this study highlight the effectiveness of selecting an optimal MLP model structure for shallow landslide susceptibility mapping using an appropriate predisposing factor section method.

One of the main concerns of industry is energy efficiency, in which the paradigm of Industry 4.0 opens new possibilities by facing optimization approaches using data-driven methodologies. In this regard, increasing the efficiency of industrial refrigeration systems is an important challenge, since this type of process consume a huge amount of electricity that can be reduced with an optimal compressor configuration. In this paper, a novel data-driven methodology is presented, which employs self-organizing maps (SOM) and multi-layer perceptron (MLP) to deal with the (PLR) issue of refrigeration systems. The proposed methodology takes into account the variables that influence the system performance to develop a discrete model of the operating conditions. The aforementioned model is used to find the best PLR of the compressors for each operating condition of the system. Furthermore, to overcome the limitations of the historical performance, various scenarios are artificially created to find near-optimal PLR setpoints in each operation condition. Finally, the proposed method employs a forecasting strategy to manage the compressor switching situations. Thus, undesirable starts and stops of the machine are avoided, preserving its remaining useful life and being more efficient. An experimental validation in a real industrial system is performed in order to validate the suitability and the performance of the methodology. The proposed methodology improves refrigeration system efficiency up to 8%, depending on the operating conditions. The results obtained validates the feasibility of applying data-driven techniques for the optimal control of refrigeration system compressors to increase its efficiency. The authors would like to thank the support of Corporación Alimentaria Guissona S.A. for providing access to their refrigeration system dataset and their expert advice.

In this paper, the urinary bladder cancer diagnostic method which is based on Multi-Layer Perceptron and Laplacian edge detector is presented. The aim of this paper is to investigate the implementation possibility of a simpler method (Multi-Layer Perceptron) alongside commonly used methods, such as Deep Learning Convolutional Neural Networks, for the urinary bladder cancer detection. The dataset used for this research consisted of 1997 images of bladder cancer and 986 images of non-cancer tissue. The results of the conducted research showed that using Multi-Layer Perceptron trained and tested with images pre- processed with Laplacian edge detector are achieving AUC value up to 0.99. When different image sizes are compared it can be seen that the best results are achieved if 50*50 and 100*100 images were used.

We propose a deep learning-based spike sorting method for extracellular recordings. For analysis of extracellular single unit activity, the process of detecting and classifying action potentials called &ldquo, spike sorting&rdquo, has become essential. This is achieved through distinguishing the morphological differences of the spikes from each neuron, which arises from the differences of the surrounding environment and characteristics of the neurons. However, cases of high structural similarity and noise make the task difficult. And for manual spike sorting, it requires professional knowledge along with extensive time cost and suffers from human bias. We propose a deep learning-based spike sorting method on extracellular recordings from a single electrode that is efficient, robust to noise, and accurate. In circumstances where labelled data does not exist, we created pseudo-labels through principal component analysis and K-means clustering to be used for multi-layer perceptron training and built high performing spike classification model. When tested, our model outperformed conventional methods by 2.1% on simulation data of various noise levels, by 6.0% on simulation data of various clusters count, and by 1.7% on in-vivo data. As a result, we showed that the deep learning-based classification can classify spikes from extracellular recordings, even showing high classification accuracy on spikes that are difficult even for manual classification.

A new method for computing fracture mechanics parameters using computational Eddy Current Modelling by Multi-layer Perceptron Neural Networks for detecting surface cracks. The method is based upon an inverse problem using an Artificial Neural Network (ANN) that simulates mapping between Eddy current signals and crack profiles. Simultaneous use of ANN by MLP can be very helpful for the localization and the shape classification of defects. On the other side, it can be described as the task of reconstructing the cracks and damage in the plate profile of an inspected specimen in order to estimate its material properties. This is accomplished by inverting eddy current probe impedance measurements that are recorded as a function of probe position, excitation frequency or both. In eddy current nondestructive evaluation, this is widely recognized as a complex theoretical problem whose solution is likely to have a significant impact on the detection of cracks in materials

Credit risk analysis is important for financial institutions that provide loans to businesses and individuals. Banks and other financial institutions generally face risks that are mostly of financial nature; hence, such institutions must balance risks and returns. Analyzing or determining risk levels involved in credits, finances, and loans can be performed through predictive analytic techniques, such as an extreme learning machine (ELM). In this work, we empirically evaluated the performance of an ELM for credit risk problems and compared it to naive Bayes, decision tree, and multi-layer perceptron (MLP). The comparison was conducted on the basis of a German credit risk dataset. The simulation results of statistical measures of performance corroborated that the ELM outperforms naive Bayes, decision tree, and MLP classifiers by 1.8248%, 16.6346%, and 5.8934%, respectively.

An accurate information on the amount and location of Land use and land cover (LULC) changes is necessary to develop and implement a sustainable-urban planning.This research investigates the potential of an integrated Multi-Layer Perceptron and Markov Chain Analysis (MLP-MCA) to map and accurately predict the future LULC change scenarios in Lagos Metropolitan Region of Nigeria. Multi-temporal LULC datasets derived from remotely sensed Landsat images from 1984, 2000 and 2015 were used for modeling, validation and prediction. Predicted LULC changes for 2030 and 2050 were performed based on the LULC map of 2015 using MLP-MCA method. The result reveals a significant expansion of built-up areas during the whole study period. Analysis of LULC distribution in Lagos metropolitan region shows that about 50% of urban land expansion happened beyond the administrative boundary of Lagos State during the period of 2000–2015. It is predicted that more than 75% of future urban growth will occur across the border of Lagos State, in the neighbouring Ogun State by 2050. These results imply that a strong and consistent collaboration between different states is crucial to establish an effective regional planning framework and ensure a proper planned growth of the metropolitan region.

Made available in DSpace on 2018-12-11T16:50:37Z (GMT). No. of bitstreams: 0 Previous issue date: 2017-01-01. Added 1 bitstream(s) on 2021-07-15T14:32:55Z : No. of bitstreams: 1 S0100-69162017000601116.pdf: 779517 bytes, checksum: 7079efe39dde309e2a179c01e8e7f59e (MD5) Evapotranspiration (ET) is the main component of water balance in agricultural systems and the most active variable of the hydrological cycle. In the literature, few studies have used the forecast the day before via Artificial Neural Networks (ANNs) for the northern region of São Paulo state, Brazil. Therefore, this aimed to predict the reference evapotranspiration for Jaboticabal, the major sugarcane-producing region of São Paulo state. We used a historical series of data on average air temperature, wind speed, net radiation, soil heat flux, and daily relative humidity from 2002 to 2012, for Jaboticabal, SP (Brazil). ET was estimated by Penman-Monteith method. To forecast reference evapotranspiration, we used a feed-forward Multi-Layer Perceptron (MLP), which is a traditional Artificial Neural Network. Numerous topologies and variations were tested between neurons in intermediate and outer layers until the most accurate were obtained. We separated 75% from data for network training (2002 to 2010) and 25% for testing (2011 to 2013). The criteria for assessing the ANN performance were accuracy, precision, and trend. ET could be accurately estimated with a day to spare at any time of the year, by means of artificial neural networks, and using only air temperature data as an input variable. São Paulo State University (Unesp) School of Agricultural and Veterinarian Sciences São Paulo State University (Unesp) School of Agricultural and Veterinarian Sciences