Multilayer Perceptron Technique Research Articles

Prognosis of Tissue Stiffness Through Multilayer Perceptron Technique With Adaptive Learning Rate in Minimal Invasive Surgical Procedures

Prognosis of Tissue Stiffness Through Multilayer Perceptron Technique With Adaptive Learning Rate in Minimal Invasive Surgical Procedures

AOSMA-MLP: A Novel Method for Hybrid Metaheuristics Artificial Neural Networks and a New Approach for Prediction of Geothermal Reservoir Temperature

To ascertain the optimal and most efficient reservoir temperature of a geothermal source, long-term field studies and analyses utilizing specialized devices are essential. Although these requirements increase project costs and induce delays, utilizing machine learning techniques based on hydrogeochemical data can minimize losses by accurately predicting reservoir temperatures. In recent years, applying hybrid methods to real-world challenges has become increasingly prevalent over traditional machine learning methodologies. This study introduces a novel machine learning approach, named AOSMA-MLP, integrating the adaptive opposition slime mould algorithm (AOSMA) and multilayer perceptron (MLP) techniques, specifically designed for predicting the reservoir temperature of geothermal resources. Additionally, this work compares the basic artificial neural network and widely recognized algorithms in the literature, such as the whale optimization algorithm, ant lion algorithm, and SMA, under equal conditions using various evaluation regression metrics. The results demonstrated that AOSMA-MLP outperforms basic MLP and other metaheuristic-based MLPs, with the AOSMA-trained MLP achieving the highest performance, indicated by an R2 value of 0.8514. The proposed AOSMA-MLP approach shows significant potential for yielding effective outcomes in various regression problems.

Measurement of 3D Wrist Angles by Combining Textile Stretch Sensors and AI Algorithm.

The wrist is one of the most complex joints in our body, composed of eight bones. Therefore, measuring the angles of this intricate wrist movement can prove valuable in various fields such as sports analysis and rehabilitation. Textile stretch sensors can be easily produced by immersing an E-band in a SWCNT solution. The lightweight, cost-effective, and reproducible nature of textile stretch sensors makes them well suited for practical applications in clothing. In this paper, wrist angles were measured by attaching textile stretch sensors to an arm sleeve. Three sensors were utilized to measure all three axes of the wrist. Additionally, sensor precision was heightened through the utilization of the Multi-Layer Perceptron (MLP) technique, a subtype of deep learning. Rather than fixing the measurement values of each sensor to specific axes, we created an algorithm utilizing the coupling between sensors, allowing the measurement of wrist angles in three dimensions. Using this algorithm, the error angle of wrist angles measured with textile stretch sensors could be measured at less than 4.5°. This demonstrated higher accuracy compared to other soft sensors available for measuring wrist angles.

Early Detection of Cardiovascular Disease Utilizing Machine Learning Techniques: Evaluating the Predictive Capabilities of Seven Algorithms

Heart disease is the leading cause of death in developed countries, as it causes many deaths annually. Despite the availability of effective treatments, heart disease remains a significant challenge to public health, so early detection is essential in enhancing patient outcomes and reducing mortality. Artificial intelligence seeks to help physicians make the right decisions about a patient's health condition. In this regard, the authors decided to utilize machine learning techniques (k-nearest neighbor, decision tree, linear regression, support vector machine, naïve bayes, multilayer perceptron, random forest) to contribute to the classification of the heart disease dataset, where it is determined whether a person is suffering or not. After that, the execution of all techniques will be measured, and the accuracy of each technique will be compared to determine the most suitable performer. The public dataset is organized from the UC Irvine machine learning repository and have significantly different characteristics. The dataset will be divided such that 80% of the data is designated for training and 20% is designated for testing. This article concluded that the adequate performance is for the multilayer perceptron technique, as it gained an accuracy of more than 88%, while the poor performance is for the decision tree technique, as it gained an accuracy of more than 79%.

Feasibility of Six Metaheuristic Solutions for Estimating Induction Motor Reactance

Industry is the primary application for induction machines. As such, it is essential to calculate the induction devices’ electrical properties accurately. With DC testing, no-load rotor tests, and locked rotor tests, one may empirically evaluate the electrical variables of induction motors. These tests are expensive and difficult to conduct, however. The information supplied by machine makers can also be used to accurately approximate the equivalent variables of the circuits in induction machines. This article has successfully predicted motor reactance (Xm) for both double- and single-cage models using artificial neural networks (ANN). Although ANNs have been investigated in the literature, the ANN structures were trained to use unmemorized training. Besides ANN, six other approaches have been suggested to address this issue: heap-based optimization (HBO), leagues championship algorithm (LCA), multi-verse optimization (MVO), osprey optimization algorithm (OOA), cuckoo optimization algorithm (COA), and sooty tern optimization algorithm (STOA). The efficaciousness of the suggested approaches was compared with each another. Regarding the obtained outcomes, the suggested MVO- multi-layer perceptron (MLP) technique performed better than the other five methods regarding reactance prediction, with R2 of 0.99598 and 0.9962, and RMSE of 20.31492 and 20.80626 in the testing and training phases, respectively. For the projected model, the suggested ANNs have produced great results. The novelty lies in the mentioned methods’ ability to tackle the complexities and challenges associated with induction motor reactance optimization, providing innovative approaches to finding optimal or near-optimal solutions. As researchers continue to explore and refine these techniques, their impact on motor design and efficiency will likely grow, driving advancements in electrical engineering.

Reconstructed Graph Neural Network With Knowledge Distillation for Lightweight Anomaly Detection.

The proliferation of Internet-of-Things (IoT) technologies in modern smart society enables massive data exchange for offering intelligent services. It becomes essential to ensure secure communications while exchanging highly sensitive IoT data efficiently, which leads to high demands for lightweight models or algorithms with limited computation capability provided by individual IoT devices. In this study, a graph representation learning model, which seamlessly incorporates graph neural network (GNN) and knowledge distillation (KD) techniques, named reconstructed graph with global-local distillation (RG-GLD), is designed to realize the lightweight anomaly detection across IoT communication networks. In particular, a new graph network reconstruction strategy, which treats data communications as nodes in a directed graph while edges are then connected according to two specifically defined rules, is devised and applied to facilitate the graph representation learning in secure and efficient IoT communications. Both the structural and traffic features are then extracted from the graph data and flow data respectively, based on the graph attention network (GAT) and multilayer perceptron (MLP) techniques. These can benefit the GNN-based KD process in accordance with the more effective feature fusion and representation, considering both structural and data levels across the dynamic IoT networks. Furthermore, a lightweight local subgraph preservation mechanism improved by the graph attention mechanism and downsampling scheme to better utilize the topological information, and a so-called global information alignment defined based on the self-attention mechanism to effectively preserve the global information, are developed and incorporated in a refined graph attention based KD scheme. Compared with four different baseline methods, experiments and evaluations conducted based on two public datasets demonstrate the usefulness and effectiveness of our proposed model in improving the efficiency of knowledge transfer with higher classification accuracy but lower computational load, which can be deployed for lightweight anomaly detection in sustainable IoT computing environments.

What determines the performance of pharmaceutical firms in India on account of COVID-19 interventions?

Purpose This paper aims to examine the impact of announcements related to 77 interventions by 46 listed Indian pharmaceutical firms during COVID-19 on the abnormal returns of the firms. The study also finds the variables which explain cumulative abnormal returns (CARs). Design/methodology/approach This study uses standard event methodology to compute the abnormal returns of firms announcing pharmaceutical interventions in 2020 and 2021. Besides this, the multilayer perceptron technique is applied to identify the variables that influence the CARs of the sample firms. Findings The results show the presence of abnormal returns of 0.64% one day before the announcement, indicating information leakage. The multilayer perceptron approach identifies five variables that explain the CARs of the sample companies, which are licensing_age, licensing_size, size, commercialization_age and approval_age. Originality/value The study contributes to the efficient market literature by revealing how firm-specific nonfinancial disclosures affect stock prices, especially in times of crisis like pandemics. Prior research focused on determining the effect of COVID-19 variables on abnormal returns. This is the first research to use artificial neural networks to determine which firm-specific variables and pharmaceutical interventions can influence CARs.

Cyber Threat Detection Based on Artificial Neural Networks

Abstract: Finding an automated method for detecting cyber-attacks is one of the biggest problems in cybersecurity. We describe an artificial intelligence (AI) method based on deep learning for detecting cyber threats. The suggested solution uses a deep attempting to learn monitoring method to improve cyber-threat identification by breaking down a large volume of recorded security events into event profiles. We created an AI-SIEM system that combines event profiles for data pretreatment with several multilayer perceptron techniques, such as FCNN, CNN, and LSTM. The approach focuses on separating real positive warnings from misdiagnosis alerts to assist experts in quickly responding to cyber-attacks. We carried out tests utilising the five traditional machine-learning techniques to assess the comparison study with existing approaches (SVM, k-NN, RF, NB, and DT). The experimental findings of this study confirm that our suggested methods may be used as studying models for activity recognition and demonstrate that, when used in the real life, they outperform traditional auto techniques.

Evaluation of the global solar irradiation from the artificial neural network technique

In this study, many experiments were carried out to assess the influence of the some input parameters on performance of the multilayer perceptron techniques, which is architectures one of the artificial neural network (ANN). To estimate the daily global solar irradiation (GSI) on horizontal surface, we have developed eight models by using four weather input parameters collected from a radiometric station installed at Ghardaia site (southern of Algeria), such as sunshine duration, daily mean temperature, daily relative humidity, and Solar declination. In order to select the best configuration among the chooses combinations which provides a good accuracy, three statistical formulas (or statistical indicators) have been evaluated, such as the normalized root mean square errors, (nRMSE), normalized mean bias error (nMBE, and coefficient of determination R²). We noted that the ANN model provides best performance compared to the developed empirical models. results of the nMBE, nRMSE, and R² are about 0.048%, 4.422%, and 98.00%, for ANN and 0.0772%, 5.5381%, and 97.22% for the quadratic model. Moreover, it was proved that the sunshine duration is important parameter, for predicting the GSI.

K-Means Clustering and Multilayer Perceptron for Categorizing Student Business Groups

The research conducted in this study was driven by the East Java provincial government's requirement to assess the transaction levels of the Student Business Group (KUS) in the SMA Double Track program. These transaction levels are a basis for allocating supplementary financial aid to each business group. The system's primary objective is to assist the provincial government of East Java in making well-informed choices pertaining to the distribution of supplementary capital to the KUS. The classification technique employed in this study is the multilayer perceptron. However, the K-Means Clustering method is utilised to generate target data due to the limited availability during the classification process, which involves dividing the transaction level attributes into three distinct groups: (0) low transactions, (1) medium transactions, and (2) high transactions. The clustering process encompasses three distinct features: (1) income, (2) spending, and (3) profit. These three traits will be utilized as input data throughout the categorization procedure. The classification procedure employing the Multilayer Perceptron technique involved processing a dataset including 1383 data points. The training data constituted 80% of the dataset, while the remaining 20% was allocated for testing. In order to evaluate the efficacy of the constructed model, the training error was assessed using K-Fold cross-validation, yielding an average accuracy score of 0.92. In the present study, the categorization technique yielded an accuracy of 0.96. This model aims to classify scenarios when the dataset lacks prior target data.

Advanced Healthcare Analytics: Pneumonia Disease Classification Using Convolutional Neural Networks and Ensemble Learning

The need for this work arises from the persistent challenges in accurately classifying pneumonia disease. Existing methods, although valuable, have limitations in terms of precision, accuracy, recall, speed, and AUC, prompting the exploration of advanced healthcare analytics. The limitations of current approaches are evident in their suboptimal performance levels. These methods often struggle to achieve the precision and recall needed for reliable pneumonia classification, leading to misdiagnoses and delayed treatments. Additionally, their speed and AUC fall short of the ideal standards required for efficient disease detection. To address these issues, our paper presents an innovative approach process. We introduce a novel model that combines Convolutional Neural Networks (CNN) with Naive Bayes, Deep Forest, and Multilayer Perceptron techniques. This fusion of diverse methods capitalizes on their complementary strengths, enhancing the accuracy and robustness of pneumonia classification process. The advantages of our proposed model are multifold. Firstly, the CNN component leverages its deep learning capabilities to extract intricate features from medical images, improving the overall precision and recall. Secondly, the inclusion of Naive Bayes brings a probabilistic perspective, enhancing classification based on statistical likelihood. Thirdly, Deep Forest contributes with its ensemble learning prowess, adding another layer of accuracy to the model. Lastly, the Multilayer Perceptron serves as a flexible, non-linear classifier, fine-tuning the results. Our empirical results demonstrate the substantial impact of this work. When tested on diverse contextual datasets, our model exhibits significant improvements: a 4.9% increase in precision, a 5.5% boost in accuracy, a 4.5% rise in recall, a 3.9% enhancement in speed, and a 2.9% improvement in AUC compared to existing methods. These outcomes underscore the potential of our approach to revolutionize pneumonia disease classification in healthcare, ultimately leading to more accurate and timely diagnoses, which can significantly improve patient outcomes and reduce healthcare costs.

Creation of wildfire susceptibility maps in the Mediterranean Region (Turkey) using convolutional neural networks and multilayer perceptron techniques

Considering the natural disasters that have developed in the world in recent years, it is known that there is an increase in wildfire disasters with the effects of climate change. In this study, wildfire susceptible areas were determined in the provinces of Muğla, Antalya, Mersin, Adana, Osmaniye, and Hatay in the Mediterranean region (Turkey). Within the scope of this purpose, Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP) methods, the most widely used deep learning techniques in the literature in recent years, were preferred to create Wildfire susceptibility models. Seventeen environmental variables were used in the analyses, and these variables were grouped as topographic factors, anthropological and environmental factors, climatic factors, and vegetation factors. In addition, the number of fire inventory data has been balanced with the help of the Synthetic Minority Oversampling Technique (SMOTE) used to increase the model result performance of the scarce inventory data. In the maps obtained by CNN and MLP methods, 17% and 28% of the study area were determined as high and very high susceptible areas, respectively. The results demonstrated that the CNN model had superior performance in Wildfire susceptibility assessment with accuracy (%85.8), precision (%98.7), sensitivity (%85.5), F- Score (%91.6), and ROC curve (%78.6). This model was followed by the MLP model with slightly lower accuracy values, which indicates that the CNN models can reach considerably better prediction capability than the MLP models. Finally, the wildfire susceptibility maps produced by deep learning methods could aid decision-makers and government organizations in the Mediterranean region in preventing future natural disasters.

Classification of HEp-2 Staining Pattern Images Using Adapted Multilayer Perceptron Neural Network-Based Intra-Class Variation of Cell Shape.

There exists a growing interest from the clinical practice research communities in the development of methods to automate HEp-2 stained cells classification procedure from histopathological images. Challenges faced by these methods include variations in cell densities and cell patterns, overfitting of features, large-scale data volume and stained cells. In this paper, a multi-class multilayer perceptron technique is adapted by adding a new hidden layer to calculate the variation in the mean, scale, kurtosis and skewness of higher order spectra features of the cell shape information. The adapted technique is then jointly trained and the probability of classification calculated using a Softmax activation function. This method is proposed to address overfitting, stained and large-scale data volume problems, and classify HEp-2 staining cells into six classes. An extensive experimental analysis is studied to verify the results of the proposed method. The technique has been trained and tested on the dataset from ICPR-2014 and ICPR-2016 competitions using the Task-1. The experimental results have shown that the proposed model achieved higher accuracy of 90.3% (with data augmentation) than of 87.5% (with no data augmentation). In addition, the proposed framework is compared with existing methods, as well as, the results of methods using in ICPR2014 and ICPR2016 competitions.The results demonstrate that our proposed method effectively outperforms recent methods.

A Software Framework for Predicting the Maize Yield Using Modified Multi-Layer Perceptron

Predicting crop yields is one of agriculture’s most challenging issues. It is crucial in making national, provincial, and regional choices and estimates the government to meet the food demands of its citizens. Crop production is anticipated based on various factors such as soil conditions and meteorological, environmental, and crop variables. This study intends to develop an effective model that can accurately anticipate agricultural production in advance, assisting farmers in better planning. In the current study, the Crop Yield Prediction Dataset is normalized initially, and then feature engineering is performed to determine the significance of the feature in assessing the crop yield. Crop yield forecasting is performed using the Multi-Layer Perceptron model and the Spider Monkey Optimization method. The Multi-Layer Perceptron technique is efficient in dealing with the non-linear relations among the features in the data, and the Spider Monkey Optimization technique would assist in optimizing the corresponding feature weights. The current study uses data from the Food and Agriculture Organization and the World Data Bank to forecast maize yield in the Saudi Arabia region based on factors such as average temperature, average rainfall, and Hg/Ha production in past years. The suggested MLP-SMO model’s prediction effectiveness is being evaluated using several evaluation metrics such as Root-Mean-Square Error, R-Squared, Mean Absolute Error, and Mean Bias Error, where the model has outperformed in the prediction process with a Root-Mean-Square Error value of 0.11, which is lowest among all the techniques that are considered in the statical analysis in the current study.

An artificial neural network (ANN) model for publication bias: a machine learning-based study on PubMed meta-analyses

PurposeNo study has investigated the effects of different parameters on publication bias in meta-analyses using a machine learning approach. Therefore, this study aims to evaluate the impact of various factors on publication bias in meta-analyses.Design/methodology/approachAn electronic questionnaire was created according to some factors extracted from the Cochrane Handbook and AMSTAR-2 tool to identify factors affecting publication bias. Twelve experts were consulted to determine their opinion on the importance of each factor. Each component was evaluated based on its content validity ratio (CVR). In total, 616 meta-analyses comprising 1893 outcomes from PubMed that assessed the presence of publication bias in their reported outcomes were randomly selected to extract their data. The multilayer perceptron (MLP) technique was used in IBM SPSS Modeler 18.0 to construct a prediction model. 70, 15 and 15% of the data were used for the model's training, testing and validation partitions.FindingsThere was a publication bias in 968 (51.14%) outcomes. The established model had an accuracy rate of 86.1%, and all pre-selected nine variables were included in the model. The results showed that the number of databases searched was the most important predictive variable (0.26), followed by the number of searches in the grey literature (0.24), search in Medline (0.17) and advanced search with numerous operators (0.13).Practical implicationsThe results of this study can help clinical researchers minimize publication bias in their studies, leading to improved evidence-based medicine.Originality/valueTo the best of the author’s knowledge, this is the first study to model publication bias using machine learning.

Key predisposing factors and susceptibility assessment of landslides along the Yunnan–Tibet traffic corridor, Tibetan plateau: Comparison with the LR, RF, NB, and MLP techniques

The Yunnan–Tibet traffic corridor runs through the Three Rivers Region, southeastern Tibetan Plateau, which is characterized by high-relief topography and active tectonics, with favourable conditions for landslides. It is of great significance to identify the key predisposing factors of landslides and to reveal the landslide susceptibility in this area. A total of 2,308 landslides were identified as learning samples through remote sensing interpretation and detailed field surveys, and four machine learning algorithms involving logistic regression (LR), random forest (RF), naïve Bayes (NB) and multilayer perceptron (MLP) were compared to model the landslide susceptibility. Through the multicollinearity test, 13 influential factors were selected as conditioning factors. The area under the curve (AUC) values of LR, RF, NB and MLP models are .788, .918, .785 and .836 respectively, indicating that the four models have good or very good prediction accuracy in landslide susceptibility assessment along the Yunnan–Tibet traffic corridor. In addition, the elevation, slope, rainfall, distance to rivers, and aspect play a major role in landslide development in the study area. The susceptibility zoning map based on the best RF model shows that the areas with high susceptibility and very high susceptibility account for 12.24% and 6.72%, respectively, and are mainly distributed along the Jinsha River, the Lancang River and the G214 highway.

Detection of Breast Cancer Using Infrared Thermal Images for Improved Accuracy by Using Random Forest and Multilayer Perceptron

At the present time, breast cancer is one of the most often diagnosed forms of cancer in females. Mammography is the most common form of screening imaging used to identify breast cancer in its earlier stages. Nevertheless, thermal infrared pictures (thermography) can be utilized to detect lesions in dense breasts. In this study, the typical areas reflect warmer temperatures than malignant areas. In this study, we offer a unique approach for modeling the temperature variations in normal and abnormal breasts by combining the Random forest and Multilayer perceptron techniques. The project aims to study the accuracy, sensitivity, and specificity of the infrared breast cancer images using infrared thermal images using random forest and multilayer perceptron algorithms and comparing the accuracy, specificity, and sensitivity. Materials and Methods: The information for this study was s gained from thermal images from Visual labs DMR-IR. The samples were considered as (N=60) for Random Forest and (N= 60) for MultiLayer Perceptron. Novel Matlab software is used to calculate accuracy, specificity, and sensitivity. Results: The result demonstrates the accuracy of the thermal breast images using SPSS software. A statistically insignificant difference exists, with Random Forest accuracy (92.5%) with specificity (90%) and with sensitivity (95%) and demonstrated a better outcome in comparison with Multilayer Perceptron accuracy (90%), specificity (91.6%) and sensitivity (88.3%). Conclusion: Random Forest gives better accuracy, specificity, and sensitivity than Multilayer Perceptron to detect breast cancer.

Automatic Sentimental Analysis by Firefly with Levy and Multilayer Perceptron

The field of sentiment analysis (SA) has grown in tandem with the aid of social networking platforms to exchange opinions and ideas. Many people share their views and ideas around the world through social media like Facebook and Twitter. The goal of opinion mining, commonly referred to as sentiment analysis, is to categorise and forecast a target’s opinion. Depending on if they provide a positive or negative perspective on a given topic, text documents or sentences can be classified. When compared to sentiment analysis, text categorization may appear to be a simple process, but number of challenges have prompted numerous studies in this area. A feature selection-based classification algorithm in conjunction with the firefly with levy and multilayer perceptron (MLP) techniques has been proposed as a way to automate sentiment analysis (SA). In this study, online product reviews can be enhanced by integrating classification and feature election. The firefly (FF) algorithm was used to extract features from online product reviews, and a multi-layer perceptron was used to classify sentiment (MLP). The experiment employs two datasets, and the results are assessed using a variety of criteria. On account of these tests, it is possible to conclude that the FFL-MLP algorithm has the better classification performance for Canon (98% accuracy) and iPod (99% accuracy).

An Application of Feature Selection Methods to Compare the Performances of Classification Algorithms

In this study, it is aimed to determine fewer and significant variables with the help of feature selection methods among a large number of variables in the data discussed. Feature selection methods are effective methods that have great importance in statistics in recent years and provide great convenience to researchers. Depending on the technique used in the method, different numbers of variables are included in the model, but the correct classification rates may vary. In this context, being able to express the variables in a data set with a large number of variables of interest with a high classification percentage and fewer new variables makes positive contributions to issues such as time and cost. The variables in the data set discussed in this study were firstly analyzed with different feature selection methods and new data sets were created. Afterwards, these new data sets containing different numbers of variables were analyzed with different machine learning techniques and the best machine learning technique was determined. In this study, chronic kidney disease data were handled and the variables in the data set were classified with different feature selection methods. When the results of the study are examined, the highest classification rate with 99.75% was obtained from the correlation-based feature selection method, which includes the random forest and multilayer perceptron technique, and the filter method, which includes the k-nearest neighbor technique, with the same rate. The results of the study show that the percentage of correct classification obtained from this study is higher than that of other studies, when compared with other studies using the same dataset.

Deep learning based electricity demand forecasting to minimize the cost of energy imbalance: A real case application with some fortune 500 companies in Türkiye

In this study, the electricity demands of some Fortune 500 companies in Türkiye have been forecasted by using deep learning techniques. This is a quite harder problem than the forecasting of the aggregated electricity demand in which the negative and positive fluctuations are absorbed on paper. Forecasting of firm-level electricity demand is an important problem since it can help automating firms’ routine forecasting operations, reducing the electricity supply costs of the firms by improving the quality of the forecasts, and improving the quality of the electricity on the transmission network. Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) techniques have been preferred concerning the successful results in the literature. As the originality of this paper, the Multiple Seasonal-Trend Decomposition using Loess (MSTL) technique is used for the electricity demand forecasting problem for the first time. The obtained results showed that although it is simple to implement, MSTL outperforms MLP and LSTM for most of the firms operating in mass production form. It is seen that the complexity of the model does not always guarantee good results and simple methods sometimes can work well. Load balancing studies are also very important for the economic sustainability of the industry since the electricity price and imbalance penalty have extremely increased (i.e., 8 times in Türkiye) during the post-pandemic period. Therefore, the energy cost reduction potential of the companies has also been assessed. This study resulted in cost savings of approximately 378 minimum wages for the pilot company.