Deep Learning Artificial Neural Network Research Articles

Successive bootstrapping deep learning approach and airborne EM-borehole data fusion to understand salt water in the Mississippi River Valley Alluvial Aquifer

Increasing demands from agriculture and urbanization have decreased groundwater level and increased salinity worldwide. Better aquifer characterization and soil salinity mapping are important for proactive groundwater management. Airborne electromagnetic (AEM) is a powerful tool for aquifer characterization and salinity delineation. However, AEM needs to be interpreted with caution before being used for groundwater quality analysis. This study introduces a framework that utilizes the AEM data for both lithologic modeling and salinity delineation. A resistivity-to-lithology (R2L) model is developed to interpret AEM resistivity to lithology based a depth-dependent multi-resistivity thresholds. Then, a cokriging method is used to integrate AEM data from two different EM systems to predict resistivity at the aquifer. Finally, a resistivity-to-chloride concentration (R2C) model utilizes the resistivity model to estimate chloride concentrations at sand facies. A deep learning artificial neural network (DL-ANN) model is introduced with a successive bootstrapping approach to estimate total dissolved solids first and then use it together with resistivity data to estimate chloride concentration. The methodology was applied to delineating salinity plumes in the Mississippi River Valley alluvial aquifer (MRVA). This study found that the salinity distribution in MRVA is highly correlated with the Jurassic salt basin, salt domes, faulting, seismicity, and river water quality. The result indicates salinity upconing due to excessive pumping.

Code-Free Machine Learning Solutions for Microscopy Image Processing: Deep Learning.

In recent years, there has been a significant expansion in the realm of processing microscopy images, thanks to the advent of machine learning techniques. These techniques offer diverse applications for image processing. Currently, numerous methods are used for processing microscopy images in the field of biology, ranging from conventional machine learning algorithms to sophisticated deep learning artificial neural networks with millions of parameters. However, a comprehensive grasp of the intricacies of these methods usually necessitates proficiency in programming and advanced mathematics. In our comprehensive review, we explore various widely used deep learning approaches tailored for the processing of microscopy images. Our emphasis is on algorithms that have gained popularity in the field of biology and have been adapted to cater to users lacking programming expertise. In essence, our target audience comprises biologists interested in exploring the potential of deep learning algorithms, even without programming skills. Throughout the review, we elucidate each algorithm's fundamental concepts and capabilities without delving into mathematical and programming complexities. Crucially, all the highlighted algorithms are accessible on open platforms without requiring code, and we provide detailed descriptions and links within our review. It's essential to recognize that addressing each specific problem demands an individualized approach. Consequently, our focus is not on comparing algorithms but on delineating the problems they are adept at solving. In practical scenarios, researchers typically select multiple algorithms suited to their tasks and experimentally determine the most effective one. It is worth noting that microscopy extends beyond the realm of biology; its applications span diverse fields such as geology and material science. Although our review predominantly centers on biomedical applications, the algorithms and principles outlined here are equally applicable to other scientific domains. Furthermore, a number of the proposed solutions can be modified for use in entirely distinct computer vision cases.

Predictive analysis of terrorist activities in Thailand's Southern provinces: a deep learning approach

Terrorist activities have been on the rise globally, with Thailand experiencing significant challenges, particularly in its three southern border provinces. This study offers a comprehensive analysis aiming to predict forthcoming terrorist events in these provinces. We employed historical data, categorized into nine groups based on military expert recommendations, to train our prediction model. This research tested the prediction capabilities of various methodologies, including decision trees, naïve Bayesian learning techniques, and deep learning artificial neural networks. Notably, the deep neural network emerged as the superior predictive tool, achieving an impressive accuracy of 98.21% and a root mean square error (RMSE) of 0.59%. The primary anticipated events include bombings, shootings, assaults, and acts of vandalism. Our findings also revealed that Pattani Province was the most affected, accounting for 45% of incidents. Specific districts, such as Panare and Yarang, exhibited high crime rates of 40% and 36.84%, respectively. Yala Province, particularly Bannang Sata District, was identified as the hotspot for shooting incidents, with a rate of 34%.

Machine Learning-Based Lithological Mapping from ASTER Remote-Sensing Imagery

Accurately mapping lithological features is essential for geological surveys and the exploration of mineral resources. Remote-sensing images have been widely used to extract information about mineralized alteration zones due to their cost-effectiveness and potential for being widely applied. Automated methods, such as machine-learning algorithms, for lithological mapping using satellite imagery have also received attention. This study aims to map lithologies and minerals indirectly through machine-learning algorithms using advanced spaceborne thermal emission and reflection radiometer (ASTER) remote-sensing data. The capabilities of several machine-learning (ML) algorithms were evaluated for lithological mapping, including random forest (RF), support vector machine (SVM), gradient boosting (GB), extreme gradient boosting (XGB), and a deep-learning artificial neural network (ANN). These methods were applied to ASTER imagery of the Sar-Cheshmeh copper mining region of Kerman Province, in southern Iran. First, several spectral features that were extracted from ASTER bands were used as input data. Second, correlation coefficients between the original spectral bands and features were extracted. The importance of the random forest features (RF’s feature importance) was subsequently computed, and features with less importance were removed. Finally, the remained features were given to the models as input data in the second scenario. Accuracy assessments were performed for lithological classes in the study region, including Sar-Cheshmeh porphyry, quartz eye, late fine porphyry, hornblende dike, granodiorite, feldspar dike, biotite dike, andesite, and alluvium. The overall accuracy results of lithological mapping showed that ML-based algorithms without feature extraction have the highest accuracy. The overall accuracy percentages for ML-based algorithms without conducting feature extraction were 84%, 85%, 80%, 82%, and 80% for RF, SVM, GB, XGB, and ANN, respectively. The results of this study would be of great interest to geologists for lithological mapping and mineral exploration, particularly for selecting appropriate ML-based techniques to be implemented in similar regions.

Automated Detection of Abnormal Optical Coherence Tomography B-scans Using a Deep Learning Artificial Intelligence Neural Network Platform.

Automated Detection of Abnormal Optical Coherence Tomography B-scans Using a Deep Learning Artificial Intelligence Neural Network Platform.

Semantic speech analysis using machine learning and deep learning techniques: a comprehensive review

AbstractHuman cognitive functions such as perception, attention, learning, memory, reasoning, and problem-solving are all significantly influenced by emotion. Emotion has a particularly potent impact on attention, modifying its selectivity in particular and influencing behavior and action motivation. Artificial Emotional Intelligence (AEI) technologies enable computers to understand a user's emotional state and respond appropriately. These systems enable a realistic dialogue between people and machines. The current generation of adaptive user interference technologies is built on techniques from data analytics and machine learning (ML), namely deep learning (DL) artificial neural networks (ANN) from multimodal data, such as videos of facial expressions, stance, and gesture, voice, and bio-physiological data (such as eye movement, ECG, respiration, EEG, FMRT, EMG, eye tracking). In this study, we reviewed existing literature based on ML and data analytics techniques being used to detect emotions in speech. The efficacy of data analytics and ML techniques in this unique area of multimodal data processing and extracting emotions from speech. This study analyzes how emotional chatbots, facial expressions, images, and social media texts can be effective in detecting emotions. PRISMA methodology is used to review the existing survey. Support Vector Machines (SVM), Naïve Bayes (NB), Random Forests (RF), Recurrent Neural Networks (RNN), Logistic Regression (LR), etc., are commonly used ML techniques for emotion extraction purposes. This study provides a new taxonomy about the application of ML in SER. The result shows that Long-Short Term Memory (LSTM) and Convolutional Neural Networks (CNN) are found to be the most useful methodology for this purpose.

Evaluation of Feature Selection Methods in Estimation of Precipitation Based on Deep Learning Artificial Neural Networks

Precipitation is the most important element of the water cycle and an indispensable element of water resources management. This paper’s aim is to model the monthly precipitation in 8 precipitation observation stations in the province of Hamadan, Iran. The effects and role of different feature weights pre-processing methods (Weight by deviation, Weight by PCA, Weight by correlation and Weight by Support Vector Machine) on artificial intelligence modeling were investigated. Deep learning method based on a multi-layer feed-forward artificial neural network that is trained with Stochastic Gradient Descent using back-propagation (DL-SGD) and Convolutional Neural Networks (CNN) modelling were applied. The precipitation of each station is modeled using the precipitation values of the other stations. The best result, among all scenarios, at the Vasaj station according to the DL-SGD method (CC = 0.9845, NS = 0.9543 and RMSE = 10.4169 mm) and at the Varayineh station according to the CNN method (CC = 0.9679, NS = 0.9362 and RMSE = 16.0988 mm) were estimated.

Classification of yellow rust of wheat from Sentinel-2 satellite imagery using deep learning artificial neural network

Classification of yellow rust of wheat from Sentinel-2 satellite imagery using deep learning artificial neural network

Time resolved study of temperature sensing using Gd2O3:Er,Yb: deep learning approach

This paper examines the potential applications of machine learning algorithms in the analysis of optical spectra from Gd2O3:Er,Yb thermophosphor. The material was synthesized using the solution combustion method. For data acquisition, we employed pulsed laser diode excitation at 980 nm and utilized a streak camera with a spectrograph to obtain time-resolved spectral data of the optical emission from Gd2O3:Er,Yb. To ensure data consistency and facilitate visualization, we employed principal component analysis and Uniform Manifold Approximation and Projection clustering. Our findings demonstrate that, instead of the conventional approach of identifying spectral peaks and calculating intensity ratios, it is feasible to train computer software to recognize time-resolved spectra associated with different temperatures of the thermophosphor. Through our analysis, we have successfully devised a technique for remote temperature estimation by leveraging deep learning artificial neural networks.

A posterior hybrid ML optimization to analyze the relationship between high temperature rheological factors of the Superpave PG and improved PG + asphalt specifications

This study investigated the relationship between the parameters of the Superpave PG asphalt classification method and the improved MCSR PG-Plus asphalt classification method with two hybrid fuzzy models based on deep learning artificial neural network (ANN) and Support Vector Machine (SVM). For this purpose, virgin asphalt was modified with four well-known polymers namely, styrene butadiene styrene (SBS), styrene butadiene rubber (SBR), ethylene vinyl acetate (EVA) and high-density polyethylene (HDPE) at various modification percentages. In order to collect data, a total of 294 high temperature rheological experiments were carried out on neat and modified samples. Complex modulus (), phase angle (), percent recovery () and the non-recoverable creep compliance () were determined at five different temperatures to construct dataset. The relationship between, and factors two models were utilized namely ANN_FL and SVM_FL. Results showed that the ANN based model outperforms the SVM based hybrid model with a value of 0.96 R2 and 0.83 RMSE. The uncertain situation behind road traffic classification were interpreted with the help of FL. Regarding the experimental procedure and machine learning (ML) model results, it has been concluded that the all ML methods were represented the meaningful relation between Superpave PG and MSCR PG-Plus asphalt classification methods.

Model construction and optimization for raising the concentration of industrial bioethanol production by using a data-driven ANN model

This work aims to model and predict the bioethanol produced from a conventional fermentation process. An industrial dataset was obtained from a sugar mill in India. These datasets comprised a total of 1300 experimental values acquired from a total 100 days of production of the sugar mill in the year 2021. Using this data, a framework based on deep learning Artificial Neural Network (ANN) technique model was developed and validated with the test data. Specifically, the normalized dataset was passed through an ANN model consisting of one input layer, two hidden layers and one output layer, and the percent model error calculated by using average absolute deviation metric and was found to be 4.48 and 1.99% for training and testing data, respectively. The optimization of the process variables was performed for the first time using a data synthesis technique in which the normalized dataset was first synthesized and then passed through an ANN model to get an optimized input variable set for an increase in bioethanol concentration (BEC) in the final product by 1°GL. The operating parameters which significantly influenced the BEC are concentration of cell in pre-fermentation (PFM), water fermentation pH (WFMpH), and water fermentation hardness (WFH). An increase of 8.45% in BEC was obtained for Sugar mill, India.

Exploring Influential Factors with Structural Equation Modeling–Artificial Neural Network to Involve Medicine Users in Home Medicine Waste Management and Preventing Pharmacopollution

The appropriate management of home medical waste is of paramount importance due to the adverse consequences that arise from improper handling. Incorrect disposal practices can lead to pharmacopollution, which poses significant risks to environmental integrity and human well-being. Involving medicine users in waste management empowers them to take responsibility for their waste and make informed decisions to safeguard the environment and public health. The objective of this research was to contribute to the prevention of pharmacopollution by identifying influential factors that promote responsible disposal practices among medicine users. Factors such as attitude, marketing campaigns, collection points, safe handling, medical prescription, package contents, and public policies and laws were examined. To analyze the complex relationships and interactions among these factors, a dual-staged approach was employed, utilizing advanced statistical modeling techniques and deep learning artificial neural network algorithms. Data were collected from 952 respondents in Pernambuco, a state in northeastern Brazil known for high rates of pharmacopollution resulting from improper disposal of household medical waste. The results of the study indicated that the propositions related to safety in handling and medical prescription were statistically rejected in the structural equation modeling (SEM) model. However, in the artificial neural network (ANN) model, these two propositions were found to be important predictors of cooperative behavior, highlighting the ANN’s ability to capture complex, non-linear relationships between variables. The findings emphasize the significance of user cooperation and provide insights for the development of effective strategies and policies to address pharmacopollution.

An Explainable Machine-Learning Model for Compensatory Reserve Measurement: Methods for Feature Selection and the Effects of Subject Variability.

Tracking vital signs accurately is critical for triaging a patient and ensuring timely therapeutic intervention. The patient's status is often clouded by compensatory mechanisms that can mask injury severity. The compensatory reserve measurement (CRM) is a triaging tool derived from an arterial waveform that has been shown to allow for earlier detection of hemorrhagic shock. However, the deep-learning artificial neural networks developed for its estimation do not explain how specific arterial waveform elements lead to predicting CRM due to the large number of parameters needed to tune these models. Alternatively, we investigate how classical machine-learning models driven by specific features extracted from the arterial waveform can be used to estimate CRM. More than 50 features were extracted from human arterial blood pressure data sets collected during simulated hypovolemic shock resulting from exposure to progressive levels of lower body negative pressure. A bagged decision tree design using the ten most significant features was selected as optimal for CRM estimation. This resulted in an average root mean squared error in all test data of 0.171, similar to the error for a deep-learning CRM algorithm at 0.159. By separating the dataset into sub-groups based on the severity of simulated hypovolemic shock withstood, large subject variability was observed, and the key features identified for these sub-groups differed. This methodology could allow for the identification of unique features and machine-learning models to differentiate individuals with good compensatory mechanisms against hypovolemia from those that might be poor compensators, leading to improved triage of trauma patients and ultimately enhancing military and emergency medicine.

Mechanical Strength Estimation of Self-Compacting Geopolymer Concrete using ReLU based Deep Neural Network

ABSTRACT A deep learning artificial neural network model developed in Tensorflow using the ReLU function is presented in this paper to determine the effect of nine different input parameters on the mechanical strength of self-compacting geopolymer concrete (SGC). With the application of the above model, it has been observed that the convergence outcome of our model is predicted with minimum error. The novelty of our model is the ReLU function which improves the accuracy of the results. Our study presents a systematic investigation of the compressive strength, flexural strength, and tensile strengths of SGC depending upon nine vital parameters, such as GFS, Fly ash, NaOH, Na2SiO3 content, Age of specimens, Slump Value, T50, L Box and J Ring value as input. A large number of experiments were conducted to prepare a comprehensive database of the mechanical strength of Flyash-GFS-based SGC. The database has a total of 396 samples which were collected from 132 distinct mixtures, where the minimum and maximum compressive strength value is 7.7 Mpa and 66.7 Mpa, respectively. For the prediction based on deep learning, authors have performed an adequate number of iterations for both training and testing using error estimation parameters such as mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The error parameter values for the compressive strength of SGC are 2.42, 2.94 and 1.07, respectively, for MAE, RMSE and MSE. The other mechanical properties and their error parameter have also been thoroughly evaluated in our work.

A data-driven intelligent decision support system that combines predictive and prescriptive analytics for the design of new textile fabrics

In this paper, we propose an Intelligent Decision Support System (IDSS) for the design of new textile fabrics. The IDSS uses predictive analytics to estimate fabric properties (e.g., elasticity) and composition values (% cotton) and then prescriptive techniques to optimize the fabric design inputs that feed the predictive models (e.g., types of yarns used). Using thousands of data records from a Portuguese textile company, we compared two distinct Machine Learning (ML) predictive approaches: Single-Target Regression (STR), via an Automated ML (AutoML) tool, and Multi-target Regression, via a deep learning Artificial Neural Network. For the prescriptive analytics, we compared two Evolutionary Multi-objective Optimization (EMO) methods (NSGA-II and R-NSGA-II) when optimizing 100 new fabrics, aiming to simultaneously minimize the physical property predictive error and the distance of the optimized values when compared with the learned input space. The two EMO methods were applied to design of 100 new fabrics. Overall, the STR approach provided the best results for both prediction tasks, with Normalized Mean Absolute Error values that range from 4% (weft elasticity) to 11% (pilling) in terms of the fabric properties and a textile composition classification accuracy of 87% when adopting a small tolerance of 0.01 for predicting the percentages of six types of fibers (e.g., cotton). As for the prescriptive results, they favored the R-NSGA-II EMO method, which tends to select Pareto curves that are associated with an average 11% predictive error and 16% distance.

Алгоритмизация задачи видеоскопического контроля состояния стальных канатов

The paper considers the problem of monitoring the technical state of steel ropes used in industrial and civil installations, such as elevators, cable cars, lifts, etc. To date, the assessment of the state of steel ropes and the safety of their operation is carried out mainly through visual-instrumental control, which is long in time and subject to the influence of the human factor, which determines the relevance of the task of automating this process using computer technology and artificial intelligence methods in order to improve the quality of the assessment, reducing the check interval, detecting defects in steel ropes at an early stage. The article proposes two approaches to the algorithmizing of the problem of videoscopic control of the state of steel ropes using computer vision technologies, based on software modeling of the logic of visual analysis and machine learning methods, such as deep learning artificial neural networks. The authors have developed algorithms for automatic detection of the main types of defects in images of the surface of steel ropes: increase/decrease in diameter, deformation in the form of rope, breaks in the outer wires, thermal and electric damage. The paper presents the results of preliminary testing of the developed algorithms and programs, the composition and methods for determining the main indicators for evaluating their effectiveness are proposed.

Remembrance of things perceived: Adding thalamocortical function to artificial neural networks.

Recent research has illuminated the complexity and importance of the thalamocortical system but it has been difficult to identify what computational functions it performs. Meanwhile, deep-learning artificial neural networks (ANNs) based on bio-inspired models of purely cortical circuits have achieved surprising success solving sophisticated cognitive problems associated historically with human intelligence. Nevertheless, the limitations and shortcomings of artificial intelligence (AI) based on such ANNs are becoming increasingly clear. This review considers how the addition of thalamocortical connectivity and its putative functions related to cortical attention might address some of those shortcomings. Such bio-inspired models are now providing both testable theories of biological cognition and improved AI technology, much of which is happening outside the usual academic venues.

Automatic Generation of Literary Sentences in French

In this paper, we describe a model for the automatic generation of literary sentences in French. Although there has been much recent effort directed towards automatic text generation in general, the generation of creative, literary sentences that is not restricted to a specific genre, which we approached in this work, is a difficult task that is not commonly treated in the scientific literature. In particular, our present model has not been previously applied to the generation of sentences in the French language. Our model was based on algorithms that we previously used to generate sentences in Spanish and Portuguese and on a new corpus, which we constructed and present here, consisting of literary texts in French, called MegaLitefr. Our automatic text generation algorithm combines language models, shallow parsing, the canned text method, and deep learning artificial neural networks. We also present a manual evaluation protocol that we propose and implemented to assess the quality of the artificial sentences generated by our algorithm, by testing if they fulfil four simple criteria. We obtained encouraging results from the evaluators for most of the desired features of our artificially generated sentences.

Prognostic Prediction of Cancer Based on Radiomics Features of Diagnostic Imaging: The Performance of Machine Learning Strategies.

Tumor phenotypes can be characterized by radiomics features extracted from images. However, the prediction accuracy is challenged by difficulties such as small sample size and data imbalance. The purpose of the study was to evaluate the performance of machine learning strategies for the prediction of cancer prognosis. A total of 422 patients diagnosed with non-small cell lung carcinoma (NSCLC) were selected from The Cancer Imaging Archive (TCIA). The gross tumor volume (GTV) of each case was delineated from the respective CT images for radiomic features extraction. The samples were divided into 4 groups with survival endpoints of 1 year, 3 years, 5 years, and 7 years. The radiomic image features were analyzed with 6 different machine learning methods: decision tree (DT), boosted tree (BT), random forests (RF), support vector machine (SVM), generalized linear model (GLM), and deep learning artificial neural networks (DL-ANNs) with 70:30 cross-validation. The overall average prediction performance of the BT, RF, DT, SVM, GLM and DL-ANNs was AUC with 0.912, 0.938, 0.793, 0.746, 0.789 and 0.705 respectively. The RF and BT gave the best and second performance in the prediction. The DL-ANN did not show obvious advantage in predicting prognostic outcomes. Deep learning artificial neural networks did not show a significant improvement than traditional machine learning methods such as random forest and boosted trees. On the whole, the accurate outcome prediction using radiomics serves as a supportive reference for formulating treatment strategy for cancer patients.

An Intrusion Detection Mechanism for MANETS based on Deep Learning Artificial Neural Networks (ANNS)

Mobile Ad-hoc Network (MANET) is a distributed, decentralized network of wireless portable nodes connecting directly without any fixed communication base station or centralized administration. Nodes in MANET move continuously in random directions and follow an arbitrary manner, which presents numerous challenges to these networks and make them more susceptible to different security threats. Due to this decentralized nature of their overall architecture, combined with the limitation of hardware resources, those infrastructure-less networks are more susceptible to different security attacks such as black hole attack, network partition, node selfishness, and Denial of Service (DoS) attacks. This work aims to present, investigate, and design an intrusion detection predictive technique for Mobile Ad hoc networks using deep learning artificial neural networks (ANNs). A simulation-based evaluation and a deep ANNs modelling for detecting and isolating a Denial of Service (DoS) attack are presented to improve the overall security level of Mobile ad hoc networks.