Automatic Hyperparameter Tuning Research Articles

Modified Cuttlefish Swarm Optimization with Machine Learning-Based Sustainable Application of Solid Waste Management in IoT

The internet of things (IoT) paradigm roles an important play in enhancing smart city tracking applications and managing city procedures in real time. The most important problem connected to smart city applications has been solid waste management, which can have adverse effects on society’s health and environment. Waste management has developed a challenge faced by not only evolving nations but also established and developed counties. Solid waste management is an important and stimulating problem for environments across the entire world. Therefore, there is the need to develop an effective technique that will remove these problems, or at least decreases them to a minimal level. This study develops a modified cuttlefish swarm optimization with machine learning-based solid waste management (MCSOML-SWM) in smart cities. The MCSOML-SWM technique aims to recognize different categories of solid wastes and enable smart waste management. In the MCSOML-SWM model, a single shot detector (SSD) model allows effectual recognition of objects. Then, a deep convolutional neural network-based MixNet model was exploited to produce feature vectors. Since trial-and-error hyperparameter tuning is a tedious process, the MCSO algorithm was applied for automated hyperparameter tuning. For accurate waste classification, the MCSOML-SWM technique applies support vector machine (SVM) in this study. A comprehensive set of simulations demonstrate the improved classification performance of the MCSOML-SWM model with maximum accuracy of 99.34%.

Vegetation Cover Type Classification Using Cartographic Data for Prediction of Wildfire Behaviour

Predicting the behaviour of wildfires can help save lives and reduce health, socioeconomic, and environmental impacts. Because wildfire behaviour is highly dependent on fuel type and distribution, their accurate estimation is paramount for accurate prediction of the fire propagation dynamics. This paper studies the effect of combining automated hyperparameter tuning with Bayesian optimisation and recursive feature elimination on the accuracy of three boosting (AdaB, XGB, CatB), two bagging (Random Forest, Extremely Randomised Trees), and three stacking ensemble models with respect to their ability to estimate the vegetation cover type from cartographic data. The models are trained on the University of California Irvine (UCI) cover type dataset using five-fold cross-validation. Feature importance scores are calculated and used in recursive feature elimination analysis to study the sensitivity of model accuracy to the different feature combinations. Our results indicate that the implemented fine-tuning procedure significantly affects the accuracy of all models investigated, with XGB achieving an overall accuracy of 97.1% slightly outperforming the others.

A Hybrid Deep Learning Model for Link Dynamic Vehicle Count Forecasting with Bayesian Optimization

The link dynamic vehicle count is a spatial variable that measures the traffic state of road sections, which reflects the actual traffic demand. This paper presents a hybrid deep learning method that combines the gated recurrent unit (GRU) neural network model with automatic hyperparameter tuning based on Bayesian optimization (BO) and the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) model. There are four steps in this hybrid approach. First, the ICEEMDAN is employed to decompose the link dynamic vehicle count time series data into several intrinsic components. Second, the components are predicted by the GRU model. At the same time, the Bayesian optimization method is utilized to automatically optimize the hyperparameters of the GRU model. Finally, the predicted subcomponents are reconstructed to obtain the final prediction results. The proposed hybrid deep learning method is tested on two roads of Hangzhou, China. Results show that, compared with the 12 benchmark models, the proposed hybrid deep learning model achieves the best performance in link dynamic vehicle count forecasting.

Automated Graph Neural Networks Accelerate the Screening of Optoelectronic Properties of Metal–Organic Frameworks

The numerous organic and inorganic components of metal-organic framework (MOF) materials provide intriguing optoelectronic properties. Accurately predicting the electronic structural properties of MOFs has become the main focus. This work establishes two graph neural network models, crystal graph convolutional neural networks and a materials graph network, for predicting the band gaps of more than 10 000 MOF structures and promotes to improve the prediction accuracy through automatic hyperparameter tuning algorithms. Subsequently, for exploring machine learning-assisted screening of MOFs for the broader electronic properties, the screened copper-based MOFs are compared with lead-based MAPbI3 solar cells with respect to the band gaps, densities of states, and charge density distributions, and the results have demonstrated that the overlap of the wave functions between the initial and final states of MOFs is weakened, which is conducive to the improvement of photoelectric performance. The chlorine doping strategy further enhances the advantage. The tuning of the machine learning model and hyperparameters and the doping strategy of halogen elements furnish empirical rules for the design of MOFs with excellent optoelectronic properties.

Diabetic Retinopathy Grading From Color Fundus Images: An Autotuned Deep Learning Approach

Diabetic Retinopathy (DR) is a consequence of long-term diabetes which affects the eyes. It causes affliction to the veins in the eyes causing raptures on the retina which can impact vision. If the condition is failed to be detected at an early stage, it can lead to complete vision loss. The conventional diagnosing cycle of DR using fundus images requires very skilled practitioners due to the minute nature of features of the anomalies which can even lead to misdiagnosis and is time consuming. Therefore, devising an automated method for the diagnosis of DR can assist individuals with diabetes to identify symptoms of DR at a very early stage. This research also encompasses the classification of the detected images into its corresponding 3 stages namely No Diabetic Retinopathy (No DR), Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR) that can greatly aid in monitoring the dynamics of the key features including lesions, hemorrhages, and density of blood vessels. Deep learning algorithms has gotten to become a well-known method that can accomplish a wide variety of classification tasks. However, most of these methods are only efficient in classifying the various stages of DR with low accuracies notably, for the early stages. The devised algorithm in this research uses enriched images processing techniques, automatic hyperparameter tuning and neural network training strategies to provide more emphasis on the minute features for better prediction. The algorithm was tested and compared with modified Resnet50, VGG16, Mobilenetv2, Inceptionv3 and InceptionResnetv2 which gave a classification accuracy of 94.7%, 86.1%, 85.8%, 85.3% and 87% respectively with corresponding detection accuracies of 99.8%, 94%, 94.2%, 94.9% and 98.2% respectively on a test set of 508 images. Using the proposed algorithm, the results indicate Resnet50 based network gave superior performance for both detection and classification tasks.

Effects of Automatic Hyperparameter Tuning on the Performance of Multi‐Variate Deep Learning‐Based Rainfall Nowcasting

AbstractRainfall nowcasting has become increasingly important as we move into an era where more and more storms are occurring in many countries as a result of climate change. Developing an accurate rainfall nowcasting model could provide insights into rainfall dynamics and ultimately could prevent significant damages. In this paper, deep neural networks (DNNs) and numerical weather predictions (NWPs) are applied for rainfall and runoff forecasting in an urban catchment with a complex drainage system. DNNs are among the most accurate models for rainfall nowcasting. However, the design and training of DNNs are usually complicated. This paper combines different convolutional, long short‐term memory (LSTM)‐based networks and NWPs using ensemble techniques (i.e., bagging, random forest, and adaboost methods) with automatic hyperparameter tuning for multi‐step rainfall nowcasting. The relative humidity, air temperature, and previous rainfall sequences are considered the inputs of the DNNs. We focus on applying two hyperparameter tuning methods (i.e., random search and tree structured Parzen estimator) to improve the performance of the proposed rainfall nowcasting models. The proposed framework was applied to the eastern drainage catchment (EDC) in Tehran city. The results illustrate that the utilization of automatic hyperparameter tuning along with multivariate DNNs, NWPs, and ensemble techniques could improve the nowcasting performance (10%–25%) compared to the traditional univariate models. Also, Adaboost is more accurate than other ensemble techniques in predicting both extreme and normal rainfall events with average RMSE of 0.765, and random forest obtain better results when predict sub normal rainfall events with overall RMSE of 0.315. The proposed framework is applicable to different climates and catchments.

An explainable intelligent algorithm for the multiple performance prediction of cement-based grouting materials

Cement-based grouting material, distinguished by excellent fluidity and high strength, is widely used in the field of construction reinforcement, and anchoring of restraints. Owing to the high-performance requirements and complicated influencing factors of grouting material, the design of the mixing proportion has been challenging. This study proposes a machine learning (ML) based algorithmic framework integrating prediction, interpretation, and automatic hyperparameter tuning to identify the complex potential relationships between the mixing proportion parameters on the compressive strength and fluidity of cement-based grouting materials. The 442 compressive strength data and 217 fluidity data derived from both published literatures and laboratory experiments were collected to build a dataset for demonstrating the predictive performance of the ML models. The results indicated that the hyperparameter tuning technique via Bayesian Optimisation (BO) can significantly improve the time efficiency compared to grid search, reducing time consumption from 8000 s to 197 s with comparable accuracy. The optimal prediction results were obtained based on the XGBoost model with R2 = 0.93, RMSE = 7.37 for compressive strength, and R2 = 0.92, RMSE = 16.33 for fluidity. The SHapley Additive exPlainations (SHAP) is introduced to interpret the evaluation results and the influence of the various mix factors on grouting material from both global(model) and local(instance) perspectives. The suggested model can be seen as a function of influential input variables that help engineers conduct a rapid assessment and then in turn to optimize the design of the mixture proportion.

Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception.

In this work, a method for automatic hyper-parameter tuning of the stacked asymmetric auto-encoder is proposed. In previous work, the deep learning ability to extract personality perception from speech was shown, but hyper-parameter tuning was attained by trial-and-error, which is time-consuming and requires machine learning knowledge. Therefore, obtaining hyper-parameter values is challenging and places limits on deep learning usage. To address this challenge, researchers have applied optimization methods. Although there were successes, the search space is very large due to the large number of deep learning hyper-parameters, which increases the probability of getting stuck in local optima. Researchers have also focused on improving global optimization methods. In this regard, we suggest a novel global optimization method based on the cultural algorithm, multi-island and the concept of parallelism to search this large space smartly. At first, we evaluated our method on three well-known optimization benchmarks and compared the results with recently published papers. Results indicate that the convergence of the proposed method speeds up due to the ability to escape from local optima, and the precision of the results improves dramatically. Afterward, we applied our method to optimize five hyper-parameters of an asymmetric auto-encoder for automatic personality perception. Since inappropriate hyper-parameters lead the network to over-fitting and under-fitting, we used a novel cost function to prevent over-fitting and under-fitting. As observed, the unweighted average recall (accuracy) was improved by 6.52% (9.54%) compared to our previous work and had remarkable outcomes compared to other published personality perception works.

Fast anomaly detection with locality-sensitive hashing and hyperparameter autotuning

This paper presents LSHAD, an anomaly detection (AD) method based on Locality Sensitive Hashing (LSH), capable of dealing with large-scale datasets. The resulting algorithm is highly parallelizable and its implementation in Apache Spark further increases its ability to handle very large datasets. Moreover, the algorithm incorporates an automatic hyperparameter tuning mechanism so that users do not have to implement costly manual tuning. Our LSHAD method is novel as both hyperparameter automation and distributed properties are not usual in AD techniques. Our results for experiments with LSHAD across a variety of datasets point to state-of-the-art AD performance while handling much larger datasets than state-of-the-art alternatives. In addition, evaluation results for the tradeoff between AD performance and scalability show that our method offers significant advantages over competing methods.

Multi-Classification of Motor Imagery EEG Signals Using Bayesian Optimization-Based Average Ensemble Approach

Motor Imagery (MI) classification using electroencephalography (EEG) has been extensively applied in healthcare scenarios for rehabilitation aims. EEG signal decoding is a difficult process due to its complexity and poor signal-to-noise ratio. Convolutional neural networks (CNN) have demonstrated their ability to extract time–space characteristics from EEG signals for better classification results. However, to discover dynamic correlations in these signals, CNN models must be improved. Hyperparameter choice strongly affects the robustness of CNNs. It is still challenging since the manual tuning performed by domain experts lacks the high performance needed for real-life applications. To overcome these limitations, we presented a fusion of three optimum CNN models using the Average Ensemble strategy, a method that is utilized for the first time for MI movement classification. Moreover, we adopted the Bayesian Optimization (BO) algorithm to reach the optimal hyperparameters’ values. The experimental results demonstrate that without data augmentation, our approach reached 92% accuracy, whereas Linear Discriminate Analysis, Support Vector Machine, Random Forest, Multi-Layer Perceptron, and Gaussian Naive Bayes achieved 68%, 70%, 58%, 64%, and 40% accuracy, respectively. Further, we surpassed state-of-the-art strategies on the BCI competition IV-2a multiclass MI database by a wide margin, proving the benefit of combining the output of CNN models with automated hyperparameter tuning.

A Comprehensive Performance Analysis of Transfer Learning Optimization in Visual Field Defect Classification

Numerous research have demonstrated that Convolutional Neural Network (CNN) models are capable of classifying visual field (VF) defects with great accuracy. In this study, we evaluated the performance of different pre-trained models (VGG-Net, MobileNet, ResNet, and DenseNet) in classifying VF defects and produced a comprehensive comparative analysis to compare the performance of different CNN models before and after hyperparameter tuning and fine-tuning. Using 32 batch sizes, 50 epochs, and ADAM as the optimizer to optimize weight, bias, and learning rate, VGG-16 obtained the highest accuracy of 97.63 percent, according to experimental findings. Subsequently, Bayesian optimization was utilized to execute automated hyperparameter tuning and automated fine-tuning layers of the pre-trained models to determine the optimal hyperparameter and fine-tuning layer for classifying many VF defect with the highest accuracy. We found that the combination of different hyperparameters and fine-tuning of the pre-trained models significantly impact the performance of deep learning models for this classification task. In addition, we also discovered that the automated selection of optimal hyperparameters and fine-tuning by Bayesian has significantly enhanced the performance of the pre-trained models. The results observed the best performance for the DenseNet-121 model with a validation accuracy of 98.46% and a test accuracy of 99.57% for the tested datasets.

A scalable deep learning system for monitoring and forecasting pollutant concentration levels on UK highways

The construction of intercity highways by the government has resulted in a progressive increase in vehicle emissions and pollution from noise, dust, and vibrations despite its recognition of the air pollution menace. Efforts that have targeted roadside pollution still do not accurately monitor deadly pollutants such as nitrogen oxides and particulate matter. Reports on regional highways across the country are based on a limited number of fixed monitoring stations that are sometimes located far from the highway. These periodic and coarse-grained measurements cause inefficient highway air quality reporting, leading to inaccurate air quality forecasts. This paper, therefore, proposes and validates a scalable deep learning framework for efficiently capturing fine-grained highway data and forecasting future concentration levels. Highways in four different UK regions - Newport, Lewisham, Southwark, and Chepstow were used as case studies to develop a REVIS system and validate the proposed framework. REVIS examined the framework's ability to capture granular pollution data, scale up its storage facility to rapid data growth and translate high-level user queries to structured query language (SQL) required for exploratory data analysis. Finally, the framework's suitability for predictive analytics was tested using fastai's library for tabular data, and automated hyperparameter tuning was implemented using bayesian optimisation. The results of our experiments demonstrate the suitability of the proposed framework in building end-to-end systems for extensive monitoring and forecasting of pollutant concentration levels on highways. The study serves as a background for future related research looking to improve the overall performance of roadside and highway air quality forecasting models.

Convolutional neural network hyperparameter optimization applied to land cover classification

In recent times, machine learning algorithms have shown great performance in solving problems in different fields of study, including the analysis of remote sensing images, computer vision, natural language processing, medical issues, etc. A well-prepared input dataset can have a huge impact on the result metrics. However, a correctly selected hyperparameter combined with neural network architecture could highly increase the final metrics. Therefore, the hyperparameters optimization problem becomes a key issue in a deep learning algorithm. The process of finding a suitable hyperparameter combination could be performed manually or automatically. Manual search is based on previous research and requires enormous human efforts. However, there are many automated hyperparameter optimization methods have been successfully applied in practice. The automated hyperparameter tuning techniques are divided into two groups: black-box optimization techniques (such as Grid Search, Random Search) and multi-fidelity optimization techniques (HyperBand, BOHB). The most recent and promising among all approaches is BOHB which, which combines both Bayesian optimization and bandit-based methods, outperforms classical approaches, and can run asynchronously with given GPU resources and time budget that plays a vital role in the hyperparameter optimization process. The previous study proposed a convolutional deep learning neural network for solving land cover classification problems in the EuroSAT dataset. It was found that adding spectral indexes NDVI, NDWI, and GNDVI with RGB channels increased the result accuracy (from 64.72% to 84.19%) and F1 (from 63.89 % to 84.05%) score. However, the convolutional neural network architecture and hyperparameter combination were selected manually. The research optimizes convolutional neural network architecture and finds suitable hyperparameter combinations applied to land cover classification problems using multispectral images. The obtained results must increase result performance compared with the previous study and given budget constraints.

Accurate estimation of tool wear levels during milling, drilling and turning operations by designing novel hyperparameter tuned models based on LightGBM and stacking

The study is focused on executing machining operations by using 18 tools of milling, drilling, and turning thus 6 tools were used for each machining process. The VB of tool was measured for categorizing the tools ranging from level-1 to level-5 based on the severity of tool wear. The first model was designed based on LightGBM whereas the second model was developed by designing six algorithms i.e. LR, RF, CART, NB, SVM, and KNN. All algorithms were combined to develop an ensemble stacking model. Manual hyperparameter tuning was done for the LightGBM model whereas automatic hyperparameter tuning was adopted for the Stacking model by using GridSearchCV. The force signals’ features extraction was done by SSA whereas dimensionality reduction was accomplished by PCA. One-hot encoding technique has transformed target variables into binary form. The application of techniques of dropout and early stopping to both models has overcome overfitting.

Energy demand prediction with machine learning supported by auto-tuning: a case study

The operational energy of buildings is making up one of the highest proportions of life-cycle carbon emissions. A more efficient operation of facilities would result in significant energy savings but necessitates computational models to predict a building’s future energy demands with high precision. To this end, various machine learning models have been proposed in recent years. These models’ prediction accuracies, however, strongly depend on their internal structure and hyperparameters. The time demand and expertise required for their finetuning call for a more efficient solution. In the context of a case study, this paper describes the relationship between a machine learning model’s prediction accuracy and its hyperparameters. Based on time-stamped recordings of outdoor temperatures and electricity demands of a hospital in Japan, recorded every 30 minutes for more than four years, using a deep neural network (DNN) ensemble model, electricity demands were predicted for sixty time steps to follow. Specifically, we used automatic hyperparameter tuning methods, such as grid search, random search, and Bayesian optimization. A single time step ahead, all tuning methods reduced the RSME to less than 50%, compared to non-optimized tuning. The results attest to machine learning models’ reliance on hyperparameters and the effectiveness of their automatic tuning.

A Hadoop Based Framework Integrating Machine Learning Classifiers for Anomaly Detection in the Internet of Things

In recent years, different variants of the botnet are targeting government, private organizations and there is a crucial need to develop a robust framework for securing the IoT (Internet of Things) network. In this paper, a Hadoop based framework is proposed to identify the malicious IoT traffic using a modified Tomek-link under-sampling integrated with automated Hyper-parameter tuning of machine learning classifiers. The novelty of this paper is to utilize a big data platform for benchmark IoT datasets to minimize computational time. The IoT benchmark datasets are loaded in the Hadoop Distributed File System (HDFS) environment. Three machine learning approaches namely naive Bayes (NB), K-nearest neighbor (KNN), and support vector machine (SVM) are used for categorizing IoT traffic. Artificial immune network optimization is deployed during cross-validation to obtain the best classifier parameters. Experimental analysis is performed on the Hadoop platform. The average accuracy of 99% and 90% is obtained for BoT_IoT and ToN_IoT datasets. The accuracy difference in ToN-IoT dataset is due to the huge number of data samples captured at the edge layer and fog layer. However, in BoT-IoT dataset only 5% of the training and test samples from the complete dataset are considered for experimental analysis as released by the dataset developers. The overall accuracy is improved by 19% in comparison with state-of-the-art techniques. The computational times for the huge datasets are reduced by 3–4 hours through Map Reduce in HDFS.

Constraint Preserving Score for Automatic Hyperparameter Tuning of Dimensionality Reduction Methods for Visualization

In data analysis, visualization through dimensionality reduction (DR) is one of the most effective ways to understand a dataset. However, the quality of a visualization is hard to evaluate quantitatively and the hyperparameters of visualization algorithms are sometimes difficult to tune for end-users. This article proposes a score for visualization assessment that can be used to ease the choice of hyperparameter values for widely used DR methods like <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$t$</tex-math></inline-formula> -distributed stochastic neighbor embedding, LargeVis, and uniform manifold approximation and projection. We present the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">constraint preserving score</i> , a computationally efficient score to measure visualization quality. The idea is to measure how well a visualization preserves the information encoded in pairwise constraints like group information or similarity/dissimilarity relationships between instances. Based on this quantitative measure, we use Bayesian optimization to effectively explore the solution space of all visualizations and find the most suitable one. The proposed score is flexible as it can measure quality in different ways depending on the provided constraints. Experiments show its interest for end-users, its complementarity with existing visualization quality measures, and its flexibility to easily express different quality aspects. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>Impact Statement</i>—When working with high-dimensional data, visualization techniques are useful tools to help us to understand patterns in data. Widely used visualization methods such as <inline-formula><tex-math notation="LaTeX">$t$</tex-math></inline-formula>-distributed stochastic neighbor embedding, LargeVis, and uniform manifold approximation and projection require tuning several hyperparameters, which is a tedious task for end-users. The visualizations are usually assessed qualitatively and subjectively by users since we lack quantitative measures that fit their needs. Our work tackles this problem by proposing a novel score based on user's constraints to measure visualization quality. This score can, thus, be used to automatically tune the hyperparameters of visualization methods. For real-world datasets, there are typically multiple aspects hidden in the data under the form of local or global structures, or relationships between data groups. One visualization gives us one vantage point to look at the data and, thus, reveals one specific aspect of the data. Assessing the visualization quality is still an open question and each state-of-the-art visualization quality metric is designed to capture only one specific aspect like local neighborhood structure. However, our proposed constraints preserving score can capture other different aspects of the visualization like the global structure or semantic relationships between groups according to the information encoded in the input constraints. Our score measures how well the information encoded in input constraints is preserved in a visualization, and suggests the best visualization corresponding to the users’ needs. This score can have a large impact since it is very easy to use and works with any visualization method. Domain experts can express their knowledge in a simple form of similar or dissimilar groups of points. If needed, end-users can use a small amount of labeled data to express their constraints.

AutoBOT: evolving neuro-symbolic representations for explainable low resource text classification

Learning from texts has been widely adopted throughout industry and science. While state-of-the-art neural language models have shown very promising results for text classification, they are expensive to (pre-)train, require large amounts of data and tuning of hundreds of millions or more parameters. This paper explores how automatically evolved text representations can serve as a basis for explainable, low-resource branch of models with competitive performance that are subject to automated hyperparameter tuning. We present autoBOT (automatic Bags-Of-Tokens), an autoML approach suitable for low resource learning scenarios, where both the hardware and the amount of data required for training are limited. The proposed approach consists of an evolutionary algorithm that jointly optimizes various sparse representations of a given text (including word, subword, POS tag, keyword-based, knowledge graph-based and relational features) and two types of document embeddings (non-sparse representations). The key idea of autoBOT is that, instead of evolving at the learner level, evolution is conducted at the representation level. The proposed method offers competitive classification performance on fourteen real-world classification tasks when compared against a competitive autoML approach that evolves ensemble models, as well as state-of-the-art neural language models such as BERT and RoBERTa. Moreover, the approach is explainable, as the importance of the parts of the input space is part of the final solution yielded by the proposed optimization procedure, offering potential for meta-transfer learning.

A new strategy for spatial predictive mapping of mineral prospectivity: Automated hyperparameter tuning of random forest approach

Machine learning algorithms (e.g., random forest (RF)) have recently been performed in data-driven mineral prospectivity mapping. These methods are highly sensitive to hyperparameter values, since the predictive accuracy of them can significantly increase when the optimized hyperparameters are predefined and then adjusted to training procedure. The main goal of this contribution is to propose a hybrid genetic-based RF model, namely GRF, which is able to automatically adjust the optimized hyperparameters of RF with the excellent predictive accuracy. Therefore, three primary parameters of RF comprising NT, NS and d, were well-tuned employing genetic algorithm (GA) in establishing an efficient RF model. The proposed GRF model and also conventional RF were tested on mineralization-related geo-spatial dataset and the predictive models were generated for comparing the accuracy of the proposed GRF model with that of RF. The input dataset (e.g., multi-element geochemical signature, geological-structural layer and hydrothermal alteration evidences) which acquired from Feizabad district, NE Iran, were translated into mappable targeting criteria in the form of four predictor maps. In addition, the locations of 13 known Cu–Au deposits as prospect data and the locations of 13 randomly selected non-prospect data were used as target variables to train the models. Three authentic validation measures, K-fold cross-validation, confusion matrix and success-rate curves, were employed to evaluate the overall performance of two predictive models. Experimental results suggested the superiority of GRF model over the RF, as the favorable areas derived by GRF model occupy only 9% of the study area while predicting 100% of the known deposits.

Part-of-Speech Tagging via Deep Neural Networks for Northern-Ethiopic Languages

Deep Neural Networks (DNNs) have proven to be especially successful in the area of Natural Language Processing (NLP) and Part-Of-Speech (POS) tagging—which is the process of mapping words to their corresponding POS labels depending on the context. Despite recent development of language technologies, low-resourced languages (such as an East African Tigrinya language), have received too little attention. We investigate the effectiveness of Deep Learning (DL) solutions for the low-resourced Tigrinya language of the Northern-Ethiopic branch. We have selected Tigrinya as the testbed example and have tested state-of-the-art DL approaches seeking to build the most accurate POS tagger. We have evaluated DNN classifiers (Feed Forward Neural Network – FFNN, Long Short-Term Memory method – LSTM, Bidirectional LSTM, and Convolutional Neural Network – CNN) on a top of neural word2vec word embeddings with a small training corpus known as Nagaoka Tigrinya Corpus. To determine the best DNN classifier type, its architecture and hyper-parameter set both manual and automatic hyper-parameter tuning has been performed. BiLSTM method was proved to be the most suitable for our solving task: it achieved the highest accuracy equal to 92% that is 65% above the random baseline.